End of training
Browse files- README.md +54 -0
- adapter_config.json +28 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- args.txt +14 -0
- train_results.json +7 -0
- trainer_state.json +988 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
base_model: lmsys/vicuna-7b-v1.5
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: cs_cot_32
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# cs_cot_32
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) on an unknown dataset.
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 0.0001
|
| 36 |
+
- train_batch_size: 4
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_steps: 5
|
| 42 |
+
- num_epochs: 20
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
### Framework versions
|
| 50 |
+
|
| 51 |
+
- Transformers 4.36.0.dev0
|
| 52 |
+
- Pytorch 2.1.0+cu121
|
| 53 |
+
- Datasets 2.13.1
|
| 54 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 64,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 16,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"gate_proj",
|
| 21 |
+
"up_proj",
|
| 22 |
+
"down_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"o_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM"
|
| 28 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17af2117ec8742464ad725e49fa3ceeb13886b570b4592d6979b299bc9e55305
|
| 3 |
+
size 160069834
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0899289ca8b47dfa6a853be5d9934f1ed627571acb1a1be08c3fc12a5459394
|
| 3 |
+
size 159967880
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.4629385274136439,
|
| 4 |
+
"train_runtime": 260.0227,
|
| 5 |
+
"train_samples_per_second": 2.461,
|
| 6 |
+
"train_steps_per_second": 0.615
|
| 7 |
+
}
|
args.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
base_model_name: lmsys/vicuna-7b-v1.5
|
| 2 |
+
batch_size: 4
|
| 3 |
+
cot: true
|
| 4 |
+
dataset_name: BENBENBENb/CommonsenseQA1000COT
|
| 5 |
+
epochs: 20
|
| 6 |
+
eval_strategy: epoch
|
| 7 |
+
evaluation: false
|
| 8 |
+
learning_rate: 0.0001
|
| 9 |
+
logging_steps: 1
|
| 10 |
+
output_dir: brettbbb/cs_cot_32
|
| 11 |
+
seed: 42
|
| 12 |
+
skip_example: true
|
| 13 |
+
train_size: 32
|
| 14 |
+
warmup_steps: 5
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.4629385274136439,
|
| 4 |
+
"train_runtime": 260.0227,
|
| 5 |
+
"train_samples_per_second": 2.461,
|
| 6 |
+
"train_steps_per_second": 0.615
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,988 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 2.6536,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.25,
|
| 19 |
+
"learning_rate": 4e-05,
|
| 20 |
+
"loss": 3.3995,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.38,
|
| 25 |
+
"learning_rate": 6e-05,
|
| 26 |
+
"loss": 4.281,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.5,
|
| 31 |
+
"learning_rate": 8e-05,
|
| 32 |
+
"loss": 2.4605,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.62,
|
| 37 |
+
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 2.538,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.75,
|
| 43 |
+
"learning_rate": 9.935483870967742e-05,
|
| 44 |
+
"loss": 2.629,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.88,
|
| 49 |
+
"learning_rate": 9.870967741935484e-05,
|
| 50 |
+
"loss": 2.1875,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"learning_rate": 9.806451612903226e-05,
|
| 56 |
+
"loss": 1.9768,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.12,
|
| 61 |
+
"learning_rate": 9.741935483870968e-05,
|
| 62 |
+
"loss": 2.0199,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.25,
|
| 67 |
+
"learning_rate": 9.677419354838711e-05,
|
| 68 |
+
"loss": 2.0266,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.38,
|
| 73 |
+
"learning_rate": 9.612903225806452e-05,
|
| 74 |
+
"loss": 1.7383,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.5,
|
| 79 |
+
"learning_rate": 9.548387096774195e-05,
|
| 80 |
+
"loss": 1.7494,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.62,
|
| 85 |
+
"learning_rate": 9.483870967741936e-05,
|
| 86 |
+
"loss": 1.8509,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.75,
|
| 91 |
+
"learning_rate": 9.419354838709677e-05,
|
| 92 |
+
