Upload 16 files
Browse files- README.md +59 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- all_results.json +8 -0
- merges.txt +0 -0
- running_log.txt +1079 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_config.yaml +28 -0
- trainer_log.jsonl +417 -0
- trainer_state.json +2942 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: Qwen/Qwen1.5-4B-Chat
|
| 9 |
+
model-index:
|
| 10 |
+
- name: sft_seed
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# sft_seed
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/datas/huggingface/Qwen1.5-4B-Chat](https://huggingface.co//datas/huggingface/Qwen1.5-4B-Chat) on the LangGPT_community and the LangGPT_seed datasets.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- num_epochs: 10.0
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- PEFT 0.10.0
|
| 56 |
+
- Transformers 4.40.2
|
| 57 |
+
- Pytorch 2.3.0+cu121
|
| 58 |
+
- Datasets 2.19.1
|
| 59 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:571aa58c6345b354d0e80fa485fdaf83773f40ed4561c6c7b5307bca2d12c350
|
| 3 |
+
size 13128368
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.987995198079231,
|
| 3 |
+
"total_flos": 8.185270082173747e+17,
|
| 4 |
+
"train_loss": 0.7521515275423344,
|
| 5 |
+
"train_runtime": 19400.1091,
|
| 6 |
+
"train_samples_per_second": 1.717,
|
| 7 |
+
"train_steps_per_second": 0.107
|
| 8 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
running_log.txt
ADDED
|
@@ -0,0 +1,1079 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file vocab.json
|
| 2 |
+
|
| 3 |
+
05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file merges.txt
|
| 4 |
+
|
| 5 |
+
05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json
|
| 6 |
+
|
| 7 |
+
05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json
|
| 8 |
+
|
| 9 |
+
05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json
|
| 10 |
+
|
| 11 |
+
05/20/2024 11:37:53 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json
|
| 12 |
+
|
| 13 |
+
05/20/2024 11:37:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
| 14 |
+
|
| 15 |
+
05/20/2024 11:37:54 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/LangGPT_community.jsonl...
|
| 16 |
+
|
| 17 |
+
05/20/2024 11:37:54 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
|
| 18 |
+
|
| 19 |
+
05/20/2024 11:37:55 - INFO - llmtuner.data.loader - Loading dataset /datas/wangm/LLM4LangGPT/constructed_datasets/langgpt_seed.jsonl...
|
| 20 |
+
|
| 21 |
+
05/20/2024 11:37:55 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
|
| 22 |
+
|
| 23 |
+
05/20/2024 11:38:03 - INFO - transformers.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-4B-Chat/config.json
|
| 24 |
+
|
| 25 |
+
05/20/2024 11:38:03 - INFO - transformers.configuration_utils - Model config Qwen2Config {
|
| 26 |
+
"_name_or_path": "/datas/huggingface/Qwen1.5-4B-Chat",
|
| 27 |
+
"architectures": [
|
| 28 |
+
"Qwen2ForCausalLM"
|
| 29 |
+
],
|
| 30 |
+
"attention_dropout": 0.0,
|
| 31 |
+
"bos_token_id": 151643,
|
| 32 |
+
"eos_token_id": 151645,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 2560,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 6912,
|
| 37 |
+
"max_position_embeddings": 32768,
|
| 38 |
+
"max_window_layers": 21,
|
| 39 |
+
"model_type": "qwen2",
|
| 40 |
+
"num_attention_heads": 20,
|
| 41 |
+
"num_hidden_layers": 40,
|
| 42 |
+
"num_key_value_heads": 20,
|
| 43 |
+
"rms_norm_eps": 1e-06,
|
| 44 |
+
"rope_theta": 5000000.0,
|
| 45 |
+
"sliding_window": 32768,
|
| 46 |
+
"tie_word_embeddings": false,
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"transformers_version": "4.40.2",
|
| 49 |
+
"use_cache": true,
|
| 50 |
+
"use_sliding_window": false,
|
| 51 |
+
"vocab_size": 151936
|
| 52 |
+
}
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
05/20/2024 11:38:04 - INFO - transformers.modeling_utils - loading weights file /datas/huggingface/Qwen1.5-4B-Chat/model.safetensors.index.json
|
| 56 |
+
|
| 57 |
+
05/20/2024 11:38:04 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
|
| 58 |
+
|
| 59 |
+
05/20/2024 11:38:04 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
|
| 60 |
+
"bos_token_id": 151643,
|
| 61 |
+
"eos_token_id": 151645,
|
| 62 |
+
"use_cache": false
|
| 63 |
+
}
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
05/20/2024 11:38:08 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM.
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
05/20/2024 11:38:08 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at /datas/huggingface/Qwen1.5-4B-Chat.
|
| 70 |
+
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
|
| 71 |
+
|
| 72 |
+
05/20/2024 11:38:08 - INFO - transformers.generation.configuration_utils - loading configuration file /datas/huggingface/Qwen1.5-4B-Chat/generation_config.json
|
| 73 |
+
|
| 74 |
+
05/20/2024 11:38:08 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
|
| 75 |
+
"bos_token_id": 151643,
|
| 76 |
+
"do_sample": true,
|
| 77 |
+
"eos_token_id": [
|
| 78 |
+
151645,
|
| 79 |
+
151643
|
| 80 |
+
],
|
| 81 |
+
"pad_token_id": 151643,
|
| 82 |
+
"repetition_penalty": 1.1,
|
| 83 |
+
"top_p": 0.8
|
| 84 |
+
}
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
05/20/2024 11:38:09 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled.
|
| 88 |
+
|
| 89 |
+
05/20/2024 11:38:09 - INFO - llmtuner.model.utils.attention - Using torch SDPA for faster training and inference.
|
| 90 |
+
|
| 91 |
+
05/20/2024 11:38:09 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
|
| 92 |
+
|
| 93 |
+
05/20/2024 11:38:09 - INFO - llmtuner.model.loader - trainable params: 3276800 || all params: 3953646080 || trainable%: 0.0829
|
| 94 |
+
|
| 95 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Using auto half precision backend
|
| 96 |
+
|
| 97 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - ***** Running training *****
|
| 98 |
+
|
| 99 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Num examples = 3,331
|
| 100 |
+
|
| 101 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Num Epochs = 10
|
| 102 |
+
|
| 103 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Instantaneous batch size per device = 2
|
| 104 |
+
|
| 105 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Total train batch size (w. parallel, distributed & accumulation) = 16
|
| 106 |
+
|
| 107 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Gradient Accumulation steps = 8
|
| 108 |
+
|
| 109 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Total optimization steps = 2,080
|
| 110 |
+
|
| 111 |
+
05/20/2024 11:38:09 - INFO - transformers.trainer - Number of trainable parameters = 3,276,800
|
| 112 |
+
|
| 113 |
+
05/20/2024 11:38:55 - INFO - llmtuner.extras.callbacks - {'loss': 1.2537, 'learning_rate': 4.9999e-05, 'epoch': 0.02}
|
| 114 |
+
|
| 115 |
+
05/20/2024 11:39:49 - INFO - llmtuner.extras.callbacks - {'loss': 1.1695, 'learning_rate': 4.9997e-05, 'epoch': 0.05}
|
| 116 |
+
|
| 117 |
+
05/20/2024 11:40:37 - INFO - llmtuner.extras.callbacks - {'loss': 1.1879, 'learning_rate': 4.9994e-05, 'epoch': 0.07}
|
| 118 |
+
|
| 119 |
+
05/20/2024 11:41:20 - INFO - llmtuner.extras.callbacks - {'loss': 1.0137, 'learning_rate': 4.9989e-05, 'epoch': 0.10}
|
| 120 |
+
|
| 121 |
+
05/20/2024 11:42:08 - INFO - llmtuner.extras.callbacks - {'loss': 1.1109, 'learning_rate': 4.9982e-05, 'epoch': 0.12}
|
| 122 |
+
|
| 123 |
+
05/20/2024 11:42:55 - INFO - llmtuner.extras.callbacks - {'loss': 1.0400, 'learning_rate': 4.9974e-05, 'epoch': 0.14}
|
| 124 |
+
|
| 125 |
+
05/20/2024 11:43:41 - INFO - llmtuner.extras.callbacks - {'loss': 1.0158, 'learning_rate': 4.9965e-05, 'epoch': 0.17}
|
| 126 |
+
|
| 127 |
+
05/20/2024 11:44:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.9004, 'learning_rate': 4.9954e-05, 'epoch': 0.19}
|
| 128 |
+
|
| 129 |
+
05/20/2024 11:45:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.9626, 'learning_rate': 4.9942e-05, 'epoch': 0.22}
|
| 130 |
+
|
| 131 |
+
05/20/2024 11:45:57 - INFO - llmtuner.extras.callbacks - {'loss': 1.0787, 'learning_rate': 4.9929e-05, 'epoch': 0.24}
|
| 132 |
+
|
| 133 |
+
05/20/2024 11:46:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8533, 'learning_rate': 4.9914e-05, 'epoch': 0.26}
|
| 134 |
+
|
| 135 |
+
05/20/2024 11:47:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.9406, 'learning_rate': 4.9897e-05, 'epoch': 0.29}
|
| 136 |
+
|
| 137 |
+
05/20/2024 11:48:16 - INFO - llmtuner.extras.callbacks - {'loss': 1.0017, 'learning_rate': 4.9880e-05, 'epoch': 0.31}
|
| 138 |
+
|
| 139 |
+
05/20/2024 11:49:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.8902, 'learning_rate': 4.9860e-05, 'epoch': 0.34}
|
| 140 |
+
|
| 141 |
+
05/20/2024 11:49:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.9070, 'learning_rate': 4.9840e-05, 'epoch': 0.36}
|
| 142 |
+
|
| 143 |
+
05/20/2024 11:50:40 - INFO - llmtuner.extras.callbacks - {'loss': 1.0197, 'learning_rate': 4.9818e-05, 'epoch': 0.38}
|
| 144 |
+
|
| 145 |
+
05/20/2024 11:51:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.8131, 'learning_rate': 4.9794e-05, 'epoch': 0.41}
|
| 146 |
+
|
| 147 |
+
05/20/2024 11:52:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.8665, 'learning_rate': 4.9769e-05, 'epoch': 0.43}
|
| 148 |
+
|
| 149 |
+
05/20/2024 11:52:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.9219, 'learning_rate': 4.9743e-05, 'epoch': 0.46}
|
| 150 |
+
|
| 151 |
+
05/20/2024 11:53:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.9425, 'learning_rate': 4.9715e-05, 'epoch': 0.48}
|
| 152 |
+
|
| 153 |
+
05/20/2024 11:53:46 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-100
|
| 154 |
+
|
| 155 |
+
05/20/2024 11:53:46 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-100/tokenizer_config.json
|
| 156 |
+
|
| 157 |
+
05/20/2024 11:53:46 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-100/special_tokens_map.json
|
| 158 |
+
|
| 159 |
+
05/20/2024 11:54:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8781, 'learning_rate': 4.9686e-05, 'epoch': 0.50}
|
| 160 |
+
|
| 161 |
+
05/20/2024 11:55:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.8446, 'learning_rate': 4.9656e-05, 'epoch': 0.53}
|
| 162 |
+
|
| 163 |
+
05/20/2024 11:56:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.9453, 'learning_rate': 4.9624e-05, 'epoch': 0.55}
|
| 164 |
+
|
| 165 |
+
05/20/2024 11:56:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.8086, 'learning_rate': 4.9590e-05, 'epoch': 0.58}
|
| 166 |
+
|
| 167 |
+
05/20/2024 11:57:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8657, 'learning_rate': 4.9556e-05, 'epoch': 0.60}
|
| 168 |
+
|
| 169 |
+
05/20/2024 11:58:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.9168, 'learning_rate': 4.9520e-05, 'epoch': 0.62}
|
| 170 |
+
|
| 171 |
+
05/20/2024 11:59:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.9192, 'learning_rate': 4.9482e-05, 'epoch': 0.65}
|
| 172 |
+
|
| 173 |
+
05/20/2024 11:59:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7927, 'learning_rate': 4.9443e-05, 'epoch': 0.67}
|
| 174 |
+
|
| 175 |
+
05/20/2024 12:00:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8486, 'learning_rate': 4.9403e-05, 'epoch': 0.70}
|
| 176 |
+
|
| 177 |
+
05/20/2024 12:01:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7937, 'learning_rate': 4.9361e-05, 'epoch': 0.72}
|
| 178 |
+
|
| 179 |
+
05/20/2024 12:02:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.8340, 'learning_rate': 4.9318e-05, 'epoch': 0.74}
|
| 180 |
+
|
| 181 |
+
05/20/2024 12:03:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7799, 'learning_rate': 4.9274e-05, 'epoch': 0.77}
|
| 182 |
+
|
| 183 |
+
05/20/2024 12:03:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.8608, 'learning_rate': 4.9228e-05, 'epoch': 0.79}
|
| 184 |
+
|
| 185 |
+
05/20/2024 12:04:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.8872, 'learning_rate': 4.9180e-05, 'epoch': 0.82}
|
| 186 |
+
|
| 187 |
+
05/20/2024 12:05:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.8681, 'learning_rate': 4.9132e-05, 'epoch': 0.84}
|
| 188 |
+
|
| 189 |
+
05/20/2024 12:06:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.8451, 'learning_rate': 4.9082e-05, 'epoch': 0.86}
|
| 190 |
+
|
| 191 |
+
05/20/2024 12:06:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.8662, 'learning_rate': 4.9030e-05, 'epoch': 0.89}
|
| 192 |
+
|
| 193 |
+
05/20/2024 12:07:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8183, 'learning_rate': 4.8978e-05, 'epoch': 0.91}
|
| 194 |
+
|
| 195 |
+
05/20/2024 12:08:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.8887, 'learning_rate': 4.8924e-05, 'epoch': 0.94}
|
| 196 |
+
|
| 197 |
+
05/20/2024 12:09:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.8505, 'learning_rate': 4.8868e-05, 'epoch': 0.96}
|
| 198 |
+
|
| 199 |
+
05/20/2024 12:09:17 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-200
|
| 200 |
+
|
| 201 |
+
05/20/2024 12:09:17 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-200/tokenizer_config.json
|
| 202 |
+
|
| 203 |
+
05/20/2024 12:09:17 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-200/special_tokens_map.json
|
| 204 |
+
|
| 205 |
+
05/20/2024 12:10:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.8350, 'learning_rate': 4.8811e-05, 'epoch': 0.98}
|
| 206 |
+
|
| 207 |
+
05/20/2024 12:10:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.8531, 'learning_rate': 4.8753e-05, 'epoch': 1.01}
|
| 208 |
+
|
| 209 |
+
05/20/2024 12:11:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.8679, 'learning_rate': 4.8693e-05, 'epoch': 1.03}
|
| 210 |
+
|
| 211 |
+
05/20/2024 12:12:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.8432, 'learning_rate': 4.8632e-05, 'epoch': 1.06}
|
| 212 |
+
|
| 213 |
+
05/20/2024 12:13:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.8362, 'learning_rate': 4.8570e-05, 'epoch': 1.08}
|
| 214 |
+
|
| 215 |
+
05/20/2024 12:13:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7704, 'learning_rate': 4.8507e-05, 'epoch': 1.10}
|
| 216 |
+
|
| 217 |
+
05/20/2024 12:14:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.8357, 'learning_rate': 4.8442e-05, 'epoch': 1.13}
|
| 218 |
+
|
| 219 |
+
05/20/2024 12:15:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.7461, 'learning_rate': 4.8375e-05, 'epoch': 1.15}
|
| 220 |
+
|
| 221 |
+
05/20/2024 12:16:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.8821, 'learning_rate': 4.8308e-05, 'epoch': 1.18}
|
| 222 |
+
|
| 223 |
+
05/20/2024 12:17:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.8890, 'learning_rate': 4.8239e-05, 'epoch': 1.20}
|
| 224 |
+
|
| 225 |
+
05/20/2024 12:17:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7407, 'learning_rate': 4.8169e-05, 'epoch': 1.22}
|
| 226 |
+
|
| 227 |
+
05/20/2024 12:18:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7822, 'learning_rate': 4.8097e-05, 'epoch': 1.25}
|
| 228 |
+
|
| 229 |
+
05/20/2024 12:19:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.9008, 'learning_rate': 4.8024e-05, 'epoch': 1.27}
|
| 230 |
+
|
| 231 |
+
05/20/2024 12:20:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7477, 'learning_rate': 4.7950e-05, 'epoch': 1.30}
|
| 232 |
+
|
| 233 |
+
05/20/2024 12:20:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7846, 'learning_rate': 4.7874e-05, 'epoch': 1.32}
|
| 234 |
+
|
| 235 |
+
05/20/2024 12:21:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.8544, 'learning_rate': 4.7797e-05, 'epoch': 1.34}
|
| 236 |
+
|
| 237 |
+
05/20/2024 12:22:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7706, 'learning_rate': 4.7719e-05, 'epoch': 1.37}
|
| 238 |
+
|
| 239 |
+
05/20/2024 12:23:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.8256, 'learning_rate': 4.7640e-05, 'epoch': 1.39}
|
| 240 |
+
|
| 241 |
+
05/20/2024 12:23:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.8185, 'learning_rate': 4.7559e-05, 'epoch': 1.42}
|
| 242 |
+
|
| 243 |
+
05/20/2024 12:24:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7356, 'learning_rate': 4.7477e-05, 'epoch': 1.44}
|
| 244 |
+
|
| 245 |
+
05/20/2024 12:24:41 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-300
|
| 246 |
+
|
| 247 |
+
05/20/2024 12:24:41 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-300/tokenizer_config.json
|
| 248 |
+
|
| 249 |
+
05/20/2024 12:24:41 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-300/special_tokens_map.json
|
| 250 |
+
|
| 251 |
+
05/20/2024 12:25:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.8015, 'learning_rate': 4.7394e-05, 'epoch': 1.46}
|
| 252 |
+
|
| 253 |
+
05/20/2024 12:26:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.8103, 'learning_rate': 4.7309e-05, 'epoch': 1.49}
|
| 254 |
+
|
| 255 |
+
05/20/2024 12:27:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6949, 'learning_rate': 4.7224e-05, 'epoch': 1.51}
|
| 256 |
+
|
| 257 |
+
05/20/2024 12:27:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7790, 'learning_rate': 4.7136e-05, 'epoch': 1.54}
|
| 258 |
+
|
| 259 |
+
05/20/2024 12:28:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8016, 'learning_rate': 4.7048e-05, 'epoch': 1.56}
|
| 260 |
+
|
| 261 |
+
05/20/2024 12:29:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7460, 'learning_rate': 4.6958e-05, 'epoch': 1.58}
|
| 262 |
+
|
| 263 |
+
05/20/2024 12:30:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7439, 'learning_rate': 4.6868e-05, 'epoch': 1.61}
|
| 264 |
+
|
| 265 |
+
05/20/2024 12:30:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7969, 'learning_rate': 4.6775e-05, 'epoch': 1.63}
|
| 266 |
+
|
| 267 |
+
05/20/2024 12:31:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.8580, 'learning_rate': 4.6682e-05, 'epoch': 1.66}
|
| 268 |
+
|
| 269 |
+
05/20/2024 12:32:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.8538, 'learning_rate': 4.6587e-05, 'epoch': 1.68}
|
| 270 |
+
|
| 271 |
+
05/20/2024 12:33:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.8241, 'learning_rate': 4.6492e-05, 'epoch': 1.70}
|
| 272 |
+
|
| 273 |
+
05/20/2024 12:34:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7388, 'learning_rate': 4.6395e-05, 'epoch': 1.73}
|
| 274 |
+
|
| 275 |
+
05/20/2024 12:34:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7924, 'learning_rate': 4.6296e-05, 'epoch': 1.75}
|
| 276 |
+
|
| 277 |
+
05/20/2024 12:35:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7719, 'learning_rate': 4.6197e-05, 'epoch': 1.78}
|
| 278 |
+
|
| 279 |
+
05/20/2024 12:36:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.8365, 'learning_rate': 4.6096e-05, 'epoch': 1.80}
|
| 280 |
+
|
| 281 |
+
05/20/2024 12:37:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.8118, 'learning_rate': 4.5994e-05, 'epoch': 1.82}
|
| 282 |
+
|
| 283 |
+
05/20/2024 12:38:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7881, 'learning_rate': 4.5891e-05, 'epoch': 1.85}
|
| 284 |
+
|
| 285 |
+
05/20/2024 12:38:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7155, 'learning_rate': 4.5787e-05, 'epoch': 1.87}
|
| 286 |
+
|
| 287 |
+
05/20/2024 12:39:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.8555, 'learning_rate': 4.5681e-05, 'epoch': 1.90}
|
| 288 |
+
|
| 289 |
+
05/20/2024 12:40:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.8685, 'learning_rate': 4.5575e-05, 'epoch': 1.92}
|
| 290 |
+
|
| 291 |
+
05/20/2024 12:40:26 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-400
|
| 292 |
+
|
| 293 |
+
05/20/2024 12:40:26 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-400/tokenizer_config.json
|
| 294 |
+
|
| 295 |
+
05/20/2024 12:40:26 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-400/special_tokens_map.json
|
| 296 |
+
|
| 297 |
+
05/20/2024 12:41:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7708, 'learning_rate': 4.5467e-05, 'epoch': 1.94}
|
| 298 |
+
|
| 299 |
+
05/20/2024 12:42:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.8448, 'learning_rate': 4.5358e-05, 'epoch': 1.97}
|
| 300 |
+
|
| 301 |
+
05/20/2024 12:42:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7360, 'learning_rate': 4.5248e-05, 'epoch': 1.99}
|
| 302 |
+
|
| 303 |
+
05/20/2024 12:43:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7223, 'learning_rate': 4.5136e-05, 'epoch': 2.02}
|
| 304 |
+
|
| 305 |
+
05/20/2024 12:44:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7504, 'learning_rate': 4.5024e-05, 'epoch': 2.04}
|
| 306 |
+
|
| 307 |
+
05/20/2024 12:45:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.8011, 'learning_rate': 4.4910e-05, 'epoch': 2.06}
|
| 308 |
+
|
| 309 |
+
05/20/2024 12:46:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.8665, 'learning_rate': 4.4795e-05, 'epoch': 2.09}
|
| 310 |
+
|
| 311 |
+
05/20/2024 12:46:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7490, 'learning_rate': 4.4680e-05, 'epoch': 2.11}
|
| 312 |
+
|
| 313 |
+
05/20/2024 12:47:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7962, 'learning_rate': 4.4563e-05, 'epoch': 2.14}
|
| 314 |
+
|
| 315 |
+
05/20/2024 12:48:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7964, 'learning_rate': 4.4444e-05, 'epoch': 2.16}
|
| 316 |
+
|
| 317 |
+
05/20/2024 12:49:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7516, 'learning_rate': 4.4325e-05, 'epoch': 2.18}
|
| 318 |
+
|
| 319 |
+
05/20/2024 12:50:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.8173, 'learning_rate': 4.4205e-05, 'epoch': 2.21}
|
| 320 |
+
|
| 321 |
+
05/20/2024 12:50:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.8038, 'learning_rate': 4.4084e-05, 'epoch': 2.23}
|
| 322 |
+
|
| 323 |
+
05/20/2024 12:51:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.8055, 'learning_rate': 4.3961e-05, 'epoch': 2.26}
|
| 324 |
+
|
| 325 |
+
05/20/2024 12:52:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7459, 'learning_rate': 4.3837e-05, 'epoch': 2.28}
|
| 326 |
+
|
| 327 |
+
05/20/2024 12:53:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7959, 'learning_rate': 4.3713e-05, 'epoch': 2.30}
|
| 328 |
+
|
| 329 |
+
05/20/2024 12:53:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.8528, 'learning_rate': 4.3587e-05, 'epoch': 2.33}
|
| 330 |
+
|
| 331 |
+
05/20/2024 12:54:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7590, 'learning_rate': 4.3460e-05, 'epoch': 2.35}
|
| 332 |
+
|
| 333 |
+
05/20/2024 12:55:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7499, 'learning_rate': 4.3332e-05, 'epoch': 2.38}
|
| 334 |
+
|
| 335 |
+
05/20/2024 12:56:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7279, 'learning_rate': 4.3204e-05, 'epoch': 2.40}
|
| 336 |
+
|
| 337 |
+
05/20/2024 12:56:18 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-500
|
| 338 |
+
|
| 339 |
+
05/20/2024 12:56:18 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-500/tokenizer_config.json
|
| 340 |
+
|
| 341 |
+
05/20/2024 12:56:18 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-500/special_tokens_map.json
|
| 342 |
+
|
| 343 |
+
05/20/2024 12:57:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7453, 'learning_rate': 4.3074e-05, 'epoch': 2.42}
|
| 344 |
+
|
| 345 |
+
05/20/2024 12:57:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.8311, 'learning_rate': 4.2943e-05, 'epoch': 2.45}
|
| 346 |
+
|
| 347 |
+
05/20/2024 12:58:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7172, 'learning_rate': 4.2811e-05, 'epoch': 2.47}
|
| 348 |
+
|
| 349 |
+
05/20/2024 12:59:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.8084, 'learning_rate': 4.2678e-05, 'epoch': 2.50}
|
| 350 |
+
|
| 351 |
+
05/20/2024 13:00:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7020, 'learning_rate': 4.2544e-05, 'epoch': 2.52}
|
| 352 |
+
|
| 353 |
+
05/20/2024 13:00:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7261, 'learning_rate': 4.2409e-05, 'epoch': 2.55}
|
| 354 |
+
|
| 355 |
+
05/20/2024 13:01:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7540, 'learning_rate': 4.2273e-05, 'epoch': 2.57}
|
| 356 |
+
|
| 357 |
+
05/20/2024 13:02:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7855, 'learning_rate': 4.2136e-05, 'epoch': 2.59}
|
| 358 |
+
|
| 359 |
+
05/20/2024 13:03:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7584, 'learning_rate': 4.1998e-05, 'epoch': 2.62}
|
| 360 |
+
|
| 361 |
+
05/20/2024 13:04:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.8196, 'learning_rate': 4.1859e-05, 'epoch': 2.64}
|
| 362 |
+
|
| 363 |
+
05/20/2024 13:04:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6836, 'learning_rate': 4.1719e-05, 'epoch': 2.67}
|
| 364 |
+
|
| 365 |
+
05/20/2024 13:05:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.7656, 'learning_rate': 4.1578e-05, 'epoch': 2.69}
|
| 366 |
+
|
| 367 |
+
05/20/2024 13:06:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7787, 'learning_rate': 4.1436e-05, 'epoch': 2.71}
|
| 368 |
+
|
| 369 |
+
05/20/2024 13:07:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7665, 'learning_rate': 4.1294e-05, 'epoch': 2.74}
|
| 370 |
+
|
| 371 |
+
05/20/2024 13:07:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7480, 'learning_rate': 4.1150e-05, 'epoch': 2.76}
|
| 372 |
+
|
| 373 |
+
05/20/2024 13:08:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7761, 'learning_rate': 4.1005e-05, 'epoch': 2.79}
|
| 374 |
+
|
| 375 |
+
05/20/2024 13:09:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7873, 'learning_rate': 4.0860e-05, 'epoch': 2.81}
|
| 376 |
+
|
| 377 |
+
05/20/2024 13:10:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.8288, 'learning_rate': 4.0713e-05, 'epoch': 2.83}
|
| 378 |
+
|
| 379 |
+
05/20/2024 13:10:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.7587, 'learning_rate': 4.0566e-05, 'epoch': 2.86}
|
| 380 |
+
|
| 381 |
+
05/20/2024 13:11:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 4.0418e-05, 'epoch': 2.88}
|
| 382 |
+
|
| 383 |
+
05/20/2024 13:11:37 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-600
|
| 384 |
+
|
| 385 |
+
05/20/2024 13:11:37 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-600/tokenizer_config.json
|
| 386 |
+
|
| 387 |
+
05/20/2024 13:11:37 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-600/special_tokens_map.json
|
| 388 |
+
|
| 389 |
+
05/20/2024 13:12:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7177, 'learning_rate': 4.0269e-05, 'epoch': 2.91}
|
| 390 |
+
|
| 391 |
+
05/20/2024 13:13:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7244, 'learning_rate': 4.0119e-05, 'epoch': 2.93}
|
| 392 |
+
|
| 393 |
+
05/20/2024 13:13:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7627, 'learning_rate': 3.9968e-05, 'epoch': 2.95}
|
| 394 |
+
|
| 395 |
+
05/20/2024 13:14:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7562, 'learning_rate': 3.9817e-05, 'epoch': 2.98}
|
| 396 |
+
|
| 397 |
+
05/20/2024 13:15:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.8271, 'learning_rate': 3.9664e-05, 'epoch': 3.00}
|
| 398 |
+
|
| 399 |
+
05/20/2024 13:16:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.7639, 'learning_rate': 3.9511e-05, 'epoch': 3.03}
|
| 400 |
+
|
| 401 |
+
05/20/2024 13:17:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7117, 'learning_rate': 3.9357e-05, 'epoch': 3.05}
|
| 402 |
+
|
| 403 |
+
05/20/2024 13:17:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7358, 'learning_rate': 3.9202e-05, 'epoch': 3.07}
|
| 404 |
+
|
| 405 |
+
05/20/2024 13:18:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7409, 'learning_rate': 3.9046e-05, 'epoch': 3.10}
|
| 406 |
+
|
| 407 |
+
05/20/2024 13:19:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7052, 'learning_rate': 3.8889e-05, 'epoch': 3.12}
|
| 408 |
+
|
| 409 |
+
05/20/2024 13:20:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7602, 'learning_rate': 3.8732e-05, 'epoch': 3.15}
|
| 410 |
+
|
| 411 |
+
05/20/2024 13:21:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.8514, 'learning_rate': 3.8574e-05, 'epoch': 3.17}
|
| 412 |
+
|
| 413 |
+
05/20/2024 13:21:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7699, 'learning_rate': 3.8415e-05, 'epoch': 3.19}
|
| 414 |
+
|
| 415 |
+
05/20/2024 13:22:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.8067, 'learning_rate': 3.8255e-05, 'epoch': 3.22}
|
| 416 |
+
|
| 417 |
+
05/20/2024 13:23:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6783, 'learning_rate': 3.8095e-05, 'epoch': 3.24}
|
| 418 |
+
|
| 419 |
+
05/20/2024 13:24:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7315, 'learning_rate': 3.7933e-05, 'epoch': 3.27}
|
| 420 |
+
|
| 421 |
+
05/20/2024 13:24:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6999, 'learning_rate': 3.7772e-05, 'epoch': 3.29}
|
| 422 |
+
|
| 423 |
+
05/20/2024 13:25:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7182, 'learning_rate': 3.7609e-05, 'epoch': 3.31}
|
| 424 |
+
|
| 425 |
+
05/20/2024 13:26:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7577, 'learning_rate': 3.7445e-05, 'epoch': 3.34}
|
| 426 |
+
|
| 427 |
+
05/20/2024 13:27:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7825, 'learning_rate': 3.7281e-05, 'epoch': 3.36}
|
| 428 |
+
|
| 429 |
+
05/20/2024 13:27:16 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-700
|
| 430 |
+
|
| 431 |
+
05/20/2024 13:27:16 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-700/tokenizer_config.json
|
| 432 |
+
|
| 433 |
+
05/20/2024 13:27:16 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-700/special_tokens_map.json
|
| 434 |
+
|
| 435 |
+
05/20/2024 13:28:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7414, 'learning_rate': 3.7117e-05, 'epoch': 3.39}
|
| 436 |
+
|
| 437 |
+
05/20/2024 13:28:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7144, 'learning_rate': 3.6951e-05, 'epoch': 3.41}
|
| 438 |
+
|
| 439 |
+
05/20/2024 13:29:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7516, 'learning_rate': 3.6785e-05, 'epoch': 3.43}
|
| 440 |
+
|
| 441 |
+
05/20/2024 13:30:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7484, 'learning_rate': 3.6618e-05, 'epoch': 3.46}
|
| 442 |
+
|
| 443 |
+
05/20/2024 13:31:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7775, 'learning_rate': 3.6451e-05, 'epoch': 3.48}
|
| 444 |
+
|
| 445 |
+
05/20/2024 13:31:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.7086, 'learning_rate': 3.6282e-05, 'epoch': 3.51}
|
| 446 |
+
|
| 447 |
+
05/20/2024 13:32:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7165, 'learning_rate': 3.6114e-05, 'epoch': 3.53}
|
| 448 |
+
|
| 449 |
+
05/20/2024 13:33:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7668, 'learning_rate': 3.5944e-05, 'epoch': 3.55}
|
| 450 |
+
|
| 451 |
+
05/20/2024 13:34:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.6595, 'learning_rate': 3.5774e-05, 'epoch': 3.58}
|
| 452 |
+
|
| 453 |
+
05/20/2024 13:34:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7469, 'learning_rate': 3.5603e-05, 'epoch': 3.60}
|
| 454 |
+
|
| 455 |
+
05/20/2024 13:35:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7063, 'learning_rate': 3.5432e-05, 'epoch': 3.63}
|
| 456 |
+
|
| 457 |
+
05/20/2024 13:36:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6694, 'learning_rate': 3.5260e-05, 'epoch': 3.65}
|
| 458 |
+
|
| 459 |
+
05/20/2024 13:37:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7789, 'learning_rate': 3.5088e-05, 'epoch': 3.67}
|
| 460 |
+
|
| 461 |
+
05/20/2024 13:38:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7934, 'learning_rate': 3.4915e-05, 'epoch': 3.70}
|
| 462 |
+
|
| 463 |
+
05/20/2024 13:38:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.7295, 'learning_rate': 3.4741e-05, 'epoch': 3.72}
|
| 464 |
+
|
| 465 |
+
05/20/2024 13:39:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7474, 'learning_rate': 3.4567e-05, 'epoch': 3.75}
|
| 466 |
+
|
| 467 |
+
05/20/2024 13:40:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7711, 'learning_rate': 3.4392e-05, 'epoch': 3.77}
|
| 468 |
+
|
| 469 |
+
05/20/2024 13:41:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7363, 'learning_rate': 3.4217e-05, 'epoch': 3.79}
|
| 470 |
+
|
| 471 |
+
05/20/2024 13:41:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.8531, 'learning_rate': 3.4041e-05, 'epoch': 3.82}
|
| 472 |
+
|
| 473 |
+
05/20/2024 13:42:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.8025, 'learning_rate': 3.3865e-05, 'epoch': 3.84}
|
| 474 |
+
|
| 475 |
+
05/20/2024 13:42:40 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-800
|
| 476 |
+
|
| 477 |
+
