Commit
•
f16d96e
1
Parent(s):
f523ece
End of training
Browse files- README.md +97 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- all_results.json +12 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +937 -0
- train_results.json +12 -0
- trainer_state.json +2400 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google-t5/t5-base
|
| 3 |
+
datasets:
|
| 4 |
+
- Andyrasika/TweetSumm-tuned
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
metrics:
|
| 8 |
+
- rouge
|
| 9 |
+
- f1
|
| 10 |
+
- precision
|
| 11 |
+
- recall
|
| 12 |
+
tags:
|
| 13 |
+
- generated_from_trainer
|
| 14 |
+
model-index:
|
| 15 |
+
- name: t5-base-qlora-finetune-tweetsumm-1724817707
|
| 16 |
+
results:
|
| 17 |
+
- task:
|
| 18 |
+
type: summarization
|
| 19 |
+
name: Summarization
|
| 20 |
+
dataset:
|
| 21 |
+
name: Andyrasika/TweetSumm-tuned
|
| 22 |
+
type: Andyrasika/TweetSumm-tuned
|
| 23 |
+
metrics:
|
| 24 |
+
- type: rouge
|
| 25 |
+
value: 0.4708
|
| 26 |
+
name: Rouge1
|
| 27 |
+
- type: f1
|
| 28 |
+
value: 0.8942
|
| 29 |
+
name: F1
|
| 30 |
+
- type: precision
|
| 31 |
+
value: 0.8941
|
| 32 |
+
name: Precision
|
| 33 |
+
- type: recall
|
| 34 |
+
value: 0.8945
|
| 35 |
+
name: Recall
|
| 36 |
+
---
|
| 37 |
+
|
| 38 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 39 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 40 |
+
|
| 41 |
+
# t5-base-qlora-finetune-tweetsumm-1724817707
|
| 42 |
+
|
| 43 |
+
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on the Andyrasika/TweetSumm-tuned dataset.
|
| 44 |
+
It achieves the following results on the evaluation set:
|
| 45 |
+
- Loss: 1.7934
|
| 46 |
+
- Rouge1: 0.4708
|
| 47 |
+
- Rouge2: 0.2246
|
| 48 |
+
- Rougel: 0.3984
|
| 49 |
+
- Rougelsum: 0.4357
|
| 50 |
+
- Gen Len: 49.4091
|
| 51 |
+
- F1: 0.8942
|
| 52 |
+
- Precision: 0.8941
|
| 53 |
+
- Recall: 0.8945
|
| 54 |
+
|
| 55 |
+
## Model description
|
| 56 |
+
|
| 57 |
+
More information needed
|
| 58 |
+
|
| 59 |
+
## Intended uses & limitations
|
| 60 |
+
|
| 61 |
+
More information needed
|
| 62 |
+
|
| 63 |
+
## Training and evaluation data
|
| 64 |
+
|
| 65 |
+
More information needed
|
| 66 |
+
|
| 67 |
+
## Training procedure
|
| 68 |
+
|
| 69 |
+
### Training hyperparameters
|
| 70 |
+
|
| 71 |
+
The following hyperparameters were used during training:
|
| 72 |
+
- learning_rate: 0.0005
|
| 73 |
+
- train_batch_size: 8
|
| 74 |
+
- eval_batch_size: 8
|
| 75 |
+
- seed: 42
|
| 76 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 77 |
+
- lr_scheduler_type: linear
|
| 78 |
+
- lr_scheduler_warmup_steps: 2
|
| 79 |
+
- num_epochs: 3
|
| 80 |
+
- mixed_precision_training: Native AMP
|
| 81 |
+
|
| 82 |
+
### Training results
|
| 83 |
+
|
| 84 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | F1 | Precision | Recall |
|
| 85 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:|:---------:|:------:|
|
| 86 |
+
| 2.062 | 1.0 | 110 | 1.8472 | 0.4633 | 0.2177 | 0.3919 | 0.428 | 49.7273 | 0.8911 | 0.8897 | 0.8927 |
|
| 87 |
+
| 1.7853 | 2.0 | 220 | 1.8120 | 0.4633 | 0.2203 | 0.3941 | 0.4285 | 49.4273 | 0.8953 | 0.8945 | 0.8963 |
|
| 88 |
+
| 1.5952 | 3.0 | 330 | 1.7934 | 0.4708 | 0.2246 | 0.3984 | 0.4357 | 49.4091 | 0.8942 | 0.8941 | 0.8945 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- PEFT 0.12.1.dev0
|
| 94 |
+
- Transformers 4.44.0
|
| 95 |
+
- Pytorch 2.4.0
|
| 96 |
+
- Datasets 2.21.0
|
| 97 |
+
- 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": "google-t5/t5-base",
|
| 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": 64,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q",
|
| 24 |
+
"v"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": true