"loss": 1.8364,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.88,
|
| 97 |
+
"learning_rate": 9.35483870967742e-05,
|
| 98 |
+
"loss": 1.6808,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.0,
|
| 103 |
+
"learning_rate": 9.290322580645162e-05,
|
| 104 |
+
"loss": 1.5642,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.12,
|
| 109 |
+
"learning_rate": 9.225806451612904e-05,
|
| 110 |
+
"loss": 1.6336,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.25,
|
| 115 |
+
"learning_rate": 9.161290322580646e-05,
|
| 116 |
+
"loss": 1.6452,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.38,
|
| 121 |
+
"learning_rate": 9.096774193548387e-05,
|
| 122 |
+
"loss": 1.1714,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.5,
|
| 127 |
+
"learning_rate": 9.096774193548387e-05,
|
| 128 |
+
"loss": 1.9018,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.62,
|
| 133 |
+
"learning_rate": 9.032258064516129e-05,
|
| 134 |
+
"loss": 1.6711,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.75,
|
| 139 |
+
"learning_rate": 8.967741935483871e-05,
|
| 140 |
+
"loss": 1.1646,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.88,
|
| 145 |
+
"learning_rate": 8.903225806451614e-05,
|
| 146 |
+
"loss": 1.0608,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 3.0,
|
| 151 |
+
"learning_rate": 8.838709677419355e-05,
|
| 152 |
+
"loss": 1.2916,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 3.12,
|
| 157 |
+
"learning_rate": 8.774193548387098e-05,
|
| 158 |
+
"loss": 0.9801,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.25,
|
| 163 |
+
"learning_rate": 8.709677419354839e-05,
|
| 164 |
+
"loss": 1.0964,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.38,
|
| 169 |
+
"learning_rate": 8.645161290322581e-05,
|
| 170 |
+
"loss": 1.1112,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.5,
|
| 175 |
+
"learning_rate": 8.580645161290323e-05,
|
| 176 |
+
"loss": 1.2538,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.62,
|
| 181 |
+
"learning_rate": 8.516129032258064e-05,
|
| 182 |
+
"loss": 1.0811,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.75,
|
| 187 |
+
"learning_rate": 8.451612903225808e-05,
|
| 188 |
+
"loss": 0.9926,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.88,
|
| 193 |
+
"learning_rate": 8.387096774193549e-05,
|
| 194 |
+
"loss": 1.3067,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.0,
|
| 199 |
+
"learning_rate": 8.32258064516129e-05,
|
| 200 |
+
"loss": 0.9473,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.12,
|
| 205 |
+
"learning_rate": 8.258064516129033e-05,
|
| 206 |
+
"loss": 0.8545,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.25,
|
| 211 |
+
"learning_rate": 8.193548387096774e-05,
|
| 212 |
+
"loss": 0.704,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.38,
|
| 217 |
+
"learning_rate": 8.129032258064517e-05,
|
| 218 |
+
"loss": 0.8111,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.5,
|
| 223 |
+
"learning_rate": 8.064516129032258e-05,
|
| 224 |
+
"loss": 0.9651,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.62,
|
| 229 |
+
"learning_rate": 8e-05,
|
| 230 |
+
"loss": 0.6063,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.75,
|
| 235 |
+
"learning_rate": 7.935483870967743e-05,
|
| 236 |
+
"loss": 0.5452,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.88,
|
| 241 |
+
"learning_rate": 7.870967741935484e-05,
|
| 242 |
+
"loss": 0.8213,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 5.0,
|
| 247 |
+
"learning_rate": 7.806451612903226e-05,
|
| 248 |
+
"loss": 0.7832,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.12,
|
| 253 |
+
"learning_rate": 7.741935483870968e-05,
|
| 254 |
+
"loss": 0.3778,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 5.25,
|
| 259 |
+
"learning_rate": 7.67741935483871e-05,
|
| 260 |
+
"loss": 0.3637,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.38,
|
| 265 |
+
"learning_rate": 7.612903225806451e-05,
|
| 266 |
+
"loss": 0.6275,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 5.5,
|
| 271 |
+
"learning_rate": 7.548387096774195e-05,
|
| 272 |
+
"loss": 0.6516,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.62,
|
| 277 |
+
"learning_rate": 7.483870967741936e-05,