05/20/2024 13:42:40 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-800/tokenizer_config.json
|
| 478 |
+
|
| 479 |
+
05/20/2024 13:42:40 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-800/special_tokens_map.json
|
| 480 |
+
|
| 481 |
+
05/20/2024 13:43:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6634, 'learning_rate': 3.3688e-05, 'epoch': 3.87}
|
| 482 |
+
|
| 483 |
+
05/20/2024 13:44:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.7664, 'learning_rate': 3.3511e-05, 'epoch': 3.89}
|
| 484 |
+
|
| 485 |
+
05/20/2024 13:45:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.8650, 'learning_rate': 3.3333e-05, 'epoch': 3.91}
|
| 486 |
+
|
| 487 |
+
05/20/2024 13:45:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 3.3155e-05, 'epoch': 3.94}
|
| 488 |
+
|
| 489 |
+
05/20/2024 13:46:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.8476, 'learning_rate': 3.2976e-05, 'epoch': 3.96}
|
| 490 |
+
|
| 491 |
+
05/20/2024 13:47:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.7050, 'learning_rate': 3.2797e-05, 'epoch': 3.99}
|
| 492 |
+
|
| 493 |
+
05/20/2024 13:48:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7086, 'learning_rate': 3.2618e-05, 'epoch': 4.01}
|
| 494 |
+
|
| 495 |
+
05/20/2024 13:48:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.6899, 'learning_rate': 3.2438e-05, 'epoch': 4.03}
|
| 496 |
+
|
| 497 |
+
05/20/2024 13:49:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.8088, 'learning_rate': 3.2257e-05, 'epoch': 4.06}
|
| 498 |
+
|
| 499 |
+
05/20/2024 13:50:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7096, 'learning_rate': 3.2076e-05, 'epoch': 4.08}
|
| 500 |
+
|
| 501 |
+
05/20/2024 13:51:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7646, 'learning_rate': 3.1895e-05, 'epoch': 4.11}
|
| 502 |
+
|
| 503 |
+
05/20/2024 13:51:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7525, 'learning_rate': 3.1713e-05, 'epoch': 4.13}
|
| 504 |
+
|
| 505 |
+
05/20/2024 13:52:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7231, 'learning_rate': 3.1531e-05, 'epoch': 4.15}
|
| 506 |
+
|
| 507 |
+
05/20/2024 13:53:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.7431, 'learning_rate': 3.1349e-05, 'epoch': 4.18}
|
| 508 |
+
|
| 509 |
+
05/20/2024 13:54:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7619, 'learning_rate': 3.1166e-05, 'epoch': 4.20}
|
| 510 |
+
|
| 511 |
+
05/20/2024 13:55:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7806, 'learning_rate': 3.0983e-05, 'epoch': 4.23}
|
| 512 |
+
|
| 513 |
+
05/20/2024 13:55:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.7010, 'learning_rate': 3.0799e-05, 'epoch': 4.25}
|
| 514 |
+
|
| 515 |
+
05/20/2024 13:56:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7114, 'learning_rate': 3.0616e-05, 'epoch': 4.27}
|
| 516 |
+
|
| 517 |
+
05/20/2024 13:57:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7407, 'learning_rate': 3.0431e-05, 'epoch': 4.30}
|
| 518 |
+
|
| 519 |
+
05/20/2024 13:58:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7560, 'learning_rate': 3.0247e-05, 'epoch': 4.32}
|
| 520 |
+
|
| 521 |
+
05/20/2024 13:58:04 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-900
|
| 522 |
+
|
| 523 |
+
05/20/2024 13:58:04 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-900/tokenizer_config.json
|
| 524 |
+
|
| 525 |
+
05/20/2024 13:58:04 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-900/special_tokens_map.json
|
| 526 |
+
|
| 527 |
+
05/20/2024 13:58:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6897, 'learning_rate': 3.0062e-05, 'epoch': 4.35}
|
| 528 |
+
|
| 529 |
+
05/20/2024 13:59:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7212, 'learning_rate': 2.9877e-05, 'epoch': 4.37}
|
| 530 |
+
|
| 531 |
+
05/20/2024 14:00:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.8578, 'learning_rate': 2.9692e-05, 'epoch': 4.39}
|
| 532 |
+
|
| 533 |
+
05/20/2024 14:01:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7116, 'learning_rate': 2.9506e-05, 'epoch': 4.42}
|
| 534 |
+
|
| 535 |
+
05/20/2024 14:01:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7693, 'learning_rate': 2.9321e-05, 'epoch': 4.44}
|
| 536 |
+
|
| 537 |
+
05/20/2024 14:02:48 - INFO - llmtuner.extras.callbacks - {'loss': 0.6641, 'learning_rate': 2.9134e-05, 'epoch': 4.47}
|
| 538 |
+
|
| 539 |
+
05/20/2024 14:03:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7488, 'learning_rate': 2.8948e-05, 'epoch': 4.49}
|
| 540 |
+
|
| 541 |
+
05/20/2024 14:04:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6626, 'learning_rate': 2.8762e-05, 'epoch': 4.51}
|
| 542 |
+
|
| 543 |
+
05/20/2024 14:05:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7064, 'learning_rate': 2.8575e-05, 'epoch': 4.54}
|
| 544 |
+
|
| 545 |
+
05/20/2024 14:05:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7030, 'learning_rate': 2.8388e-05, 'epoch': 4.56}
|
| 546 |
+
|
| 547 |
+
05/20/2024 14:06:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.8085, 'learning_rate': 2.8201e-05, 'epoch': 4.59}
|
| 548 |
+
|
| 549 |
+
05/20/2024 14:07:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7251, 'learning_rate': 2.8013e-05, 'epoch': 4.61}
|
| 550 |
+
|
| 551 |
+
05/20/2024 14:08:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7358, 'learning_rate': 2.7826e-05, 'epoch': 4.63}
|
| 552 |
+
|
| 553 |
+
05/20/2024 14:09:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7625, 'learning_rate': 2.7638e-05, 'epoch': 4.66}
|
| 554 |
+
|
| 555 |
+
05/20/2024 14:09:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.8123, 'learning_rate': 2.7450e-05, 'epoch': 4.68}
|
| 556 |
+
|
| 557 |
+
05/20/2024 14:10:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7068, 'learning_rate': 2.7262e-05, 'epoch': 4.71}
|
| 558 |
+
|
| 559 |
+
05/20/2024 14:11:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7431, 'learning_rate': 2.7074e-05, 'epoch': 4.73}
|
| 560 |
+
|
| 561 |
+
05/20/2024 14:12:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7161, 'learning_rate': 2.6886e-05, 'epoch': 4.75}
|
| 562 |
+
|
| 563 |
+
05/20/2024 14:13:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7311, 'learning_rate': 2.6698e-05, 'epoch': 4.78}
|
| 564 |
+
|
| 565 |
+
05/20/2024 14:13:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6689, 'learning_rate': 2.6509e-05, 'epoch': 4.80}
|
| 566 |
+
|
| 567 |
+
05/20/2024 14:13:45 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1000
|
| 568 |
+
|
| 569 |
+
05/20/2024 14:13:46 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1000/tokenizer_config.json
|
| 570 |
+
|
| 571 |
+
05/20/2024 14:13:46 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1000/special_tokens_map.json
|
| 572 |
+
|
| 573 |
+
05/20/2024 14:14:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6888, 'learning_rate': 2.6321e-05, 'epoch': 4.83}
|
| 574 |
+
|
| 575 |
+
05/20/2024 14:15:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.7879, 'learning_rate': 2.6132e-05, 'epoch': 4.85}
|
| 576 |
+
|
| 577 |
+
05/20/2024 14:16:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6958, 'learning_rate': 2.5944e-05, 'epoch': 4.87}
|
| 578 |
+
|
| 579 |
+
05/20/2024 14:16:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6858, 'learning_rate': 2.5755e-05, 'epoch': 4.90}
|
| 580 |
+
|
| 581 |
+
05/20/2024 14:17:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6799, 'learning_rate': 2.5566e-05, 'epoch': 4.92}
|
| 582 |
+
|
| 583 |
+
05/20/2024 14:18:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7670, 'learning_rate': 2.5378e-05, 'epoch': 4.95}
|
| 584 |
+
|
| 585 |
+
05/20/2024 14:19:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7453, 'learning_rate': 2.5189e-05, 'epoch': 4.97}
|
| 586 |
+
|
| 587 |
+
05/20/2024 14:19:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7559, 'learning_rate': 2.5000e-05, 'epoch': 4.99}
|
| 588 |
+
|
| 589 |
+
05/20/2024 14:20:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7729, 'learning_rate': 2.4811e-05, 'epoch': 5.02}
|
| 590 |
+
|
| 591 |
+
05/20/2024 14:21:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6956, 'learning_rate': 2.4622e-05, 'epoch': 5.04}
|
| 592 |
+
|
| 593 |
+
05/20/2024 14:22:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7124, 'learning_rate': 2.4434e-05, 'epoch': 5.07}
|
| 594 |
+
|
| 595 |
+
05/20/2024 14:23:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7472, 'learning_rate': 2.4245e-05, 'epoch': 5.09}
|
| 596 |
+
|
| 597 |
+
05/20/2024 14:23:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6805, 'learning_rate': 2.4056e-05, 'epoch': 5.11}
|
| 598 |
+
|
| 599 |
+
05/20/2024 14:24:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6898, 'learning_rate': 2.3868e-05, 'epoch': 5.14}
|
| 600 |
+
|
| 601 |
+
05/20/2024 14:25:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.6664, 'learning_rate': 2.3679e-05, 'epoch': 5.16}
|
| 602 |
+
|
| 603 |
+
05/20/2024 14:26:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.7125, 'learning_rate': 2.3491e-05, 'epoch': 5.19}
|
| 604 |
+
|
| 605 |
+
05/20/2024 14:26:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7797, 'learning_rate': 2.3302e-05, 'epoch': 5.21}
|
| 606 |
+
|
| 607 |
+
05/20/2024 14:27:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7587, 'learning_rate': 2.3114e-05, 'epoch': 5.23}
|
| 608 |
+
|
| 609 |
+
05/20/2024 14:28:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7414, 'learning_rate': 2.2926e-05, 'epoch': 5.26}
|
| 610 |
+
|
| 611 |
+
05/20/2024 14:29:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6972, 'learning_rate': 2.2738e-05, 'epoch': 5.28}
|
| 612 |
+
|
| 613 |
+
05/20/2024 14:29:12 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1100
|
| 614 |
+
|
| 615 |
+
05/20/2024 14:29:12 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1100/tokenizer_config.json
|
| 616 |
+
|
| 617 |
+
05/20/2024 14:29:12 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1100/special_tokens_map.json
|
| 618 |
+
|
| 619 |
+
05/20/2024 14:29:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7168, 'learning_rate': 2.2550e-05, 'epoch': 5.31}
|
| 620 |
+
|
| 621 |
+
05/20/2024 14:30:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6441, 'learning_rate': 2.2362e-05, 'epoch': 5.33}
|
| 622 |
+
|
| 623 |
+
05/20/2024 14:31:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.7473, 'learning_rate': 2.2174e-05, 'epoch': 5.35}
|
| 624 |
+
|
| 625 |
+
05/20/2024 14:32:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6849, 'learning_rate': 2.1987e-05, 'epoch': 5.38}
|
| 626 |
+
|
| 627 |
+
05/20/2024 14:32:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6715, 'learning_rate': 2.1799e-05, 'epoch': 5.40}
|
| 628 |
+
|
| 629 |
+
05/20/2024 14:33:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7139, 'learning_rate': 2.1612e-05, 'epoch': 5.43}
|
| 630 |
+
|
| 631 |
+
05/20/2024 14:34:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.8102, 'learning_rate': 2.1425e-05, 'epoch': 5.45}
|
| 632 |
+
|
| 633 |
+
05/20/2024 14:35:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7772, 'learning_rate': 2.1238e-05, 'epoch': 5.47}
|
| 634 |
+
|
| 635 |
+
05/20/2024 14:36:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7506, 'learning_rate': 2.1052e-05, 'epoch': 5.50}
|
| 636 |
+
|
| 637 |
+
05/20/2024 14:37:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7174, 'learning_rate': 2.0866e-05, 'epoch': 5.52}
|
| 638 |
+
|
| 639 |
+
05/20/2024 14:37:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7339, 'learning_rate': 2.0679e-05, 'epoch': 5.55}
|
| 640 |
+
|
| 641 |
+
05/20/2024 14:38:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.7076, 'learning_rate': 2.0494e-05, 'epoch': 5.57}
|
| 642 |
+
|
| 643 |
+
05/20/2024 14:39:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7758, 'learning_rate': 2.0308e-05, 'epoch': 5.59}
|
| 644 |
+
|
| 645 |
+
05/20/2024 14:40:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7103, 'learning_rate': 2.0123e-05, 'epoch': 5.62}
|
| 646 |
+
|
| 647 |
+
05/20/2024 14:41:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.7470, 'learning_rate': 1.9938e-05, 'epoch': 5.64}
|
| 648 |
+
|
| 649 |
+
05/20/2024 14:41:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7325, 'learning_rate': 1.9753e-05, 'epoch': 5.67}
|
| 650 |
+
|
| 651 |
+
05/20/2024 14:42:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7336, 'learning_rate': 1.9569e-05, 'epoch': 5.69}
|
| 652 |
+
|
| 653 |
+
05/20/2024 14:43:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7238, 'learning_rate': 1.9384e-05, 'epoch': 5.71}
|
| 654 |
+
|
| 655 |
+
05/20/2024 14:44:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6934, 'learning_rate': 1.9201e-05, 'epoch': 5.74}
|
| 656 |
+
|
| 657 |
+
05/20/2024 14:44:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7573, 'learning_rate': 1.9017e-05, 'epoch': 5.76}
|
| 658 |
+
|
| 659 |
+
05/20/2024 14:44:55 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1200
|
| 660 |
+
|
| 661 |
+
05/20/2024 14:44:55 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1200/tokenizer_config.json
|
| 662 |
+
|
| 663 |
+
05/20/2024 14:44:55 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1200/special_tokens_map.json
|
| 664 |
+
|
| 665 |
+
05/20/2024 14:45:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7232, 'learning_rate': 1.8834e-05, 'epoch': 5.79}
|
| 666 |
+
|
| 667 |
+
05/20/2024 14:46:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.7221, 'learning_rate': 1.8651e-05, 'epoch': 5.81}
|
| 668 |
+
|
| 669 |
+
05/20/2024 14:47:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7550, 'learning_rate': 1.8469e-05, 'epoch': 5.83}
|
| 670 |
+
|
| 671 |
+
05/20/2024 14:48:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6962, 'learning_rate': 1.8287e-05, 'epoch': 5.86}
|
| 672 |
+
|
| 673 |
+
05/20/2024 14:48:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7443, 'learning_rate': 1.8105e-05, 'epoch': 5.88}
|
| 674 |
+
|
| 675 |
+
05/20/2024 14:49:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6654, 'learning_rate': 1.7924e-05, 'epoch': 5.91}
|
| 676 |
+
|
| 677 |
+
05/20/2024 14:50:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7271, 'learning_rate': 1.7743e-05, 'epoch': 5.93}
|
| 678 |
+
|
| 679 |
+
05/20/2024 14:51:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7538, 'learning_rate': 1.7562e-05, 'epoch': 5.95}
|
| 680 |
+
|
| 681 |
+
05/20/2024 14:51:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6795, 'learning_rate': 1.7382e-05, 'epoch': 5.98}
|
| 682 |
+
|
| 683 |
+
05/20/2024 14:52:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6446, 'learning_rate': 1.7203e-05, 'epoch': 6.00}
|
| 684 |
+
|
| 685 |
+
05/20/2024 14:53:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6994, 'learning_rate': 1.7024e-05, 'epoch': 6.03}
|
| 686 |
+
|
| 687 |
+
05/20/2024 14:54:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6886, 'learning_rate': 1.6845e-05, 'epoch': 6.05}
|
| 688 |
+
|
| 689 |
+
05/20/2024 14:54:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7485, 'learning_rate': 1.6667e-05, 'epoch': 6.07}
|
| 690 |
+
|
| 691 |
+
05/20/2024 14:55:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6399, 'learning_rate': 1.6489e-05, 'epoch': 6.10}
|
| 692 |
+
|
| 693 |
+
05/20/2024 14:56:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7799, 'learning_rate': 1.6312e-05, 'epoch': 6.12}
|
| 694 |
+
|
| 695 |
+
05/20/2024 14:57:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.7589, 'learning_rate': 1.6135e-05, 'epoch': 6.15}
|
| 696 |
+
|
| 697 |
+
05/20/2024 14:58:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6969, 'learning_rate': 1.5959e-05, 'epoch': 6.17}
|
| 698 |
+
|
| 699 |
+
05/20/2024 14:58:58 - INFO - llmtuner.extras.callbacks - {'loss': 0.7108, 'learning_rate': 1.5783e-05, 'epoch': 6.19}
|
| 700 |
+
|
| 701 |
+
05/20/2024 14:59:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7478, 'learning_rate': 1.5608e-05, 'epoch': 6.22}
|
| 702 |
+
|
| 703 |
+
05/20/2024 15:00:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7225, 'learning_rate': 1.5433e-05, 'epoch': 6.24}
|
| 704 |
+
|
| 705 |
+
05/20/2024 15:00:35 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1300
|
| 706 |
+
|
| 707 |
+
05/20/2024 15:00:35 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1300/tokenizer_config.json
|
| 708 |
+
|
| 709 |
+
05/20/2024 15:00:35 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1300/special_tokens_map.json
|
| 710 |
+
|
| 711 |
+
05/20/2024 15:01:20 - INFO - llmtuner.extras.callbacks - {'loss': 0.6964, 'learning_rate': 1.5259e-05, 'epoch': 6.27}
|
| 712 |
+
|
| 713 |
+
05/20/2024 15:02:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.7673, 'learning_rate': 1.5085e-05, 'epoch': 6.29}
|
| 714 |
+
|
| 715 |
+
05/20/2024 15:02:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.7194, 'learning_rate': 1.4912e-05, 'epoch': 6.31}
|
| 716 |
+
|
| 717 |
+
05/20/2024 15:03:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.6869, 'learning_rate': 1.4740e-05, 'epoch': 6.34}
|
| 718 |
+
|
| 719 |
+
05/20/2024 15:04:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6851, 'learning_rate': 1.4568e-05, 'epoch': 6.36}
|
| 720 |
+
|
| 721 |
+
05/20/2024 15:05:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.7242, 'learning_rate': 1.4397e-05, 'epoch': 6.39}
|
| 722 |
+
|
| 723 |
+
05/20/2024 15:05:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.7155, 'learning_rate': 1.4226e-05, 'epoch': 6.41}
|
| 724 |
+
|
| 725 |
+
05/20/2024 15:06:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6706, 'learning_rate': 1.4056e-05, 'epoch': 6.43}
|
| 726 |
+
|
| 727 |
+
05/20/2024 15:07:26 - INFO - llmtuner.extras.callbacks - {'loss': 0.6937, 'learning_rate': 1.3886e-05, 'epoch': 6.46}
|
| 728 |
+
|
| 729 |
+
05/20/2024 15:08:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.8316, 'learning_rate': 1.3718e-05, 'epoch': 6.48}
|
| 730 |
+
|
| 731 |
+
05/20/2024 15:09:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.7229, 'learning_rate': 1.3549e-05, 'epoch': 6.51}
|
| 732 |
+
|
| 733 |
+
05/20/2024 15:09:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7025, 'learning_rate': 1.3382e-05, 'epoch': 6.53}
|
| 734 |
+
|
| 735 |
+
05/20/2024 15:10:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7420, 'learning_rate': 1.3215e-05, 'epoch': 6.55}
|
| 736 |
+
|
| 737 |
+
05/20/2024 15:11:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6737, 'learning_rate': 1.3049e-05, 'epoch': 6.58}
|
| 738 |
+
|
| 739 |
+
05/20/2024 15:12:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7577, 'learning_rate': 1.2883e-05, 'epoch': 6.60}
|
| 740 |
+
|
| 741 |
+
05/20/2024 15:12:53 - INFO - llmtuner.extras.callbacks - {'loss': 0.6495, 'learning_rate': 1.2719e-05, 'epoch': 6.63}
|
| 742 |
+
|
| 743 |
+
05/20/2024 15:13:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7069, 'learning_rate': 1.2555e-05, 'epoch': 6.65}
|
| 744 |
+
|
| 745 |
+
05/20/2024 15:14:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7050, 'learning_rate': 1.2391e-05, 'epoch': 6.67}
|
| 746 |
+
|
| 747 |
+
05/20/2024 15:15:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6710, 'learning_rate': 1.2228e-05, 'epoch': 6.70}
|
| 748 |
+
|
| 749 |
+
05/20/2024 15:15:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7456, 'learning_rate': 1.2067e-05, 'epoch': 6.72}
|
| 750 |
+
|
| 751 |
+
05/20/2024 15:15:56 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1400
|
| 752 |
+
|
| 753 |
+
05/20/2024 15:15:57 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1400/tokenizer_config.json
|
| 754 |
+
|
| 755 |
+
05/20/2024 15:15:57 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1400/special_tokens_map.json
|
| 756 |
+
|
| 757 |
+
05/20/2024 15:16:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6899, 'learning_rate': 1.1905e-05, 'epoch': 6.75}
|
| 758 |
+
|
| 759 |
+
05/20/2024 15:17:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7024, 'learning_rate': 1.1745e-05, 'epoch': 6.77}
|
| 760 |
+
|
| 761 |
+
05/20/2024 15:18:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6571, 'learning_rate': 1.1585e-05, 'epoch': 6.79}
|
| 762 |
+
|
| 763 |
+
05/20/2024 15:19:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7290, 'learning_rate': 1.1426e-05, 'epoch': 6.82}
|
| 764 |
+
|
| 765 |
+
05/20/2024 15:19:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.7971, 'learning_rate': 1.1268e-05, 'epoch': 6.84}
|
| 766 |
+
|
| 767 |
+
05/20/2024 15:20:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.6376, 'learning_rate': 1.1111e-05, 'epoch': 6.87}
|
| 768 |
+
|
| 769 |
+
05/20/2024 15:21:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6663, 'learning_rate': 1.0954e-05, 'epoch': 6.89}
|
| 770 |
+
|
| 771 |
+
05/20/2024 15:22:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.6898, 'learning_rate': 1.0798e-05, 'epoch': 6.91}
|
| 772 |
+
|
| 773 |
+
05/20/2024 15:22:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.6860, 'learning_rate': 1.0643e-05, 'epoch': 6.94}
|
| 774 |
+
|
| 775 |
+
05/20/2024 15:23:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.7803, 'learning_rate': 1.0489e-05, 'epoch': 6.96}
|
| 776 |
+
|
| 777 |
+
05/20/2024 15:24:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6809, 'learning_rate': 1.0336e-05, 'epoch': 6.99}
|
| 778 |
+
|
| 779 |
+
05/20/2024 15:25:11 - INFO - llmtuner.extras.callbacks - {'loss': 0.6936, 'learning_rate': 1.0183e-05, 'epoch': 7.01}
|
| 780 |
+
|
| 781 |
+
05/20/2024 15:26:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7005, 'learning_rate': 1.0032e-05, 'epoch': 7.03}
|
| 782 |
+
|
| 783 |
+
05/20/2024 15:26:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.8484, 'learning_rate': 9.8810e-06, 'epoch': 7.06}
|
| 784 |
+
|
| 785 |
+
05/20/2024 15:27:38 - INFO - llmtuner.extras.callbacks - {'loss': 0.7897, 'learning_rate': 9.7311e-06, 'epoch': 7.08}
|
| 786 |
+
|
| 787 |
+
05/20/2024 15:28:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6696, 'learning_rate': 9.5820e-06, 'epoch': 7.11}
|
| 788 |
+
|
| 789 |
+
05/20/2024 15:29:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6867, 'learning_rate': 9.4339e-06, 'epoch': 7.13}
|
| 790 |
+
|
| 791 |
+
05/20/2024 15:29:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.7372, 'learning_rate': 9.2866e-06, 'epoch': 7.15}
|
| 792 |
+
|
| 793 |
+
05/20/2024 15:30:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.6718, 'learning_rate': 9.1402e-06, 'epoch': 7.18}
|
| 794 |
+
|
| 795 |
+
05/20/2024 15:31:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6819, 'learning_rate': 8.9947e-06, 'epoch': 7.20}
|
| 796 |
+
|
| 797 |
+
05/20/2024 15:31:24 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1500
|
| 798 |
+
|
| 799 |
+
05/20/2024 15:31:24 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1500/tokenizer_config.json
|
| 800 |
+
|
| 801 |
+
05/20/2024 15:31:24 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1500/special_tokens_map.json
|
| 802 |
+
|
| 803 |
+
05/20/2024 15:32:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7094, 'learning_rate': 8.8501e-06, 'epoch': 7.23}
|
| 804 |
+
|
| 805 |
+
05/20/2024 15:32:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7423, 'learning_rate': 8.7064e-06, 'epoch': 7.25}
|
| 806 |
+
|
| 807 |
+
05/20/2024 15:33:46 - INFO - llmtuner.extras.callbacks - {'loss': 0.6957, 'learning_rate': 8.5637e-06, 'epoch': 7.27}
|
| 808 |
+
|
| 809 |
+
05/20/2024 15:34:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6382, 'learning_rate': 8.4219e-06, 'epoch': 7.30}
|
| 810 |
+
|
| 811 |
+
05/20/2024 15:35:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6939, 'learning_rate': 8.2811e-06, 'epoch': 7.32}
|
| 812 |
+
|
| 813 |
+
05/20/2024 15:36:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7682, 'learning_rate': 8.1412e-06, 'epoch': 7.35}
|
| 814 |
+
|
| 815 |
+
05/20/2024 15:36:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6319, 'learning_rate': 8.0023e-06, 'epoch': 7.37}
|
| 816 |
+
|
| 817 |
+
05/20/2024 15:37:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.7331, 'learning_rate': 7.8643e-06, 'epoch': 7.39}
|
| 818 |
+
|
| 819 |
+
05/20/2024 15:38:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7249, 'learning_rate': 7.7273e-06, 'epoch': 7.42}
|
| 820 |
+
|
| 821 |
+
05/20/2024 15:39:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6484, 'learning_rate': 7.5913e-06, 'epoch': 7.44}
|
| 822 |
+
|
| 823 |
+
05/20/2024 15:39:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.7723, 'learning_rate': 7.4563e-06, 'epoch': 7.47}
|
| 824 |
+
|
| 825 |
+
05/20/2024 15:40:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7266, 'learning_rate': 7.3223e-06, 'epoch': 7.49}
|
| 826 |
+
|
| 827 |
+
05/20/2024 15:41:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.6927, 'learning_rate': 7.1893e-06, 'epoch': 7.52}
|
| 828 |
+
|
| 829 |
+
05/20/2024 15:42:22 - INFO - llmtuner.extras.callbacks - {'loss': 0.7219, 'learning_rate': 7.0574e-06, 'epoch': 7.54}
|
| 830 |
+
|
| 831 |
+
05/20/2024 15:43:09 - INFO - llmtuner.extras.callbacks - {'loss': 0.6933, 'learning_rate': 6.9264e-06, 'epoch': 7.56}
|
| 832 |
+
|
| 833 |
+
05/20/2024 15:43:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.7651, 'learning_rate': 6.7965e-06, 'epoch': 7.59}
|
| 834 |
+
|
| 835 |
+
05/20/2024 15:44:44 - INFO - llmtuner.extras.callbacks - {'loss': 0.6558, 'learning_rate': 6.6676e-06, 'epoch': 7.61}
|
| 836 |
+
|
| 837 |
+
05/20/2024 15:45:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6601, 'learning_rate': 6.5397e-06, 'epoch': 7.64}
|
| 838 |
+
|
| 839 |
+
05/20/2024 15:46:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6938, 'learning_rate': 6.4130e-06, 'epoch': 7.66}
|
| 840 |
+
|
| 841 |
+
05/20/2024 15:47:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.7301, 'learning_rate': 6.2872e-06, 'epoch': 7.68}
|
| 842 |
+
|
| 843 |
+
05/20/2024 15:47:01 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1600
|
| 844 |
+
|
| 845 |
+
05/20/2024 15:47:01 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1600/tokenizer_config.json
|
| 846 |
+
|
| 847 |
+
05/20/2024 15:47:01 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1600/special_tokens_map.json
|
| 848 |
+
|
| 849 |
+
05/20/2024 15:47:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.6848, 'learning_rate': 6.1626e-06, 'epoch': 7.71}
|
| 850 |
+
|
| 851 |
+
05/20/2024 15:48:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6372, 'learning_rate': 6.0390e-06, 'epoch': 7.73}
|
| 852 |
+
|
| 853 |
+
05/20/2024 15:49:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6736, 'learning_rate': 5.9165e-06, 'epoch': 7.76}
|
| 854 |
+
|
| 855 |
+
05/20/2024 15:50:04 - INFO - llmtuner.extras.callbacks - {'loss': 0.6915, 'learning_rate': 5.7951e-06, 'epoch': 7.78}
|
| 856 |
+
|
| 857 |
+
05/20/2024 15:50:52 - INFO - llmtuner.extras.callbacks - {'loss': 0.6960, 'learning_rate': 5.6747e-06, 'epoch': 7.80}
|
| 858 |
+
|
| 859 |
+
05/20/2024 15:51:39 - INFO - llmtuner.extras.callbacks - {'loss': 0.7064, 'learning_rate': 5.5555e-06, 'epoch': 7.83}
|
| 860 |
+
|
| 861 |
+
05/20/2024 15:52:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.7497, 'learning_rate': 5.4374e-06, 'epoch': 7.85}
|
| 862 |
+
|
| 863 |
+
05/20/2024 15:53:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7025, 'learning_rate': 5.3204e-06, 'epoch': 7.88}
|
| 864 |
+
|
| 865 |
+
05/20/2024 15:53:56 - INFO - llmtuner.extras.callbacks - {'loss': 0.6823, 'learning_rate': 5.2045e-06, 'epoch': 7.90}
|
| 866 |
+
|
| 867 |
+
05/20/2024 15:54:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.8013, 'learning_rate': 5.0898e-06, 'epoch': 7.92}
|
| 868 |
+
|
| 869 |
+
05/20/2024 15:55:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7497, 'learning_rate': 4.9762e-06, 'epoch': 7.95}
|
| 870 |
+
|
| 871 |
+
05/20/2024 15:56:15 - INFO - llmtuner.extras.callbacks - {'loss': 0.7817, 'learning_rate': 4.8637e-06, 'epoch': 7.97}
|
| 872 |
+
|
| 873 |
+
05/20/2024 15:57:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.6150, 'learning_rate': 4.7524e-06, 'epoch': 8.00}
|
| 874 |
+
|
| 875 |
+
05/20/2024 15:57:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7037, 'learning_rate': 4.6422e-06, 'epoch': 8.02}
|
| 876 |
+
|
| 877 |
+
05/20/2024 15:58:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6747, 'learning_rate': 4.5332e-06, 'epoch': 8.04}
|
| 878 |
+
|
| 879 |
+
05/20/2024 15:59:14 - INFO - llmtuner.extras.callbacks - {'loss': 0.7154, 'learning_rate': 4.4254e-06, 'epoch': 8.07}
|
| 880 |
+
|
| 881 |
+
05/20/2024 16:00:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7838, 'learning_rate': 4.3187e-06, 'epoch': 8.09}
|
| 882 |
+
|
| 883 |
+
05/20/2024 16:00:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7525, 'learning_rate': 4.2133e-06, 'epoch': 8.12}
|
| 884 |
+
|
| 885 |
+
05/20/2024 16:01:32 - INFO - llmtuner.extras.callbacks - {'loss': 0.6624, 'learning_rate': 4.1090e-06, 'epoch': 8.14}
|
| 886 |
+
|
| 887 |
+
05/20/2024 16:02:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6821, 'learning_rate': 4.0059e-06, 'epoch': 8.16}
|
| 888 |
+
|
| 889 |
+
05/20/2024 16:02:18 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1700
|
| 890 |
+
|
| 891 |
+
05/20/2024 16:02:18 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1700/tokenizer_config.json
|
| 892 |
+
|
| 893 |
+
05/20/2024 16:02:18 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1700/special_tokens_map.json
|
| 894 |
+
|
| 895 |
+
05/20/2024 16:03:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6932, 'learning_rate': 3.9040e-06, 'epoch': 8.19}
|
| 896 |
+
|
| 897 |
+
05/20/2024 16:03:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7308, 'learning_rate': 3.8032e-06, 'epoch': 8.21}
|
| 898 |
+
|
| 899 |
+
05/20/2024 16:04:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.7136, 'learning_rate': 3.7037e-06, 'epoch': 8.24}
|
| 900 |
+
|
| 901 |
+
05/20/2024 16:05:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.6595, 'learning_rate': 3.6055e-06, 'epoch': 8.26}
|
| 902 |
+
|
| 903 |
+
05/20/2024 16:06:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.7671, 'learning_rate': 3.5084e-06, 'epoch': 8.28}
|
| 904 |
+
|
| 905 |
+
05/20/2024 16:06:57 - INFO - llmtuner.extras.callbacks - {'loss': 0.6561, 'learning_rate': 3.4126e-06, 'epoch': 8.31}
|
| 906 |
+
|
| 907 |
+
05/20/2024 16:07:43 - INFO - llmtuner.extras.callbacks - {'loss': 0.6876, 'learning_rate': 3.3180e-06, 'epoch': 8.33}
|
| 908 |
+
|
| 909 |
+
05/20/2024 16:08:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.6819, 'learning_rate': 3.2246e-06, 'epoch': 8.36}
|
| 910 |
+
|
| 911 |
+
05/20/2024 16:09:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.7044, 'learning_rate': 3.1325e-06, 'epoch': 8.38}
|
| 912 |
+
|
| 913 |
+
05/20/2024 16:10:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6317, 'learning_rate': 3.0416e-06, 'epoch': 8.40}
|
| 914 |
+
|
| 915 |
+
05/20/2024 16:10:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6521, 'learning_rate': 2.9520e-06, 'epoch': 8.43}
|
| 916 |
+
|
| 917 |
+
05/20/2024 16:11:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.7572, 'learning_rate': 2.8636e-06, 'epoch': 8.45}
|
| 918 |
+
|
| 919 |
+
05/20/2024 16:12:27 - INFO - llmtuner.extras.callbacks - {'loss': 0.7184, 'learning_rate': 2.7765e-06, 'epoch': 8.48}
|
| 920 |
+
|
| 921 |
+
05/20/2024 16:13:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6881, 'learning_rate': 2.6907e-06, 'epoch': 8.50}
|
| 922 |
+
|
| 923 |
+
05/20/2024 16:14:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6575, 'learning_rate': 2.6061e-06, 'epoch': 8.52}
|
| 924 |
+
|
| 925 |
+
05/20/2024 16:14:45 - INFO - llmtuner.extras.callbacks - {'loss': 0.7457, 'learning_rate': 2.5228e-06, 'epoch': 8.55}
|
| 926 |
+
|
| 927 |
+
05/20/2024 16:15:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7127, 'learning_rate': 2.4408e-06, 'epoch': 8.57}
|
| 928 |
+
|
| 929 |
+
05/20/2024 16:16:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7442, 'learning_rate': 2.3601e-06, 'epoch': 8.60}
|
| 930 |
+
|
| 931 |
+
05/20/2024 16:17:03 - INFO - llmtuner.extras.callbacks - {'loss': 0.6743, 'learning_rate': 2.2806e-06, 'epoch': 8.62}
|
| 932 |
+
|
| 933 |
+
05/20/2024 16:17:50 - INFO - llmtuner.extras.callbacks - {'loss': 0.7338, 'learning_rate': 2.2025e-06, 'epoch': 8.64}
|
| 934 |
+
|
| 935 |
+
05/20/2024 16:17:50 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1800