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d57bf549a5c134ffee8300f9e4ed5c32cf63baeff88092a8b2570e64babc6e0
|
| 3 |
+
size 7098016
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"all_params": 153894144,
|
| 3 |
+
"epoch": 3.0,
|
| 4 |
+
"memory_footprint": 403239936,
|
| 5 |
+
"total_flos": 2506179136462848.0,
|
| 6 |
+
"train_loss": 1.8787952170227513,
|
| 7 |
+
"train_runtime": 633.4063,
|
| 8 |
+
"train_samples_per_second": 4.163,
|
| 9 |
+
"train_steps_per_second": 0.521,
|
| 10 |
+
"trainable_params": 1769472,
|
| 11 |
+
"trainable_params_percent": 1.1497981365684713
|
| 12 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "</s>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 934 |
+
"pad_token": "</s>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"all_params": 153894144,
|
| 3 |
+
"epoch": 3.0,
|
| 4 |
+
"memory_footprint": 403239936,
|
| 5 |
+
"total_flos": 2506179136462848.0,
|
| 6 |
+
"train_loss": 1.8787952170227513,
|
| 7 |
+
"train_runtime": 633.4063,
|
| 8 |
+
"train_samples_per_second": 4.163,
|
| 9 |
+
"train_steps_per_second": 0.521,
|
| 10 |
+
"trainable_params": 1769472,
|
| 11 |
+
"trainable_params_percent": 1.1497981365684713
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 330,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00909090909090909,
|
| 13 |
+
"grad_norm": 4.071784019470215,
|
| 14 |
+
"learning_rate": 0.00025,
|
| 15 |
+
"loss": 3.1182,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01818181818181818,
|
| 20 |
+
"grad_norm": 4.663088321685791,
|
| 21 |
+
"learning_rate": 0.0005,
|
| 22 |
+
"loss": 3.4235,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02727272727272727,
|
| 27 |
+
"grad_norm": 3.732215404510498,
|
| 28 |
+
"learning_rate": 0.0004984756097560976,
|
| 29 |
+
"loss": 3.1436,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03636363636363636,
|
| 34 |
+
"grad_norm": 3.961653232574463,
|
| 35 |
+
"learning_rate": 0.0004969512195121951,
|
| 36 |
+
"loss": 3.167,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.045454545454545456,
|
| 41 |
+
"grad_norm": 3.813910484313965,
|
| 42 |
+
"learning_rate": 0.0004954268292682927,
|
| 43 |
+
"loss": 3.2398,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05454545454545454,
|
| 48 |
+
"grad_norm": 3.4221489429473877,
|
| 49 |
+
"learning_rate": 0.0004939024390243902,
|
| 50 |
+
"loss": 3.0624,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06363636363636363,
|
| 55 |
+
"grad_norm": 2.992903232574463,
|
| 56 |
+
"learning_rate": 0.0004923780487804878,
|
| 57 |
+
"loss": 2.2161,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07272727272727272,
|
| 62 |
+
"grad_norm": 4.314737319946289,
|
| 63 |
+
"learning_rate": 0.0004908536585365854,
|
| 64 |
+
"loss": 3.2214,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08181818181818182,
|
| 69 |
+
"grad_norm": 3.5429513454437256,
|
| 70 |
+
"learning_rate": 0.0004893292682926829,
|
| 71 |
+
"loss": 2.6857,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.09090909090909091,
|
| 76 |
+
"grad_norm": NaN,
|
| 77 |
+
"learning_rate": 0.0004893292682926829,
|
| 78 |
+
"loss": 2.4876,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1,
|
| 83 |
+
"grad_norm": 3.5051212310791016,
|
| 84 |
+
"learning_rate": 0.0004878048780487805,
|
| 85 |
+
"loss": 2.6111,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.10909090909090909,
|
| 90 |
+
"grad_norm": 4.561686038970947,
|
| 91 |
+
"learning_rate": 0.00048628048780487805,
|
| 92 |
+
"loss": 2.8702,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.11818181818181818,
|
| 97 |
+
"grad_norm": 3.360241413116455,
|
| 98 |
+
"learning_rate": 0.0004847560975609756,
|
| 99 |
+