|
| 278 |
+
"loss": 0.3812,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 5.75,
|
| 283 |
+
"learning_rate": 7.419354838709677e-05,
|
| 284 |
+
"loss": 0.3557,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.88,
|
| 289 |
+
"learning_rate": 7.35483870967742e-05,
|
| 290 |
+
"loss": 0.2963,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.0,
|
| 295 |
+
"learning_rate": 7.290322580645161e-05,
|
| 296 |
+
"loss": 0.2674,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 6.12,
|
| 301 |
+
"learning_rate": 7.225806451612904e-05,
|
| 302 |
+
"loss": 0.1111,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.25,
|
| 307 |
+
"learning_rate": 7.161290322580646e-05,
|
| 308 |
+
"loss": 0.1296,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.38,
|
| 313 |
+
"learning_rate": 7.096774193548388e-05,
|
| 314 |
+
"loss": 0.1281,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.5,
|
| 319 |
+
"learning_rate": 7.03225806451613e-05,
|
| 320 |
+
"loss": 0.238,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.62,
|
| 325 |
+
"learning_rate": 6.967741935483871e-05,
|
| 326 |
+
"loss": 0.1803,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.75,
|
| 331 |
+
"learning_rate": 6.903225806451613e-05,
|
| 332 |
+
"loss": 0.1911,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.88,
|
| 337 |
+
"learning_rate": 6.838709677419355e-05,
|
| 338 |
+
"loss": 0.2073,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.0,
|
| 343 |
+
"learning_rate": 6.774193548387096e-05,
|
| 344 |
+
"loss": 0.2415,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.12,
|
| 349 |
+
"learning_rate": 6.709677419354839e-05,
|
| 350 |
+
"loss": 0.1104,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 7.25,
|
| 355 |
+
"learning_rate": 6.645161290322582e-05,
|
| 356 |
+
"loss": 0.1154,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 7.38,
|
| 361 |
+
"learning_rate": 6.580645161290323e-05,
|
| 362 |
+
"loss": 0.0931,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 7.5,
|
| 367 |
+
"learning_rate": 6.516129032258065e-05,
|
| 368 |
+
"loss": 0.0671,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 7.62,
|
| 373 |
+
"learning_rate": 6.451612903225807e-05,
|
| 374 |
+
"loss": 0.1003,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 7.75,
|
| 379 |
+
"learning_rate": 6.387096774193548e-05,
|
| 380 |
+
"loss": 0.1646,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 7.88,
|
| 385 |
+
"learning_rate": 6.32258064516129e-05,
|
| 386 |
+
"loss": 0.1203,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.0,
|
| 391 |
+
"learning_rate": 6.258064516129033e-05,
|
| 392 |
+
"loss": 0.1888,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.12,
|
| 397 |
+
"learning_rate": 6.193548387096774e-05,
|
| 398 |
+
"loss": 0.0798,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 8.25,
|
| 403 |
+
"learning_rate": 6.129032258064517e-05,
|
| 404 |
+
"loss": 0.0921,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 8.38,
|
| 409 |
+
"learning_rate": 6.064516129032258e-05,
|
| 410 |
+
"loss": 0.1284,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 8.5,
|
| 415 |
+
"learning_rate": 6e-05,
|
| 416 |
+
"loss": 0.1008,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.62,
|
| 421 |
+
"learning_rate": 5.935483870967742e-05,
|
| 422 |
+
"loss": 0.0732,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 8.75,
|
| 427 |
+
"learning_rate": 5.870967741935483e-05,
|
| 428 |
+
"loss": 0.0628,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 8.88,
|
| 433 |
+
"learning_rate": 5.8064516129032266e-05,
|
| 434 |
+
"loss": 0.0694,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 9.0,
|
| 439 |
+
"learning_rate": 5.7419354838709685e-05,
|
| 440 |
+
"loss": 0.0856,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 9.12,
|
| 445 |
+
"learning_rate": 5.67741935483871e-05,
|
| 446 |
+
"loss": 0.0698,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 9.25,
|
| 451 |
+
"learning_rate": 5.612903225806452e-05,
|
| 452 |
+
"loss": 0.0619,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 9.38,
|
| 457 |
+
"learning_rate": 5.5483870967741936e-05,
|
| 458 |
+
"loss": 0.1077,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.5,