|
| 936 |
+
|
| 937 |
+
05/20/2024 16:17:50 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1800/tokenizer_config.json
|
| 938 |
+
|
| 939 |
+
05/20/2024 16:17:50 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1800/special_tokens_map.json
|
| 940 |
+
|
| 941 |
+
05/20/2024 16:18:35 - INFO - llmtuner.extras.callbacks - {'loss': 0.7514, 'learning_rate': 2.1257e-06, 'epoch': 8.67}
|
| 942 |
+
|
| 943 |
+
05/20/2024 16:19:24 - INFO - llmtuner.extras.callbacks - {'loss': 0.7774, 'learning_rate': 2.0501e-06, 'epoch': 8.69}
|
| 944 |
+
|
| 945 |
+
05/20/2024 16:20:12 - INFO - llmtuner.extras.callbacks - {'loss': 0.6895, 'learning_rate': 1.9759e-06, 'epoch': 8.72}
|
| 946 |
+
|
| 947 |
+
05/20/2024 16:21:00 - INFO - llmtuner.extras.callbacks - {'loss': 0.7218, 'learning_rate': 1.9030e-06, 'epoch': 8.74}
|
| 948 |
+
|
| 949 |
+
05/20/2024 16:21:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7553, 'learning_rate': 1.8314e-06, 'epoch': 8.76}
|
| 950 |
+
|
| 951 |
+
05/20/2024 16:22:34 - INFO - llmtuner.extras.callbacks - {'loss': 0.6779, 'learning_rate': 1.7612e-06, 'epoch': 8.79}
|
| 952 |
+
|
| 953 |
+
05/20/2024 16:23:19 - INFO - llmtuner.extras.callbacks - {'loss': 0.6946, 'learning_rate': 1.6922e-06, 'epoch': 8.81}
|
| 954 |
+
|
| 955 |
+
05/20/2024 16:24:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7149, 'learning_rate': 1.6246e-06, 'epoch': 8.84}
|
| 956 |
+
|
| 957 |
+
05/20/2024 16:24:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6681, 'learning_rate': 1.5583e-06, 'epoch': 8.86}
|
| 958 |
+
|
| 959 |
+
05/20/2024 16:25:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6519, 'learning_rate': 1.4934e-06, 'epoch': 8.88}
|
| 960 |
+
|
| 961 |
+
05/20/2024 16:26:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6957, 'learning_rate': 1.4298e-06, 'epoch': 8.91}
|
| 962 |
+
|
| 963 |
+
05/20/2024 16:27:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.6942, 'learning_rate': 1.3675e-06, 'epoch': 8.93}
|
| 964 |
+
|
| 965 |
+
05/20/2024 16:28:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6578, 'learning_rate': 1.3066e-06, 'epoch': 8.96}
|
| 966 |
+
|
| 967 |
+
05/20/2024 16:28:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.6994, 'learning_rate': 1.2470e-06, 'epoch': 8.98}
|
| 968 |
+
|
| 969 |
+
05/20/2024 16:29:36 - INFO - llmtuner.extras.callbacks - {'loss': 0.6430, 'learning_rate': 1.1888e-06, 'epoch': 9.00}
|
| 970 |
+
|
| 971 |
+
05/20/2024 16:30:21 - INFO - llmtuner.extras.callbacks - {'loss': 0.6307, 'learning_rate': 1.1320e-06, 'epoch': 9.03}
|
| 972 |
+
|
| 973 |
+
05/20/2024 16:31:08 - INFO - llmtuner.extras.callbacks - {'loss': 0.7088, 'learning_rate': 1.0765e-06, 'epoch': 9.05}
|
| 974 |
+
|
| 975 |
+
05/20/2024 16:31:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6603, 'learning_rate': 1.0224e-06, 'epoch': 9.08}
|
| 976 |
+
|
| 977 |
+
05/20/2024 16:32:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.8255, 'learning_rate': 9.6961e-07, 'epoch': 9.10}
|
| 978 |
+
|
| 979 |
+
05/20/2024 16:33:28 - INFO - llmtuner.extras.callbacks - {'loss': 0.6834, 'learning_rate': 9.1823e-07, 'epoch': 9.12}
|
| 980 |
+
|
| 981 |
+
05/20/2024 16:33:28 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1900
|
| 982 |
+
|
| 983 |
+
05/20/2024 16:33:28 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1900/tokenizer_config.json
|
| 984 |
+
|
| 985 |
+
05/20/2024 16:33:28 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-1900/special_tokens_map.json
|
| 986 |
+
|
| 987 |
+
05/20/2024 16:34:13 - INFO - llmtuner.extras.callbacks - {'loss': 0.6365, 'learning_rate': 8.6822e-07, 'epoch': 9.15}
|
| 988 |
+
|
| 989 |
+
05/20/2024 16:35:02 - INFO - llmtuner.extras.callbacks - {'loss': 0.7317, 'learning_rate': 8.1958e-07, 'epoch': 9.17}
|
| 990 |
+
|
| 991 |
+
05/20/2024 16:35:47 - INFO - llmtuner.extras.callbacks - {'loss': 0.7410, 'learning_rate': 7.7233e-07, 'epoch': 9.20}
|
| 992 |
+
|
| 993 |
+
05/20/2024 16:36:31 - INFO - llmtuner.extras.callbacks - {'loss': 0.6881, 'learning_rate': 7.2645e-07, 'epoch': 9.22}
|
| 994 |
+
|
| 995 |
+
05/20/2024 16:37:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.7350, 'learning_rate': 6.8196e-07, 'epoch': 9.24}
|
| 996 |
+
|
| 997 |
+
05/20/2024 16:38:06 - INFO - llmtuner.extras.callbacks - {'loss': 0.7227, 'learning_rate': 6.3886e-07, 'epoch': 9.27}
|
| 998 |
+
|
| 999 |
+
05/20/2024 16:38:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6810, 'learning_rate': 5.9715e-07, 'epoch': 9.29}
|
| 1000 |
+
|
| 1001 |
+
05/20/2024 16:39:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7081, 'learning_rate': 5.5683e-07, 'epoch': 9.32}
|
| 1002 |
+
|
| 1003 |
+
05/20/2024 16:40:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7064, 'learning_rate': 5.1790e-07, 'epoch': 9.34}
|
| 1004 |
+
|
| 1005 |
+
05/20/2024 16:41:17 - INFO - llmtuner.extras.callbacks - {'loss': 0.6829, 'learning_rate': 4.8037e-07, 'epoch': 9.36}
|
| 1006 |
+
|
| 1007 |
+
05/20/2024 16:42:01 - INFO - llmtuner.extras.callbacks - {'loss': 0.6814, 'learning_rate': 4.4423e-07, 'epoch': 9.39}
|
| 1008 |
+
|
| 1009 |
+
05/20/2024 16:42:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7690, 'learning_rate': 4.0950e-07, 'epoch': 9.41}
|
| 1010 |
+
|
| 1011 |
+
05/20/2024 16:43:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7539, 'learning_rate': 3.7617e-07, 'epoch': 9.44}
|
| 1012 |
+
|
| 1013 |
+
05/20/2024 16:44:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.6506, 'learning_rate': 3.4425e-07, 'epoch': 9.46}
|
| 1014 |
+
|
| 1015 |
+
05/20/2024 16:45:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.6763, 'learning_rate': 3.1373e-07, 'epoch': 9.48}
|
| 1016 |
+
|
| 1017 |
+
05/20/2024 16:45:51 - INFO - llmtuner.extras.callbacks - {'loss': 0.6776, 'learning_rate': 2.8461e-07, 'epoch': 9.51}
|
| 1018 |
+
|
| 1019 |
+
05/20/2024 16:46:37 - INFO - llmtuner.extras.callbacks - {'loss': 0.7292, 'learning_rate': 2.5691e-07, 'epoch': 9.53}
|
| 1020 |
+
|
| 1021 |
+
05/20/2024 16:47:23 - INFO - llmtuner.extras.callbacks - {'loss': 0.8111, 'learning_rate': 2.3062e-07, 'epoch': 9.56}
|
| 1022 |
+
|
| 1023 |
+
05/20/2024 16:48:05 - INFO - llmtuner.extras.callbacks - {'loss': 0.6473, 'learning_rate': 2.0574e-07, 'epoch': 9.58}
|
| 1024 |
+
|
| 1025 |
+
05/20/2024 16:48:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.6774, 'learning_rate': 1.8228e-07, 'epoch': 9.60}
|
| 1026 |
+
|
| 1027 |
+
05/20/2024 16:48:54 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-2000
|
| 1028 |
+
|
| 1029 |
+
05/20/2024 16:48:54 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-2000/tokenizer_config.json
|
| 1030 |
+
|
| 1031 |
+
05/20/2024 16:48:54 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/checkpoint-2000/special_tokens_map.json
|
| 1032 |
+
|
| 1033 |
+
05/20/2024 16:49:40 - INFO - llmtuner.extras.callbacks - {'loss': 0.6782, 'learning_rate': 1.6023e-07, 'epoch': 9.63}
|
| 1034 |
+
|
| 1035 |
+
05/20/2024 16:50:25 - INFO - llmtuner.extras.callbacks - {'loss': 0.6965, 'learning_rate': 1.3960e-07, 'epoch': 9.65}
|
| 1036 |
+
|
| 1037 |
+
05/20/2024 16:51:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.6496, 'learning_rate': 1.2038e-07, 'epoch': 9.68}
|
| 1038 |
+
|
| 1039 |
+
05/20/2024 16:51:59 - INFO - llmtuner.extras.callbacks - {'loss': 0.6511, 'learning_rate': 1.0259e-07, 'epoch': 9.70}
|
| 1040 |
+
|
| 1041 |
+
05/20/2024 16:52:49 - INFO - llmtuner.extras.callbacks - {'loss': 0.7524, 'learning_rate': 8.6210e-08, 'epoch': 9.72}
|
| 1042 |
+
|
| 1043 |
+
05/20/2024 16:53:33 - INFO - llmtuner.extras.callbacks - {'loss': 0.6653, 'learning_rate': 7.1255e-08, 'epoch': 9.75}
|
| 1044 |
+
|
| 1045 |
+
05/20/2024 16:54:18 - INFO - llmtuner.extras.callbacks - {'loss': 0.6718, 'learning_rate': 5.7722e-08, 'epoch': 9.77}
|
| 1046 |
+
|
| 1047 |
+
05/20/2024 16:55:07 - INFO - llmtuner.extras.callbacks - {'loss': 0.7114, 'learning_rate': 4.5611e-08, 'epoch': 9.80}
|
| 1048 |
+
|
| 1049 |
+
05/20/2024 16:55:54 - INFO - llmtuner.extras.callbacks - {'loss': 0.7125, 'learning_rate': 3.4924e-08, 'epoch': 9.82}
|
| 1050 |
+
|
| 1051 |
+
05/20/2024 16:56:42 - INFO - llmtuner.extras.callbacks - {'loss': 0.6236, 'learning_rate': 2.5660e-08, 'epoch': 9.84}
|
| 1052 |
+
|
| 1053 |
+
05/20/2024 16:57:30 - INFO - llmtuner.extras.callbacks - {'loss': 0.7353, 'learning_rate': 1.7820e-08, 'epoch': 9.87}
|
| 1054 |
+
|
| 1055 |
+
05/20/2024 16:58:16 - INFO - llmtuner.extras.callbacks - {'loss': 0.7489, 'learning_rate': 1.1405e-08, 'epoch': 9.89}
|
| 1056 |
+
|
| 1057 |
+
05/20/2024 16:59:10 - INFO - llmtuner.extras.callbacks - {'loss': 0.7743, 'learning_rate': 6.4157e-09, 'epoch': 9.92}
|
| 1058 |
+
|
| 1059 |
+
05/20/2024 16:59:55 - INFO - llmtuner.extras.callbacks - {'loss': 0.6435, 'learning_rate': 2.8515e-09, 'epoch': 9.94}
|
| 1060 |
+
|
| 1061 |
+
05/20/2024 17:00:41 - INFO - llmtuner.extras.callbacks - {'loss': 0.7375, 'learning_rate': 7.1289e-10, 'epoch': 9.96}
|
| 1062 |
+
|
| 1063 |
+
05/20/2024 17:01:29 - INFO - llmtuner.extras.callbacks - {'loss': 0.7238, 'learning_rate': 0.0000e+00, 'epoch': 9.99}
|
| 1064 |
+
|
| 1065 |
+
05/20/2024 17:01:29 - INFO - transformers.trainer -
|
| 1066 |
+
|
| 1067 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
| 1068 |
+
|
| 1069 |
+
|
| 1070 |
+
|
| 1071 |
+
05/20/2024 17:01:29 - INFO - transformers.trainer - Saving model checkpoint to /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed
|
| 1072 |
+
|
| 1073 |
+
05/20/2024 17:01:29 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/tokenizer_config.json
|
| 1074 |
+
|
| 1075 |
+
05/20/2024 17:01:29 - INFO - transformers.tokenization_utils_base - Special tokens file saved in /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed/special_tokens_map.json
|
| 1076 |
+
|
| 1077 |
+
05/20/2024 17:01:29 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
|
| 1078 |
+
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
|
| 1079 |
+
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.987995198079231,
|
| 3 |
+
"total_flos": 8.185270082173747e+17,
|
| 4 |
+
"train_loss": 0.7521515275423344,
|
| 5 |
+
"train_runtime": 19400.1091,
|
| 6 |
+
"train_samples_per_second": 1.717,
|
| 7 |
+
"train_steps_per_second": 0.107
|
| 8 |
+
}
|
trainer_config.yaml
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
cutoff_len: 4096
|
| 2 |
+
dataset: LangGPT_community,LangGPT_seed
|
| 3 |
+
dataset_dir: /datas/wangm/LLM4LangGPT
|
| 4 |
+
do_train: true
|
| 5 |
+
finetuning_type: lora
|
| 6 |
+
flash_attn: auto
|
| 7 |
+
fp16: true
|
| 8 |
+
gradient_accumulation_steps: 8
|
| 9 |
+
learning_rate: 5.0e-05
|
| 10 |
+
logging_steps: 5
|
| 11 |
+
lora_alpha: 16
|
| 12 |
+
lora_dropout: 0
|
| 13 |
+
lora_rank: 8
|
| 14 |
+
lora_target: q_proj,v_proj
|
| 15 |
+
lr_scheduler_type: cosine
|
| 16 |
+
max_grad_norm: 1.0
|
| 17 |
+
max_samples: 100000
|
| 18 |
+
model_name_or_path: Qwen/Qwen1.5-4B-Chat
|
| 19 |
+
num_train_epochs: 10.0
|
| 20 |
+
optim: adamw_torch
|
| 21 |
+
output_dir: /datas/wangm/LLM4LangGPT/output/Qwen1.5-4B-Chat/sft_seed
|
| 22 |
+
packing: false
|
| 23 |
+
per_device_train_batch_size: 2
|
| 24 |
+
report_to: none
|
| 25 |
+
save_steps: 100
|
| 26 |
+
stage: sft
|
| 27 |
+
template: default
|
| 28 |
+
warmup_steps: 0
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 2080, "loss": 1.2537, "learning_rate": 4.9999287112445194e-05, "epoch": 0.024009603841536616, "percentage": 0.24, "elapsed_time": "0:00:46", "remaining_time": "5:19:23"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 2080, "loss": 1.1695, "learning_rate": 4.999714849043745e-05, "epoch": 0.04801920768307323, "percentage": 0.48, "elapsed_time": "0:01:39", "remaining_time": "5:44:44"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 2080, "loss": 1.1879, "learning_rate": 4.999358425594454e-05, "epoch": 0.07202881152460984, "percentage": 0.72, "elapsed_time": "0:02:27", "remaining_time": "5:38:33"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 2080, "loss": 1.0137, "learning_rate": 4.9988594612238336e-05, "epoch": 0.09603841536614646, "percentage": 0.96, "elapsed_time": "0:03:11", "remaining_time": "5:28:42"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 2080, "loss": 1.1109, "learning_rate": 4.9982179843883225e-05, "epoch": 0.12004801920768307, "percentage": 1.2, "elapsed_time": "0:03:58", "remaining_time": "5:27:12"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 2080, "loss": 1.04, "learning_rate": 4.9974340316719906e-05, "epoch": 0.14405762304921968, "percentage": 1.44, "elapsed_time": "0:04:45", "remaining_time": "5:25:25"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 2080, "loss": 1.0158, "learning_rate": 4.996507647784446e-05, "epoch": 0.16806722689075632, "percentage": 1.68, "elapsed_time": "0:05:31", "remaining_time": "5:22:57"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 2080, "loss": 0.9004, "learning_rate": 4.995438885558294e-05, "epoch": 0.19207683073229292, "percentage": 1.92, "elapsed_time": "0:06:15", "remaining_time": "5:18:57"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 2080, "loss": 0.9626, "learning_rate": 4.9942278059461175e-05, "epoch": 0.21608643457382953, "percentage": 2.16, "elapsed_time": "0:07:01", "remaining_time": "5:17:19"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 2080, "loss": 1.0787, "learning_rate": 4.992874478017003e-05, "epoch": 0.24009603841536614, "percentage": 2.4, "elapsed_time": "0:07:47", "remaining_time": "5:16:39"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 2080, "loss": 0.8533, "learning_rate": 4.9913789789526023e-05, "epoch": 0.26410564225690275, "percentage": 2.64, "elapsed_time": "0:08:31", "remaining_time": "5:14:00"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 2080, "loss": 0.9406, "learning_rate": 4.989741394042727e-05, "epoch": 0.28811524609843936, "percentage": 2.88, "elapsed_time": "0:09:17", "remaining_time": "5:13:05"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 2080, "loss": 1.0017, "learning_rate": 4.987961816680492e-05, "epoch": 0.31212484993997597, "percentage": 3.12, "elapsed_time": "0:10:07", "remaining_time": "5:13:49"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 2080, "loss": 0.8902, "learning_rate": 4.9860403483569805e-05, "epoch": 0.33613445378151263, "percentage": 3.37, "elapsed_time": "0:10:52", "remaining_time": "5:12:07"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 2080, "loss": 0.907, "learning_rate": 4.983977098655461e-05, "epoch": 0.36014405762304924, "percentage": 3.61, "elapsed_time": "0:11:42", "remaining_time": "5:13:03"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 2080, "loss": 1.0197, "learning_rate": 4.981772185245135e-05, "epoch": 0.38415366146458585, "percentage": 3.85, "elapsed_time": "0:12:30", "remaining_time": "5:12:54"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 2080, "loss": 0.8131, "learning_rate": 4.979425733874431e-05, "epoch": 0.40816326530612246, "percentage": 4.09, "elapsed_time": "0:13:15", "remaining_time": "5:11:15"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 2080, "loss": 0.8665, "learning_rate": 4.9769378783638255e-05, "epoch": 0.43217286914765907, "percentage": 4.33, "elapsed_time": "0:14:02", "remaining_time": "5:10:39"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 2080, "loss": 0.9219, "learning_rate": 4.974308760598218e-05, "epoch": 0.4561824729891957, "percentage": 4.57, "elapsed_time": "0:14:49", "remaining_time": "5:09:46"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 2080, "loss": 0.9425, "learning_rate": 4.971538530518836e-05, "epoch": 0.4801920768307323, "percentage": 4.81, "elapsed_time": "0:15:37", "remaining_time": "5:09:17"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 2080, "loss": 0.8781, "learning_rate": 4.968627346114681e-05, "epoch": 0.5042016806722689, "percentage": 5.05, "elapsed_time": "0:16:23", "remaining_time": "5:08:26"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 2080, "loss": 0.8446, "learning_rate": 4.965575373413527e-05, "epoch": 0.5282112845138055, "percentage": 5.29, "elapsed_time": "0:17:09", "remaining_time": "5:07:22"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 2080, "loss": 0.9453, "learning_rate": 4.9623827864724394e-05, "epoch": 0.5522208883553421, "percentage": 5.53, "elapsed_time": "0:17:54", "remaining_time": "5:05:55"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 2080, "loss": 0.8086, "learning_rate": 4.959049767367859e-05, "epoch": 0.5762304921968787, "percentage": 5.77, "elapsed_time": "0:18:38", "remaining_time": "5:04:26"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 2080, "loss": 0.8657, "learning_rate": 4.955576506185213e-05, "epoch": 0.6002400960384153, "percentage": 6.01, "elapsed_time": "0:19:23", "remaining_time": "5:03:19"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 2080, "loss": 0.9168, "learning_rate": 4.951963201008076e-05, "epoch": 0.6242496998799519, "percentage": 6.25, "elapsed_time": "0:20:09", "remaining_time": "5:02:22"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 2080, "loss": 0.9192, "learning_rate": 4.9482100579068706e-05, "epoch": 0.6482593037214885, "percentage": 6.49, "elapsed_time": "0:20:58", "remaining_time": "5:02:07"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 2080, "loss": 0.7927, "learning_rate": 4.944317290927117e-05, "epoch": 0.6722689075630253, "percentage": 6.73, "elapsed_time": "0:21:42", "remaining_time": "5:00:52"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 2080, "loss": 0.8486, "learning_rate": 4.9402851220772274e-05, "epoch": 0.6962785114045619, "percentage": 6.97, "elapsed_time": "0:22:32", "remaining_time": "5:00:42"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 2080, "loss": 0.7937, "learning_rate": 4.93611378131584e-05, "epoch": 0.7202881152460985, "percentage": 7.21, "elapsed_time": "0:23:15", "remaining_time": "4:59:16"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 2080, "loss": 0.834, "learning_rate": 4.931803506538707e-05, "epoch": 0.7442977190876351, "percentage": 7.45, "elapsed_time": "0:24:01", "remaining_time": "4:58:22"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 2080, "loss": 0.7799, "learning_rate": 4.92735454356513e-05, "epoch": 0.7683073229291717, "percentage": 7.69, "elapsed_time": "0:24:50", "remaining_time": "4:58:07"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 2080, "loss": 0.8608, "learning_rate": 4.9227671461239354e-05, "epoch": 0.7923169267707083, "percentage": 7.93, "elapsed_time": "0:25:37", "remaining_time": "4:57:28"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 2080, "loss": 0.8872, "learning_rate": 4.918041575839007e-05, "epoch": 0.8163265306122449, "percentage": 8.17, "elapsed_time": "0:26:26", "remaining_time": "4:57:01"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 2080, "loss": 0.8681, "learning_rate": 4.913178102214363e-05, "epoch": 0.8403361344537815, "percentage": 8.41, "elapsed_time": "0:27:10", "remaining_time": "4:55:47"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 2080, "loss": 0.8451, "learning_rate": 4.9081770026187914e-05, "epoch": 0.8643457382953181, "percentage": 8.65, "elapsed_time": "0:27:57", "remaining_time": "4:55:10"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 2080, "loss": 0.8662, "learning_rate": 4.9030385622700225e-05, "epoch": 0.8883553421368547, "percentage": 8.89, "elapsed_time": "0:28:46", "remaining_time": "4:54:44"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 2080, "loss": 0.8183, "learning_rate": 4.897763074218472e-05, "epoch": 0.9123649459783914, "percentage": 9.13, "elapsed_time": "0:29:32", "remaining_time": "4:53:46"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 2080, "loss": 0.8887, "learning_rate": 4.892350839330522e-05, "epoch": 0.936374549819928, "percentage": 9.38, "elapsed_time": "0:30:18", "remaining_time": "4:52:54"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 2080, "loss": 0.8505, "learning_rate": 4.886802166271364e-05, "epoch": 0.9603841536614646, "percentage": 9.62, "elapsed_time": "0:31:07", "remaining_time": "4:52:36"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 2080, "loss": 0.835, "learning_rate": 4.881117371487396e-05, "epoch": 0.9843937575030012, "percentage": 9.86, "elapsed_time": "0:31:52", "remaining_time": "4:51:34"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 2080, "loss": 0.8531, "learning_rate": 4.875296779188173e-05, "epoch": 1.0084033613445378, "percentage": 10.1, "elapsed_time": "0:32:43", "remaining_time": "4:51:21"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 2080, "loss": 0.8679, "learning_rate": 4.8693407213279206e-05, "epoch": 1.0324129651860745, "percentage": 10.34, "elapsed_time": "0:33:29", "remaining_time": "4:50:28"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 2080, "loss": 0.8432, "learning_rate": 4.8632495375866004e-05, "epoch": 1.056422569027611, "percentage": 10.58, "elapsed_time": "0:34:16", "remaining_time": "4:49:43"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 2080, "loss": 0.8362, "learning_rate": 4.8570235753505406e-05, "epoch": 1.0804321728691477, "percentage": 10.82, "elapsed_time": "0:35:03", "remaining_time": "4:49:00"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 2080, "loss": 0.7704, "learning_rate": 4.850663189692619e-05, "epoch": 1.1044417767106842, "percentage": 11.06, "elapsed_time": "0:35:49", "remaining_time": "4:48:09"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 2080, "loss": 0.8357, "learning_rate": 4.844168743352019e-05, "epoch": 1.128451380552221, "percentage": 11.3, "elapsed_time": "0:36:34", "remaining_time": "4:47:08"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 2080, "loss": 0.7461, "learning_rate": 4.837540606713538e-05, "epoch": 1.1524609843937574, "percentage": 11.54, "elapsed_time": "0:37:17", "remaining_time": "4:45:51"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 2080, "loss": 0.8821, "learning_rate": 4.830779157786465e-05, "epoch": 1.1764705882352942, "percentage": 11.78, "elapsed_time": "0:38:05", "remaining_time": "4:45:16"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 2080, "loss": 0.889, "learning_rate": 4.823884782183023e-05, "epoch": 1.2004801920768307, "percentage": 12.02, "elapsed_time": "0:38:53", "remaining_time": "4:44:42"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 2080, "loss": 0.7407, "learning_rate": 4.8168578730963804e-05, "epoch": 1.2244897959183674, "percentage": 12.26, "elapsed_time": "0:39:41", "remaining_time": "4:44:03"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 2080, "loss": 0.7822, "learning_rate": 4.8096988312782174e-05, "epoch": 1.2484993997599039, "percentage": 12.5, "elapsed_time": "0:40:25", "remaining_time": "4:43:00"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 2080, "loss": 0.9008, "learning_rate": 4.80240806501588e-05, "epoch": 1.2725090036014406, "percentage": 12.74, "elapsed_time": "0:41:13", "remaining_time": "4:42:23"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 2080, "loss": 0.7477, "learning_rate": 4.7949859901090896e-05, "epoch": 1.296518607442977, "percentage": 12.98, "elapsed_time": "0:41:56", "remaining_time": "4:41:12"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 2080, "loss": 0.7846, "learning_rate": 4.787433029846236e-05, "epoch": 1.3205282112845138, "percentage": 13.22, "elapsed_time": "0:42:41", "remaining_time": "4:40:11"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 2080, "loss": 0.8544, "learning_rate": 4.7797496149802256e-05, "epoch": 1.3445378151260505, "percentage": 13.46, "elapsed_time": "0:43:29", "remaining_time": "4:39:34"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 2080, "loss": 0.7706, "learning_rate": 4.771936183703927e-05, "epoch": 1.368547418967587, "percentage": 13.7, "elapsed_time": "0:44:13", "remaining_time": "4:38:31"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 2080, "loss": 0.8256, "learning_rate": 4.763993181625174e-05, "epoch": 1.3925570228091235, "percentage": 13.94, "elapsed_time": "0:45:00", "remaining_time": "4:37:48"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 2080, "loss": 0.8185, "learning_rate": 4.7559210617413514e-05, "epoch": 1.4165666266506602, "percentage": 14.18, "elapsed_time": "0:45:46", "remaining_time": "4:36:59"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 2080, "loss": 0.7356, "learning_rate": 4.7477202844135646e-05, "epoch": 1.440576230492197, "percentage": 14.42, "elapsed_time": "0:46:32", "remaining_time": "4:36:08"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 2080, "loss": 0.8015, "learning_rate": 4.739391317340383e-05, "epoch": 1.4645858343337335, "percentage": 14.66, "elapsed_time": "0:47:19", "remaining_time": "4:35:24"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 2080, "loss": 0.8103, "learning_rate": 4.730934635531161e-05, "epoch": 1.4885954381752702, "percentage": 14.9, "elapsed_time": "0:48:05", "remaining_time": "4:34:36"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 2080, "loss": 0.6949, "learning_rate": 4.722350721278958e-05, "epoch": 1.5126050420168067, "percentage": 15.14, "elapsed_time": "0:48:50", "remaining_time": "4:33:40"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 2080, "loss": 0.779, "learning_rate": 4.713640064133025e-05, "epoch": 1.5366146458583434, "percentage": 15.38, "elapsed_time": "0:49:37", "remaining_time": "4:32:58"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 2080, "loss": 0.8016, "learning_rate": 4.7048031608708876e-05, "epoch": 1.5606242496998801, "percentage": 15.62, "elapsed_time": "0:50:23", "remaining_time": "4:32:08"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 2080, "loss": 0.746, "learning_rate": 4.6958405154700154e-05, "epoch": 1.5846338535414166, "percentage": 15.87, "elapsed_time": "0:51:13", "remaining_time": "4:31:37"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 2080, "loss": 0.7439, "learning_rate": 4.686752639079076e-05, "epoch": 1.6086434573829531, "percentage": 16.11, "elapsed_time": "0:51:58", "remaining_time": "4:30:43"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 2080, "loss": 0.7969, "learning_rate": 4.677540049988789e-05, "epoch": 1.6326530612244898, "percentage": 16.35, "elapsed_time": "0:52:46", "remaining_time": "4:30:04"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 2080, "loss": 0.858, "learning_rate": 4.668203273602363e-05, "epoch": 1.6566626650660266, "percentage": 16.59, "elapsed_time": "0:53:32", "remaining_time": "4:29:14"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 2080, "loss": 0.8538, "learning_rate": 4.6587428424055326e-05, "epoch": 1.680672268907563, "percentage": 16.83, "elapsed_time": "0:54:21", "remaining_time": "4:28:41"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 2080, "loss": 0.8241, "learning_rate": 4.649159295936191e-05, "epoch": 1.7046818727490995, "percentage": 17.07, "elapsed_time": "0:55:14", "remaining_time": "4:28:24"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 2080, "loss": 0.7388, "learning_rate": 4.639453180753619e-05, "epoch": 1.7286914765906363, "percentage": 17.31, "elapsed_time": "0:56:04", "remaining_time": "4:27:55"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 2080, "loss": 0.7924, "learning_rate": 4.6296250504073145e-05, "epoch": 1.752701080432173, "percentage": 17.55, "elapsed_time": "0:56:50", "remaining_time": "4:27:02"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 2080, "loss": 0.7719, "learning_rate": 4.6196754654054216e-05, "epoch": 1.7767106842737095, "percentage": 17.79, "elapsed_time": "0:57:35", "remaining_time": "4:26:09"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 2080, "loss": 0.8365, "learning_rate": 4.609604993182767e-05, "epoch": 1.800720288115246, "percentage": 18.03, "elapsed_time": "0:58:18", "remaining_time": "4:25:08"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 2080, "loss": 0.8118, "learning_rate": 4.599414208068495e-05, "epoch": 1.8247298919567827, "percentage": 18.27, "elapsed_time": "0:59:05", "remaining_time": "4:24:22"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 2080, "loss": 0.7881, "learning_rate": 4.589103691253317e-05, "epoch": 1.8487394957983194, "percentage": 18.51, "elapsed_time": "0:59:52", "remaining_time": "4:23:35"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 2080, "loss": 0.7155, "learning_rate": 4.5786740307563636e-05, "epoch": 1.872749099639856, "percentage": 18.75, "elapsed_time": "1:00:39", "remaining_time": "4:22:50"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 2080, "loss": 0.8555, "learning_rate": 4.568125821391647e-05, "epoch": 1.8967587034813924, "percentage": 18.99, "elapsed_time": "1:01:28", "remaining_time": "4:22:15"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 2080, "loss": 0.8685, "learning_rate": 4.557459664734141e-05, "epoch": 1.9207683073229291, "percentage": 19.23, "elapsed_time": "1:02:16", "remaining_time": "4:21:33"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 2080, "loss": 0.7708, "learning_rate": 4.5466761690854746e-05, "epoch": 1.9447779111644659, "percentage": 19.47, "elapsed_time": "1:03:05", "remaining_time": "4:20:57"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 2080, "loss": 0.8448, "learning_rate": 4.535775949439235e-05, "epoch": 1.9687875150060024, "percentage": 19.71, "elapsed_time": "1:03:55", "remaining_time": "4:20:21"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 2080, "loss": 0.736, "learning_rate": 4.5247596274458956e-05, "epoch": 1.9927971188475389, "percentage": 19.95, "elapsed_time": "1:04:40", "remaining_time": "4:19:30"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 2080, "loss": 0.7223, "learning_rate": 4.513627831377365e-05, "epoch": 2.0168067226890756, "percentage": 20.19, "elapsed_time": "1:05:27", "remaining_time": "4:18:43"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 2080, "loss": 0.7504, "learning_rate": 4.502381196091154e-05, "epoch": 2.0408163265306123, "percentage": 20.43, "elapsed_time": "1:06:19", "remaining_time": "4:18:16"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 2080, "loss": 0.8011, "learning_rate": 4.491020362994168e-05, "epoch": 2.064825930372149, "percentage": 20.67, "elapsed_time": "1:07:08", "remaining_time": "4:17:39"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 2080, "loss": 0.8665, "learning_rate": 4.47954598000613e-05, "epoch": 2.0888355342136853, "percentage": 20.91, "elapsed_time": "1:07:57", "remaining_time": "4:16:57"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 2080, "loss": 0.749, "learning_rate": 4.4679587015226253e-05, "epoch": 2.112845138055222, "percentage": 21.15, "elapsed_time": "1:08:42", "remaining_time": "4:16:04"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 2080, "loss": 0.7962, "learning_rate": 4.456259188377786e-05, "epoch": 2.1368547418967587, "percentage": 21.39, "elapsed_time": "1:09:30", "remaining_time": "4:15:21"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 2080, "loss": 0.7964, "learning_rate": 4.444448107806596e-05, "epoch": 2.1608643457382954, "percentage": 21.63, "elapsed_time": "1:10:17", "remaining_time": "4:14:38"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 2080, "loss": 0.7516, "learning_rate": 4.4325261334068426e-05, "epoch": 2.184873949579832, "percentage": 21.88, "elapsed_time": "1:11:05", "remaining_time": "4:13:53"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 2080, "loss": 0.8173, "learning_rate": 4.420493945100702e-05, "epoch": 2.2088835534213684, "percentage": 22.12, "elapsed_time": "1:11:53", "remaining_time": "4:13:10"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 2080, "loss": 0.8038, "learning_rate": 4.4083522290959564e-05, "epoch": 2.232893157262905, "percentage": 22.36, "elapsed_time": "1:12:40", "remaining_time": "4:12:25"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 2080, "loss": 0.8055, "learning_rate": 4.396101677846866e-05, "epoch": 2.256902761104442, "percentage": 22.6, "elapsed_time": "1:13:26", "remaining_time": "4:11:35"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 2080, "loss": 0.7459, "learning_rate": 4.383742990014671e-05, "epoch": 2.280912364945978, "percentage": 22.84, "elapsed_time": "1:14:11", "remaining_time": "4:10:40"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 2080, "loss": 0.7959, "learning_rate": 4.371276870427753e-05, "epoch": 2.304921968787515, "percentage": 