"loss": 2.3469,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.12727272727272726,
|
| 104 |
+
"grad_norm": 4.544058799743652,
|
| 105 |
+
"learning_rate": 0.00048323170731707317,
|
| 106 |
+
"loss": 2.4873,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.13636363636363635,
|
| 111 |
+
"grad_norm": 3.3817787170410156,
|
| 112 |
+
"learning_rate": 0.0004817073170731707,
|
| 113 |
+
"loss": 2.5345,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.14545454545454545,
|
| 118 |
+
"grad_norm": 3.405874013900757,
|
| 119 |
+
"learning_rate": 0.0004801829268292683,
|
| 120 |
+
"loss": 2.1892,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.15454545454545454,
|
| 125 |
+
"grad_norm": 3.5852108001708984,
|
| 126 |
+
"learning_rate": 0.00047865853658536585,
|
| 127 |
+
"loss": 2.1381,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.16363636363636364,
|
| 132 |
+
"grad_norm": 3.0975358486175537,
|
| 133 |
+
"learning_rate": 0.0004771341463414634,
|
| 134 |
+
"loss": 2.3727,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.17272727272727273,
|
| 139 |
+
"grad_norm": 3.514904260635376,
|
| 140 |
+
"learning_rate": 0.00047560975609756096,
|
| 141 |
+
"loss": 2.4526,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.18181818181818182,
|
| 146 |
+
"grad_norm": 4.176087379455566,
|
| 147 |
+
"learning_rate": 0.0004740853658536585,
|
| 148 |
+
"loss": 2.2999,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.19090909090909092,
|
| 153 |
+
"grad_norm": 2.7949447631835938,
|
| 154 |
+
"learning_rate": 0.0004725609756097561,
|
| 155 |
+
"loss": 2.2605,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2,
|
| 160 |
+
"grad_norm": 3.023271322250366,
|
| 161 |
+
"learning_rate": 0.00047103658536585364,
|
| 162 |
+
"loss": 2.2398,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.20909090909090908,
|
| 167 |
+
"grad_norm": 3.608038902282715,
|
| 168 |
+
"learning_rate": 0.0004695121951219512,
|
| 169 |
+
"loss": 2.2346,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.21818181818181817,
|
| 174 |
+
"grad_norm": 2.7044689655303955,
|
| 175 |
+
"learning_rate": 0.0004679878048780488,
|
| 176 |
+
"loss": 1.8128,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.22727272727272727,
|
| 181 |
+
"grad_norm": 2.9385201930999756,
|
| 182 |
+
"learning_rate": 0.0004664634146341464,
|
| 183 |
+
"loss": 1.9915,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.23636363636363636,
|
| 188 |
+
"grad_norm": 2.5581564903259277,
|
| 189 |
+
"learning_rate": 0.00046493902439024394,
|
| 190 |
+
"loss": 2.0105,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.24545454545454545,
|
| 195 |
+
"grad_norm": 3.774770498275757,
|
| 196 |
+
"learning_rate": 0.0004634146341463415,
|
| 197 |
+
"loss": 2.4997,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2545454545454545,
|
| 202 |
+
"grad_norm": 3.650287628173828,
|
| 203 |
+
"learning_rate": 0.00046189024390243906,
|
| 204 |
+
"loss": 2.6754,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2636363636363636,
|
| 209 |
+
"grad_norm": 3.0995235443115234,
|
| 210 |
+
"learning_rate": 0.0004603658536585366,
|
| 211 |
+
"loss": 2.5039,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2727272727272727,
|
| 216 |
+
"grad_norm": 2.6960413455963135,
|
| 217 |
+
"learning_rate": 0.0004588414634146342,
|
| 218 |
+
"loss": 2.2671,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2818181818181818,
|
| 223 |
+
"grad_norm": 2.8800947666168213,
|
| 224 |
+
"learning_rate": 0.00045731707317073173,
|
| 225 |
+
"loss": 1.9923,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2909090909090909,
|
| 230 |
+
"grad_norm": 2.768280506134033,
|
| 231 |
+
"learning_rate": 0.0004557926829268293,
|
| 232 |
+