|
| 463 |
+
"learning_rate": 5.4838709677419355e-05,
|
| 464 |
+
"loss": 0.0524,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 9.62,
|
| 469 |
+
"learning_rate": 5.419354838709678e-05,
|
| 470 |
+
"loss": 0.0747,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 9.75,
|
| 475 |
+
"learning_rate": 5.35483870967742e-05,
|
| 476 |
+
"loss": 0.0805,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 9.88,
|
| 481 |
+
"learning_rate": 5.290322580645162e-05,
|
| 482 |
+
"loss": 0.0665,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 10.0,
|
| 487 |
+
"learning_rate": 5.225806451612903e-05,
|
| 488 |
+
"loss": 0.0688,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 10.12,
|
| 493 |
+
"learning_rate": 5.161290322580645e-05,
|
| 494 |
+
"loss": 0.0421,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 10.25,
|
| 499 |
+
"learning_rate": 5.096774193548387e-05,
|
| 500 |
+
"loss": 0.0548,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 10.38,
|
| 505 |
+
"learning_rate": 5.032258064516129e-05,
|
| 506 |
+
"loss": 0.0552,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 10.5,
|
| 511 |
+
"learning_rate": 4.967741935483871e-05,
|
| 512 |
+
"loss": 0.0777,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 10.62,
|
| 517 |
+
"learning_rate": 4.903225806451613e-05,
|
| 518 |
+
"loss": 0.0574,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 10.75,
|
| 523 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 524 |
+
"loss": 0.1117,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 10.88,
|
| 529 |
+
"learning_rate": 4.774193548387097e-05,
|
| 530 |
+
"loss": 0.0512,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 11.0,
|
| 535 |
+
"learning_rate": 4.7096774193548385e-05,
|
| 536 |
+
"loss": 0.07,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 11.12,
|
| 541 |
+
"learning_rate": 4.645161290322581e-05,
|
| 542 |
+
"loss": 0.0381,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 11.25,
|
| 547 |
+
"learning_rate": 4.580645161290323e-05,
|
| 548 |
+
"loss": 0.0589,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 11.38,
|
| 553 |
+
"learning_rate": 4.516129032258064e-05,
|
| 554 |
+
"loss": 0.0407,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 11.5,
|
| 559 |
+
"learning_rate": 4.451612903225807e-05,
|
| 560 |
+
"loss": 0.0484,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 11.62,
|
| 565 |
+
"learning_rate": 4.387096774193549e-05,
|
| 566 |
+
"loss": 0.0487,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 11.75,
|
| 571 |
+
"learning_rate": 4.322580645161291e-05,
|
| 572 |
+
"loss": 0.0616,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 11.88,
|
| 577 |
+
"learning_rate": 4.258064516129032e-05,
|
| 578 |
+
"loss": 0.0739,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 12.0,
|
| 583 |
+
"learning_rate": 4.1935483870967746e-05,
|
| 584 |
+
"loss": 0.0951,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 12.12,
|
| 589 |
+
"learning_rate": 4.1290322580645165e-05,
|
| 590 |
+
"loss": 0.0978,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 12.25,
|
| 595 |
+
"learning_rate": 4.0645161290322584e-05,
|
| 596 |
+
"loss": 0.0436,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 12.38,
|
| 601 |
+
"learning_rate": 4e-05,
|
| 602 |
+
"loss": 0.0393,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 12.5,
|
| 607 |
+
"learning_rate": 3.935483870967742e-05,
|
| 608 |
+
"loss": 0.0601,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 12.62,
|
| 613 |
+
"learning_rate": 3.870967741935484e-05,
|
| 614 |
+
"loss": 0.0518,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 12.75,
|
| 619 |
+
"learning_rate": 3.8064516129032254e-05,
|
| 620 |
+
"loss": 0.0464,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.88,
|
| 625 |
+
"learning_rate": 3.741935483870968e-05,
|
| 626 |
+
"loss": 0.0483,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 13.0,
|
| 631 |
+
"learning_rate": 3.67741935483871e-05,
|
| 632 |
+
"loss": 0.0659,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 13.12,
|
| 637 |
+
"learning_rate": 3.612903225806452e-05,
|
| 638 |
+
"loss": 0.033,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 13.25,