23.08, "elapsed_time": "1:15:02", "remaining_time": "4:10:07"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 2080, "loss": 0.8528, "learning_rate": 4.358704030041432e-05, "epoch": 2.3289315726290516, "percentage": 23.32, "elapsed_time": "1:15:47", "remaining_time": "4:09:16"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 2080, "loss": 0.759, "learning_rate": 4.346025185897424e-05, "epoch": 2.3529411764705883, "percentage": 23.56, "elapsed_time": "1:16:32", "remaining_time": "4:08:22"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 2080, "loss": 0.7499, "learning_rate": 4.333241061082944e-05, "epoch": 2.376950780312125, "percentage": 23.8, "elapsed_time": "1:17:18", "remaining_time": "4:07:31"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 2080, "loss": 0.7279, "learning_rate": 4.320352384689471e-05, "epoch": 2.4009603841536613, "percentage": 24.04, "elapsed_time": "1:18:08", "remaining_time": "4:06:56"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 2080, "loss": 0.7453, "learning_rate": 4.307359891771165e-05, "epoch": 2.424969987995198, "percentage": 24.28, "elapsed_time": "1:18:53", "remaining_time": "4:06:02"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 2080, "loss": 0.8311, "learning_rate": 4.294264323302946e-05, "epoch": 2.4489795918367347, "percentage": 24.52, "elapsed_time": "1:19:43", "remaining_time": "4:05:25"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 2080, "loss": 0.7172, "learning_rate": 4.2810664261382375e-05, "epoch": 2.4729891956782715, "percentage": 24.76, "elapsed_time": "1:20:27", "remaining_time": "4:04:30"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 2080, "loss": 0.8084, "learning_rate": 4.267766952966369e-05, "epoch": 2.4969987995198077, "percentage": 25.0, "elapsed_time": "1:21:13", "remaining_time": "4:03:41"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 2080, "loss": 0.702, "learning_rate": 4.254366662269655e-05, "epoch": 2.5210084033613445, "percentage": 25.24, "elapsed_time": "1:21:57", "remaining_time": "4:02:44"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 2080, "loss": 0.7261, "learning_rate": 4.240866318280132e-05, "epoch": 2.545018007202881, "percentage": 25.48, "elapsed_time": "1:22:42", "remaining_time": "4:01:53"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 2080, "loss": 0.754, "learning_rate": 4.227266690935978e-05, "epoch": 2.569027611044418, "percentage": 25.72, "elapsed_time": "1:23:30", "remaining_time": "4:01:08"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 2080, "loss": 0.7855, "learning_rate": 4.2135685558375994e-05, "epoch": 2.593037214885954, "percentage": 25.96, "elapsed_time": "1:24:16", "remaining_time": "4:00:19"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 2080, "loss": 0.7584, "learning_rate": 4.199772694203399e-05, "epoch": 2.617046818727491, "percentage": 26.2, "elapsed_time": "1:25:04", "remaining_time": "3:59:37"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 2080, "loss": 0.8196, "learning_rate": 4.185879892825222e-05, "epoch": 2.6410564225690276, "percentage": 26.44, "elapsed_time": "1:25:51", "remaining_time": "3:58:50"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 2080, "loss": 0.6836, "learning_rate": 4.1718909440234853e-05, "epoch": 2.6650660264105643, "percentage": 26.68, "elapsed_time": "1:26:36", "remaining_time": "3:57:59"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 2080, "loss": 0.7656, "learning_rate": 4.157806645601988e-05, "epoch": 2.689075630252101, "percentage": 26.92, "elapsed_time": "1:27:22", "remaining_time": "3:57:08"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 2080, "loss": 0.7787, "learning_rate": 4.143627800802417e-05, "epoch": 2.7130852340936373, "percentage": 27.16, "elapsed_time": "1:28:08", "remaining_time": "3:56:20"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 2080, "loss": 0.7665, "learning_rate": 4.1293552182585307e-05, "epoch": 2.737094837935174, "percentage": 27.4, "elapsed_time": "1:28:52", "remaining_time": "3:55:25"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 2080, "loss": 0.748, "learning_rate": 4.114989711950047e-05, "epoch": 2.7611044417767108, "percentage": 27.64, "elapsed_time": "1:29:36", "remaining_time": "3:54:33"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 2080, "loss": 0.7761, "learning_rate": 4.1005321011562206e-05, "epoch": 2.785114045618247, "percentage": 27.88, "elapsed_time": "1:30:24", "remaining_time": "3:53:47"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 2080, "loss": 0.7873, "learning_rate": 4.085983210409114e-05, "epoch": 2.8091236494597838, "percentage": 28.12, "elapsed_time": "1:31:10", "remaining_time": "3:52:59"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 2080, "loss": 0.8288, "learning_rate": 4.0713438694465806e-05, "epoch": 2.8331332533013205, "percentage": 28.37, "elapsed_time": "1:31:55", "remaining_time": "3:52:09"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 2080, "loss": 0.7587, "learning_rate": 4.056614913164938e-05, "epoch": 2.857142857142857, "percentage": 28.61, "elapsed_time": "1:32:42", "remaining_time": "3:51:22"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 2080, "loss": 0.7096, "learning_rate": 4.0417971815713584e-05, "epoch": 2.881152460984394, "percentage": 28.85, "elapsed_time": "1:33:28", "remaining_time": "3:50:33"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 2080, "loss": 0.7177, "learning_rate": 4.026891519735955e-05, "epoch": 2.90516206482593, "percentage": 29.09, "elapsed_time": "1:34:13", "remaining_time": "3:49:43"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 2080, "loss": 0.7244, "learning_rate": 4.011898777743594e-05, "epoch": 2.929171668667467, "percentage": 29.33, "elapsed_time": "1:34:59", "remaining_time": "3:48:55"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 2080, "loss": 0.7627, "learning_rate": 3.99681981064541e-05, "epoch": 2.9531812725090036, "percentage": 29.57, "elapsed_time": "1:35:46", "remaining_time": "3:48:09"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 2080, "loss": 0.7562, "learning_rate": 3.981655478410043e-05, "epoch": 2.9771908763505404, "percentage": 29.81, "elapsed_time": "1:36:31", "remaining_time": "3:47:16"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 2080, "loss": 0.8271, "learning_rate": 3.966406645874589e-05, "epoch": 3.0012004801920766, "percentage": 30.05, "elapsed_time": "1:37:17", "remaining_time": "3:46:30"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 2080, "loss": 0.7639, "learning_rate": 3.951074182695284e-05, "epoch": 3.0252100840336134, "percentage": 30.29, "elapsed_time": "1:38:10", "remaining_time": "3:45:58"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 2080, "loss": 0.7117, "learning_rate": 3.935658963297902e-05, "epoch": 3.04921968787515, "percentage": 30.53, "elapsed_time": "1:38:54", "remaining_time": "3:45:05"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 2080, "loss": 0.7358, "learning_rate": 3.920161866827889e-05, "epoch": 3.073229291716687, "percentage": 30.77, "elapsed_time": "1:39:40", "remaining_time": "3:44:16"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 2080, "loss": 0.7409, "learning_rate": 3.904583777100223e-05, "epoch": 3.097238895558223, "percentage": 31.01, "elapsed_time": "1:40:25", "remaining_time": "3:43:24"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 2080, "loss": 0.7052, "learning_rate": 3.888925582549006e-05, "epoch": 3.12124849939976, "percentage": 31.25, "elapsed_time": "1:41:10", "remaining_time": "3:42:34"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 2080, "loss": 0.7602, "learning_rate": 3.8731881761768e-05, "epoch": 3.1452581032412965, "percentage": 31.49, "elapsed_time": "1:42:01", "remaining_time": "3:41:56"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 2080, "loss": 0.8514, "learning_rate": 3.857372455503697e-05, "epoch": 3.1692677070828332, "percentage": 31.73, "elapsed_time": "1:42:50", "remaining_time": "3:41:16"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 2080, "loss": 0.7699, "learning_rate": 3.8414793225161325e-05, "epoch": 3.19327731092437, "percentage": 31.97, "elapsed_time": "1:43:35", "remaining_time": "3:40:24"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 2080, "loss": 0.8067, "learning_rate": 3.825509683615442e-05, "epoch": 3.2172869147659062, "percentage": 32.21, "elapsed_time": "1:44:24", "remaining_time": "3:39:43"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 2080, "loss": 0.6783, "learning_rate": 3.809464449566175e-05, "epoch": 3.241296518607443, "percentage": 32.45, "elapsed_time": "1:45:11", "remaining_time": "3:38:56"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 2080, "loss": 0.7315, "learning_rate": 3.793344535444142e-05, "epoch": 3.2653061224489797, "percentage": 32.69, "elapsed_time": "1:45:57", "remaining_time": "3:38:09"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 2080, "loss": 0.6999, "learning_rate": 3.777150860584237e-05, "epoch": 3.2893157262905164, "percentage": 32.93, "elapsed_time": "1:46:44", "remaining_time": "3:37:22"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 2080, "loss": 0.7182, "learning_rate": 3.760884348528002e-05, "epoch": 3.3133253301320527, "percentage": 33.17, "elapsed_time": "1:47:29", "remaining_time": "3:36:33"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 2080, "loss": 0.7577, "learning_rate": 3.744545926970957e-05, "epoch": 3.3373349339735894, "percentage": 33.41, "elapsed_time": "1:48:18", "remaining_time": "3:35:51"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 2080, "loss": 0.7825, "learning_rate": 3.728136527709694e-05, "epoch": 3.361344537815126, "percentage": 33.65, "elapsed_time": "1:49:07", "remaining_time": "3:35:07"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 2080, "loss": 0.7414, "learning_rate": 3.711657086588733e-05, "epoch": 3.385354141656663, "percentage": 33.89, "elapsed_time": "1:49:53", "remaining_time": "3:34:19"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 2080, "loss": 0.7144, "learning_rate": 3.695108543447154e-05, "epoch": 3.409363745498199, "percentage": 34.13, "elapsed_time": "1:50:38", "remaining_time": "3:33:28"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 2080, "loss": 0.7516, "learning_rate": 3.678491842064995e-05, "epoch": 3.433373349339736, "percentage": 34.38, "elapsed_time": "1:51:26", "remaining_time": "3:32:45"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 2080, "loss": 0.7484, "learning_rate": 3.6618079301094216e-05, "epoch": 3.4573829531812725, "percentage": 34.62, "elapsed_time": "1:52:12", "remaining_time": "3:31:57"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 2080, "loss": 0.7775, "learning_rate": 3.645057759080692e-05, "epoch": 3.4813925570228093, "percentage": 34.86, "elapsed_time": "1:52:58", "remaining_time": "3:31:09"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 2080, "loss": 0.7086, "learning_rate": 3.6282422842578845e-05, "epoch": 3.505402160864346, "percentage": 35.1, "elapsed_time": "1:53:43", "remaining_time": "3:30:18"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 2080, "loss": 0.7165, "learning_rate": 3.611362464644415e-05, "epoch": 3.5294117647058822, "percentage": 35.34, "elapsed_time": "1:54:26", "remaining_time": "3:29:25"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 2080, "loss": 0.7668, "learning_rate": 3.594419262913351e-05, "epoch": 3.553421368547419, "percentage": 35.58, "elapsed_time": "1:55:12", "remaining_time": "3:28:37"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 2080, "loss": 0.6595, "learning_rate": 3.577413645352506e-05, "epoch": 3.5774309723889557, "percentage": 35.82, "elapsed_time": "1:55:59", "remaining_time": "3:27:50"}
|
| 150 |
+
{"current_steps": 750, "total_steps": 2080, "loss": 0.7469, "learning_rate": 3.560346581809328e-05, "epoch": 3.601440576230492, "percentage": 36.06, "elapsed_time": "1:56:47", "remaining_time": "3:27:06"}
|
| 151 |
+
{"current_steps": 755, "total_steps": 2080, "loss": 0.7063, "learning_rate": 3.543219045635593e-05, "epoch": 3.6254501800720287, "percentage": 36.3, "elapsed_time": "1:57:32", "remaining_time": "3:26:16"}
|
| 152 |
+
{"current_steps": 760, "total_steps": 2080, "loss": 0.6694, "learning_rate": 3.526032013631893e-05, "epoch": 3.6494597839135654, "percentage": 36.54, "elapsed_time": "1:58:19", "remaining_time": "3:25:31"}
|
| 153 |
+
{"current_steps": 765, "total_steps": 2080, "loss": 0.7789, "learning_rate": 3.508786465991923e-05, "epoch": 3.673469387755102, "percentage": 36.78, "elapsed_time": "1:59:06", "remaining_time": "3:24:44"}
|
| 154 |
+
{"current_steps": 770, "total_steps": 2080, "loss": 0.7934, "learning_rate": 3.491483386246588e-05, "epoch": 3.697478991596639, "percentage": 37.02, "elapsed_time": "1:59:53", "remaining_time": "3:23:57"}
|
| 155 |
+
{"current_steps": 775, "total_steps": 2080, "loss": 0.7295, "learning_rate": 3.474123761207905e-05, "epoch": 3.721488595438175, "percentage": 37.26, "elapsed_time": "2:00:38", "remaining_time": "3:23:09"}
|
| 156 |
+
{"current_steps": 780, "total_steps": 2080, "loss": 0.7474, "learning_rate": 3.456708580912725e-05, "epoch": 3.745498199279712, "percentage": 37.5, "elapsed_time": "2:01:25", "remaining_time": "3:22:21"}
|
| 157 |
+
{"current_steps": 785, "total_steps": 2080, "loss": 0.7711, "learning_rate": 3.4392388385662714e-05, "epoch": 3.7695078031212486, "percentage": 37.74, "elapsed_time": "2:02:08", "remaining_time": "3:21:30"}
|
| 158 |
+
{"current_steps": 790, "total_steps": 2080, "loss": 0.7363, "learning_rate": 3.4217155304854976e-05, "epoch": 3.7935174069627853, "percentage": 37.98, "elapsed_time": "2:02:54", "remaining_time": "3:20:42"}
|
| 159 |
+
{"current_steps": 795, "total_steps": 2080, "loss": 0.8531, "learning_rate": 3.4041396560422624e-05, "epoch": 3.817527010804322, "percentage": 38.22, "elapsed_time": "2:03:43", "remaining_time": "3:19:59"}
|
| 160 |
+
{"current_steps": 800, "total_steps": 2080, "loss": 0.8025, "learning_rate": 3.386512217606339e-05, "epoch": 3.8415366146458583, "percentage": 38.46, "elapsed_time": "2:04:30", "remaining_time": "3:19:13"}
|
| 161 |
+
{"current_steps": 805, "total_steps": 2080, "loss": 0.6634, "learning_rate": 3.3688342204882466e-05, "epoch": 3.865546218487395, "percentage": 38.7, "elapsed_time": "2:05:20", "remaining_time": "3:18:31"}
|
| 162 |
+
{"current_steps": 810, "total_steps": 2080, "loss": 0.7664, "learning_rate": 3.351106672881915e-05, "epoch": 3.8895558223289317, "percentage": 38.94, "elapsed_time": "2:06:04", "remaining_time": "3:17:39"}
|
| 163 |
+
{"current_steps": 815, "total_steps": 2080, "loss": 0.865, "learning_rate": 3.33333058580719e-05, "epoch": 3.913565426170468, "percentage": 39.18, "elapsed_time": "2:06:51", "remaining_time": "3:16:53"}
|
| 164 |
+
{"current_steps": 820, "total_steps": 2080, "loss": 0.7096, "learning_rate": 3.3155069730521735e-05, "epoch": 3.9375750300120047, "percentage": 39.42, "elapsed_time": "2:07:36", "remaining_time": "3:16:05"}
|
| 165 |
+
{"current_steps": 825, "total_steps": 2080, "loss": 0.8476, "learning_rate": 3.2976368511153996e-05, "epoch": 3.9615846338535414, "percentage": 39.66, "elapsed_time": "2:08:25", "remaining_time": "3:15:21"}
|
| 166 |
+
{"current_steps": 830, "total_steps": 2080, "loss": 0.705, "learning_rate": 3.2797212391478724e-05, "epoch": 3.985594237695078, "percentage": 39.9, "elapsed_time": "2:09:10", "remaining_time": "3:14:32"}
|
| 167 |
+
{"current_steps": 835, "total_steps": 2080, "loss": 0.7086, "learning_rate": 3.261761158894937e-05, "epoch": 4.009603841536615, "percentage": 40.14, "elapsed_time": "2:09:54", "remaining_time": "3:13:41"}
|
| 168 |
+
{"current_steps": 840, "total_steps": 2080, "loss": 0.6899, "learning_rate": 3.243757634638008e-05, "epoch": 4.033613445378151, "percentage": 40.38, "elapsed_time": "2:10:41", "remaining_time": "3:12:54"}
|
| 169 |
+
{"current_steps": 845, "total_steps": 2080, "loss": 0.8088, "learning_rate": 3.225711693136156e-05, "epoch": 4.057623049219688, "percentage": 40.62, "elapsed_time": "2:11:27", "remaining_time": "3:12:08"}
|
| 170 |
+
{"current_steps": 850, "total_steps": 2080, "loss": 0.7096, "learning_rate": 3.2076243635675513e-05, "epoch": 4.081632653061225, "percentage": 40.87, "elapsed_time": "2:12:12", "remaining_time": "3:11:18"}
|
| 171 |
+
{"current_steps": 855, "total_steps": 2080, "loss": 0.7646, "learning_rate": 3.189496677470765e-05, "epoch": 4.105642256902761, "percentage": 41.11, "elapsed_time": "2:12:59", "remaining_time": "3:10:32"}
|
| 172 |
+
{"current_steps": 860, "total_steps": 2080, "loss": 0.7525, "learning_rate": 3.1713296686859426e-05, "epoch": 4.129651860744298, "percentage": 41.35, "elapsed_time": "2:13:45", "remaining_time": "3:09:45"}
|
| 173 |
+
{"current_steps": 865, "total_steps": 2080, "loss": 0.7231, "learning_rate": 3.153124373295841e-05, "epoch": 4.153661464585834, "percentage": 41.59, "elapsed_time": "2:14:35", "remaining_time": "3:09:02"}
|
| 174 |
+
{"current_steps": 870, "total_steps": 2080, "loss": 0.7431, "learning_rate": 3.1348818295667424e-05, "epoch": 4.177671068427371, "percentage": 41.83, "elapsed_time": "2:15:21", "remaining_time": "3:08:16"}
|
| 175 |
+
{"current_steps": 875, "total_steps": 2080, "loss": 0.7619, "learning_rate": 3.116603077889238e-05, "epoch": 4.201680672268908, "percentage": 42.07, "elapsed_time": "2:16:07", "remaining_time": "3:07:28"}
|
| 176 |
+
{"current_steps": 880, "total_steps": 2080, "loss": 0.7806, "learning_rate": 3.098289160718895e-05, "epoch": 4.225690276110444, "percentage": 42.31, "elapsed_time": "2:16:50", "remaining_time": "3:06:36"}
|
| 177 |
+
{"current_steps": 885, "total_steps": 2080, "loss": 0.701, "learning_rate": 3.079941122516803e-05, "epoch": 4.249699879951981, "percentage": 42.55, "elapsed_time": "2:17:34", "remaining_time": "3:05:45"}
|
| 178 |
+
{"current_steps": 890, "total_steps": 2080, "loss": 0.7114, "learning_rate": 3.061560009690011e-05, "epoch": 4.2737094837935174, "percentage": 42.79, "elapsed_time": "2:18:20", "remaining_time": "3:04:57"}
|
| 179 |
+
{"current_steps": 895, "total_steps": 2080, "loss": 0.7407, "learning_rate": 3.0431468705318424e-05, "epoch": 4.297719087635054, "percentage": 43.03, "elapsed_time": "2:19:07", "remaining_time": "3:04:12"}
|
| 180 |
+
{"current_steps": 900, "total_steps": 2080, "loss": 0.756, "learning_rate": 3.024702755162119e-05, "epoch": 4.321728691476591, "percentage": 43.27, "elapsed_time": "2:19:54", "remaining_time": "3:03:26"}
|
| 181 |
+
{"current_steps": 905, "total_steps": 2080, "loss": 0.6897, "learning_rate": 3.0062287154672658e-05, "epoch": 4.345738295318127, "percentage": 43.51, "elapsed_time": "2:20:38", "remaining_time": "3:02:36"}
|
| 182 |
+
{"current_steps": 910, "total_steps": 2080, "loss": 0.7212, "learning_rate": 2.9877258050403212e-05, "epoch": 4.369747899159664, "percentage": 43.75, "elapsed_time": "2:21:27", "remaining_time": "3:01:53"}
|
| 183 |
+
{"current_steps": 915, "total_steps": 2080, "loss": 0.8578, "learning_rate": 2.9691950791208502e-05, "epoch": 4.393757503001201, "percentage": 43.99, "elapsed_time": "2:22:15", "remaining_time": "3:01:07"}
|
| 184 |
+
{"current_steps": 920, "total_steps": 2080, "loss": 0.7116, "learning_rate": 2.950637594534765e-05, "epoch": 4.417767106842737, "percentage": 44.23, "elapsed_time": "2:23:01", "remaining_time": "3:00:19"}
|
| 185 |
+
{"current_steps": 925, "total_steps": 2080, "loss": 0.7693, "learning_rate": 2.9320544096340493e-05, "epoch": 4.441776710684274, "percentage": 44.47, "elapsed_time": "2:23:49", "remaining_time": "2:59:35"}
|
| 186 |
+
{"current_steps": 930, "total_steps": 2080, "loss": 0.6641, "learning_rate": 2.9134465842364035e-05, "epoch": 4.46578631452581, "percentage": 44.71, "elapsed_time": "2:24:39", "remaining_time": "2:58:52"}
|
| 187 |
+
{"current_steps": 935, "total_steps": 2080, "loss": 0.7488, "learning_rate": 2.8948151795647993e-05, "epoch": 4.489795918367347, "percentage": 44.95, "elapsed_time": "2:25:23", "remaining_time": "2:58:03"}
|
| 188 |
+
{"current_steps": 940, "total_steps": 2080, "loss": 0.6626, "learning_rate": 2.876161258186958e-05, "epoch": 4.513805522208884, "percentage": 45.19, "elapsed_time": "2:26:09", "remaining_time": "2:57:15"}
|
| 189 |
+
{"current_steps": 945, "total_steps": 2080, "loss": 0.7064, "learning_rate": 2.8574858839547512e-05, "epoch": 4.53781512605042, "percentage": 45.43, "elapsed_time": "2:26:52", "remaining_time": "2:56:24"}
|
| 190 |
+
{"current_steps": 950, "total_steps": 2080, "loss": 0.703, "learning_rate": 2.83879012194353e-05, "epoch": 4.561824729891956, "percentage": 45.67, "elapsed_time": "2:27:37", "remaining_time": "2:55:36"}
|
| 191 |
+
{"current_steps": 955, "total_steps": 2080, "loss": 0.8085, "learning_rate": 2.8200750383913776e-05, "epoch": 4.5858343337334935, "percentage": 45.91, "elapsed_time": "2:28:31", "remaining_time": "2:54:57"}
|
| 192 |
+
{"current_steps": 960, "total_steps": 2080, "loss": 0.7251, "learning_rate": 2.8013417006383076e-05, "epoch": 4.60984393757503, "percentage": 46.15, "elapsed_time": "2:29:16", "remaining_time": "2:54:08"}
|
| 193 |
+
{"current_steps": 965, "total_steps": 2080, "loss": 0.7358, "learning_rate": 2.782591177065388e-05, "epoch": 4.633853541416567, "percentage": 46.39, "elapsed_time": "2:30:07", "remaining_time": "2:53:27"}
|
| 194 |
+
{"current_steps": 970, "total_steps": 2080, "loss": 0.7625, "learning_rate": 2.763824537033809e-05, "epoch": 4.657863145258103, "percentage": 46.63, "elapsed_time": "2:30:59", "remaining_time": "2:52:47"}
|
| 195 |
+
{"current_steps": 975, "total_steps": 2080, "loss": 0.8123, "learning_rate": 2.7450428508239024e-05, "epoch": 4.6818727490996395, "percentage": 46.88, "elapsed_time": "2:31:47", "remaining_time": "2:52:01"}
|
| 196 |
+
{"current_steps": 980, "total_steps": 2080, "loss": 0.7068, "learning_rate": 2.726247189574095e-05, "epoch": 4.705882352941177, "percentage": 47.12, "elapsed_time": "2:32:33", "remaining_time": "2:51:13"}
|
| 197 |
+
{"current_steps": 985, "total_steps": 2080, "loss": 0.7431, "learning_rate": 2.707438625219827e-05, "epoch": 4.729891956782713, "percentage": 47.36, "elapsed_time": "2:33:21", "remaining_time": "2:50:28"}
|
| 198 |
+
{"current_steps": 990, "total_steps": 2080, "loss": 0.7161, "learning_rate": 2.6886182304324153e-05, "epoch": 4.75390156062425, "percentage": 47.6, "elapsed_time": "2:34:05", "remaining_time": "2:49:39"}
|
| 199 |
+
{"current_steps": 995, "total_steps": 2080, "loss": 0.7311, "learning_rate": 2.669787078557876e-05, "epoch": 4.777911164465786, "percentage": 47.84, "elapsed_time": "2:34:51", "remaining_time": "2:48:51"}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 2080, "loss": 0.6689, "learning_rate": 2.6509462435557152e-05, "epoch": 4.801920768307323, "percentage": 48.08, "elapsed_time": "2:35:36", "remaining_time": "2:48:03"}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 2080, "loss": 0.6888, "learning_rate": 2.6320967999376767e-05, "epoch": 4.82593037214886, "percentage": 48.32, "elapsed_time": "2:36:23", "remaining_time": "2:47:17"}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 2080, "loss": 0.7879, "learning_rate": 2.6132398227064615e-05, "epoch": 4.849939975990396, "percentage": 48.56, "elapsed_time": "2:37:09", "remaining_time": "2:46:29"}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 2080, "loss": 0.6958, "learning_rate": 2.5943763872944206e-05, "epoch": 4.873949579831933, "percentage": 48.8, "elapsed_time": "2:37:55", "remaining_time": "2:45:42"}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 2080, "loss": 0.6858, "learning_rate": 2.5755075695022224e-05, "epoch": 4.8979591836734695, "percentage": 49.04, "elapsed_time": "2:38:40", "remaining_time": "2:44:53"}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 2080, "loss": 0.6799, "learning_rate": 2.5566344454374968e-05, "epoch": 4.921968787515006, "percentage": 49.28, "elapsed_time": "2:39:27", "remaining_time": "2:44:07"}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 2080, "loss": 0.767, "learning_rate": 2.5377580914534647e-05, "epoch": 4.945978391356543, "percentage": 49.52, "elapsed_time": "2:40:15", "remaining_time": "2:43:21"}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 2080, "loss": 0.7453, "learning_rate": 2.5188795840875544e-05, "epoch": 4.969987995198079, "percentage": 49.76, "elapsed_time": "2:41:01", "remaining_time": "2:42:34"}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 2080, "loss": 0.7559, "learning_rate": 2.5e-05, "epoch": 4.9939975990396155, "percentage": 50.0, "elapsed_time": "2:41:47", "remaining_time": "2:41:47"}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 2080, "loss": 0.7729, "learning_rate": 2.481120415912446e-05, "epoch": 5.018007202881153, "percentage": 50.24, "elapsed_time": "2:42:33", "remaining_time": "2:41:00"}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 2080, "loss": 0.6956, "learning_rate": 2.4622419085465355e-05, "epoch": 5.042016806722689, "percentage": 50.48, "elapsed_time": "2:43:20", "remaining_time": "2:40:13"}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 2080, "loss": 0.7124, "learning_rate": 2.4433655545625038e-05, "epoch": 5.066026410564226, "percentage": 50.72, "elapsed_time": "2:44:07", "remaining_time": "2:39:27"}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 2080, "loss": 0.7472, "learning_rate": 2.4244924304977785e-05, "epoch": 5.090036014405762, "percentage": 50.96, "elapsed_time": "2:44:53", "remaining_time": "2:38:39"}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 2080, "loss": 0.6805, "learning_rate": 2.40562361270558e-05, "epoch": 5.114045618247299, "percentage": 51.2, "elapsed_time": "2:45:42", "remaining_time": "2:37:55"}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 2080, "loss": 0.6898, "learning_rate": 2.3867601772935397e-05, "epoch": 5.138055222088836, "percentage": 51.44, "elapsed_time": "2:46:28", "remaining_time": "2:37:08"}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 2080, "loss": 0.6664, "learning_rate": 2.367903200062324e-05, "epoch": 5.162064825930372, "percentage": 51.68, "elapsed_time": "2:47:13", "remaining_time": "2:36:20"}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 2080, "loss": 0.7125, "learning_rate": 2.3490537564442847e-05, "epoch": 5.186074429771908, "percentage": 51.92, "elapsed_time": "2:47:59", "remaining_time": "2:35:33"}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 2080, "loss": 0.7797, "learning_rate": 2.3302129214421242e-05, "epoch": 5.2100840336134455, "percentage": 52.16, "elapsed_time": "2:48:45", "remaining_time": "2:34:45"}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 2080, "loss": 0.7587, "learning_rate": 2.3113817695675853e-05, "epoch": 5.234093637454982, "percentage": 52.4, "elapsed_time": "2:49:31", "remaining_time": "2:33:58"}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 2080, "loss": 0.7414, "learning_rate": 2.292561374780173e-05, "epoch": 5.258103241296519, "percentage": 52.64, "elapsed_time": "2:50:18", "remaining_time": "2:33:11"}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 2080, "loss": 0.6972, "learning_rate": 2.2737528104259056e-05, "epoch": 5.282112845138055, "percentage": 52.88, "elapsed_time": "2:51:03", "remaining_time": "2:32:23"}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 2080, "loss": 0.7168, "learning_rate": 2.2549571491760986e-05, "epoch": 5.3061224489795915, "percentage": 53.12, "elapsed_time": "2:51:48", "remaining_time": "2:31:35"}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 2080, "loss": 0.6441, "learning_rate": 2.236175462966192e-05, "epoch": 5.330132052821129, "percentage": 53.37, "elapsed_time": "2:52:35", "remaining_time": "2:30:49"}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 2080, "loss": 0.7473, "learning_rate": 2.217408822934613e-05, "epoch": 5.354141656662665, "percentage": 53.61, "elapsed_time": "2:53:23", "remaining_time": "2:30:03"}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 2080, "loss": 0.6849, "learning_rate": 2.1986582993616926e-05, "epoch": 5.378151260504202, "percentage": 53.85, "elapsed_time": "2:54:07", "remaining_time": "2:29:14"}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 2080, "loss": 0.6715, "learning_rate": 2.179924961608623e-05, "epoch": 5.402160864345738, "percentage": 54.09, "elapsed_time": "2:54:50", "remaining_time": "2:28:25"}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 2080, "loss": 0.7139, "learning_rate": 2.1612098780564714e-05, "epoch": 5.426170468187275, "percentage": 54.33, "elapsed_time": "2:55:41", "remaining_time": "2:27:42"}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 2080, "loss": 0.8102, "learning_rate": 2.1425141160452494e-05, "epoch": 5.450180072028812, "percentage": 54.57, "elapsed_time": "2:56:30", "remaining_time": "2:26:58"}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 2080, "loss": 0.7772, "learning_rate": 2.1238387418130422e-05, "epoch": 5.474189675870348, "percentage": 54.81, "elapsed_time": "2:57:17", "remaining_time": "2:26:11"}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 2080, "loss": 0.7506, "learning_rate": 2.1051848204352013e-05, "epoch": 5.498199279711884, "percentage": 55.05, "elapsed_time": "2:58:06", "remaining_time": "2:25:26"}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 2080, "loss": 0.7174, "learning_rate": 2.0865534157635967e-05, "epoch": 5.5222088835534215, "percentage": 55.29, "elapsed_time": "2:58:53", "remaining_time": "2:24:40"}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 2080, "loss": 0.7339, "learning_rate": 2.0679455903659513e-05, "epoch": 5.546218487394958, "percentage": 55.53, "elapsed_time": "2:59:37", "remaining_time": "2:23:51"}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 2080, "loss": 0.7076, "learning_rate": 2.0493624054652357e-05, "epoch": 5.570228091236495, "percentage": 55.77, "elapsed_time": "3:00:24", "remaining_time": "2:23:04"}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 2080, "loss": 0.7758, "learning_rate": 2.0308049208791507e-05, "epoch": 5.594237695078031, "percentage": 56.01, "elapsed_time": "3:01:14", "remaining_time": "2:22:20"}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 2080, "loss": 0.7103, "learning_rate": 2.0122741949596797e-05, "epoch": 5.6182472989195675, "percentage": 56.25, "elapsed_time": "3:02:01", "remaining_time": "2:21:34"}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 2080, "loss": 0.747, "learning_rate": 1.9937712845327345e-05, "epoch": 5.642256902761105, "percentage": 56.49, "elapsed_time": "3:02:54", "remaining_time": "2:20:52"}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 2080, "loss": 0.7325, "learning_rate": 1.9752972448378814e-05, "epoch": 5.666266506602641, "percentage": 56.73, "elapsed_time": "3:03:40", "remaining_time": "2:20:05"}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 2080, "loss": 0.7336, "learning_rate": 1.9568531294681586e-05, "epoch": 5.690276110444177, "percentage": 56.97, "elapsed_time": "3:04:27", "remaining_time": "2:19:19"}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 2080, "loss": 0.7238, "learning_rate": 1.938439990309991e-05, "epoch": 5.714285714285714, "percentage": 57.21, "elapsed_time": "3:05:14", "remaining_time": "2:18:32"}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 2080, "loss": 0.6934, "learning_rate": 1.9200588774831975e-05, "epoch": 5.738295318127251, "percentage": 57.45, "elapsed_time": "3:05:59", "remaining_time": "2:17:44"}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 2080, "loss": 0.7573, "learning_rate": 1.9017108392811065e-05, "epoch": 5.762304921968788, "percentage": 57.69, "elapsed_time": "3:06:46", "remaining_time": "2:16:57"}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 2080, "loss": 0.7232, "learning_rate": 1.8833969221107622e-05, "epoch": 5.786314525810324, "percentage": 57.93, "elapsed_time": "3:07:30", "remaining_time": "2:16:09"}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 2080, "loss": 0.7221, "learning_rate": 1.8651181704332578e-05, "epoch": 5.81032412965186, "percentage": 58.17, "elapsed_time": "3:08:18", "remaining_time": "2:15:23"}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 2080, "loss": 0.755, "learning_rate": 1.8468756267041595e-05, "epoch": 5.834333733493398, "percentage": 58.41, "elapsed_time": "3:09:08", "remaining_time": "2:14:39"}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 