"loss": 2.323,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3,
|
| 237 |
+
"grad_norm": 3.0355064868927,
|
| 238 |
+
"learning_rate": 0.00045426829268292685,
|
| 239 |
+
"loss": 2.1258,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3090909090909091,
|
| 244 |
+
"grad_norm": 2.860558032989502,
|
| 245 |
+
"learning_rate": 0.0004527439024390244,
|
| 246 |
+
"loss": 2.2574,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3181818181818182,
|
| 251 |
+
"grad_norm": 3.0588767528533936,
|
| 252 |
+
"learning_rate": 0.00045121951219512197,
|
| 253 |
+
"loss": 2.2413,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.32727272727272727,
|
| 258 |
+
"grad_norm": 3.065910577774048,
|
| 259 |
+
"learning_rate": 0.00044969512195121953,
|
| 260 |
+
"loss": 1.899,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.33636363636363636,
|
| 265 |
+
"grad_norm": 2.7733941078186035,
|
| 266 |
+
"learning_rate": 0.0004481707317073171,
|
| 267 |
+
"loss": 2.1158,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.34545454545454546,
|
| 272 |
+
"grad_norm": 2.811892509460449,
|
| 273 |
+
"learning_rate": 0.00044664634146341465,
|
| 274 |
+
"loss": 2.48,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.35454545454545455,
|
| 279 |
+
"grad_norm": 2.3305535316467285,
|
| 280 |
+
"learning_rate": 0.0004451219512195122,
|
| 281 |
+
"loss": 2.0319,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.36363636363636365,
|
| 286 |
+
"grad_norm": 2.5622308254241943,
|
| 287 |
+
"learning_rate": 0.00044359756097560977,
|
| 288 |
+
"loss": 1.9229,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.37272727272727274,
|
| 293 |
+
"grad_norm": 3.1169259548187256,
|
| 294 |
+
"learning_rate": 0.00044207317073170733,
|
| 295 |
+
"loss": 2.3218,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.38181818181818183,
|
| 300 |
+
"grad_norm": 2.607619285583496,
|
| 301 |
+
"learning_rate": 0.0004405487804878049,
|
| 302 |
+
"loss": 2.5146,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.39090909090909093,
|
| 307 |
+
"grad_norm": 3.1160788536071777,
|
| 308 |
+
"learning_rate": 0.00043902439024390245,
|
| 309 |
+
"loss": 2.234,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4,
|
| 314 |
+
"grad_norm": 3.0238115787506104,
|
| 315 |
+
"learning_rate": 0.0004375,
|
| 316 |
+
"loss": 1.6721,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4090909090909091,
|
| 321 |
+
"grad_norm": 2.4802684783935547,
|
| 322 |
+
"learning_rate": 0.00043597560975609757,
|
| 323 |
+
"loss": 1.7682,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.41818181818181815,
|
| 328 |
+
"grad_norm": 2.3478028774261475,
|
| 329 |
+
"learning_rate": 0.00043445121951219513,
|
| 330 |
+
"loss": 1.7369,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.42727272727272725,
|
| 335 |
+
"grad_norm": 3.590702772140503,
|
| 336 |
+
"learning_rate": 0.0004329268292682927,
|
| 337 |
+
"loss": 2.2643,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.43636363636363634,
|
| 342 |
+
"grad_norm": 2.9007341861724854,
|
| 343 |
+
"learning_rate": 0.00043140243902439025,
|
| 344 |
+
"loss": 2.0415,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.44545454545454544,
|
| 349 |
+
"grad_norm": 2.371359348297119,
|
| 350 |
+
"learning_rate": 0.0004298780487804878,
|
| 351 |
+
"loss": 1.7783,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.45454545454545453,
|
| 356 |
+
"grad_norm": 2.953730344772339,
|
| 357 |
+
"learning_rate": 0.00042835365853658537,
|
| 358 |
+
"loss": 2.3273,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4636363636363636,
|
| 363 |
+
"grad_norm": 3.101320266723633,
|
| 364 |
+
"learning_rate": 0.0004268292682926829,
|
| 365 |
+