|
| 643 |
+
"learning_rate": 3.548387096774194e-05,
|
| 644 |
+
"loss": 0.0395,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 13.38,
|
| 649 |
+
"learning_rate": 3.483870967741936e-05,
|
| 650 |
+
"loss": 0.0711,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 13.5,
|
| 655 |
+
"learning_rate": 3.4193548387096776e-05,
|
| 656 |
+
"loss": 0.051,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 13.62,
|
| 661 |
+
"learning_rate": 3.3548387096774195e-05,
|
| 662 |
+
"loss": 0.0633,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 13.75,
|
| 667 |
+
"learning_rate": 3.2903225806451614e-05,
|
| 668 |
+
"loss": 0.0406,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 13.88,
|
| 673 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 674 |
+
"loss": 0.0562,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 14.0,
|
| 679 |
+
"learning_rate": 3.161290322580645e-05,
|
| 680 |
+
"loss": 0.0406,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 14.12,
|
| 685 |
+
"learning_rate": 3.096774193548387e-05,
|
| 686 |
+
"loss": 0.0346,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 14.25,
|
| 691 |
+
"learning_rate": 3.032258064516129e-05,
|
| 692 |
+
"loss": 0.0555,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 14.38,
|
| 697 |
+
"learning_rate": 2.967741935483871e-05,
|
| 698 |
+
"loss": 0.0435,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 14.5,
|
| 703 |
+
"learning_rate": 2.9032258064516133e-05,
|
| 704 |
+
"loss": 0.0486,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 14.62,
|
| 709 |
+
"learning_rate": 2.838709677419355e-05,
|
| 710 |
+
"loss": 0.0334,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 14.75,
|
| 715 |
+
"learning_rate": 2.7741935483870968e-05,
|
| 716 |
+
"loss": 0.0571,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 14.88,
|
| 721 |
+
"learning_rate": 2.709677419354839e-05,
|
| 722 |
+
"loss": 0.0437,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 15.0,
|
| 727 |
+
"learning_rate": 2.645161290322581e-05,
|
| 728 |
+
"loss": 0.0578,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 15.12,
|
| 733 |
+
"learning_rate": 2.5806451612903226e-05,
|
| 734 |
+
"loss": 0.0373,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 15.25,
|
| 739 |
+
"learning_rate": 2.5161290322580645e-05,
|
| 740 |
+
"loss": 0.0642,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 15.38,
|
| 745 |
+
"learning_rate": 2.4516129032258064e-05,
|
| 746 |
+
"loss": 0.0428,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 15.5,
|
| 751 |
+
"learning_rate": 2.3870967741935486e-05,
|
| 752 |
+
"loss": 0.0523,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 15.62,
|
| 757 |
+
"learning_rate": 2.3225806451612906e-05,
|
| 758 |
+
"loss": 0.0311,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 15.75,
|
| 763 |
+
"learning_rate": 2.258064516129032e-05,
|
| 764 |
+
"loss": 0.038,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 15.88,
|
| 769 |
+
"learning_rate": 2.1935483870967744e-05,
|
| 770 |
+
"loss": 0.0385,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 16.0,
|
| 775 |
+
"learning_rate": 2.129032258064516e-05,
|
| 776 |
+
"loss": 0.0699,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 16.12,
|
| 781 |
+
"learning_rate": 2.0645161290322582e-05,
|
| 782 |
+
"loss": 0.061,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 16.25,
|
| 787 |
+
"learning_rate": 2e-05,
|
| 788 |
+
"loss": 0.0431,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 16.38,
|
| 793 |
+
"learning_rate": 1.935483870967742e-05,
|
| 794 |
+
"loss": 0.0665,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 16.5,
|
| 799 |
+
"learning_rate": 1.870967741935484e-05,
|
| 800 |
+
"loss": 0.032,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 16.62,
|
| 805 |
+
"learning_rate": 1.806451612903226e-05,
|
| 806 |
+
"loss": 0.045,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 16.75,
|
| 811 |
+
"learning_rate": 1.741935483870968e-05,
|
| 812 |
+
"loss": 0.0533,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 16.88,
|
| 817 |
+
"learning_rate": 1.6774193548387098e-05,
|
| 818 |
+
"loss": 0.0393,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 17.0,