2080, "loss": 0.6962, "learning_rate": 1.828670331314058e-05, "epoch": 5.858343337334934, "percentage": 58.65, "elapsed_time": "3:09:52", "remaining_time": "2:13:50"}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 2080, "loss": 0.7443, "learning_rate": 1.810503322529236e-05, "epoch": 5.882352941176471, "percentage": 58.89, "elapsed_time": "3:10:37", "remaining_time": "2:13:02"}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 2080, "loss": 0.6654, "learning_rate": 1.7923756364324492e-05, "epoch": 5.906362545018007, "percentage": 59.13, "elapsed_time": "3:11:29", "remaining_time": "2:12:19"}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 2080, "loss": 0.7271, "learning_rate": 1.7742883068638447e-05, "epoch": 5.930372148859544, "percentage": 59.38, "elapsed_time": "3:12:14", "remaining_time": "2:11:31"}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 2080, "loss": 0.7538, "learning_rate": 1.756242365361993e-05, "epoch": 5.954381752701081, "percentage": 59.62, "elapsed_time": "3:12:58", "remaining_time": "2:10:43"}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 2080, "loss": 0.6795, "learning_rate": 1.7382388411050638e-05, "epoch": 5.978391356542617, "percentage": 59.86, "elapsed_time": "3:13:42", "remaining_time": "2:09:54"}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 2080, "loss": 0.6446, "learning_rate": 1.7202787608521278e-05, "epoch": 6.002400960384153, "percentage": 60.1, "elapsed_time": "3:14:25", "remaining_time": "2:09:05"}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 2080, "loss": 0.6994, "learning_rate": 1.7023631488846006e-05, "epoch": 6.02641056422569, "percentage": 60.34, "elapsed_time": "3:15:11", "remaining_time": "2:08:18"}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 2080, "loss": 0.6886, "learning_rate": 1.6844930269478274e-05, "epoch": 6.050420168067227, "percentage": 60.58, "elapsed_time": "3:16:03", "remaining_time": "2:07:35"}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 2080, "loss": 0.7485, "learning_rate": 1.6666694141928096e-05, "epoch": 6.074429771908764, "percentage": 60.82, "elapsed_time": "3:16:49", "remaining_time": "2:06:48"}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 2080, "loss": 0.6399, "learning_rate": 1.6488933271180845e-05, "epoch": 6.0984393757503, "percentage": 61.06, "elapsed_time": "3:17:34", "remaining_time": "2:06:00"}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 2080, "loss": 0.7799, "learning_rate": 1.631165779511754e-05, "epoch": 6.122448979591836, "percentage": 61.3, "elapsed_time": "3:18:28", "remaining_time": "2:05:18"}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 2080, "loss": 0.7589, "learning_rate": 1.613487782393661e-05, "epoch": 6.146458583433374, "percentage": 61.54, "elapsed_time": "3:19:14", "remaining_time": "2:04:31"}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 2080, "loss": 0.6969, "learning_rate": 1.595860343957738e-05, "epoch": 6.17046818727491, "percentage": 61.78, "elapsed_time": "3:20:00", "remaining_time": "2:03:44"}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 2080, "loss": 0.7108, "learning_rate": 1.5782844695145033e-05, "epoch": 6.194477791116446, "percentage": 62.02, "elapsed_time": "3:20:48", "remaining_time": "2:02:58"}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 2080, "loss": 0.7478, "learning_rate": 1.5607611614337292e-05, "epoch": 6.218487394957983, "percentage": 62.26, "elapsed_time": "3:21:40", "remaining_time": "2:02:15"}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 2080, "loss": 0.7225, "learning_rate": 1.5432914190872757e-05, "epoch": 6.24249699879952, "percentage": 62.5, "elapsed_time": "3:22:25", "remaining_time": "2:01:27"}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 2080, "loss": 0.6964, "learning_rate": 1.5258762387920956e-05, "epoch": 6.266506602641057, "percentage": 62.74, "elapsed_time": "3:23:10", "remaining_time": "2:00:39"}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 2080, "loss": 0.7673, "learning_rate": 1.5085166137534123e-05, "epoch": 6.290516206482593, "percentage": 62.98, "elapsed_time": "3:23:56", "remaining_time": "1:59:52"}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 2080, "loss": 0.7194, "learning_rate": 1.4912135340080774e-05, "epoch": 6.314525810324129, "percentage": 63.22, "elapsed_time": "3:24:44", "remaining_time": "1:59:06"}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 2080, "loss": 0.6869, "learning_rate": 1.4739679863681086e-05, "epoch": 6.3385354141656665, "percentage": 63.46, "elapsed_time": "3:25:28", "remaining_time": "1:58:18"}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 2080, "loss": 0.6851, "learning_rate": 1.4567809543644076e-05, "epoch": 6.362545018007203, "percentage": 63.7, "elapsed_time": "3:26:13", "remaining_time": "1:57:30"}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 2080, "loss": 0.7242, "learning_rate": 1.4396534181906725e-05, "epoch": 6.38655462184874, "percentage": 63.94, "elapsed_time": "3:27:02", "remaining_time": "1:56:45"}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 2080, "loss": 0.7155, "learning_rate": 1.4225863546474943e-05, "epoch": 6.410564225690276, "percentage": 64.18, "elapsed_time": "3:27:48", "remaining_time": "1:55:57"}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 2080, "loss": 0.6706, "learning_rate": 1.4055807370866485e-05, "epoch": 6.4345738295318124, "percentage": 64.42, "elapsed_time": "3:28:33", "remaining_time": "1:55:10"}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 2080, "loss": 0.6937, "learning_rate": 1.388637535355585e-05, "epoch": 6.45858343337335, "percentage": 64.66, "elapsed_time": "3:29:17", "remaining_time": "1:54:22"}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 2080, "loss": 0.8316, "learning_rate": 1.3717577157421169e-05, "epoch": 6.482593037214886, "percentage": 64.9, "elapsed_time": "3:30:08", "remaining_time": "1:53:38"}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 2080, "loss": 0.7229, "learning_rate": 1.3549422409193083e-05, "epoch": 6.506602641056423, "percentage": 65.14, "elapsed_time": "3:30:54", "remaining_time": "1:52:50"}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 2080, "loss": 0.7025, "learning_rate": 1.3381920698905787e-05, "epoch": 6.530612244897959, "percentage": 65.38, "elapsed_time": "3:31:40", "remaining_time": "1:52:04"}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 2080, "loss": 0.742, "learning_rate": 1.3215081579350058e-05, "epoch": 6.554621848739496, "percentage": 65.62, "elapsed_time": "3:32:25", "remaining_time": "1:51:16"}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 2080, "loss": 0.6737, "learning_rate": 1.3048914565528454e-05, "epoch": 6.578631452581033, "percentage": 65.87, "elapsed_time": "3:33:12", "remaining_time": "1:50:29"}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 2080, "loss": 0.7577, "learning_rate": 1.2883429134112673e-05, "epoch": 6.602641056422569, "percentage": 66.11, "elapsed_time": "3:33:59", "remaining_time": "1:49:43"}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 2080, "loss": 0.6495, "learning_rate": 1.2718634722903073e-05, "epoch": 6.626650660264105, "percentage": 66.35, "elapsed_time": "3:34:43", "remaining_time": "1:48:55"}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 2080, "loss": 0.7069, "learning_rate": 1.2554540730290437e-05, "epoch": 6.6506602641056425, "percentage": 66.59, "elapsed_time": "3:35:29", "remaining_time": "1:48:07"}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 2080, "loss": 0.705, "learning_rate": 1.2391156514719984e-05, "epoch": 6.674669867947179, "percentage": 66.83, "elapsed_time": "3:36:16", "remaining_time": "1:47:21"}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 2080, "loss": 0.671, "learning_rate": 1.222849139415764e-05, "epoch": 6.698679471788715, "percentage": 67.07, "elapsed_time": "3:37:01", "remaining_time": "1:46:34"}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 2080, "loss": 0.7456, "learning_rate": 1.2066554645558578e-05, "epoch": 6.722689075630252, "percentage": 67.31, "elapsed_time": "3:37:47", "remaining_time": "1:45:47"}
|
| 281 |
+
{"current_steps": 1405, "total_steps": 2080, "loss": 0.6899, "learning_rate": 1.1905355504338248e-05, "epoch": 6.7466986794717885, "percentage": 67.55, "elapsed_time": "3:38:33", "remaining_time": "1:45:00"}
|
| 282 |
+
{"current_steps": 1410, "total_steps": 2080, "loss": 0.7024, "learning_rate": 1.1744903163845577e-05, "epoch": 6.770708283313326, "percentage": 67.79, "elapsed_time": "3:39:21", "remaining_time": "1:44:13"}
|
| 283 |
+
{"current_steps": 1415, "total_steps": 2080, "loss": 0.6571, "learning_rate": 1.1585206774838683e-05, "epoch": 6.794717887154862, "percentage": 68.03, "elapsed_time": "3:40:03", "remaining_time": "1:43:25"}
|
| 284 |
+
{"current_steps": 1420, "total_steps": 2080, "loss": 0.729, "learning_rate": 1.1426275444963034e-05, "epoch": 6.818727490996398, "percentage": 68.27, "elapsed_time": "3:40:51", "remaining_time": "1:42:39"}
|
| 285 |
+
{"current_steps": 1425, "total_steps": 2080, "loss": 0.7971, "learning_rate": 1.1268118238232003e-05, "epoch": 6.842737094837935, "percentage": 68.51, "elapsed_time": "3:41:36", "remaining_time": "1:41:51"}
|
| 286 |
+
{"current_steps": 1430, "total_steps": 2080, "loss": 0.6376, "learning_rate": 1.1110744174509952e-05, "epoch": 6.866746698679472, "percentage": 68.75, "elapsed_time": "3:42:25", "remaining_time": "1:41:06"}
|
| 287 |
+
{"current_steps": 1435, "total_steps": 2080, "loss": 0.6663, "learning_rate": 1.0954162228997777e-05, "epoch": 6.890756302521009, "percentage": 68.99, "elapsed_time": "3:43:10", "remaining_time": "1:40:18"}
|
| 288 |
+
{"current_steps": 1440, "total_steps": 2080, "loss": 0.6898, "learning_rate": 1.0798381331721109e-05, "epoch": 6.914765906362545, "percentage": 69.23, "elapsed_time": "3:43:56", "remaining_time": "1:39:31"}
|
| 289 |
+
{"current_steps": 1445, "total_steps": 2080, "loss": 0.686, "learning_rate": 1.0643410367020983e-05, "epoch": 6.938775510204081, "percentage": 69.47, "elapsed_time": "3:44:40", "remaining_time": "1:38:43"}
|
| 290 |
+
{"current_steps": 1450, "total_steps": 2080, "loss": 0.7803, "learning_rate": 1.048925817304717e-05, "epoch": 6.9627851140456185, "percentage": 69.71, "elapsed_time": "3:45:26", "remaining_time": "1:37:57"}
|
| 291 |
+
{"current_steps": 1455, "total_steps": 2080, "loss": 0.6809, "learning_rate": 1.0335933541254129e-05, "epoch": 6.986794717887155, "percentage": 69.95, "elapsed_time": "3:46:13", "remaining_time": "1:37:10"}
|
| 292 |
+
{"current_steps": 1460, "total_steps": 2080, "loss": 0.6936, "learning_rate": 1.0183445215899584e-05, "epoch": 7.010804321728691, "percentage": 70.19, "elapsed_time": "3:47:01", "remaining_time": "1:36:24"}
|
| 293 |
+
{"current_steps": 1465, "total_steps": 2080, "loss": 0.7005, "learning_rate": 1.0031801893545895e-05, "epoch": 7.034813925570228, "percentage": 70.43, "elapsed_time": "3:47:51", "remaining_time": "1:35:39"}
|
| 294 |
+
{"current_steps": 1470, "total_steps": 2080, "loss": 0.8484, "learning_rate": 9.881012222564065e-06, "epoch": 7.0588235294117645, "percentage": 70.67, "elapsed_time": "3:48:40", "remaining_time": "1:34:53"}
|
| 295 |
+
{"current_steps": 1475, "total_steps": 2080, "loss": 0.7897, "learning_rate": 9.731084802640459e-06, "epoch": 7.082833133253302, "percentage": 70.91, "elapsed_time": "3:49:29", "remaining_time": "1:34:07"}
|
| 296 |
+
{"current_steps": 1480, "total_steps": 2080, "loss": 0.6696, "learning_rate": 9.582028184286423e-06, "epoch": 7.106842737094838, "percentage": 71.15, "elapsed_time": "3:50:14", "remaining_time": "1:33:20"}
|
| 297 |
+
{"current_steps": 1485, "total_steps": 2080, "loss": 0.6867, "learning_rate": 9.43385086835062e-06, "epoch": 7.130852340936374, "percentage": 71.39, "elapsed_time": "3:50:58", "remaining_time": "1:32:32"}
|
| 298 |
+
{"current_steps": 1490, "total_steps": 2080, "loss": 0.7372, "learning_rate": 9.286561305534203e-06, "epoch": 7.154861944777911, "percentage": 71.63, "elapsed_time": "3:51:45", "remaining_time": "1:31:46"}
|
| 299 |
+
{"current_steps": 1495, "total_steps": 2080, "loss": 0.6718, "learning_rate": 9.140167895908867e-06, "epoch": 7.178871548619448, "percentage": 71.88, "elapsed_time": "3:52:29", "remaining_time": "1:30:58"}
|
| 300 |
+
{"current_steps": 1500, "total_steps": 2080, "loss": 0.6819, "learning_rate": 8.994678988437802e-06, "epoch": 7.202881152460985, "percentage": 72.12, "elapsed_time": "3:53:15", "remaining_time": "1:30:11"}
|
| 301 |
+
{"current_steps": 1505, "total_steps": 2080, "loss": 0.7094, "learning_rate": 8.850102880499531e-06, "epoch": 7.226890756302521, "percentage": 72.36, "elapsed_time": "3:54:00", "remaining_time": "1:29:24"}
|
| 302 |
+
{"current_steps": 1510, "total_steps": 2080, "loss": 0.7423, "learning_rate": 8.706447817414696e-06, "epoch": 7.250900360144057, "percentage": 72.6, "elapsed_time": "3:54:47", "remaining_time": "1:28:37"}
|
| 303 |
+
{"current_steps": 1515, "total_steps": 2080, "loss": 0.6957, "learning_rate": 8.563721991975843e-06, "epoch": 7.2749099639855945, "percentage": 72.84, "elapsed_time": "3:55:37", "remaining_time": "1:27:52"}
|
| 304 |
+
{"current_steps": 1520, "total_steps": 2080, "loss": 0.6382, "learning_rate": 8.421933543980126e-06, "epoch": 7.298919567827131, "percentage": 73.08, "elapsed_time": "3:56:23", "remaining_time": "1:27:05"}
|
| 305 |
+
{"current_steps": 1525, "total_steps": 2080, "loss": 0.6939, "learning_rate": 8.281090559765156e-06, "epoch": 7.322929171668667, "percentage": 73.32, "elapsed_time": "3:57:08", "remaining_time": "1:26:18"}
|
| 306 |
+
{"current_steps": 1530, "total_steps": 2080, "loss": 0.7682, "learning_rate": 8.141201071747784e-06, "epoch": 7.346938775510204, "percentage": 73.56, "elapsed_time": "3:57:59", "remaining_time": "1:25:33"}
|
| 307 |
+
{"current_steps": 1535, "total_steps": 2080, "loss": 0.6319, "learning_rate": 8.002273057966011e-06, "epoch": 7.3709483793517405, "percentage": 73.8, "elapsed_time": "3:58:45", "remaining_time": "1:24:46"}
|
| 308 |
+
{"current_steps": 1540, "total_steps": 2080, "loss": 0.7331, "learning_rate": 7.864314441624004e-06, "epoch": 7.394957983193278, "percentage": 74.04, "elapsed_time": "3:59:30", "remaining_time": "1:23:59"}
|
| 309 |
+
{"current_steps": 1545, "total_steps": 2080, "loss": 0.7249, "learning_rate": 7.727333090640218e-06, "epoch": 7.418967587034814, "percentage": 74.28, "elapsed_time": "4:00:16", "remaining_time": "1:23:11"}
|
| 310 |
+
{"current_steps": 1550, "total_steps": 2080, "loss": 0.6484, "learning_rate": 7.591336817198682e-06, "epoch": 7.44297719087635, "percentage": 74.52, "elapsed_time": "4:01:00", "remaining_time": "1:22:24"}
|
| 311 |
+
{"current_steps": 1555, "total_steps": 2080, "loss": 0.7723, "learning_rate": 7.456333377303457e-06, "epoch": 7.466986794717887, "percentage": 74.76, "elapsed_time": "4:01:47", "remaining_time": "1:21:37"}
|
| 312 |
+
{"current_steps": 1560, "total_steps": 2080, "loss": 0.7266, "learning_rate": 7.3223304703363135e-06, "epoch": 7.490996398559424, "percentage": 75.0, "elapsed_time": "4:02:40", "remaining_time": "1:20:53"}
|
| 313 |
+
{"current_steps": 1565, "total_steps": 2080, "loss": 0.6927, "learning_rate": 7.189335738617633e-06, "epoch": 7.515006002400961, "percentage": 75.24, "elapsed_time": "4:03:27", "remaining_time": "1:20:06"}
|
| 314 |
+
{"current_steps": 1570, "total_steps": 2080, "loss": 0.7219, "learning_rate": 7.057356766970541e-06, "epoch": 7.539015606242497, "percentage": 75.48, "elapsed_time": "4:04:13", "remaining_time": "1:19:19"}
|
| 315 |
+
{"current_steps": 1575, "total_steps": 2080, "loss": 0.6933, "learning_rate": 6.926401082288359e-06, "epoch": 7.563025210084033, "percentage": 75.72, "elapsed_time": "4:04:59", "remaining_time": "1:18:33"}
|
| 316 |
+
{"current_steps": 1580, "total_steps": 2080, "loss": 0.7651, "learning_rate": 6.796476153105294e-06, "epoch": 7.5870348139255706, "percentage": 75.96, "elapsed_time": "4:05:49", "remaining_time": "1:17:47"}
|
| 317 |
+
{"current_steps": 1585, "total_steps": 2080, "loss": 0.6558, "learning_rate": 6.667589389170562e-06, "epoch": 7.611044417767107, "percentage": 76.2, "elapsed_time": "4:06:34", "remaining_time": "1:17:00"}
|
| 318 |
+
{"current_steps": 1590, "total_steps": 2080, "loss": 0.6601, "learning_rate": 6.5397481410257645e-06, "epoch": 7.635054021608643, "percentage": 76.44, "elapsed_time": "4:07:20", "remaining_time": "1:16:13"}
|
| 319 |
+
{"current_steps": 1595, "total_steps": 2080, "loss": 0.6938, "learning_rate": 6.41295969958568e-06, "epoch": 7.65906362545018, "percentage": 76.68, "elapsed_time": "4:08:06", "remaining_time": "1:15:26"}
|
| 320 |
+
{"current_steps": 1600, "total_steps": 2080, "loss": 0.7301, "learning_rate": 6.28723129572247e-06, "epoch": 7.6830732292917165, "percentage": 76.92, "elapsed_time": "4:08:51", "remaining_time": "1:14:39"}
|
| 321 |
+
{"current_steps": 1605, "total_steps": 2080, "loss": 0.6848, "learning_rate": 6.16257009985329e-06, "epoch": 7.707082833133253, "percentage": 77.16, "elapsed_time": "4:09:36", "remaining_time": "1:13:52"}
|
| 322 |
+
{"current_steps": 1610, "total_steps": 2080, "loss": 0.6372, "learning_rate": 6.038983221531352e-06, "epoch": 7.73109243697479, "percentage": 77.4, "elapsed_time": "4:10:22", "remaining_time": "1:13:05"}
|
| 323 |
+
{"current_steps": 1615, "total_steps": 2080, "loss": 0.6736, "learning_rate": 5.916477709040444e-06, "epoch": 7.755102040816326, "percentage": 77.64, "elapsed_time": "4:11:08", "remaining_time": "1:12:18"}
|
| 324 |
+
{"current_steps": 1620, "total_steps": 2080, "loss": 0.6915, "learning_rate": 5.79506054899299e-06, "epoch": 7.779111644657863, "percentage": 77.88, "elapsed_time": "4:11:54", "remaining_time": "1:11:31"}
|
| 325 |
+
{"current_steps": 1625, "total_steps": 2080, "loss": 0.696, "learning_rate": 5.674738665931575e-06, "epoch": 7.8031212484994, "percentage": 78.12, "elapsed_time": "4:12:43", "remaining_time": "1:10:45"}
|
| 326 |
+
{"current_steps": 1630, "total_steps": 2080, "loss": 0.7064, "learning_rate": 5.555518921934047e-06, "epoch": 7.827130852340936, "percentage": 78.37, "elapsed_time": "4:13:30", "remaining_time": "1:09:59"}
|
| 327 |
+
{"current_steps": 1635, "total_steps": 2080, "loss": 0.7497, "learning_rate": 5.437408116222148e-06, "epoch": 7.851140456182473, "percentage": 78.61, "elapsed_time": "4:14:15", "remaining_time": "1:09:12"}
|
| 328 |
+
{"current_steps": 1640, "total_steps": 2080, "loss": 0.7025, "learning_rate": 5.320412984773748e-06, "epoch": 7.875150060024009, "percentage": 78.85, "elapsed_time": "4:15:01", "remaining_time": "1:08:25"}
|
| 329 |
+
{"current_steps": 1645, "total_steps": 2080, "loss": 0.6823, "learning_rate": 5.204540199938707e-06, "epoch": 7.899159663865547, "percentage": 79.09, "elapsed_time": "4:15:46", "remaining_time": "1:07:38"}
|
| 330 |
+
{"current_steps": 1650, "total_steps": 2080, "loss": 0.8013, "learning_rate": 5.089796370058325e-06, "epoch": 7.923169267707083, "percentage": 79.33, "elapsed_time": "4:16:32", "remaining_time": "1:06:51"}
|
| 331 |
+
{"current_steps": 1655, "total_steps": 2080, "loss": 0.7497, "learning_rate": 4.9761880390884694e-06, "epoch": 7.947178871548619, "percentage": 79.57, "elapsed_time": "4:17:18", "remaining_time": "1:06:04"}
|
| 332 |
+
{"current_steps": 1660, "total_steps": 2080, "loss": 0.7817, "learning_rate": 4.86372168622635e-06, "epoch": 7.971188475390156, "percentage": 79.81, "elapsed_time": "4:18:05", "remaining_time": "1:05:18"}
|
| 333 |
+
{"current_steps": 1665, "total_steps": 2080, "loss": 0.615, "learning_rate": 4.7524037255410434e-06, "epoch": 7.995198079231693, "percentage": 80.05, "elapsed_time": "4:18:51", "remaining_time": "1:04:31"}
|
| 334 |
+
{"current_steps": 1670, "total_steps": 2080, "loss": 0.7037, "learning_rate": 4.642240505607659e-06, "epoch": 8.01920768307323, "percentage": 80.29, "elapsed_time": "4:19:35", "remaining_time": "1:03:44"}
|
| 335 |
+
{"current_steps": 1675, "total_steps": 2080, "loss": 0.6747, "learning_rate": 4.533238309145258e-06, "epoch": 8.043217286914766, "percentage": 80.53, "elapsed_time": "4:20:20", "remaining_time": "1:02:56"}
|
| 336 |
+
{"current_steps": 1680, "total_steps": 2080, "loss": 0.7154, "learning_rate": 4.425403352658591e-06, "epoch": 8.067226890756302, "percentage": 80.77, "elapsed_time": "4:21:05", "remaining_time": "1:02:09"}
|
| 337 |
+
{"current_steps": 1685, "total_steps": 2080, "loss": 0.7838, "learning_rate": 4.318741786083538e-06, "epoch": 8.091236494597839, "percentage": 81.01, "elapsed_time": "4:21:50", "remaining_time": "1:01:22"}
|
| 338 |
+
{"current_steps": 1690, "total_steps": 2080, "loss": 0.7525, "learning_rate": 4.213259692436367e-06, "epoch": 8.115246098439377, "percentage": 81.25, "elapsed_time": "4:22:36", "remaining_time": "1:00:36"}
|
| 339 |
+
{"current_steps": 1695, "total_steps": 2080, "loss": 0.6624, "learning_rate": 4.1089630874668325e-06, "epoch": 8.139255702280913, "percentage": 81.49, "elapsed_time": "4:23:22", "remaining_time": "0:59:49"}
|
| 340 |
+
{"current_steps": 1700, "total_steps": 2080, "loss": 0.6821, "learning_rate": 4.0058579193150535e-06, "epoch": 8.16326530612245, "percentage": 81.73, "elapsed_time": "4:24:08", "remaining_time": "0:59:02"}
|
| 341 |
+
{"current_steps": 1705, "total_steps": 2080, "loss": 0.6932, "learning_rate": 3.903950068172338e-06, "epoch": 8.187274909963985, "percentage": 81.97, "elapsed_time": "4:24:53", "remaining_time": "0:58:15"}
|
| 342 |
+
{"current_steps": 1710, "total_steps": 2080, "loss": 0.7308, "learning_rate": 3.8032453459457884e-06, "epoch": 8.211284513805522, "percentage": 82.21, "elapsed_time": "4:25:38", "remaining_time": "0:57:28"}
|
| 343 |
+
{"current_steps": 1715, "total_steps": 2080, "loss": 0.7136, "learning_rate": 3.7037494959268644e-06, "epoch": 8.235294117647058, "percentage": 82.45, "elapsed_time": "4:26:25", "remaining_time": "0:56:42"}
|
| 344 |
+
{"current_steps": 1720, "total_steps": 2080, "loss": 0.6595, "learning_rate": 3.605468192463815e-06, "epoch": 8.259303721488596, "percentage": 82.69, "elapsed_time": "4:27:15", "remaining_time": "0:55:56"}
|
| 345 |
+
{"current_steps": 1725, "total_steps": 2080, "loss": 0.7671, "learning_rate": 3.5084070406380897e-06, "epoch": 8.283313325330132, "percentage": 82.93, "elapsed_time": "4:28:02", "remaining_time": "0:55:09"}
|
| 346 |
+
{"current_steps": 1730, "total_steps": 2080, "loss": 0.6561, "learning_rate": 3.4125715759446785e-06, "epoch": 8.307322929171669, "percentage": 83.17, "elapsed_time": "4:28:48", "remaining_time": "0:54:22"}
|
| 347 |
+
{"current_steps": 1735, "total_steps": 2080, "loss": 0.6876, "learning_rate": 3.317967263976374e-06, "epoch": 8.331332533013205, "percentage": 83.41, "elapsed_time": "4:29:34", "remaining_time": "0:53:36"}
|
| 348 |
+
{"current_steps": 1740, "total_steps": 2080, "loss": 0.6819, "learning_rate": 3.2245995001121106e-06, "epoch": 8.355342136854741, "percentage": 83.65, "elapsed_time": "4:30:19", "remaining_time": "0:52:49"}
|
| 349 |
+
{"current_steps": 1745, "total_steps": 2080, "loss": 0.7044, "learning_rate": 3.1324736092092412e-06, "epoch": 8.37935174069628, "percentage": 83.89, "elapsed_time": "4:31:12", "remaining_time": "0:52:03"}
|
| 350 |
+
{"current_steps": 1750, "total_steps": 2080, "loss": 0.6317, "learning_rate": 3.0415948452998557e-06, "epoch": 8.403361344537815, "percentage": 84.13, "elapsed_time": "4:31:58", "remaining_time": "0:51:17"}
|
| 351 |
+
{"current_steps": 1755, "total_steps": 2080, "loss": 0.6521, "learning_rate": 2.9519683912911266e-06, "epoch": 8.427370948379352, "percentage": 84.38, "elapsed_time": "4:32:45", "remaining_time": "0:50:30"}
|
| 352 |
+
{"current_steps": 1760, "total_steps": 2080, "loss": 0.7572, "learning_rate": 2.8635993586697553e-06, "epoch": 8.451380552220888, "percentage": 84.62, "elapsed_time": "4:33:33", "remaining_time": "0:49:44"}
|
| 353 |
+
{"current_steps": 1765, "total_steps": 2080, "loss": 0.7184, "learning_rate": 2.776492787210425e-06, "epoch": 8.475390156062424, "percentage": 84.86, "elapsed_time": "4:34:18", "remaining_time": "0:48:57"}
|
| 354 |
+
{"current_steps": 1770, "total_steps": 2080, "loss": 0.6881, "learning_rate": 2.690653644688393e-06, "epoch": 8.499399759903962, "percentage": 85.1, "elapsed_time": "4:35:04", "remaining_time": "0:48:10"}
|
| 355 |
+
{"current_steps": 1775, "total_steps": 2080, "loss": 0.6575, "learning_rate": 2.6060868265961822e-06, "epoch": 8.523409363745499, "percentage": 85.34, "elapsed_time": "4:35:51", "remaining_time": "0:47:24"}
|
| 356 |
+
{"current_steps": 1780, "total_steps": 2080, "loss": 0.7457, "learning_rate": 2.5227971558643537e-06, "epoch": 8.547418967587035, "percentage": 85.58, "elapsed_time": "4:36:36", "remaining_time": "0:46:37"}
|
| 357 |
+
{"current_steps": 1785, "total_steps": 2080, "loss": 0.7127, "learning_rate": 2.4407893825864892e-06, "epoch": 8.571428571428571, "percentage": 85.82, "elapsed_time": "4:37:20", "remaining_time": "0:45:50"}
|
| 358 |
+
{"current_steps": 1790, "total_steps": 2080, "loss": 0.7442, "learning_rate": 2.360068183748268e-06, "epoch": 8.595438175270107, "percentage": 86.06, "elapsed_time": "4:38:07", "remaining_time": "0:45:03"}
|
| 359 |
+
{"current_steps": 1795, "total_steps": 2080, "loss": 0.6743, "learning_rate": 2.2806381629607327e-06, "epoch": 8.619447779111646, "percentage": 86.3, "elapsed_time": "4:38:54", "remaining_time": "0:44:16"}
|
| 360 |
+
{"current_steps": 1800, "total_steps": 2080, "loss": 0.7338, "learning_rate": 2.2025038501977486e-06, "epoch": 8.643457382953182, "percentage": 86.54, "elapsed_time": "4:39:41", "remaining_time": "0:43:30"}
|
| 361 |
+
{"current_steps": 1805, "total_steps": 2080, "loss": 0.7514, "learning_rate": 2.125669701537647e-06, "epoch": 8.667466986794718, "percentage": 86.78, "elapsed_time": "4:40:26", "remaining_time": "0:42:43"}
|
| 362 |
+
{"current_steps": 1810, "total_steps": 2080, "loss": 0.7774, "learning_rate": 2.0501400989091036e-06, "epoch": 8.691476590636254, "percentage": 87.02, "elapsed_time": "4:41:15", "remaining_time": "0:41:57"}
|
| 363 |
+
{"current_steps": 1815, "total_steps": 2080, "loss": 0.6895, "learning_rate": 1.97591934984121e-06, "epoch": 8.71548619447779, "percentage": 87.26, "elapsed_time": "4:42:03", "remaining_time": "0:41:10"}
|
| 364 |
+
{"current_steps": 1820, "total_steps": 2080, "loss": 0.7218, "learning_rate": 1.9030116872178316e-06, "epoch": 8.739495798319329, "percentage": 87.5, "elapsed_time": "4:42:50", "remaining_time": "0:40:24"}
|
| 365 |
+
{"current_steps": 1825, "total_steps": 2080, "loss": 0.7553, "learning_rate": 1.8314212690361987e-06, "epoch": 8.763505402160865, "percentage": 87.74, "elapsed_time": "4:43:37", "remaining_time": "0:39:37"}
|
| 366 |
+
{"current_steps": 1830, "total_steps": 2080, "loss": 0.6779, "learning_rate": 1.7611521781697644e-06, "epoch": 8.787515006002401, "percentage": 87.98, "elapsed_time": "4:44:24", "remaining_time": "0:38:51"}
|
| 367 |
+
{"current_steps": 1835, "total_steps": 2080, "loss": 0.6946, "learning_rate": 1.6922084221353607e-06, "epoch": 8.811524609843937, "percentage": 88.22, "elapsed_time": "4:45:10", "remaining_time": "0:38:04"}
|
| 368 |
+
{"current_steps": 1840, "total_steps": 2080, "loss": 0.7149, "learning_rate": 1.624593932864632e-06, "epoch": 8.835534213685474, "percentage": 88.46, "elapsed_time": "4:45:58", "remaining_time": "0:37:18"}
|
| 369 |
+
{"current_steps": 1845, "total_steps": 2080, "loss": 0.6681, "learning_rate": 1.5583125664798165e-06, "epoch": 8.85954381752701, "percentage": 88.7, "elapsed_time": "4:46:44", "remaining_time": "0:36:31"}
|
| 370 |
+
{"current_steps": 1850, "total_steps": 2080, "loss": 0.6519, "learning_rate": 1.4933681030738138e-06, "epoch": 8.883553421368548, "percentage": 88.94, "elapsed_time": "4:47:31", "remaining_time": "0:35:44"}
|
| 371 |
+
{"current_steps": 1855, "total_steps": 2080, "loss": 0.6957, "learning_rate": 1.429764246494597e-06, "epoch": 8.907563025210084, "percentage": 89.18, "elapsed_time": "4:48:18", "remaining_time": "0:34:58"}
|
| 372 |
+
{"current_steps": 1860, "total_steps": 2080, "loss": 0.6942, "learning_rate": 1.3675046241339918e-06, "epoch": 8.93157262905162, "percentage": 89.42, "elapsed_time": "4:49:07", "remaining_time": "0:34:11"}
|
| 373 |
+
{"current_steps": 1865, "total_steps": 2080, "loss": 0.6578, "learning_rate": 1.306592786720795e-06, "epoch": 8.955582232893157, "percentage": 89.66, "elapsed_time": "4:49:52", "remaining_time": "0:33:24"}
|
| 374 |
+
{"current_steps": 1870, "total_steps": 2080, "loss": 0.6994, "learning_rate": 1.2470322081182761e-06, "epoch": 8.979591836734693, "percentage": 89.9, "elapsed_time": "4:50:37", "remaining_time": "0:32:38"}
|
| 375 |
+
{"current_steps": 1875, "total_steps": 2080, "loss": 0.643, "learning_rate": 1.1888262851260462e-06, "epoch": 9.003601440576231, "percentage": 90.14, "elapsed_time": "4:51:27", "remaining_time": "0:31:51"}
|
| 376 |
+
{"current_steps": 1880, "total_steps": 2080, "loss": 0.6307, "learning_rate": 1.1319783372863602e-06, "epoch": 9.027611044417768, "percentage": 90.38, "elapsed_time": "4:52:11", "remaining_time": "0:31:05"}
|
| 377 |
+
{"current_steps": 1885, "total_steps": 2080, "loss": 0.7088, "learning_rate": 1.0764916066947794e-06, "epoch": 9.051620648259304, "percentage": 90.62, "elapsed_time": "4:52:58", "remaining_time": "0:30:18"}
|
| 378 |
+
{"current_steps": 1890, "total_steps": 2080, "loss": 0.6603, "learning_rate": 1.0223692578152782e-06, "epoch": 9.07563025210084, "percentage": 90.87, "elapsed_time": "4:53:45", "remaining_time": "0:29:31"}
|
| 379 |
+
{"current_steps": 1895, "total_steps": 2080, "loss": 0.8255, "learning_rate": 9.696143772997768e-07, "epoch": 9.099639855942376, "percentage": 91.11, "elapsed_time": "4:54:33", "remaining_time": "0:28:45"}
|
| 380 |
+
{"current_steps": 1900, "total_steps": 2080, "loss": 0.6834, "learning_rate": 9.182299738120931e-07, "epoch": 9.123649459783914, "percentage": 91.35, "elapsed_time": "4:55:19", "remaining_time": "0:27:58"}
|
| 381 |
+
{"current_steps": 1905, "total_steps": 2080, "loss": 0.6365, "learning_rate": 8.682189778563693e-07, "epoch": 9.14765906362545, "percentage": 91.59, "elapsed_time": "4:56:04", "remaining_time": "0:27:11"}
|
| 382 |
+
{"current_steps": 1910, "total_steps": 2080, "loss": 0.7317, "learning_rate": 8.195842416099359e-07, "epoch": 9.171668667466987, "percentage": 91.83, "elapsed_time": "4:56:52", "remaining_time": "0:26:25"}
|
| 383 |
+
{"current_steps": 1915, "total_steps": 2080, "loss": 0.741, "learning_rate": 7.723285387606471e-07, "epoch": 9.195678271308523, "percentage": 92.07, "elapsed_time": "4:57:37", "remaining_time": "0:25:38"}
|
| 384 |
+
{"current_steps": 1920, "total_steps": 2080, "loss": 0.6881, "learning_rate": 7.264545643486997e-07, "epoch": 9.21968787515006, "percentage": 92.31, "elapsed_time": "4:58:21", "remaining_time": "0:24:51"}
|
| 385 |
+
{"current_steps": 1925, "total_steps": 2080, "loss": 0.735, "learning_rate": 6.819649346129304e-07, "epoch": 9.243697478991596, "percentage": 92.55, "elapsed_time": "4:59:07", "remaining_time": "0:24:05"}
|
| 386 |
+
{"current_steps": 1930, "total_steps": 2080, "loss": 0.7227, "learning_rate": 6.3886218684161e-07, "epoch": 9.267707082833134, "percentage": 92.79, "elapsed_time": "4:59:56", "remaining_time": "0:23:18"}
|
| 387 |
+
{"current_steps": 1935, "total_steps": 2080, "loss": 0.681, "learning_rate": 5.971487792277297e-07, "epoch": 9.29171668667467, "percentage": 93.03, "elapsed_time": "5:00:41", "remaining_time": "0:22:31"}
|
| 388 |
+
{"current_steps": 1940, "total_steps": 2080, "loss": 0.7081, "learning_rate": 5.568270907288287e-07, "epoch": 9.315726290516206, "percentage": 93.27, "elapsed_time": "5:01:27", "remaining_time": "0:21:45"}
|
| 389 |
+
{"current_steps": 1945, "total_steps": 2080, "loss": 0.7064, "learning_rate": 5.178994209312948e-07, "epoch": 9.339735894357743, "percentage": 93.51, "elapsed_time": "5:02:19", "remaining_time": "0:20:59"}
|
| 390 |
+
{"current_steps": 1950, "total_steps": 2080, "loss": 0.6829, "learning_rate": 4.803679899192392e-07, "epoch": 9.363745498199279, "percentage": 93.75, "elapsed_time": "5:03:07", "remaining_time": "0:20:12"}
|
| 391 |
+
{"current_steps": 1955, "total_steps": 2080, "loss": 0.6814, "learning_rate": 4.4423493814786667e-07, "epoch": 9.387755102040817, "percentage": 93.99, "elapsed_time": "5:03:51", "remaining_time": "0:19:25"}
|
| 392 |
+
{"current_steps": 1960, "total_steps": 2080, "loss": 0.769, "learning_rate": 4.095023263214121e-07, "epoch": 9.411764705882353, "percentage": 94.23, "elapsed_time": "5:04:39", "remaining_time": "0:18:39"}
|
| 393 |
+
{"current_steps": 1965, "total_steps": 2080, "loss": 0.7539, "learning_rate": 3.761721352756098e-07, "epoch": 9.43577430972389, "percentage": 94.47, "elapsed_time": "5:05:28", "remaining_time": "0:17:52"}
|
| 394 |
+
{"current_steps": 1970, "total_steps": 2080, "loss": 0.6506, "learning_rate": 3.4424626586473385e-07, "epoch": 9.459783913565426, "percentage": 94.71, "elapsed_time": "5:06:14", "remaining_time": "0:17:05"}
|
| 395 |
+
{"current_steps": 1975, "total_steps": 2080, "loss": 0.6763, "learning_rate": 3.1372653885318736e-07, "epoch": 9.483793517406962, "percentage": 94.95, "elapsed_time": "5:06:58", "remaining_time": "0:16:19"}
|
| 396 |
+
{"current_steps": 1980, "total_steps": 2080, "loss": 0.6776, "learning_rate": 2.846146948116468e-07, "epoch": 9.5078031212485, "percentage": 95.19, "elapsed_time": "5:07:42", "remaining_time": "0:15:32"}
|
| 397 |
+
{"current_steps": 1985, "total_steps": 2080, "loss": 0.7292, "learning_rate": 2.569123940178192e-07, "epoch": 9.531812725090036, "percentage": 95.43, "elapsed_time": "5:08:27", "remaining_time": "0:14:45"}
|
| 398 |
+
{"current_steps": 1990, "total_steps": 2080, "loss": 0.8111, "learning_rate": 2.3062121636174826e-07, "epoch": 9.555822328931573, "percentage": 95.67, "elapsed_time": "5:09:14", "remaining_time": "0:13:59"}
|
| 399 |
+
{"current_steps": 1995, "total_steps": 2080, "loss": 0.6473, "learning_rate": 2.0574266125569509e-07, "epoch": 9.579831932773109, "percentage": 95.91, "elapsed_time": "5:09:56", "remaining_time": "0:13:12"}
|
| 400 |
+
{"current_steps": 2000, "total_steps": 2080, "loss": 0.6774, "learning_rate": 1.8227814754865068e-07, "epoch": 9.603841536614645, "percentage": 96.15, "elapsed_time": "5:10:44", "remaining_time": "0:12:25"}
|
| 401 |
+
{"current_steps": 2005, "total_steps": 2080, "loss": 0.6782, "learning_rate": 1.6022901344539543e-07, "epoch": 9.627851140456183, "percentage": 96.39, "elapsed_time": "5:11:30", "remaining_time": "0:11:39"}
|
| 402 |
+
{"current_steps": 2010, "total_steps": 2080, "loss": 0.6965, "learning_rate": 1.39596516430196e-07, "epoch": 9.65186074429772, "percentage": 96.63, "elapsed_time": "5:12:15", "remaining_time": "0:10:52"}
|
| 403 |
+
{"current_steps": 2015, "total_steps": 2080, "loss": 0.6496, "learning_rate": 1.2038183319507955e-07, "epoch": 9.675870348139256, "percentage": 96.88, "elapsed_time": "5:13:01", "remaining_time": "0:10:05"}
|
| 404 |
+
{"current_steps": 2020, "total_steps": 2080, "loss": 0.6511, "learning_rate": 1.0258605957272627e-07, "epoch": 9.699879951980792, "percentage": 97.12, "elapsed_time": "5:13:49", "remaining_time": "0:09:19"}
|
| 405 |
+
{"current_steps": 2025, "total_steps": 2080, "loss": 0.7524, "learning_rate": 8.621021047398314e-08, "epoch": 9.723889555822328, "percentage": 97.36, "elapsed_time": "5:14:40", "remaining_time": "0:08:32"}
|
| 406 |
+
{"current_steps": 2030, "total_steps": 2080, "loss": 0.6653, "learning_rate": 7.125521982997152e-08, "epoch": 9.747899159663866, "percentage": 97.6, "elapsed_time": "5:15:23", "remaining_time": "0:07:46"}
|
| 407 |
+
{"current_steps": 2035, "total_steps": 2080, "loss": 0.6718, "learning_rate": 5.772194053882962e-08, "epoch": 9.771908763505403, "percentage": 97.84, "elapsed_time": "5:16:08", "remaining_time": "0:06:59"}
|
| 408 |
+
{"current_steps": 2040, "total_steps": 2080, "loss": 0.7114, "learning_rate": 4.56111444170626e-08, "epoch": 9.795918367346939, "percentage": 98.08, "elapsed_time": "5:16:58", "remaining_time": "0:06:12"}
|
| 409 |
+
{"current_steps": 2045, "total_steps": 2080, "loss": 0.7125, "learning_rate": 3.4923522155544394e-08, "epoch": 9.819927971188475, "percentage": 98.32, "elapsed_time": "5:17:44", "remaining_time": "0:05:26"}
|
| 410 |
+
{"current_steps": 2050, "total_steps": 2080, "loss": 0.6236, "learning_rate": 2.5659683280102044e-08, "epoch": 9.843937575030012, "percentage": 98.56, "elapsed_time": "5:18:33", "remaining_time": "0:04:39"}
|
| 411 |
+
{"current_steps": 2055, "total_steps": 2080, "loss": 0.7353, "learning_rate": 1.782015611677401e-08, "epoch": 9.867947178871548, "percentage": 98.8, "elapsed_time": "5:19:20", "remaining_time": "0:03:53"}
|
| 412 |
+
{"current_steps": 2060, "total_steps": 2080, "loss": 0.7489, "learning_rate": 1.1405387761664887e-08, "epoch": 9.891956782713086, "percentage": 99.04, "elapsed_time": "5:20:06", "remaining_time": "0:03:06"}
|
| 413 |
+
{"current_steps": 2065, "total_steps": 2080, "loss": 0.7743, "learning_rate": 6.415744055460193e-09, "epoch": 9.915966386554622, "percentage": 99.28, "elapsed_time": "5:21:00", "remaining_time": "0:02:19"}
|
| 414 |
+
{"current_steps": 2070, "total_steps": 2080, "loss": 0.6435, "learning_rate": 2.8515095625514244e-09, "epoch": 9.939975990396158, "percentage": 99.52, "elapsed_time": "5:21:45", "remaining_time": "0:01:33"}
|
| 415 |
+
{"current_steps": 2075, "total_steps": 2080, "loss": 0.7375, "learning_rate": 7.128875548101377e-10, "epoch": 9.963985594237695, "percentage": 99.76, "elapsed_time": "5:22:32", "remaining_time": "0:00:46"}
|
| 416 |
+
{"current_steps": 2080, "total_steps": 2080, "loss": 0.7238, "learning_rate": 0.0, "epoch": 9.987995198079231, "percentage": 100.0, "elapsed_time": "5:23:20", "remaining_time": "0:00:00"}
|
| 417 |
+
{"current_steps": 2080, "total_steps": 2080, "epoch": 9.987995198079231, "percentage": 100.0, "elapsed_time": "5:23:20", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2942 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.987995198079231,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2080,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.024009603841536616,
|
| 13 |
+
"grad_norm": 0.48156169056892395,
|
| 14 |
+
"learning_rate": 4.9999287112445194e-05,
|
| 15 |
+
"loss": 1.2537,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04801920768307323,
|
| 20 |
+
"grad_norm": 0.48818066716194153,
|
| 21 |
+
"learning_rate": 4.999714849043745e-05,
|
| 22 |
+
"loss": 1.1695,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07202881152460984,
|
| 27 |
+
"grad_norm": 0.42254194617271423,
|
| 28 |
+
"learning_rate": 4.999358425594454e-05,
|
| 29 |
+
"loss": 1.1879,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09603841536614646,
|
| 34 |
+
"grad_norm": 0.4787527024745941,
|
| 35 |
+
"learning_rate": 4.9988594612238336e-05,
|
| 36 |
+
"loss": 1.0137,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.12004801920768307,
|
| 41 |
+
"grad_norm": 0.5006477236747742,
|
| 42 |
+
"learning_rate": 4.9982179843883225e-05,
|
| 43 |
+
"loss": 1.1109,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.14405762304921968,
|
| 48 |
+
"grad_norm": 0.4857625961303711,
|
| 49 |
+
"learning_rate": 4.9974340316719906e-05,
|
| 50 |
+
"loss": 1.04,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16806722689075632,
|
| 55 |
+
"grad_norm": 0.5294004678726196,
|
| 56 |
+
"learning_rate": 4.996507647784446e-05,
|
| 57 |
+
"loss": 1.0158,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.19207683073229292,
|
| 62 |
+
"grad_norm": 0.5924685597419739,
|
| 63 |
+
"learning_rate": 4.995438885558294e-05,
|
| 64 |
+
"loss": 0.9004,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.21608643457382953,
|
| 69 |
+
"grad_norm": 0.5567044615745544,
|
| 70 |
+
"learning_rate": 4.9942278059461175e-05,
|
| 71 |
+
"loss": 0.9626,
|
| 72 |
+
"step": 45
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.24009603841536614,
|
| 76 |
+
"grad_norm": 0.5250746607780457,
|
| 77 |
+
"learning_rate": 4.992874478017003e-05,
|
| 78 |
+
"loss": 1.0787,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.26410564225690275,
|
| 83 |
+
"grad_norm": 0.5340147018432617,
|
| 84 |
+
"learning_rate": 4.9913789789526023e-05,
|
| 85 |
+
"loss": 0.8533,
|
| 86 |
+
"step": 55
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.28811524609843936,
|
| 90 |
+
"grad_norm": 0.5907275080680847,
|
| 91 |
+
"learning_rate": 4.989741394042727e-05,
|
| 92 |
+
"loss": 0.9406,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.31212484993997597,
|
| 97 |
+
"grad_norm": 0.6365830898284912,
|
| 98 |
+
"learning_rate": 4.987961816680492e-05,
|
| 99 |
+
"loss": 1.0017,
|
| 100 |
+
"step": 65
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.33613445378151263,
|
| 104 |
+
"grad_norm": 0.6287215948104858,
|
| 105 |
+
"learning_rate": 4.9860403483569805e-05,
|
| 106 |
+
"loss": 0.8902,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.36014405762304924,
|
| 111 |
+
"grad_norm": 0.6473432183265686,
|
| 112 |
+
"learning_rate": 4.983977098655461e-05,
|
| 113 |
+
"loss": 0.907,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.38415366146458585,
|
| 118 |
+
"grad_norm": 0.663551926612854,
|
| 119 |
+
"learning_rate": 4.981772185245135e-05,
|
| 120 |
+
"loss": 1.0197,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.40816326530612246,
|
| 125 |
+
"grad_norm": 0.5929960012435913,
|
| 126 |
+
"learning_rate": 4.979425733874431e-05,
|
| 127 |
+
"loss": 0.8131,
|
| 128 |
+
"step": 85
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.43217286914765907,
|
| 132 |
+
"grad_norm": 0.6948341131210327,
|
| 133 |
+
"learning_rate": 4.9769378783638255e-05,
|
| 134 |
+
"loss": 0.8665,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4561824729891957,
|
| 139 |
+
"grad_norm": 0.8430640697479248,
|
| 140 |
+
"learning_rate": 4.974308760598218e-05,
|
| 141 |
+
"loss": 0.9219,
|
| 142 |
+
"step": 95
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4801920768307323,
|
| 146 |
+
"grad_norm": 0.7752465009689331,
|
| 147 |
+
"learning_rate": 4.971538530518836e-05,
|
| 148 |
+
"loss": 0.9425,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5042016806722689,
|
| 153 |
+
"grad_norm": 0.7160285711288452,
|
| 154 |
+
"learning_rate": 4.968627346114681e-05,
|
| 155 |
+
"loss": 0.8781,
|
| 156 |
+
"step": 105
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5282112845138055,
|
| 160 |
+
"grad_norm": 0.7385575175285339,
|
| 161 |
+
"learning_rate": 4.965575373413527e-05,
|
| 162 |
+
"loss": 0.8446,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5522208883553421,
|
| 167 |
+
"grad_norm": 0.8385459184646606,
|
| 168 |
+
"learning_rate": 4.9623827864724394e-05,
|
| 169 |
+
"loss": 0.9453,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5762304921968787,
|
| 174 |
+
"grad_norm": 0.8416388630867004,
|
| 175 |
+
"learning_rate": 4.959049767367859e-05,
|
| 176 |
+
"loss": 0.8086,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6002400960384153,
|
| 181 |
+
"grad_norm": 0.7977305054664612,
|
| 182 |
+
"learning_rate": 4.955576506185213e-05,
|
| 183 |
+
"loss": 0.8657,
|
| 184 |
+
"step": 125
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6242496998799519,
|
| 188 |
+
"grad_norm": 0.8073853850364685,
|
| 189 |
+
"learning_rate": 4.951963201008076e-05,
|
| 190 |
+
"loss": 0.9168,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6482593037214885,
|
| 195 |
+
"grad_norm": 0.825240433216095,
|
| 196 |
+
"learning_rate": 4.9482100579068706e-05,
|
| 197 |
+
"loss": 0.9192,
|
| 198 |
+
"step": 135
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6722689075630253,
|
| 202 |
+
"grad_norm": 0.7907525300979614,
|
| 203 |
+
"learning_rate": 4.944317290927117e-05,
|
| 204 |
+
"loss": 0.7927,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6962785114045619,
|
| 209 |
+
"grad_norm": 0.7800418138504028,
|
| 210 |
+
"learning_rate": 4.9402851220772274e-05,
|
| 211 |
+
"loss": 0.8486,
|
| 212 |
+
"step": 145
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7202881152460985,
|
| 216 |
+
"grad_norm": 0.8340911269187927,
|
| 217 |
+
"learning_rate": 4.93611378131584e-05,
|
| 218 |
+
"loss": 0.7937,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7442977190876351,
|
| 223 |
+
"grad_norm": 0.9103155732154846,
|
| 224 |
+
"learning_rate": 4.931803506538707e-05,
|
| 225 |
+
"loss": 0.834,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7683073229291717,
|
| 230 |
+
"grad_norm": 0.8660081028938293,
|
| 231 |
+
"learning_rate": 4.92735454356513e-05,
|
| 232 |
+
"loss": 0.7799,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7923169267707083,
|
| 237 |
+
"grad_norm": 0.7390795350074768,
|
| 238 |
+
"learning_rate": 4.9227671461239354e-05,
|
| 239 |
+
"loss": 0.8608,
|
| 240 |
+
"step": 165
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8163265306122449,
|
| 244 |
+
"grad_norm": 0.8534154891967773,
|
| 245 |
+
"learning_rate": 4.918041575839007e-05,
|
| 246 |
+
"loss": 0.8872,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8403361344537815,
|
| 251 |
+
"grad_norm": 1.0927950143814087,
|
| 252 |
+
"learning_rate": 4.913178102214363e-05,
|
| 253 |
+
"loss": 0.8681,
|
| 254 |
+
"step": 175
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8643457382953181,
|
| 258 |
+
"grad_norm": 0.8660680055618286,
|
| 259 |
+
"learning_rate": 4.9081770026187914e-05,
|
| 260 |
+
"loss": 0.8451,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8883553421368547,
|
| 265 |
+
"grad_norm": 0.7952775955200195,
|
| 266 |
+
"learning_rate": 4.9030385622700225e-05,
|
| 267 |
+
"loss": 0.8662,
|
| 268 |
+
"step": 185
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9123649459783914,
|
| 272 |
+
"grad_norm": 0.8808633685112,
|
| 273 |
+
"learning_rate": 4.897763074218472e-05,
|
| 274 |
+
"loss": 0.8183,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.936374549819928,
|
| 279 |
+
"grad_norm": 0.7455188632011414,
|
| 280 |
+
"learning_rate": 4.892350839330522e-05,
|
| 281 |
+
"loss": 0.8887,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9603841536614646,
|
| 286 |
+
"grad_norm": 0.7687739729881287,
|
| 287 |
+
"learning_rate": 4.886802166271364e-05,
|
| 288 |
+
"loss": 0.8505,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9843937575030012,
|
| 293 |
+
"grad_norm": 0.7754830121994019,
|
| 294 |
+
"learning_rate": 4.881117371487396e-05,
|
| 295 |
+
"loss": 0.835,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.0084033613445378,
|
| 300 |
+
"grad_norm": 0.7828541398048401,
|
| 301 |
+
"learning_rate": 4.875296779188173e-05,
|
| 302 |
+
"loss": 0.8531,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.0324129651860745,
|
| 307 |
+
"grad_norm": 1.015205979347229,
|
| 308 |
+
"learning_rate": 4.8693407213279206e-05,
|
| 309 |
+
"loss": 0.8679,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.056422569027611,
|
| 314 |
+
"grad_norm": 0.8347631692886353,
|
| 315 |
+
"learning_rate": 4.8632495375866004e-05,
|
| 316 |
+
"loss": 0.8432,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.0804321728691477,
|
| 321 |
+
"grad_norm": 0.9165553450584412,
|
| 322 |
+
"learning_rate": 4.8570235753505406e-05,
|
| 323 |
+
"loss": 0.8362,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.1044417767106842,
|
| 328 |
+
"grad_norm": 0.954313337802887,
|
| 329 |
+
"learning_rate": 4.850663189692619e-05,
|
| 330 |
+
"loss": 0.7704,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.128451380552221,
|
| 335 |
+
"grad_norm": 1.096909761428833,
|
| 336 |
+
"learning_rate": 4.844168743352019e-05,
|
| 337 |
+
"loss": 0.8357,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.1524609843937574,
|
| 342 |
+
"grad_norm": 0.9319111108779907,
|
| 343 |
+
"learning_rate": 4.837540606713538e-05,
|
| 344 |
+
"loss": 0.7461,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.1764705882352942,
|
| 349 |
+
"grad_norm": 1.0731585025787354,
|
| 350 |
+
"learning_rate": 4.830779157786465e-05,
|
| 351 |
+
"loss": 0.8821,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.2004801920768307,
|
| 356 |
+
"grad_norm": 0.8962486982345581,
|
| 357 |
+
"learning_rate": 4.823884782183023e-05,
|
| 358 |
+
"loss": 0.889,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.2244897959183674,
|
| 363 |
+
"grad_norm": 0.8899649381637573,
|
| 364 |
+
"learning_rate": 4.8168578730963804e-05,
|
| 365 |
+
"loss": 0.7407,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.2484993997599039,
|
| 370 |
+
"grad_norm": 0.9980818033218384,
|
| 371 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 372 |
+
"loss": 0.7822,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.2725090036014406,
|
| 377 |
+
"grad_norm": 0.9607000350952148,
|
| 378 |
+
"learning_rate": 4.80240806501588e-05,
|
| 379 |
+
"loss": 0.9008,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.296518607442977,
|
| 384 |
+
"grad_norm": 1.0252315998077393,
|
| 385 |
+
"learning_rate": 4.7949859901090896e-05,
|
| 386 |
+
"loss": 0.7477,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.3205282112845138,
|
| 391 |
+
"grad_norm": 0.8092382550239563,
|
| 392 |
+
"learning_rate": 4.787433029846236e-05,
|
| 393 |
+
"loss": 0.7846,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.3445378151260505,
|
| 398 |
+
"grad_norm": 0.9593423008918762,
|
| 399 |
+
"learning_rate": 4.7797496149802256e-05,
|
| 400 |
+
"loss": 0.8544,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.368547418967587,
|
| 405 |
+
"grad_norm": 0.9516417980194092,
|
| 406 |
+
"learning_rate": 4.771936183703927e-05,
|
| 407 |
+
"loss": 0.7706,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.3925570228091235,
|
| 412 |
+
"grad_norm": 1.2291992902755737,
|
| 413 |
+
"learning_rate": 4.763993181625174e-05,
|
| 414 |
+
"loss": 0.8256,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.4165666266506602,
|
| 419 |
+
"grad_norm": 0.9861960411071777,
|
| 420 |
+
"learning_rate": 4.7559210617413514e-05,
|
| 421 |
+
"loss": 0.8185,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.440576230492197,
|
| 426 |
+
"grad_norm": 0.8679934144020081,
|
| 427 |
+
"learning_rate": 4.7477202844135646e-05,
|
| 428 |
+
"loss": 0.7356,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.4645858343337335,
|
| 433 |
+
"grad_norm": 0.754160463809967,
|
| 434 |
+
"learning_rate": 4.739391317340383e-05,
|
| 435 |
+
"loss": 0.8015,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.4885954381752702,
|
| 440 |
+
"grad_norm": 1.0975936651229858,
|
| 441 |
+
"learning_rate": 4.730934635531161e-05,
|
| 442 |
+
"loss": 0.8103,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.5126050420168067,
|
| 447 |
+
"grad_norm": 0.8794222474098206,
|
| 448 |
+
"learning_rate": 4.722350721278958e-05,
|
| 449 |
+
"loss": 0.6949,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.5366146458583434,
|
| 454 |
+
"grad_norm": 1.009118676185608,
|
| 455 |
+
"learning_rate": 4.713640064133025e-05,
|
| 456 |
+
"loss": 0.779,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.5606242496998801,
|
| 461 |
+
"grad_norm": 1.1100735664367676,
|
| 462 |
+
"learning_rate": 4.7048031608708876e-05,
|
| 463 |
+
"loss": 0.8016,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.5846338535414166,
|
| 468 |
+
"grad_norm": 0.8312719464302063,
|
| 469 |
+
"learning_rate": 4.6958405154700154e-05,
|
| 470 |
+
"loss": 0.746,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.6086434573829531,
|
| 475 |
+
"grad_norm": 0.9220231175422668,
|
| 476 |
+
"learning_rate": 4.686752639079076e-05,
|
| 477 |
+
"loss": 0.7439,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.6326530612244898,
|
| 482 |
+
"grad_norm": 1.1262476444244385,
|
| 483 |
+
"learning_rate": 4.677540049988789e-05,
|
| 484 |
+
"loss": 0.7969,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.6566626650660266,
|
| 489 |
+
"grad_norm": 1.1132248640060425,
|
| 490 |
+
"learning_rate": 4.668203273602363e-05,
|
| 491 |
+
"loss": 0.858,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.680672268907563,
|
| 496 |
+
"grad_norm": 1.0028260946273804,
|
| 497 |
+
"learning_rate": 4.6587428424055326e-05,
|
| 498 |
+
"loss": 0.8538,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.7046818727490995,
|
| 503 |
+
"grad_norm": 1.057077407836914,
|
| 504 |
+
"learning_rate": 4.649159295936191e-05,
|
| 505 |
+
"loss": 0.8241,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.7286914765906363,
|
| 510 |
+
"grad_norm": 0.8777754902839661,
|
| 511 |
+
"learning_rate": 4.639453180753619e-05,
|
| 512 |
+
"loss": 0.7388,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.752701080432173,
|
| 517 |
+
"grad_norm": 0.9972108006477356,
|
| 518 |
+
"learning_rate": 4.6296250504073145e-05,
|
| 519 |
+
"loss": 0.7924,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.7767106842737095,
|
| 524 |
+
"grad_norm": 1.0971965789794922,
|
| 525 |
+
"learning_rate": 4.6196754654054216e-05,
|
| 526 |
+
"loss": 0.7719,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.800720288115246,
|
| 531 |
+
"grad_norm": 1.1859172582626343,
|
| 532 |
+
"learning_rate": 4.609604993182767e-05,
|
| 533 |
+
"loss": 0.8365,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.8247298919567827,
|
| 538 |
+
"grad_norm": 0.9028448462486267,
|
| 539 |
+
"learning_rate": 4.599414208068495e-05,
|
| 540 |
+
"loss": 0.8118,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.8487394957983194,
|
| 545 |
+
"grad_norm": 0.8329624533653259,
|
| 546 |
+
"learning_rate": 4.589103691253317e-05,
|
| 547 |
+
"loss": 0.7881,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.872749099639856,
|
| 552 |
+
"grad_norm": 0.985603928565979,
|
| 553 |
+
"learning_rate": 4.5786740307563636e-05,
|
| 554 |
+
"loss": 0.7155,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.8967587034813924,
|
| 559 |
+
"grad_norm": 0.9097521901130676,
|
| 560 |
+
"learning_rate": 4.568125821391647e-05,
|
| 561 |
+
"loss": 0.8555,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.9207683073229291,
|
| 566 |
+
"grad_norm": 1.0277526378631592,
|
| 567 |
+
"learning_rate": 4.557459664734141e-05,
|
| 568 |
+
"loss": 0.8685,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.9447779111644659,
|
| 573 |
+
"grad_norm": 0.8617818355560303,
|
| 574 |
+
"learning_rate": 4.5466761690854746e-05,
|
| 575 |
+
"loss": 0.7708,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.9687875150060024,
|
| 580 |
+
"grad_norm": 0.8086485266685486,
|
| 581 |
+
"learning_rate": 4.535775949439235e-05,
|
| 582 |
+
"loss": 0.8448,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.9927971188475389,
|
| 587 |
+
"grad_norm": 1.0069591999053955,
|
| 588 |
+
"learning_rate": 4.5247596274458956e-05,
|
| 589 |
+
"loss": 0.736,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.0168067226890756,
|
| 594 |
+
"grad_norm": 0.7122059464454651,
|
| 595 |
+
"learning_rate": 4.513627831377365e-05,
|
| 596 |
+
"loss": 0.7223,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.0408163265306123,
|
| 601 |
+
"grad_norm": 0.9053510427474976,
|
| 602 |
+
"learning_rate": 4.502381196091154e-05,
|
| 603 |
+
"loss": 0.7504,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.064825930372149,
|
| 608 |
+
"grad_norm": 1.0357030630111694,
|
| 609 |
+
"learning_rate": 4.491020362994168e-05,
|
| 610 |
+
"loss": 0.8011,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.0888355342136853,
|
| 615 |
+
"grad_norm": 0.9885731339454651,
|
| 616 |
+
"learning_rate": 4.47954598000613e-05,
|
| 617 |
+
"loss": 0.8665,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.112845138055222,
|
| 622 |
+
"grad_norm": 0.9989228844642639,
|
| 623 |
+
"learning_rate": 4.4679587015226253e-05,
|
| 624 |
+
"loss": 0.749,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.1368547418967587,
|
| 629 |
+
"grad_norm": 0.8704085350036621,
|
| 630 |
+
"learning_rate": 4.456259188377786e-05,
|
| 631 |
+
"loss": 0.7962,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.1608643457382954,
|
| 636 |
+
"grad_norm": 0.9389162063598633,
|
| 637 |
+
"learning_rate": 4.444448107806596e-05,
|
| 638 |
+
"loss": 0.7964,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.184873949579832,
|
| 643 |
+
"grad_norm": 0.9259791970252991,
|
| 644 |
+
"learning_rate": 4.4325261334068426e-05,
|
| 645 |
+
"loss": 0.7516,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.2088835534213684,
|
| 650 |
+
"grad_norm": 1.4041215181350708,
|
| 651 |
+
"learning_rate": 4.420493945100702e-05,
|
| 652 |
+
"loss": 0.8173,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.232893157262905,
|
| 657 |
+
"grad_norm": 0.9259509444236755,
|
| 658 |
+
"learning_rate": 4.4083522290959564e-05,
|
| 659 |
+
"loss": 0.8038,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.256902761104442,
|
| 664 |
+
"grad_norm": 1.0205409526824951,
|
| 665 |
+
"learning_rate": 4.396101677846866e-05,
|
| 666 |
+
"loss": 0.8055,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 2.280912364945978,
|
| 671 |
+
"grad_norm": 0.9302276372909546,
|
| 672 |
+
"learning_rate": 4.383742990014671e-05,
|
| 673 |
+
"loss": 0.7459,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.304921968787515,
|
| 678 |
+
"grad_norm": 0.9929239749908447,
|
| 679 |
+
"learning_rate": 4.371276870427753e-05,
|
| 680 |
+
"loss": 0.7959,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.3289315726290516,
|
| 685 |
+
"grad_norm": 1.0315582752227783,
|
| 686 |
+
"learning_rate": 4.358704030041432e-05,
|
| 687 |
+
"loss": 0.8528,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.3529411764705883,
|
| 692 |
+
"grad_norm": 0.9557288289070129,
|
| 693 |
+
"learning_rate": 4.346025185897424e-05,
|
| 694 |
+
"loss": 0.759,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.376950780312125,
|
| 699 |
+
"grad_norm": 1.080580472946167,
|
| 700 |
+
"learning_rate": 4.333241061082944e-05,
|
| 701 |
+
"loss": 0.7499,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.4009603841536613,
|
| 706 |
+
"grad_norm": 0.96761155128479,
|
| 707 |
+
"learning_rate": 4.320352384689471e-05,
|
| 708 |
+
"loss": 0.7279,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.424969987995198,
|
| 713 |
+
"grad_norm": 1.0945556163787842,
|
| 714 |
+
"learning_rate": 4.307359891771165e-05,
|
| 715 |
+
"loss": 0.7453,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.4489795918367347,
|
| 720 |
+
"grad_norm": 0.9983144998550415,
|
| 721 |
+
"learning_rate": 4.294264323302946e-05,
|
| 722 |
+
"loss": 0.8311,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.4729891956782715,
|
| 727 |
+
"grad_norm": 0.8600877523422241,
|
| 728 |
+
"learning_rate": 4.2810664261382375e-05,
|
| 729 |
+
"loss": 0.7172,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.4969987995198077,
|
| 734 |
+
"grad_norm": 1.0828715562820435,
|
| 735 |
+
"learning_rate": 4.267766952966369e-05,
|
| 736 |
+
"loss": 0.8084,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.5210084033613445,
|
| 741 |
+
"grad_norm": 0.9153307676315308,
|
| 742 |
+
"learning_rate": 4.254366662269655e-05,
|
| 743 |
+
"loss": 0.702,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.545018007202881,
|
| 748 |
+
"grad_norm": 0.8633860349655151,
|
| 749 |
+
"learning_rate": 4.240866318280132e-05,
|
| 750 |
+
"loss": 0.7261,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.569027611044418,
|
| 755 |
+
"grad_norm": 0.9197015762329102,
|
| 756 |
+
"learning_rate": 4.227266690935978e-05,
|
| 757 |
+
"loss": 0.754,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.593037214885954,
|
| 762 |
+
"grad_norm": 0.9729764461517334,
|
| 763 |
+
"learning_rate": 4.2135685558375994e-05,
|
| 764 |
+
"loss": 0.7855,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.617046818727491,
|
| 769 |
+
"grad_norm": 0.981951117515564,
|
| 770 |
+
"learning_rate": 4.199772694203399e-05,
|
| 771 |
+
"loss": 0.7584,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.6410564225690276,
|
| 776 |
+
"grad_norm": 0.8585065603256226,
|
| 777 |
+
"learning_rate": 4.185879892825222e-05,
|
| 778 |
+
"loss": 0.8196,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.6650660264105643,
|
| 783 |
+
"grad_norm": 0.8955056071281433,
|
| 784 |
+
"learning_rate": 4.1718909440234853e-05,
|
| 785 |
+
"loss": 0.6836,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.689075630252101,
|
| 790 |
+
"grad_norm": 0.9751344919204712,
|
| 791 |
+
"learning_rate": 4.157806645601988e-05,
|
| 792 |
+
"loss": 0.7656,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.7130852340936373,
|
| 797 |
+
"grad_norm": 0.9694618582725525,
|
| 798 |
+
"learning_rate": 4.143627800802417e-05,
|
| 799 |
+
"loss": 0.7787,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.737094837935174,
|
| 804 |
+
"grad_norm": 1.0527385473251343,
|
| 805 |
+
"learning_rate": 4.1293552182585307e-05,
|
| 806 |
+
"loss": 0.7665,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.7611044417767108,
|
| 811 |
+
"grad_norm": 0.9396669864654541,
|
| 812 |
+
"learning_rate": 4.114989711950047e-05,
|
| 813 |
+
"loss": 0.748,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.785114045618247,
|
| 818 |
+
"grad_norm": 1.0898234844207764,
|
| 819 |
+
"learning_rate": 4.1005321011562206e-05,
|
| 820 |
+
"loss": 0.7761,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.8091236494597838,
|
| 825 |
+
"grad_norm": 1.0972914695739746,
|
| 826 |
+
"learning_rate": 4.085983210409114e-05,
|
| 827 |
+
"loss": 0.7873,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.8331332533013205,
|
| 832 |
+
"grad_norm": 1.1150754690170288,
|
| 833 |
+
"learning_rate": 4.0713438694465806e-05,
|
| 834 |
+
"loss": 0.8288,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.857142857142857,
|
| 839 |
+
"grad_norm": 0.9612060785293579,
|
| 840 |
+
"learning_rate": 4.056614913164938e-05,
|
| 841 |
+
"loss": 0.7587,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.881152460984394,
|
| 846 |
+
"grad_norm": 0.8540961146354675,
|
| 847 |
+
"learning_rate": 4.0417971815713584e-05,
|
| 848 |
+
"loss": 0.7096,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.90516206482593,
|
| 853 |
+
"grad_norm": 1.1552797555923462,
|
| 854 |
+
"learning_rate": 4.026891519735955e-05,
|
| 855 |
+
"loss": 0.7177,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.929171668667467,
|
| 860 |
+
"grad_norm": 0.8366991281509399,
|
| 861 |
+
"learning_rate": 4.011898777743594e-05,
|
| 862 |
+
"loss": 0.7244,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.9531812725090036,
|
| 867 |
+
"grad_norm": 1.1516789197921753,
|
| 868 |
+
"learning_rate": 3.99681981064541e-05,
|
| 869 |
+
"loss": 0.7627,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.9771908763505404,
|
| 874 |
+
"grad_norm": 1.119287133216858,
|
| 875 |
+
"learning_rate": 3.981655478410043e-05,
|
| 876 |
+
"loss": 0.7562,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 3.0012004801920766,
|
| 881 |
+
"grad_norm": 0.9897541403770447,
|
| 882 |
+
"learning_rate": 3.966406645874589e-05,
|
| 883 |
+
"loss": 0.8271,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.0252100840336134,
|
| 888 |
+
"grad_norm": 0.979117214679718,
|
| 889 |
+
"learning_rate": 3.951074182695284e-05,
|
| 890 |
+
"loss": 0.7639,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 3.04921968787515,
|
| 895 |
+
"grad_norm": 1.234833836555481,
|
| 896 |
+
"learning_rate": 3.935658963297902e-05,
|
| 897 |
+
"loss": 0.7117,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 3.073229291716687,
|
| 902 |
+
"grad_norm": 1.0178768634796143,
|
| 903 |
+
"learning_rate": 3.920161866827889e-05,
|
| 904 |
+
"loss": 0.7358,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.097238895558223,
|
| 909 |
+
"grad_norm": 0.9386712312698364,
|
| 910 |
+
"learning_rate": 3.904583777100223e-05,
|
| 911 |
+
"loss": 0.7409,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.12124849939976,
|
| 916 |
+
"grad_norm": 1.140830397605896,
|
| 917 |
+
"learning_rate": 3.888925582549006e-05,
|
| 918 |
+
"loss": 0.7052,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 3.1452581032412965,
|
| 923 |
+
"grad_norm": 0.9676099419593811,
|
| 924 |
+
"learning_rate": 3.8731881761768e-05,
|
| 925 |
+
"loss": 0.7602,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.1692677070828332,
|
| 930 |
+
"grad_norm": 1.1593329906463623,
|
| 931 |
+
"learning_rate": 3.857372455503697e-05,
|
| 932 |
+
"loss": 0.8514,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 3.19327731092437,
|
| 937 |
+
"grad_norm": 1.1297277212142944,
|
| 938 |
+
"learning_rate": 3.8414793225161325e-05,
|
| 939 |
+
"loss": 0.7699,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 3.2172869147659062,
|
| 944 |
+
"grad_norm": 0.9413173794746399,
|
| 945 |
+