|
| 823 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 824 |
+
"loss": 0.0462,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 17.12,
|
| 829 |
+
"learning_rate": 1.5483870967741936e-05,
|
| 830 |
+
"loss": 0.042,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 17.25,
|
| 835 |
+
"learning_rate": 1.4838709677419355e-05,
|
| 836 |
+
"loss": 0.0694,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 17.38,
|
| 841 |
+
"learning_rate": 1.4193548387096774e-05,
|
| 842 |
+
"loss": 0.0253,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 17.5,
|
| 847 |
+
"learning_rate": 1.3548387096774195e-05,
|
| 848 |
+
"loss": 0.0367,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 17.62,
|
| 853 |
+
"learning_rate": 1.2903225806451613e-05,
|
| 854 |
+
"loss": 0.0391,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 17.75,
|
| 859 |
+
"learning_rate": 1.2258064516129032e-05,
|
| 860 |
+
"loss": 0.0508,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 17.88,
|
| 865 |
+
"learning_rate": 1.1612903225806453e-05,
|
| 866 |
+
"loss": 0.0516,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 18.0,
|
| 871 |
+
"learning_rate": 1.0967741935483872e-05,
|
| 872 |
+
"loss": 0.0562,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 18.12,
|
| 877 |
+
"learning_rate": 1.0322580645161291e-05,
|
| 878 |
+
"loss": 0.0404,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 18.25,
|
| 883 |
+
"learning_rate": 9.67741935483871e-06,
|
| 884 |
+
"loss": 0.0427,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 18.38,
|
| 889 |
+
"learning_rate": 9.03225806451613e-06,
|
| 890 |
+
"loss": 0.0318,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 18.5,
|
| 895 |
+
"learning_rate": 8.387096774193549e-06,
|
| 896 |
+
"loss": 0.052,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 18.62,
|
| 901 |
+
"learning_rate": 7.741935483870968e-06,
|
| 902 |
+
"loss": 0.0278,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 18.75,
|
| 907 |
+
"learning_rate": 7.096774193548387e-06,
|
| 908 |
+
"loss": 0.095,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 18.88,
|
| 913 |
+
"learning_rate": 6.451612903225806e-06,
|
| 914 |
+
"loss": 0.0408,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 19.0,
|
| 919 |
+
"learning_rate": 5.806451612903226e-06,
|
| 920 |
+
"loss": 0.0509,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 19.12,
|
| 925 |
+
"learning_rate": 5.161290322580646e-06,
|
| 926 |
+
"loss": 0.0297,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 19.25,
|
| 931 |
+
"learning_rate": 4.516129032258065e-06,
|
| 932 |
+
"loss": 0.0493,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 19.38,
|
| 937 |
+
"learning_rate": 3.870967741935484e-06,
|
| 938 |
+
"loss": 0.1001,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 19.5,
|
| 943 |
+
"learning_rate": 3.225806451612903e-06,
|
| 944 |
+
"loss": 0.0401,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 19.62,
|
| 949 |
+
"learning_rate": 2.580645161290323e-06,
|
| 950 |
+
"loss": 0.0434,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 19.75,
|
| 955 |
+
"learning_rate": 1.935483870967742e-06,
|
| 956 |
+
"loss": 0.0363,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 19.88,
|
| 961 |
+
"learning_rate": 1.2903225806451614e-06,
|
| 962 |
+
"loss": 0.0432,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 20.0,
|
| 967 |
+
"learning_rate": 6.451612903225807e-07,
|
| 968 |
+
"loss": 0.0328,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 20.0,
|
| 973 |
+
"step": 160,
|
| 974 |
+
"total_flos": 7453507615457280.0,
|
| 975 |
+
"train_loss": 0.4629385274136439,
|
| 976 |
+
"train_runtime": 260.0227,
|
| 977 |
+
"train_samples_per_second": 2.461,
|
| 978 |
+
"train_steps_per_second": 0.615
|
| 979 |
+
}
|
| 980 |
+
],
|
| 981 |
+
"logging_steps": 1,
|
| 982 |
+
"max_steps": 160,
|
| 983 |
+
"num_train_epochs": 20,
|
| 984 |
+
"save_steps": 500,
|
| 985 |
+
"total_flos": 7453507615457280.0,
|
| 986 |
+
"trial_name": null,
|
| 987 |
+
"trial_params": null
|
| 988 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0289c8be0a154caa6331c59ea2fa13fa4f0a694d07634ccc5808360a502d707
|
| 3 |
+
size 4600
|