"learning_rate": 3.825509683615442e-05,
|
| 946 |
+
"loss": 0.8067,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.241296518607443,
|
| 951 |
+
"grad_norm": 0.9704225063323975,
|
| 952 |
+
"learning_rate": 3.809464449566175e-05,
|
| 953 |
+
"loss": 0.6783,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 3.2653061224489797,
|
| 958 |
+
"grad_norm": 0.9347226023674011,
|
| 959 |
+
"learning_rate": 3.793344535444142e-05,
|
| 960 |
+
"loss": 0.7315,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 3.2893157262905164,
|
| 965 |
+
"grad_norm": 0.9760938882827759,
|
| 966 |
+
"learning_rate": 3.777150860584237e-05,
|
| 967 |
+
"loss": 0.6999,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.3133253301320527,
|
| 972 |
+
"grad_norm": 1.114785075187683,
|
| 973 |
+
"learning_rate": 3.760884348528002e-05,
|
| 974 |
+
"loss": 0.7182,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.3373349339735894,
|
| 979 |
+
"grad_norm": 1.0659857988357544,
|
| 980 |
+
"learning_rate": 3.744545926970957e-05,
|
| 981 |
+
"loss": 0.7577,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.361344537815126,
|
| 986 |
+
"grad_norm": 1.0988335609436035,
|
| 987 |
+
"learning_rate": 3.728136527709694e-05,
|
| 988 |
+
"loss": 0.7825,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.385354141656663,
|
| 993 |
+
"grad_norm": 0.9283490180969238,
|
| 994 |
+
"learning_rate": 3.711657086588733e-05,
|
| 995 |
+
"loss": 0.7414,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.409363745498199,
|
| 1000 |
+
"grad_norm": 1.1617555618286133,
|
| 1001 |
+
"learning_rate": 3.695108543447154e-05,
|
| 1002 |
+
"loss": 0.7144,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.433373349339736,
|
| 1007 |
+
"grad_norm": 1.1011674404144287,
|
| 1008 |
+
"learning_rate": 3.678491842064995e-05,
|
| 1009 |
+
"loss": 0.7516,
|
| 1010 |
+
"step": 715
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.4573829531812725,
|
| 1014 |
+
"grad_norm": 0.9130650758743286,
|
| 1015 |
+
"learning_rate": 3.6618079301094216e-05,
|
| 1016 |
+
"loss": 0.7484,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.4813925570228093,
|
| 1021 |
+
"grad_norm": 1.1056820154190063,
|
| 1022 |
+
"learning_rate": 3.645057759080692e-05,
|
| 1023 |
+
"loss": 0.7775,
|
| 1024 |
+
"step": 725
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.505402160864346,
|
| 1028 |
+
"grad_norm": 1.219381332397461,
|
| 1029 |
+
"learning_rate": 3.6282422842578845e-05,
|
| 1030 |
+
"loss": 0.7086,
|
| 1031 |
+
"step": 730
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.5294117647058822,
|
| 1035 |
+
"grad_norm": 1.2623860836029053,
|
| 1036 |
+
"learning_rate": 3.611362464644415e-05,
|
| 1037 |
+
"loss": 0.7165,
|
| 1038 |
+
"step": 735
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.553421368547419,
|
| 1042 |
+
"grad_norm": 1.0355645418167114,
|
| 1043 |
+
"learning_rate": 3.594419262913351e-05,
|
| 1044 |
+
"loss": 0.7668,
|
| 1045 |
+
"step": 740
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.5774309723889557,
|
| 1049 |
+
"grad_norm": 0.9813769459724426,
|
| 1050 |
+
"learning_rate": 3.577413645352506e-05,
|
| 1051 |
+
"loss": 0.6595,
|
| 1052 |
+
"step": 745
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.601440576230492,
|
| 1056 |
+
"grad_norm": 1.0704172849655151,
|
| 1057 |
+
"learning_rate": 3.560346581809328e-05,
|
| 1058 |
+
"loss": 0.7469,
|
| 1059 |
+
"step": 750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.6254501800720287,
|
| 1063 |
+
"grad_norm": 1.0033190250396729,
|
| 1064 |
+
"learning_rate": 3.543219045635593e-05,
|
| 1065 |
+
"loss": 0.7063,
|
| 1066 |
+
"step": 755
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.6494597839135654,
|
| 1070 |
+
"grad_norm": 0.9432305097579956,
|
| 1071 |
+
"learning_rate": 3.526032013631893e-05,
|
| 1072 |
+
"loss": 0.6694,
|
| 1073 |
+
"step": 760
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.673469387755102,
|
| 1077 |
+
"grad_norm": 1.0187017917633057,
|
| 1078 |
+
"learning_rate": 3.508786465991923e-05,
|
| 1079 |
+
"loss": 0.7789,
|
| 1080 |
+
"step": 765
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.697478991596639,
|
| 1084 |
+
"grad_norm": 1.076158881187439,
|
| 1085 |
+
"learning_rate": 3.491483386246588e-05,
|
| 1086 |
+
"loss": 0.7934,
|
| 1087 |
+
"step": 770
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 3.721488595438175,
|
| 1091 |
+
"grad_norm": 0.8803985714912415,
|
| 1092 |
+
"learning_rate": 3.474123761207905e-05,
|
| 1093 |
+
"loss": 0.7295,
|
| 1094 |
+
"step": 775
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.745498199279712,
|
| 1098 |
+
"grad_norm": 0.9059305787086487,
|
| 1099 |
+
"learning_rate": 3.456708580912725e-05,
|
| 1100 |
+
"loss": 0.7474,
|
| 1101 |
+
"step": 780
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 3.7695078031212486,
|
| 1105 |
+
"grad_norm": 1.1186120510101318,
|
| 1106 |
+
"learning_rate": 3.4392388385662714e-05,
|
| 1107 |
+
"loss": 0.7711,
|
| 1108 |
+
"step": 785
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 3.7935174069627853,
|
| 1112 |
+
"grad_norm": 1.0779385566711426,
|
| 1113 |
+
"learning_rate": 3.4217155304854976e-05,
|
| 1114 |
+
"loss": 0.7363,
|
| 1115 |
+
"step": 790
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 3.817527010804322,
|
| 1119 |
+
"grad_norm": 1.0094141960144043,
|
| 1120 |
+
"learning_rate": 3.4041396560422624e-05,
|
| 1121 |
+
"loss": 0.8531,
|
| 1122 |
+
"step": 795
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 3.8415366146458583,
|
| 1126 |
+
"grad_norm": 0.9442546963691711,
|
| 1127 |
+
"learning_rate": 3.386512217606339e-05,
|
| 1128 |
+
"loss": 0.8025,
|
| 1129 |
+
"step": 800
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.865546218487395,
|
| 1133 |
+
"grad_norm": 1.0685694217681885,
|
| 1134 |
+
"learning_rate": 3.3688342204882466e-05,
|
| 1135 |
+
"loss": 0.6634,
|
| 1136 |
+
"step": 805
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.8895558223289317,
|
| 1140 |
+
"grad_norm": 0.9987934827804565,
|
| 1141 |
+
"learning_rate": 3.351106672881915e-05,
|
| 1142 |
+
"loss": 0.7664,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.913565426170468,
|
| 1147 |
+
"grad_norm": 1.0503917932510376,
|
| 1148 |
+
"learning_rate": 3.33333058580719e-05,
|
| 1149 |
+
"loss": 0.865,
|
| 1150 |
+
"step": 815
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 3.9375750300120047,
|
| 1154 |
+
"grad_norm": 0.9366332292556763,
|
| 1155 |
+
"learning_rate": 3.3155069730521735e-05,
|
| 1156 |
+
"loss": 0.7096,
|
| 1157 |
+
"step": 820
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 3.9615846338535414,
|
| 1161 |
+
"grad_norm": 1.173298954963684,
|
| 1162 |
+
"learning_rate": 3.2976368511153996e-05,
|
| 1163 |
+
"loss": 0.8476,
|
| 1164 |
+
"step": 825
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 3.985594237695078,
|
| 1168 |
+
"grad_norm": 1.0985863208770752,
|
| 1169 |
+
"learning_rate": 3.2797212391478724e-05,
|
| 1170 |
+
"loss": 0.705,
|
| 1171 |
+
"step": 830
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 4.009603841536615,
|
| 1175 |
+
"grad_norm": 1.124514102935791,
|
| 1176 |
+
"learning_rate": 3.261761158894937e-05,
|
| 1177 |
+
"loss": 0.7086,
|
| 1178 |
+
"step": 835
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 4.033613445378151,
|
| 1182 |
+
"grad_norm": 0.9647889733314514,
|
| 1183 |
+
"learning_rate": 3.243757634638008e-05,
|
| 1184 |
+
"loss": 0.6899,
|
| 1185 |
+
"step": 840
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 4.057623049219688,
|
| 1189 |
+
"grad_norm": 0.9771691560745239,
|
| 1190 |
+
"learning_rate": 3.225711693136156e-05,
|
| 1191 |
+
"loss": 0.8088,
|
| 1192 |
+
"step": 845
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 4.081632653061225,
|
| 1196 |
+
"grad_norm": 1.1176905632019043,
|
| 1197 |
+
"learning_rate": 3.2076243635675513e-05,
|
| 1198 |
+
"loss": 0.7096,
|
| 1199 |
+
"step": 850
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 4.105642256902761,
|
| 1203 |
+
"grad_norm": 1.0890402793884277,
|
| 1204 |
+
"learning_rate": 3.189496677470765e-05,
|
| 1205 |
+
"loss": 0.7646,
|
| 1206 |
+
"step": 855
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 4.129651860744298,
|
| 1210 |
+
"grad_norm": 1.099631905555725,
|
| 1211 |
+
"learning_rate": 3.1713296686859426e-05,
|
| 1212 |
+
"loss": 0.7525,
|
| 1213 |
+
"step": 860
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 4.153661464585834,
|
| 1217 |
+
"grad_norm": 0.995556652545929,
|
| 1218 |
+
"learning_rate": 3.153124373295841e-05,
|
| 1219 |
+
"loss": 0.7231,
|
| 1220 |
+
"step": 865
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.177671068427371,
|
| 1224 |
+
"grad_norm": 1.1333503723144531,
|
| 1225 |
+
"learning_rate": 3.1348818295667424e-05,
|
| 1226 |
+
"loss": 0.7431,
|
| 1227 |
+
"step": 870
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 4.201680672268908,
|
| 1231 |
+
"grad_norm": 1.0261584520339966,
|
| 1232 |
+
"learning_rate": 3.116603077889238e-05,
|
| 1233 |
+
"loss": 0.7619,
|
| 1234 |
+
"step": 875
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 4.225690276110444,
|
| 1238 |
+
"grad_norm": 0.9810305833816528,
|
| 1239 |
+
"learning_rate": 3.098289160718895e-05,
|
| 1240 |
+
"loss": 0.7806,
|
| 1241 |
+
"step": 880
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 4.249699879951981,
|
| 1245 |
+
"grad_norm": 1.160054087638855,
|
| 1246 |
+
"learning_rate": 3.079941122516803e-05,
|
| 1247 |
+
"loss": 0.701,
|
| 1248 |
+
"step": 885
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 4.2737094837935174,
|
| 1252 |
+
"grad_norm": 0.9885622262954712,
|
| 1253 |
+
"learning_rate": 3.061560009690011e-05,
|
| 1254 |
+
"loss": 0.7114,
|
| 1255 |
+
"step": 890
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 4.297719087635054,
|
| 1259 |
+
"grad_norm": 1.092362880706787,
|
| 1260 |
+
"learning_rate": 3.0431468705318424e-05,
|
| 1261 |
+
"loss": 0.7407,
|
| 1262 |
+
"step": 895
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.321728691476591,
|
| 1266 |
+
"grad_norm": 1.3226685523986816,
|
| 1267 |
+
"learning_rate": 3.024702755162119e-05,
|
| 1268 |
+
"loss": 0.756,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 4.345738295318127,
|
| 1273 |
+
"grad_norm": 1.164993166923523,
|
| 1274 |
+
"learning_rate": 3.0062287154672658e-05,
|
| 1275 |
+
"loss": 0.6897,
|
| 1276 |
+
"step": 905
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 4.369747899159664,
|
| 1280 |
+
"grad_norm": 1.1299794912338257,
|
| 1281 |
+
"learning_rate": 2.9877258050403212e-05,
|
| 1282 |
+
"loss": 0.7212,
|
| 1283 |
+
"step": 910
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 4.393757503001201,
|
| 1287 |
+
"grad_norm": 1.1793334484100342,
|
| 1288 |
+
"learning_rate": 2.9691950791208502e-05,
|
| 1289 |
+
"loss": 0.8578,
|
| 1290 |
+
"step": 915
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 4.417767106842737,
|
| 1294 |
+
"grad_norm": 1.2607135772705078,
|
| 1295 |
+
"learning_rate": 2.950637594534765e-05,
|
| 1296 |
+
"loss": 0.7116,
|
| 1297 |
+
"step": 920
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 4.441776710684274,
|
| 1301 |
+
"grad_norm": 1.309200644493103,
|
| 1302 |
+
"learning_rate": 2.9320544096340493e-05,
|
| 1303 |
+
"loss": 0.7693,
|
| 1304 |
+
"step": 925
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.46578631452581,
|
| 1308 |
+
"grad_norm": 0.9688151478767395,
|
| 1309 |
+
"learning_rate": 2.9134465842364035e-05,
|
| 1310 |
+
"loss": 0.6641,
|
| 1311 |
+
"step": 930
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 4.489795918367347,
|
| 1315 |
+
"grad_norm": 1.155928373336792,
|
| 1316 |
+
"learning_rate": 2.8948151795647993e-05,
|
| 1317 |
+
"loss": 0.7488,
|
| 1318 |
+
"step": 935
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 4.513805522208884,
|
| 1322 |
+
"grad_norm": 1.2800368070602417,
|
| 1323 |
+
"learning_rate": 2.876161258186958e-05,
|
| 1324 |
+
"loss": 0.6626,
|
| 1325 |
+
"step": 940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 4.53781512605042,
|
| 1329 |
+
"grad_norm": 1.2294648885726929,
|
| 1330 |
+
"learning_rate": 2.8574858839547512e-05,
|
| 1331 |
+
"loss": 0.7064,
|
| 1332 |
+
"step": 945
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 4.561824729891956,
|
| 1336 |
+
"grad_norm": 1.1497923135757446,
|
| 1337 |
+
"learning_rate": 2.83879012194353e-05,
|
| 1338 |
+
"loss": 0.703,
|
| 1339 |
+
"step": 950
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.5858343337334935,
|
| 1343 |
+
"grad_norm": 1.0689631700515747,
|
| 1344 |
+
"learning_rate": 2.8200750383913776e-05,
|
| 1345 |
+
"loss": 0.8085,
|
| 1346 |
+
"step": 955
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.60984393757503,
|
| 1350 |
+
"grad_norm": 1.038040041923523,
|
| 1351 |
+
"learning_rate": 2.8013417006383076e-05,
|
| 1352 |
+
"loss": 0.7251,
|
| 1353 |
+
"step": 960
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 4.633853541416567,
|
| 1357 |
+
"grad_norm": 0.9959046244621277,
|
| 1358 |
+
"learning_rate": 2.782591177065388e-05,
|
| 1359 |
+
"loss": 0.7358,
|
| 1360 |
+
"step": 965
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 4.657863145258103,
|
| 1364 |
+
"grad_norm": 1.1039036512374878,
|
| 1365 |
+
"learning_rate": 2.763824537033809e-05,
|
| 1366 |
+
"loss": 0.7625,
|
| 1367 |
+
"step": 970
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 4.6818727490996395,
|
| 1371 |
+
"grad_norm": 0.98404860496521,
|
| 1372 |
+
"learning_rate": 2.7450428508239024e-05,
|
| 1373 |
+
"loss": 0.8123,
|
| 1374 |
+
"step": 975
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.705882352941177,
|
| 1378 |
+
"grad_norm": 1.1559010744094849,
|
| 1379 |
+
"learning_rate": 2.726247189574095e-05,
|
| 1380 |
+
"loss": 0.7068,
|
| 1381 |
+
"step": 980
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 4.729891956782713,
|
| 1385 |
+
"grad_norm": 1.0589702129364014,
|
| 1386 |
+
"learning_rate": 2.707438625219827e-05,
|
| 1387 |
+
"loss": 0.7431,
|
| 1388 |
+
"step": 985
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 4.75390156062425,
|
| 1392 |
+
"grad_norm": 1.207343339920044,
|
| 1393 |
+
"learning_rate": 2.6886182304324153e-05,
|
| 1394 |
+
"loss": 0.7161,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 4.777911164465786,
|
| 1399 |
+
"grad_norm": 1.023870825767517,
|
| 1400 |
+
"learning_rate": 2.669787078557876e-05,
|
| 1401 |
+
"loss": 0.7311,
|
| 1402 |
+
"step": 995
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 4.801920768307323,
|
| 1406 |
+
"grad_norm": 0.9353678226470947,
|
| 1407 |
+
"learning_rate": 2.6509462435557152e-05,
|
| 1408 |
+
"loss": 0.6689,
|
| 1409 |
+
"step": 1000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 4.82593037214886,
|
| 1413 |
+
"grad_norm": 0.8823081851005554,
|
| 1414 |
+
"learning_rate": 2.6320967999376767e-05,
|
| 1415 |
+
"loss": 0.6888,
|
| 1416 |
+
"step": 1005
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 4.849939975990396,
|
| 1420 |
+
"grad_norm": 1.1103065013885498,
|
| 1421 |
+
"learning_rate": 2.6132398227064615e-05,
|
| 1422 |
+
"loss": 0.7879,
|
| 1423 |
+
"step": 1010
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 4.873949579831933,
|
| 1427 |
+
"grad_norm": 1.061865210533142,
|
| 1428 |
+
"learning_rate": 2.5943763872944206e-05,
|
| 1429 |
+
"loss": 0.6958,
|
| 1430 |
+
"step": 1015
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 4.8979591836734695,
|
| 1434 |
+
"grad_norm": 1.1248444318771362,
|
| 1435 |
+
"learning_rate": 2.5755075695022224e-05,
|
| 1436 |
+
"loss": 0.6858,
|
| 1437 |
+
"step": 1020
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 4.921968787515006,
|
| 1441 |
+
"grad_norm": 1.1603715419769287,
|
| 1442 |
+
"learning_rate": 2.5566344454374968e-05,
|
| 1443 |
+
"loss": 0.6799,
|
| 1444 |
+
"step": 1025
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 4.945978391356543,
|
| 1448 |
+
"grad_norm": 1.1303590536117554,
|
| 1449 |
+
"learning_rate": 2.5377580914534647e-05,
|
| 1450 |
+
"loss": 0.767,
|
| 1451 |
+
"step": 1030
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 4.969987995198079,
|
| 1455 |
+
"grad_norm": 1.2461163997650146,
|
| 1456 |
+
"learning_rate": 2.5188795840875544e-05,
|
| 1457 |
+
"loss": 0.7453,
|
| 1458 |
+
"step": 1035
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 4.9939975990396155,
|
| 1462 |
+
"grad_norm": 1.0747658014297485,
|
| 1463 |
+
"learning_rate": 2.5e-05,
|
| 1464 |
+
"loss": 0.7559,
|
| 1465 |
+
"step": 1040
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 5.018007202881153,
|
| 1469 |
+
"grad_norm": 1.0154122114181519,
|
| 1470 |
+
"learning_rate": 2.481120415912446e-05,
|
| 1471 |
+
"loss": 0.7729,
|
| 1472 |
+
"step": 1045
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 5.042016806722689,
|
| 1476 |
+
"grad_norm": 1.195665717124939,
|
| 1477 |
+
"learning_rate": 2.4622419085465355e-05,
|
| 1478 |
+
"loss": 0.6956,
|
| 1479 |
+
"step": 1050
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 5.066026410564226,
|
| 1483 |
+
"grad_norm": 1.1738536357879639,
|
| 1484 |
+
"learning_rate": 2.4433655545625038e-05,
|
| 1485 |
+
"loss": 0.7124,
|
| 1486 |
+
"step": 1055
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 5.090036014405762,
|
| 1490 |
+
"grad_norm": 1.158319354057312,
|
| 1491 |
+
"learning_rate": 2.4244924304977785e-05,
|
| 1492 |
+
"loss": 0.7472,
|
| 1493 |
+
"step": 1060
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 5.114045618247299,
|
| 1497 |
+
"grad_norm": 1.1242644786834717,
|
| 1498 |
+
"learning_rate": 2.40562361270558e-05,
|
| 1499 |
+
"loss": 0.6805,
|
| 1500 |
+
"step": 1065
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 5.138055222088836,
|
| 1504 |
+
"grad_norm": 1.0289393663406372,
|
| 1505 |
+
"learning_rate": 2.3867601772935397e-05,
|
| 1506 |
+
"loss": 0.6898,
|
| 1507 |
+
"step": 1070
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 5.162064825930372,
|
| 1511 |
+
"grad_norm": 1.0357887744903564,
|
| 1512 |
+
"learning_rate": 2.367903200062324e-05,
|
| 1513 |
+
"loss": 0.6664,
|
| 1514 |
+
"step": 1075
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 5.186074429771908,
|
| 1518 |
+
"grad_norm": 1.1436580419540405,
|
| 1519 |
+
"learning_rate": 2.3490537564442847e-05,
|
| 1520 |
+
"loss": 0.7125,
|
| 1521 |
+
"step": 1080
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 5.2100840336134455,
|
| 1525 |
+
"grad_norm": 1.1259691715240479,
|
| 1526 |
+
"learning_rate": 2.3302129214421242e-05,
|
| 1527 |
+
"loss": 0.7797,
|
| 1528 |
+
"step": 1085
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 5.234093637454982,
|
| 1532 |
+
"grad_norm": 1.1516937017440796,
|
| 1533 |
+
"learning_rate": 2.3113817695675853e-05,
|
| 1534 |
+
"loss": 0.7587,
|
| 1535 |
+
"step": 1090
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 5.258103241296519,
|
| 1539 |
+
"grad_norm": 1.1358476877212524,
|
| 1540 |
+
"learning_rate": 2.292561374780173e-05,
|
| 1541 |
+
"loss": 0.7414,
|
| 1542 |
+
"step": 1095
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 5.282112845138055,
|
| 1546 |
+
"grad_norm": 1.2753323316574097,
|
| 1547 |
+
"learning_rate": 2.2737528104259056e-05,
|
| 1548 |
+
"loss": 0.6972,
|
| 1549 |
+
"step": 1100
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 5.3061224489795915,
|
| 1553 |
+
"grad_norm": 1.2500908374786377,
|
| 1554 |
+
"learning_rate": 2.2549571491760986e-05,
|
| 1555 |
+
"loss": 0.7168,
|
| 1556 |
+
"step": 1105
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 5.330132052821129,
|
| 1560 |
+
"grad_norm": 1.157196283340454,
|
| 1561 |
+
"learning_rate": 2.236175462966192e-05,
|
| 1562 |
+
"loss": 0.6441,
|
| 1563 |
+
"step": 1110
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 5.354141656662665,
|
| 1567 |
+
"grad_norm": 1.1226704120635986,
|
| 1568 |
+
"learning_rate": 2.217408822934613e-05,
|
| 1569 |
+
"loss": 0.7473,
|
| 1570 |
+
"step": 1115
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 5.378151260504202,
|
| 1574 |
+
"grad_norm": 1.0768887996673584,
|
| 1575 |
+
"learning_rate": 2.1986582993616926e-05,
|
| 1576 |
+
"loss": 0.6849,
|
| 1577 |
+
"step": 1120
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 5.402160864345738,
|
| 1581 |
+
"grad_norm": 1.2554682493209839,
|
| 1582 |
+
"learning_rate": 2.179924961608623e-05,
|
| 1583 |
+
"loss": 0.6715,
|
| 1584 |
+
"step": 1125
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 5.426170468187275,
|
| 1588 |
+
"grad_norm": 0.9506689310073853,
|
| 1589 |
+
"learning_rate": 2.1612098780564714e-05,
|
| 1590 |
+
"loss": 0.7139,
|
| 1591 |
+
"step": 1130
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 5.450180072028812,
|
| 1595 |
+
"grad_norm": 1.2209597826004028,
|
| 1596 |
+
"learning_rate": 2.1425141160452494e-05,
|
| 1597 |
+
"loss": 0.8102,
|
| 1598 |
+
"step": 1135
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 5.474189675870348,
|
| 1602 |
+
"grad_norm": 0.9822332262992859,
|
| 1603 |
+
"learning_rate": 2.1238387418130422e-05,
|
| 1604 |
+
"loss": 0.7772,
|
| 1605 |
+
"step": 1140
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 5.498199279711884,
|
| 1609 |
+
"grad_norm": 1.1269121170043945,
|
| 1610 |
+
"learning_rate": 2.1051848204352013e-05,
|
| 1611 |
+
"loss": 0.7506,
|
| 1612 |
+
"step": 1145
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 5.5222088835534215,
|
| 1616 |
+
"grad_norm": 1.1985368728637695,
|
| 1617 |
+
"learning_rate": 2.0865534157635967e-05,
|
| 1618 |
+
"loss": 0.7174,
|
| 1619 |
+
"step": 1150
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 5.546218487394958,
|
| 1623 |
+
"grad_norm": 1.1794227361679077,
|
| 1624 |
+
"learning_rate": 2.0679455903659513e-05,
|
| 1625 |
+
"loss": 0.7339,
|
| 1626 |
+
"step": 1155
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 5.570228091236495,
|
| 1630 |
+
"grad_norm": 1.1553770303726196,
|
| 1631 |
+
"learning_rate": 2.0493624054652357e-05,
|
| 1632 |
+
"loss": 0.7076,
|
| 1633 |
+
"step": 1160
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 5.594237695078031,
|
| 1637 |
+
"grad_norm": 1.0076508522033691,
|
| 1638 |
+
"learning_rate": 2.0308049208791507e-05,
|
| 1639 |
+
"loss": 0.7758,
|
| 1640 |
+
"step": 1165
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 5.6182472989195675,
|
| 1644 |
+
"grad_norm": 1.0329455137252808,
|
| 1645 |
+
"learning_rate": 2.0122741949596797e-05,
|
| 1646 |
+
"loss": 0.7103,
|
| 1647 |
+
"step": 1170
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 5.642256902761105,
|
| 1651 |
+
"grad_norm": 1.0466042757034302,
|
| 1652 |
+
"learning_rate": 1.9937712845327345e-05,
|
| 1653 |
+
"loss": 0.747,
|
| 1654 |
+
"step": 1175
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 5.666266506602641,
|
| 1658 |
+
"grad_norm": 1.1813960075378418,
|
| 1659 |
+
"learning_rate": 1.9752972448378814e-05,
|
| 1660 |
+
"loss": 0.7325,
|
| 1661 |
+
"step": 1180
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 5.690276110444177,
|
| 1665 |
+
"grad_norm": 1.0979856252670288,
|
| 1666 |
+
"learning_rate": 1.9568531294681586e-05,
|
| 1667 |
+
"loss": 0.7336,
|
| 1668 |
+
"step": 1185
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 5.714285714285714,
|
| 1672 |
+
"grad_norm": 1.1668668985366821,
|
| 1673 |
+
"learning_rate": 1.938439990309991e-05,
|
| 1674 |
+
"loss": 0.7238,
|
| 1675 |
+
"step": 1190
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 5.738295318127251,
|
| 1679 |
+
"grad_norm": 1.1428868770599365,
|
| 1680 |
+
"learning_rate": 1.9200588774831975e-05,
|
| 1681 |
+
"loss": 0.6934,
|
| 1682 |
+
"step": 1195
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 5.762304921968788,
|
| 1686 |
+
"grad_norm": 1.1208099126815796,
|
| 1687 |
+
"learning_rate": 1.9017108392811065e-05,
|
| 1688 |
+
"loss": 0.7573,
|
| 1689 |
+
"step": 1200
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 5.786314525810324,
|
| 1693 |
+
"grad_norm": 1.1175333261489868,
|
| 1694 |
+
"learning_rate": 1.8833969221107622e-05,
|
| 1695 |
+
"loss": 0.7232,
|
| 1696 |
+
"step": 1205
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 5.81032412965186,
|
| 1700 |
+
"grad_norm": 0.9412729740142822,
|
| 1701 |
+
"learning_rate": 1.8651181704332578e-05,
|
| 1702 |
+
"loss": 0.7221,
|
| 1703 |
+
"step": 1210
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 5.834333733493398,
|
| 1707 |
+
"grad_norm": 1.0848782062530518,
|
| 1708 |
+
"learning_rate": 1.8468756267041595e-05,
|
| 1709 |
+
"loss": 0.755,
|
| 1710 |
+
"step": 1215
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 5.858343337334934,
|
| 1714 |
+
"grad_norm": 1.2409135103225708,
|
| 1715 |
+
"learning_rate": 1.828670331314058e-05,
|
| 1716 |
+
"loss": 0.6962,
|
| 1717 |
+
"step": 1220
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 5.882352941176471,
|
| 1721 |
+
"grad_norm": 1.05846107006073,
|
| 1722 |
+
"learning_rate": 1.810503322529236e-05,
|
| 1723 |
+
"loss": 0.7443,
|
| 1724 |
+
"step": 1225
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 5.906362545018007,
|
| 1728 |
+
"grad_norm": 1.0066033601760864,
|
| 1729 |
+
"learning_rate": 1.7923756364324492e-05,
|
| 1730 |
+
"loss": 0.6654,
|
| 1731 |
+
"step": 1230
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 5.930372148859544,
|
| 1735 |
+
"grad_norm": 0.9819132685661316,
|
| 1736 |
+
"learning_rate": 1.7742883068638447e-05,
|
| 1737 |
+
"loss": 0.7271,
|
| 1738 |
+
"step": 1235
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 5.954381752701081,
|
| 1742 |
+
"grad_norm": 1.143143892288208,
|
| 1743 |
+
"learning_rate": 1.756242365361993e-05,
|
| 1744 |
+
"loss": 0.7538,
|
| 1745 |
+
"step": 1240
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 5.978391356542617,
|
| 1749 |
+
"grad_norm": 1.1252750158309937,
|
| 1750 |
+
"learning_rate": 1.7382388411050638e-05,
|
| 1751 |
+
"loss": 0.6795,
|
| 1752 |
+
"step": 1245
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 6.002400960384153,
|
| 1756 |
+
"grad_norm": 1.3320536613464355,
|
| 1757 |
+
"learning_rate": 1.7202787608521278e-05,
|
| 1758 |
+
"loss": 0.6446,
|
| 1759 |
+
"step": 1250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 6.02641056422569,
|
| 1763 |
+
"grad_norm": 1.1098029613494873,
|
| 1764 |
+
"learning_rate": 1.7023631488846006e-05,
|
| 1765 |
+
"loss": 0.6994,
|
| 1766 |
+
"step": 1255
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 6.050420168067227,
|
| 1770 |
+
"grad_norm": 1.1677411794662476,
|
| 1771 |
+
"learning_rate": 1.6844930269478274e-05,
|
| 1772 |
+
"loss": 0.6886,
|
| 1773 |
+
"step": 1260
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 6.074429771908764,
|
| 1777 |
+
"grad_norm": 1.1150180101394653,
|
| 1778 |
+
"learning_rate": 1.6666694141928096e-05,
|
| 1779 |
+
"loss": 0.7485,
|
| 1780 |
+
"step": 1265
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 6.0984393757503,
|
| 1784 |
+
"grad_norm": 1.2847915887832642,
|
| 1785 |
+
"learning_rate": 1.6488933271180845e-05,
|
| 1786 |
+
"loss": 0.6399,
|
| 1787 |
+
"step": 1270
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 6.122448979591836,
|
| 1791 |
+
"grad_norm": 1.1303415298461914,
|
| 1792 |
+
"learning_rate": 1.631165779511754e-05,
|
| 1793 |
+
"loss": 0.7799,
|
| 1794 |
+
"step": 1275
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 6.146458583433374,
|
| 1798 |
+
"grad_norm": 1.2571803331375122,
|
| 1799 |
+
"learning_rate": 1.613487782393661e-05,
|
| 1800 |
+
"loss": 0.7589,
|
| 1801 |
+
"step": 1280
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 6.17046818727491,
|
| 1805 |
+
"grad_norm": 1.0048649311065674,
|
| 1806 |
+
"learning_rate": 1.595860343957738e-05,
|
| 1807 |
+
"loss": 0.6969,
|
| 1808 |
+
"step": 1285
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 6.194477791116446,
|
| 1812 |
+
"grad_norm": 1.129724383354187,
|
| 1813 |
+
"learning_rate": 1.5782844695145033e-05,
|
| 1814 |
+
"loss": 0.7108,
|
| 1815 |
+
"step": 1290
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 6.218487394957983,
|
| 1819 |
+
"grad_norm": 1.0512356758117676,
|
| 1820 |
+
"learning_rate": 1.5607611614337292e-05,
|
| 1821 |
+
"loss": 0.7478,
|
| 1822 |
+
"step": 1295
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 6.24249699879952,
|
| 1826 |
+
"grad_norm": 1.0714658498764038,
|
| 1827 |
+
"learning_rate": 1.5432914190872757e-05,
|
| 1828 |
+
"loss": 0.7225,
|
| 1829 |
+
"step": 1300
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 6.266506602641057,
|
| 1833 |
+
"grad_norm": 1.2147399187088013,
|
| 1834 |
+
"learning_rate": 1.5258762387920956e-05,
|
| 1835 |
+
"loss": 0.6964,
|
| 1836 |
+
"step": 1305
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 6.290516206482593,
|
| 1840 |
+
"grad_norm": 1.1545813083648682,
|
| 1841 |
+
"learning_rate": 1.5085166137534123e-05,
|
| 1842 |
+
"loss": 0.7673,
|
| 1843 |
+
"step": 1310
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 6.314525810324129,
|
| 1847 |
+
"grad_norm": 1.092599630355835,
|
| 1848 |
+
"learning_rate": 1.4912135340080774e-05,
|
| 1849 |
+
"loss": 0.7194,
|
| 1850 |
+
"step": 1315
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 6.3385354141656665,
|
| 1854 |
+
"grad_norm": 1.2281053066253662,
|
| 1855 |
+
"learning_rate": 1.4739679863681086e-05,
|
| 1856 |
+
"loss": 0.6869,
|
| 1857 |
+
"step": 1320
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 6.362545018007203,
|
| 1861 |
+
"grad_norm": 1.1293562650680542,
|
| 1862 |
+
"learning_rate": 1.4567809543644076e-05,
|
| 1863 |
+
"loss": 0.6851,
|
| 1864 |
+
"step": 1325
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 6.38655462184874,
|
| 1868 |
+
"grad_norm": 1.459465742111206,
|
| 1869 |
+
"learning_rate": 1.4396534181906725e-05,
|
| 1870 |
+
"loss": 0.7242,
|
| 1871 |
+
"step": 1330
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 6.410564225690276,
|
| 1875 |
+
"grad_norm": 1.203008770942688,
|
| 1876 |
+
"learning_rate": 1.4225863546474943e-05,
|
| 1877 |
+
"loss": 0.7155,
|
| 1878 |
+
"step": 1335
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 6.4345738295318124,
|
| 1882 |
+
"grad_norm": 1.0592601299285889,
|
| 1883 |
+
"learning_rate": 1.4055807370866485e-05,
|
| 1884 |
+
"loss": 0.6706,
|
| 1885 |
+
"step": 1340
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 6.45858343337335,
|
| 1889 |
+
"grad_norm": 1.1361570358276367,
|
| 1890 |
+
"learning_rate": 1.388637535355585e-05,
|
| 1891 |
+
"loss": 0.6937,
|
| 1892 |
+
"step": 1345
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 6.482593037214886,
|
| 1896 |
+
"grad_norm": 1.135237455368042,
|
| 1897 |
+
"learning_rate": 1.3717577157421169e-05,
|
| 1898 |
+
"loss": 0.8316,
|
| 1899 |
+
"step": 1350
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 6.506602641056423,
|
| 1903 |
+
"grad_norm": 1.0417910814285278,
|
| 1904 |
+
"learning_rate": 1.3549422409193083e-05,
|
| 1905 |
+
"loss": 0.7229,
|
| 1906 |
+
"step": 1355
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 6.530612244897959,
|
| 1910 |
+
"grad_norm": 1.1558960676193237,
|
| 1911 |
+
"learning_rate": 1.3381920698905787e-05,
|
| 1912 |
+
"loss": 0.7025,
|
| 1913 |
+
"step": 1360
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 6.554621848739496,
|
| 1917 |
+
"grad_norm": 1.0858848094940186,
|
| 1918 |
+
"learning_rate": 1.3215081579350058e-05,
|
| 1919 |
+
"loss": 0.742,
|
| 1920 |
+
"step": 1365
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 6.578631452581033,
|
| 1924 |
+
"grad_norm": 1.2004518508911133,
|
| 1925 |
+
"learning_rate": 1.3048914565528454e-05,
|
| 1926 |
+
"loss": 0.6737,
|
| 1927 |
+
"step": 1370
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 6.602641056422569,
|
| 1931 |
+
"grad_norm": 1.1666450500488281,
|
| 1932 |
+
"learning_rate": 1.2883429134112673e-05,
|
| 1933 |
+
"loss": 0.7577,
|
| 1934 |
+
"step": 1375
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 6.626650660264105,
|
| 1938 |
+
"grad_norm": 1.1294101476669312,
|
| 1939 |
+
"learning_rate": 1.2718634722903073e-05,
|
| 1940 |
+
"loss": 0.6495,
|
| 1941 |
+
"step": 1380
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 6.6506602641056425,
|
| 1945 |
+
"grad_norm": 1.2848787307739258,
|
| 1946 |
+
"learning_rate": 1.2554540730290437e-05,
|
| 1947 |
+
"loss": 0.7069,
|
| 1948 |
+
"step": 1385
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 6.674669867947179,
|
| 1952 |
+
"grad_norm": 1.2171602249145508,
|
| 1953 |
+
"learning_rate": 1.2391156514719984e-05,
|
| 1954 |
+
"loss": 0.705,
|
| 1955 |
+
"step": 1390
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 6.698679471788715,
|
| 1959 |
+
"grad_norm": 1.0168397426605225,
|
| 1960 |
+
"learning_rate": 1.222849139415764e-05,
|
| 1961 |
+
"loss": 0.671,
|
| 1962 |
+
"step": 1395
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 6.722689075630252,
|
| 1966 |
+
"grad_norm": 1.2341060638427734,
|
| 1967 |
+
"learning_rate": 1.2066554645558578e-05,
|
| 1968 |
+
"loss": 0.7456,
|
| 1969 |
+
"step": 1400
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 6.7466986794717885,
|
| 1973 |
+
"grad_norm": 1.174575686454773,
|
| 1974 |
+
"learning_rate": 1.1905355504338248e-05,
|
| 1975 |
+
"loss": 0.6899,
|
| 1976 |
+
"step": 1405
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 6.770708283313326,
|
| 1980 |
+
"grad_norm": 1.125368595123291,
|
| 1981 |
+
"learning_rate": 1.1744903163845577e-05,
|
| 1982 |
+
"loss": 0.7024,
|
| 1983 |
+
"step": 1410
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 6.794717887154862,
|
| 1987 |
+
"grad_norm": 1.157349705696106,
|
| 1988 |
+
"learning_rate": 1.1585206774838683e-05,
|
| 1989 |
+
"loss": 0.6571,
|
| 1990 |
+
"step": 1415
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 6.818727490996398,
|
| 1994 |
+
"grad_norm": 1.1240679025650024,
|
| 1995 |
+
"learning_rate": 1.1426275444963034e-05,
|
| 1996 |
+
"loss": 0.729,
|
| 1997 |
+
"step": 1420
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 6.842737094837935,
|
| 2001 |
+
"grad_norm": 1.2598992586135864,
|
| 2002 |
+
"learning_rate": 1.1268118238232003e-05,
|
| 2003 |
+
"loss": 0.7971,
|
| 2004 |
+
"step": 1425
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 6.866746698679472,
|
| 2008 |
+
"grad_norm": 1.2101902961730957,
|
| 2009 |
+
"learning_rate": 1.1110744174509952e-05,
|
| 2010 |
+
"loss": 0.6376,
|
| 2011 |
+
"step": 1430
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 6.890756302521009,
|
| 2015 |
+
"grad_norm": 1.2665272951126099,
|
| 2016 |
+
"learning_rate": 1.0954162228997777e-05,
|
| 2017 |
+
"loss": 0.6663,
|
| 2018 |
+
"step": 1435
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 6.914765906362545,
|
| 2022 |
+
"grad_norm": 1.0040076971054077,
|
| 2023 |
+
"learning_rate": 1.0798381331721109e-05,
|
| 2024 |
+
"loss": 0.6898,
|
| 2025 |
+
"step": 1440
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 6.938775510204081,
|
| 2029 |
+
"grad_norm": 1.180012583732605,
|
| 2030 |
+
"learning_rate": 1.0643410367020983e-05,
|
| 2031 |
+
"loss": 0.686,
|
| 2032 |
+
"step": 1445
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 6.9627851140456185,
|
| 2036 |
+
"grad_norm": 1.1320979595184326,
|
| 2037 |
+
"learning_rate": 1.048925817304717e-05,
|
| 2038 |
+
"loss": 0.7803,
|
| 2039 |
+
"step": 1450
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 6.986794717887155,
|
| 2043 |
+
"grad_norm": 1.141840934753418,
|
| 2044 |
+
"learning_rate": 1.0335933541254129e-05,
|
| 2045 |
+
"loss": 0.6809,
|
| 2046 |
+
"step": 1455
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 7.010804321728691,
|
| 2050 |
+
"grad_norm": 1.0778816938400269,
|
| 2051 |
+
"learning_rate": 1.0183445215899584e-05,
|
| 2052 |
+
"loss": 0.6936,
|
| 2053 |
+
"step": 1460
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 7.034813925570228,
|
| 2057 |
+
"grad_norm": 0.9368105530738831,
|
| 2058 |
+
"learning_rate": 1.0031801893545895e-05,
|
| 2059 |
+
"loss": 0.7005,
|
| 2060 |
+
"step": 1465
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 7.0588235294117645,
|
| 2064 |
+
"grad_norm": 1.0788689851760864,
|
| 2065 |
+
"learning_rate": 9.881012222564065e-06,
|
| 2066 |
+
"loss": 0.8484,
|
| 2067 |
+
"step": 1470
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 7.082833133253302,
|
| 2071 |
+
"grad_norm": 1.1011931896209717,
|
| 2072 |
+
"learning_rate": 9.731084802640459e-06,
|
| 2073 |
+
"loss": 0.7897,
|
| 2074 |
+
"step": 1475
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 7.106842737094838,
|
| 2078 |
+
"grad_norm": 1.22800612449646,
|
| 2079 |
+
"learning_rate": 9.582028184286423e-06,
|
| 2080 |
+
"loss": 0.6696,
|
| 2081 |
+
"step": 1480
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 7.130852340936374,
|
| 2085 |
+
"grad_norm": 1.224184274673462,
|
| 2086 |
+
"learning_rate": 9.43385086835062e-06,
|
| 2087 |
+
"loss": 0.6867,
|
| 2088 |
+
"step": 1485
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 7.154861944777911,
|
| 2092 |
+
"grad_norm": 1.2134716510772705,
|
| 2093 |
+
"learning_rate": 9.286561305534203e-06,
|
| 2094 |
+
"loss": 0.7372,
|
| 2095 |
+
"step": 1490
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 7.178871548619448,
|
| 2099 |
+
"grad_norm": 1.01565682888031,
|
| 2100 |
+
"learning_rate": 9.140167895908867e-06,
|
| 2101 |
+
"loss": 0.6718,
|
| 2102 |
+
"step": 1495
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 7.202881152460985,
|
| 2106 |
+
"grad_norm": 1.176138162612915,
|
| 2107 |
+
"learning_rate": 8.994678988437802e-06,
|
| 2108 |
+
"loss": 0.6819,
|
| 2109 |
+
"step": 1500
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 7.226890756302521,
|
| 2113 |
+
"grad_norm": 1.1396265029907227,
|
| 2114 |
+
"learning_rate": 8.850102880499531e-06,
|
| 2115 |
+
"loss": 0.7094,
|
| 2116 |
+
"step": 1505
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 7.250900360144057,
|
| 2120 |
+
"grad_norm": 1.1229872703552246,
|
| 2121 |
+
"learning_rate": 8.706447817414696e-06,
|
| 2122 |
+
"loss": 0.7423,
|
| 2123 |
+
"step": 1510
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 7.2749099639855945,
|
| 2127 |
+
"grad_norm": 1.0950995683670044,
|
| 2128 |
+
"learning_rate": 8.563721991975843e-06,
|
| 2129 |
+
"loss": 0.6957,
|
| 2130 |
+
"step": 1515
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 7.298919567827131,
|
| 2134 |
+
"grad_norm": 1.322180986404419,
|
| 2135 |
+
"learning_rate": 8.421933543980126e-06,
|
| 2136 |
+
"loss": 0.6382,
|
| 2137 |
+
"step": 1520
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 7.322929171668667,
|
| 2141 |
+
"grad_norm": 1.1946529150009155,
|
| 2142 |
+
"learning_rate": 8.281090559765156e-06,
|
| 2143 |
+
"loss": 0.6939,
|
| 2144 |
+
"step": 1525
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 7.346938775510204,
|
| 2148 |
+
"grad_norm": 1.3446452617645264,
|
| 2149 |
+
"learning_rate": 8.141201071747784e-06,
|
| 2150 |
+
"loss": 0.7682,
|
| 2151 |
+
"step": 1530
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 7.3709483793517405,
|
| 2155 |
+
"grad_norm": 1.063050627708435,
|
| 2156 |
+
"learning_rate": 8.002273057966011e-06,
|
| 2157 |
+
"loss": 0.6319,
|
| 2158 |
+
"step": 1535
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 7.394957983193278,
|
| 2162 |
+
"grad_norm": 1.0960049629211426,
|
| 2163 |
+
"learning_rate": 7.864314441624004e-06,
|
| 2164 |
+
"loss": 0.7331,
|
| 2165 |
+
"step": 1540
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 7.418967587034814,
|
| 2169 |
+
"grad_norm": 1.153906226158142,
|
| 2170 |
+
"learning_rate": 7.727333090640218e-06,
|
| 2171 |
+
"loss": 0.7249,
|
| 2172 |
+
"step": 1545
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 7.44297719087635,
|
| 2176 |
+
"grad_norm": 1.1610156297683716,
|
| 2177 |
+
"learning_rate": 7.591336817198682e-06,
|
| 2178 |
+
"loss": 0.6484,
|
| 2179 |
+
"step": 1550
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 7.466986794717887,
|
| 2183 |
+
"grad_norm": 1.1550188064575195,
|
| 2184 |
+
"learning_rate": 7.456333377303457e-06,
|
| 2185 |
+
"loss": 0.7723,
|
| 2186 |
+
"step": 1555
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 7.490996398559424,
|
| 2190 |
+
"grad_norm": 1.2671056985855103,
|
| 2191 |
+
"learning_rate": 7.3223304703363135e-06,
|
| 2192 |
+
"loss": 0.7266,
|
| 2193 |
+
"step": 1560
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 7.515006002400961,
|
| 2197 |
+
"grad_norm": 1.234147548675537,
|
| 2198 |
+
"learning_rate": 7.189335738617633e-06,
|
| 2199 |
+
"loss": 0.6927,
|
| 2200 |
+
"step": 1565
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 7.539015606242497,
|
| 2204 |
+
"grad_norm": 1.1650274991989136,
|
| 2205 |
+
"learning_rate": 7.057356766970541e-06,
|
| 2206 |
+
"loss": 0.7219,
|
| 2207 |
+
"step": 1570
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 7.563025210084033,
|
| 2211 |
+
"grad_norm": 1.2067919969558716,
|
| 2212 |
+
"learning_rate": 6.926401082288359e-06,
|
| 2213 |
+
"loss": 0.6933,
|
| 2214 |
+
"step": 1575
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 7.5870348139255706,
|
| 2218 |
+
"grad_norm": 1.1489832401275635,
|
| 2219 |
+
"learning_rate": 6.796476153105294e-06,
|
| 2220 |
+
"loss": 0.7651,
|
| 2221 |
+
"step": 1580
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 7.611044417767107,
|
| 2225 |
+
"grad_norm": 1.24705970287323,
|
| 2226 |
+
"learning_rate": 6.667589389170562e-06,
|
| 2227 |
+
"loss": 0.6558,
|
| 2228 |
+
"step": 1585
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 7.635054021608643,
|
| 2232 |
+
"grad_norm": 1.0954616069793701,
|
| 2233 |
+
"learning_rate": 6.5397481410257645e-06,
|
| 2234 |
+
"loss": 0.6601,
|
| 2235 |
+
"step": 1590
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 7.65906362545018,
|
| 2239 |
+
"grad_norm": 1.272865653038025,
|
| 2240 |
+
"learning_rate": 6.41295969958568e-06,
|
| 2241 |
+
"loss": 0.6938,
|
| 2242 |
+
"step": 1595
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 7.6830732292917165,
|
| 2246 |
+
"grad_norm": 1.2320659160614014,
|
| 2247 |
+
"learning_rate": 6.28723129572247e-06,
|
| 2248 |
+
"loss": 0.7301,
|
| 2249 |
+
"step": 1600
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 7.707082833133253,
|
| 2253 |
+
"grad_norm": 1.2697712182998657,
|
| 2254 |
+
"learning_rate": 6.16257009985329e-06,
|
| 2255 |
+
"loss": 0.6848,
|
| 2256 |
+
"step": 1605
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 7.73109243697479,
|
| 2260 |
+
"grad_norm": 1.1409835815429688,
|
| 2261 |
+
"learning_rate": 6.038983221531352e-06,
|
| 2262 |
+
"loss": 0.6372,
|
| 2263 |
+
"step": 1610
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 7.755102040816326,
|
| 2267 |
+
"grad_norm": 1.1304911375045776,
|
| 2268 |
+
"learning_rate": 5.916477709040444e-06,
|
| 2269 |
+
"loss": 0.6736,
|
| 2270 |
+
"step": 1615
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 7.779111644657863,
|
| 2274 |
+
"grad_norm": 1.1968624591827393,
|
| 2275 |
+
"learning_rate": 5.79506054899299e-06,
|
| 2276 |
+
"loss": 0.6915,
|
| 2277 |
+
"step": 1620
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 7.8031212484994,
|
| 2281 |
+
"grad_norm": 1.0843942165374756,
|
| 2282 |
+
"learning_rate": 5.674738665931575e-06,
|
| 2283 |
+
"loss": 0.696,
|
| 2284 |
+
"step": 1625
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 7.827130852340936,
|
| 2288 |
+
"grad_norm": 1.0682406425476074,
|
| 2289 |
+
"learning_rate": 5.555518921934047e-06,
|
| 2290 |
+
"loss": 0.7064,
|
| 2291 |
+
"step": 1630
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 7.851140456182473,
|
| 2295 |
+
"grad_norm": 1.13326096534729,
|
| 2296 |
+
"learning_rate": 5.437408116222148e-06,
|
| 2297 |
+
"loss": 0.7497,
|
| 2298 |
+
"step": 1635
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 7.875150060024009,
|
| 2302 |
+
"grad_norm": 1.1618019342422485,
|
| 2303 |
+
"learning_rate": 5.320412984773748e-06,
|
| 2304 |
+
"loss": 0.7025,
|
| 2305 |
+
"step": 1640
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 7.899159663865547,
|
| 2309 |
+
"grad_norm": 1.2662303447723389,
|
| 2310 |
+
"learning_rate": 5.204540199938707e-06,
|
| 2311 |
+
"loss": 0.6823,
|
| 2312 |
+
"step": 1645
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 7.923169267707083,
|
| 2316 |
+
"grad_norm": 1.1508044004440308,
|
| 2317 |
+
"learning_rate": 5.089796370058325e-06,
|
| 2318 |
+
"loss": 0.8013,
|
| 2319 |
+
"step": 1650
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 7.947178871548619,
|
| 2323 |
+
"grad_norm": 1.1236162185668945,
|
| 2324 |
+
"learning_rate": 4.9761880390884694e-06,
|
| 2325 |
+
"loss": 0.7497,
|
| 2326 |
+
"step": 1655
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 7.971188475390156,
|
| 2330 |
+
"grad_norm": 1.239221453666687,
|
| 2331 |
+
"learning_rate": 4.86372168622635e-06,
|
| 2332 |
+
"loss": 0.7817,
|
| 2333 |
+
"step": 1660
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 7.995198079231693,
|
| 2337 |
+
"grad_norm": 1.1400153636932373,
|
| 2338 |
+
"learning_rate": 4.7524037255410434e-06,
|
| 2339 |
+
"loss": 0.615,
|
| 2340 |
+
"step": 1665
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 8.01920768307323,
|
| 2344 |
+
"grad_norm": 1.1075925827026367,
|
| 2345 |
+
"learning_rate": 4.642240505607659e-06,
|
| 2346 |
+
"loss": 0.7037,
|
| 2347 |
+
"step": 1670
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 8.043217286914766,
|
| 2351 |
+
"grad_norm": 1.244471788406372,
|
| 2352 |
+
"learning_rate": 4.533238309145258e-06,
|
| 2353 |
+
"loss": 0.6747,
|
| 2354 |
+
"step": 1675
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 8.067226890756302,
|
| 2358 |
+
"grad_norm": 1.114261269569397,
|
| 2359 |
+
"learning_rate": 4.425403352658591e-06,
|
| 2360 |
+
"loss": 0.7154,
|
| 2361 |
+
"step": 1680
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 8.091236494597839,
|
| 2365 |
+
"grad_norm": 1.2810643911361694,
|
| 2366 |
+
"learning_rate": 4.318741786083538e-06,
|
| 2367 |
+
"loss": 0.7838,
|
| 2368 |
+
"step": 1685
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 8.115246098439377,
|
| 2372 |
+
"grad_norm": 1.1281261444091797,
|
| 2373 |
+
"learning_rate": 4.213259692436367e-06,
|
| 2374 |
+
"loss": 0.7525,
|
| 2375 |
+
"step": 1690
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 8.139255702280913,
|
| 2379 |
+
"grad_norm": 1.111745834350586,
|
| 2380 |
+
"learning_rate": 4.1089630874668325e-06,
|
| 2381 |
+
"loss": 0.6624,
|
| 2382 |
+
"step": 1695
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 8.16326530612245,
|
| 2386 |
+
"grad_norm": 0.9732471108436584,
|
| 2387 |
+
"learning_rate": 4.0058579193150535e-06,
|
| 2388 |
+
"loss": 0.6821,
|
| 2389 |
+
"step": 1700
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 8.187274909963985,
|
| 2393 |
+
"grad_norm": 1.1068557500839233,
|
| 2394 |
+
"learning_rate": 3.903950068172338e-06,
|
| 2395 |
+
"loss": 0.6932,
|
| 2396 |
+
"step": 1705
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 8.211284513805522,
|
| 2400 |
+
"grad_norm": 1.1466325521469116,
|
| 2401 |
+
"learning_rate": 3.8032453459457884e-06,
|
| 2402 |
+
"loss": 0.7308,
|
| 2403 |
+
"step": 1710
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 8.235294117647058,
|
| 2407 |
+
"grad_norm": 1.076535940170288,
|
| 2408 |
+
"learning_rate": 3.7037494959268644e-06,
|
| 2409 |
+
"loss": 0.7136,
|
| 2410 |
+
"step": 1715
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 8.259303721488596,
|
| 2414 |
+
"grad_norm": 1.234830617904663,
|
| 2415 |
+
"learning_rate": 3.605468192463815e-06,
|
| 2416 |
+
"loss": 0.6595,
|
| 2417 |
+
"step": 1720
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 8.283313325330132,
|
| 2421 |
+
"grad_norm": 1.2779568433761597,
|
| 2422 |
+
"learning_rate": 3.5084070406380897e-06,
|
| 2423 |
+
"loss": 0.7671,
|
| 2424 |
+
"step": 1725
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 8.307322929171669,
|
| 2428 |
+
"grad_norm": 1.0826342105865479,
|
| 2429 |
+
"learning_rate": 3.4125715759446785e-06,
|
| 2430 |
+
"loss": 0.6561,
|
| 2431 |
+
"step": 1730
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 8.331332533013205,
|
| 2435 |
+
"grad_norm": 1.292898416519165,
|
| 2436 |
+
"learning_rate": 3.317967263976374e-06,
|
| 2437 |
+
"loss": 0.6876,
|
| 2438 |
+
"step": 1735
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 8.355342136854741,
|
| 2442 |
+
"grad_norm": 1.2453337907791138,
|
| 2443 |
+
"learning_rate": 3.2245995001121106e-06,
|
| 2444 |
+
"loss": 0.6819,
|
| 2445 |
+
"step": 1740
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 8.37935174069628,
|
| 2449 |
+
"grad_norm": 1.109753131866455,
|
| 2450 |
+
"learning_rate": 3.1324736092092412e-06,
|
| 2451 |
+
"loss": 0.7044,
|
| 2452 |
+
"step": 1745
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 8.403361344537815,
|
| 2456 |
+
"grad_norm": 1.1907482147216797,
|
| 2457 |
+
"learning_rate": 3.0415948452998557e-06,
|
| 2458 |
+
"loss": 0.6317,
|
| 2459 |
+
"step": 1750
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 8.427370948379352,
|
| 2463 |
+
"grad_norm": 1.036994218826294,
|
| 2464 |
+
"learning_rate": 2.9519683912911266e-06,
|
| 2465 |
+
"loss": 0.6521,
|
| 2466 |
+
"step": 1755
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 8.451380552220888,
|
| 2470 |
+
"grad_norm": 1.1481200456619263,
|
| 2471 |
+
"learning_rate": 2.8635993586697553e-06,
|
| 2472 |
+
"loss": 0.7572,
|
| 2473 |
+
"step": 1760
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 8.475390156062424,
|
| 2477 |
+
"grad_norm": 1.2365052700042725,
|
| 2478 |
+
"learning_rate": 2.776492787210425e-06,
|
| 2479 |
+
"loss": 0.7184,
|
| 2480 |
+
"step": 1765
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 8.499399759903962,
|
| 2484 |
+
"grad_norm": 1.1394840478897095,
|
| 2485 |
+
"learning_rate": 2.690653644688393e-06,
|
| 2486 |
+
"loss": 0.6881,
|
| 2487 |
+
"step": 1770
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 8.523409363745499,
|
| 2491 |
+
"grad_norm": 1.2600808143615723,
|
| 2492 |
+
"learning_rate": 2.6060868265961822e-06,
|
| 2493 |
+
"loss": 0.6575,
|
| 2494 |
+
"step": 1775
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 8.547418967587035,
|
| 2498 |
+
"grad_norm": 1.09065842628479,
|
| 2499 |
+
"learning_rate": 2.5227971558643537e-06,
|
| 2500 |
+
"loss": 0.7457,
|
| 2501 |
+
"step": 1780
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 8.571428571428571,
|
| 2505 |
+
"grad_norm": 1.245969533920288,
|
| 2506 |
+
"learning_rate": 2.4407893825864892e-06,
|
| 2507 |
+
"loss": 0.7127,
|
| 2508 |
+
"step": 1785
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 8.595438175270107,
|
| 2512 |
+
"grad_norm": 1.3175572156906128,
|
| 2513 |
+
"learning_rate": 2.360068183748268e-06,
|
| 2514 |
+
"loss": 0.7442,
|
| 2515 |
+
"step": 1790
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 8.619447779111646,
|
| 2519 |
+
"grad_norm": 1.220615267753601,
|
| 2520 |
+
"learning_rate": 2.2806381629607327e-06,
|
| 2521 |
+
"loss": 0.6743,
|
| 2522 |
+
"step": 1795
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 8.643457382953182,
|
| 2526 |
+
"grad_norm": 1.1195836067199707,
|
| 2527 |
+
"learning_rate": 2.2025038501977486e-06,
|
| 2528 |
+
"loss": 0.7338,
|
| 2529 |
+
"step": 1800
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 8.667466986794718,
|
| 2533 |
+
"grad_norm": 1.075049638748169,
|
| 2534 |
+
"learning_rate": 2.125669701537647e-06,
|
| 2535 |
+
"loss": 0.7514,
|
| 2536 |
+
"step": 1805
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 8.691476590636254,
|
| 2540 |
+
"grad_norm": 1.1793599128723145,
|
| 2541 |
+
"learning_rate": 2.0501400989091036e-06,
|
| 2542 |
+
"loss": 0.7774,
|
| 2543 |
+
"step": 1810
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 8.71548619447779,
|
| 2547 |
+
"grad_norm": 1.165880560874939,
|
| 2548 |
+
"learning_rate": 1.97591934984121e-06,
|
| 2549 |
+
"loss": 0.6895,
|
| 2550 |
+
"step": 1815
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 8.739495798319329,
|
| 2554 |
+
"grad_norm": 1.101431131362915,
|
| 2555 |
+
"learning_rate": 1.9030116872178316e-06,
|
| 2556 |
+
"loss": 0.7218,
|
| 2557 |
+
"step": 1820
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 8.763505402160865,
|
| 2561 |
+
"grad_norm": 1.2261079549789429,
|
| 2562 |
+
"learning_rate": 1.8314212690361987e-06,
|
| 2563 |
+
"loss": 0.7553,
|
| 2564 |
+
"step": 1825
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 8.787515006002401,
|
| 2568 |
+
"grad_norm": 1.1773276329040527,
|
| 2569 |
+
"learning_rate": 1.7611521781697644e-06,
|
| 2570 |
+
"loss": 0.6779,
|
| 2571 |
+
"step": 1830
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 8.811524609843937,
|
| 2575 |
+
"grad_norm": 1.2577153444290161,
|
| 2576 |
+
"learning_rate": 1.6922084221353607e-06,
|
| 2577 |
+
"loss": 0.6946,
|
| 2578 |
+
"step": 1835
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 8.835534213685474,
|
| 2582 |
+
"grad_norm": 1.1246775388717651,
|
| 2583 |
+
"learning_rate": 1.624593932864632e-06,
|
| 2584 |
+
"loss": 0.7149,
|
| 2585 |
+
"step": 1840
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 8.85954381752701,
|
| 2589 |
+
"grad_norm": 1.1089775562286377,
|
| 2590 |
+
"learning_rate": 1.5583125664798165e-06,
|
| 2591 |
+
"loss": 0.6681,
|
| 2592 |
+
"step": 1845
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 8.883553421368548,
|
| 2596 |
+
"grad_norm": 1.138650894165039,
|
| 2597 |
+
"learning_rate": 1.4933681030738138e-06,
|
| 2598 |
+
"loss": 0.6519,
|
| 2599 |
+
"step": 1850
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 8.907563025210084,
|
| 2603 |
+
"grad_norm": 1.1409391164779663,
|
| 2604 |
+
"learning_rate": 1.429764246494597e-06,
|
| 2605 |
+
"loss": 0.6957,
|
| 2606 |
+
"step": 1855
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 8.93157262905162,
|
| 2610 |
+
"grad_norm": 1.2397470474243164,
|
| 2611 |
+
"learning_rate": 1.3675046241339918e-06,
|
| 2612 |
+
"loss": 0.6942,
|
| 2613 |
+
"step": 1860
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 8.955582232893157,
|
| 2617 |
+
"grad_norm": 1.310257077217102,
|
| 2618 |
+
"learning_rate": 1.306592786720795e-06,
|
| 2619 |
+
"loss": 0.6578,
|
| 2620 |
+
"step": 1865
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 8.979591836734693,
|
| 2624 |
+
"grad_norm": 1.057267189025879,
|
| 2625 |
+
"learning_rate": 1.2470322081182761e-06,
|
| 2626 |
+
"loss": 0.6994,
|
| 2627 |
+
"step": 1870
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 9.003601440576231,
|
| 2631 |
+
"grad_norm": 1.2477996349334717,
|
| 2632 |
+
"learning_rate": 1.1888262851260462e-06,
|
| 2633 |
+
"loss": 0.643,
|
| 2634 |
+
"step": 1875
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 9.027611044417768,
|
| 2638 |
+
"grad_norm": 1.2775191068649292,
|
| 2639 |
+
"learning_rate": 1.1319783372863602e-06,
|
| 2640 |
+
"loss": 0.6307,
|
| 2641 |
+
"step": 1880
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 9.051620648259304,
|
| 2645 |
+
"grad_norm": 1.1136633157730103,
|
| 2646 |
+
"learning_rate": 1.0764916066947794e-06,
|
| 2647 |
+
"loss": 0.7088,
|
| 2648 |
+
"step": 1885
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 9.07563025210084,
|
| 2652 |
+
"grad_norm": 1.2463817596435547,
|
| 2653 |
+
"learning_rate": 1.0223692578152782e-06,
|
| 2654 |
+
"loss": 0.6603,
|
| 2655 |
+
"step": 1890
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 9.099639855942376,
|
| 2659 |
+
"grad_norm": 1.140369176864624,
|
| 2660 |
+
"learning_rate": 9.696143772997768e-07,
|
| 2661 |
+
"loss": 0.8255,
|
| 2662 |
+
"step": 1895
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 9.123649459783914,
|
| 2666 |
+
"grad_norm": 1.0478204488754272,
|
| 2667 |
+
"learning_rate": 9.182299738120931e-07,
|
| 2668 |
+
"loss": 0.6834,
|
| 2669 |
+
"step": 1900
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 9.14765906362545,
|
| 2673 |
+
"grad_norm": 1.243027925491333,
|
| 2674 |
+
"learning_rate": 8.682189778563693e-07,
|
| 2675 |
+
"loss": 0.6365,
|
| 2676 |
+
"step": 1905
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 9.171668667466987,
|
| 2680 |
+
"grad_norm": 1.1335963010787964,
|
| 2681 |
+
"learning_rate": 8.195842416099359e-07,
|
| 2682 |
+
"loss": 0.7317,
|
| 2683 |
+
"step": 1910
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 9.195678271308523,
|
| 2687 |
+
"grad_norm": 1.2012873888015747,
|
| 2688 |
+
"learning_rate": 7.723285387606471e-07,
|
| 2689 |
+
"loss": 0.741,
|
| 2690 |
+
"step": 1915
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 9.21968787515006,
|
| 2694 |
+
"grad_norm": 1.098880648612976,
|
| 2695 |
+
"learning_rate": 7.264545643486997e-07,
|
| 2696 |
+
"loss": 0.6881,
|
| 2697 |
+
"step": 1920
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 9.243697478991596,
|
| 2701 |
+
"grad_norm": 1.138432502746582,
|
| 2702 |
+
"learning_rate": 6.819649346129304e-07,
|
| 2703 |
+
"loss": 0.735,
|
| 2704 |
+
"step": 1925
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 9.267707082833134,
|
| 2708 |
+
"grad_norm": 1.163900375366211,
|
| 2709 |
+
"learning_rate": 6.3886218684161e-07,
|
| 2710 |
+
"loss": 0.7227,
|
| 2711 |
+
"step": 1930
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 9.29171668667467,
|
| 2715 |
+
"grad_norm": 1.163901448249817,
|
| 2716 |
+
"learning_rate": 5.971487792277297e-07,
|
| 2717 |
+
"loss": 0.681,
|
| 2718 |
+
"step": 1935
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 9.315726290516206,
|
| 2722 |
+
"grad_norm": 1.3683992624282837,
|
| 2723 |
+
"learning_rate": 5.568270907288287e-07,
|
| 2724 |
+
"loss": 0.7081,
|
| 2725 |
+
"step": 1940
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 9.339735894357743,
|
| 2729 |
+
"grad_norm": 1.2360917329788208,
|
| 2730 |
+
"learning_rate": 5.178994209312948e-07,
|
| 2731 |
+
"loss": 0.7064,
|
| 2732 |
+
"step": 1945
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 9.363745498199279,
|
| 2736 |
+
"grad_norm": 1.0632774829864502,
|
| 2737 |
+
"learning_rate": 4.803679899192392e-07,
|
| 2738 |
+
"loss": 0.6829,
|
| 2739 |
+
"step": 1950
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 9.387755102040817,
|
| 2743 |
+
"grad_norm": 1.200908899307251,
|
| 2744 |
+
"learning_rate": 4.4423493814786667e-07,
|
| 2745 |
+
"loss": 0.6814,
|
| 2746 |
+
"step": 1955
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 9.411764705882353,
|
| 2750 |
+
"grad_norm": 1.2517386674880981,
|
| 2751 |
+
"learning_rate": 4.095023263214121e-07,
|
| 2752 |
+
"loss": 0.769,
|
| 2753 |
+
"step": 1960
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 9.43577430972389,
|
| 2757 |
+
"grad_norm": 1.0798803567886353,
|
| 2758 |
+
"learning_rate": 3.761721352756098e-07,
|
| 2759 |
+
"loss": 0.7539,
|
| 2760 |
+
"step": 1965
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 9.459783913565426,
|
| 2764 |
+
"grad_norm": 0.9635175466537476,
|
| 2765 |
+
"learning_rate": 3.4424626586473385e-07,
|
| 2766 |
+
"loss": 0.6506,
|
| 2767 |
+
"step": 1970
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 9.483793517406962,
|
| 2771 |
+
"grad_norm": 1.1478654146194458,
|
| 2772 |
+
"learning_rate": 3.1372653885318736e-07,
|
| 2773 |
+
"loss": 0.6763,
|
| 2774 |
+
"step": 1975
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 9.5078031212485,
|
| 2778 |
+
"grad_norm": 1.2677192687988281,
|
| 2779 |
+
"learning_rate": 2.846146948116468e-07,
|
| 2780 |
+
"loss": 0.6776,
|
| 2781 |
+
"step": 1980
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 9.531812725090036,
|
| 2785 |
+
"grad_norm": 1.1099594831466675,
|
| 2786 |
+
"learning_rate": 2.569123940178192e-07,
|
| 2787 |
+
"loss": 0.7292,
|
| 2788 |
+
"step": 1985
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 9.555822328931573,
|
| 2792 |
+
"grad_norm": 1.1103848218917847,
|
| 2793 |
+
"learning_rate": 2.3062121636174826e-07,
|
| 2794 |
+
"loss": 0.8111,
|
| 2795 |
+
"step": 1990
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 9.579831932773109,
|
| 2799 |
+
"grad_norm": 1.1750984191894531,
|
| 2800 |
+
"learning_rate": 2.0574266125569509e-07,
|
| 2801 |
+
"loss": 0.6473,
|
| 2802 |
+
"step": 1995
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 9.603841536614645,
|
| 2806 |
+
"grad_norm": 1.0524730682373047,
|
| 2807 |
+
"learning_rate": 1.8227814754865068e-07,
|
| 2808 |
+
"loss": 0.6774,
|
| 2809 |
+
"step": 2000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 9.627851140456183,
|
| 2813 |
+
"grad_norm": 1.1044491529464722,
|
| 2814 |
+
"learning_rate": 1.6022901344539543e-07,
|
| 2815 |
+
"loss": 0.6782,
|
| 2816 |
+
"step": 2005
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 9.65186074429772,
|
| 2820 |
+
"grad_norm": 1.2015644311904907,
|
| 2821 |
+
"learning_rate": 1.39596516430196e-07,
|
| 2822 |
+
"loss": 0.6965,
|
| 2823 |
+
"step": 2010
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 9.675870348139256,
|
| 2827 |
+
"grad_norm": 1.066968560218811,
|
| 2828 |
+
"learning_rate": 1.2038183319507955e-07,
|
| 2829 |
+
"loss": 0.6496,
|
| 2830 |
+
"step": 2015
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 9.699879951980792,
|
| 2834 |
+
"grad_norm": 1.1246190071105957,
|
| 2835 |
+
"learning_rate": 1.0258605957272627e-07,
|
| 2836 |
+
"loss": 0.6511,
|
| 2837 |
+
"step": 2020
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 9.723889555822328,
|
| 2841 |
+
"grad_norm": 1.017182469367981,
|
| 2842 |
+
"learning_rate": 8.621021047398314e-08,
|
| 2843 |
+
"loss": 0.7524,
|
| 2844 |
+
"step": 2025
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 9.747899159663866,
|
| 2848 |
+
"grad_norm": 1.2211177349090576,
|
| 2849 |
+
"learning_rate": 7.125521982997152e-08,
|
| 2850 |
+
"loss": 0.6653,
|
| 2851 |
+
"step": 2030
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 9.771908763505403,
|
| 2855 |
+
"grad_norm": 1.2134476900100708,
|
| 2856 |
+
"learning_rate": 5.772194053882962e-08,
|
| 2857 |
+
"loss": 0.6718,
|
| 2858 |
+
"step": 2035
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 9.795918367346939,
|
| 2862 |
+
"grad_norm": 1.3641300201416016,
|
| 2863 |
+
"learning_rate": 4.56111444170626e-08,
|
| 2864 |
+
"loss": 0.7114,
|
| 2865 |
+
"step": 2040
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 9.819927971188475,
|
| 2869 |
+
"grad_norm": 1.1759401559829712,
|
| 2870 |
+
"learning_rate": 3.4923522155544394e-08,
|
| 2871 |
+
"loss": 0.7125,
|
| 2872 |
+
"step": 2045
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 9.843937575030012,
|
| 2876 |
+
"grad_norm": 1.0511598587036133,
|
| 2877 |
+
"learning_rate": 2.5659683280102044e-08,
|
| 2878 |
+
"loss": 0.6236,
|
| 2879 |
+
"step": 2050
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 9.867947178871548,
|
| 2883 |
+
"grad_norm": 1.1891964673995972,
|
| 2884 |
+
"learning_rate": 1.782015611677401e-08,
|
| 2885 |
+
"loss": 0.7353,
|
| 2886 |
+
"step": 2055
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 9.891956782713086,
|
| 2890 |
+
"grad_norm": 1.116445541381836,
|
| 2891 |
+
"learning_rate": 1.1405387761664887e-08,
|
| 2892 |
+
"loss": 0.7489,
|
| 2893 |
+
"step": 2060
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 9.915966386554622,
|
| 2897 |
+
"grad_norm": 1.1506844758987427,
|
| 2898 |
+
"learning_rate": 6.415744055460193e-09,
|
| 2899 |
+
"loss": 0.7743,
|
| 2900 |
+
"step": 2065
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 9.939975990396158,
|
| 2904 |
+
"grad_norm": 1.2120825052261353,
|
| 2905 |
+
"learning_rate": 2.8515095625514244e-09,
|
| 2906 |
+
"loss": 0.6435,
|
| 2907 |
+
"step": 2070
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 9.963985594237695,
|
| 2911 |
+
"grad_norm": 1.1971231698989868,
|
| 2912 |
+
"learning_rate": 7.128875548101377e-10,
|
| 2913 |
+
"loss": 0.7375,
|
| 2914 |
+
"step": 2075
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 9.987995198079231,
|
| 2918 |
+
"grad_norm": 1.2055232524871826,
|
| 2919 |
+
"learning_rate": 0.0,
|
| 2920 |
+
"loss": 0.7238,
|
| 2921 |
+
"step": 2080
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 9.987995198079231,
|
| 2925 |
+
"step": 2080,
|
| 2926 |
+
"total_flos": 8.185270082173747e+17,
|
| 2927 |
+
"train_loss": 0.7521515275423344,
|
| 2928 |
+
"train_runtime": 19400.1091,
|
| 2929 |
+
"train_samples_per_second": 1.717,
|
| 2930 |
+
"train_steps_per_second": 0.107
|
| 2931 |
+
}
|
| 2932 |
+
],
|
| 2933 |
+
"logging_steps": 5,
|
| 2934 |
+
"max_steps": 2080,
|
| 2935 |
+
"num_input_tokens_seen": 0,
|
| 2936 |
+
"num_train_epochs": 10,
|
| 2937 |
+
"save_steps": 100,
|
| 2938 |
+
"total_flos": 8.185270082173747e+17,
|
| 2939 |
+
"train_batch_size": 2,
|
| 2940 |
+
"trial_name": null,
|
| 2941 |
+
"trial_params": null
|
| 2942 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5638080a8b2dd706aa1fc0355868c9e379a83c43a8f4bf35167d99e019217066
|
| 3 |
+
size 5176
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|