"loss": 2.2416,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.4727272727272727,
|
| 370 |
+
"grad_norm": 2.7180256843566895,
|
| 371 |
+
"learning_rate": 0.0004253048780487805,
|
| 372 |
+
"loss": 2.3769,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.4818181818181818,
|
| 377 |
+
"grad_norm": 3.001201868057251,
|
| 378 |
+
"learning_rate": 0.00042378048780487805,
|
| 379 |
+
"loss": 2.189,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.4909090909090909,
|
| 384 |
+
"grad_norm": 3.2738707065582275,
|
| 385 |
+
"learning_rate": 0.0004222560975609756,
|
| 386 |
+
"loss": 2.2839,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5,
|
| 391 |
+
"grad_norm": 2.4475655555725098,
|
| 392 |
+
"learning_rate": 0.00042073170731707316,
|
| 393 |
+
"loss": 1.8438,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.509090909090909,
|
| 398 |
+
"grad_norm": 2.2483181953430176,
|
| 399 |
+
"learning_rate": 0.0004192073170731707,
|
| 400 |
+
"loss": 1.6211,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5181818181818182,
|
| 405 |
+
"grad_norm": 3.2838337421417236,
|
| 406 |
+
"learning_rate": 0.0004176829268292683,
|
| 407 |
+
"loss": 2.255,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5272727272727272,
|
| 412 |
+
"grad_norm": 2.5919408798217773,
|
| 413 |
+
"learning_rate": 0.00041615853658536584,
|
| 414 |
+
"loss": 2.0132,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5363636363636364,
|
| 419 |
+
"grad_norm": 2.7850112915039062,
|
| 420 |
+
"learning_rate": 0.0004146341463414634,
|
| 421 |
+
"loss": 2.1505,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5454545454545454,
|
| 426 |
+
"grad_norm": 2.3396100997924805,
|
| 427 |
+
"learning_rate": 0.00041310975609756096,
|
| 428 |
+
"loss": 1.8747,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.5545454545454546,
|
| 433 |
+
"grad_norm": 2.788200616836548,
|
| 434 |
+
"learning_rate": 0.0004115853658536585,
|
| 435 |
+
"loss": 2.305,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5636363636363636,
|
| 440 |
+
"grad_norm": 2.750195264816284,
|
| 441 |
+
"learning_rate": 0.0004100609756097561,
|
| 442 |
+
"loss": 1.8235,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.5727272727272728,
|
| 447 |
+
"grad_norm": 3.041684865951538,
|
| 448 |
+
"learning_rate": 0.00040853658536585364,
|
| 449 |
+
"loss": 2.1002,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.5818181818181818,
|
| 454 |
+
"grad_norm": 3.0440473556518555,
|
| 455 |
+
"learning_rate": 0.0004070121951219512,
|
| 456 |
+
"loss": 1.7584,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5909090909090909,
|
| 461 |
+
"grad_norm": 3.090240955352783,
|
| 462 |
+
"learning_rate": 0.0004054878048780488,
|
| 463 |
+
"loss": 1.8738,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.6,
|
| 468 |
+
"grad_norm": 2.376418352127075,
|
| 469 |
+
"learning_rate": 0.0004039634146341464,
|
| 470 |
+
"loss": 1.8655,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6090909090909091,
|
| 475 |
+
"grad_norm": 2.83278489112854,
|
| 476 |
+
"learning_rate": 0.00040243902439024393,
|
| 477 |
+
"loss": 2.6537,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6181818181818182,
|
| 482 |
+
"grad_norm": 3.2327969074249268,
|
| 483 |
+
"learning_rate": 0.0004009146341463415,
|
| 484 |
+
"loss": 1.9686,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.6272727272727273,
|
| 489 |
+
"grad_norm": 2.8755669593811035,
|
| 490 |
+
"learning_rate": 0.00039939024390243905,
|
| 491 |
+
"loss": 2.1451,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6363636363636364,
|
| 496 |
+
"grad_norm": 2.6152892112731934,
|
| 497 |
+
"learning_rate": 0.0003978658536585366,
|
| 498 |
+
"loss": 1.5981,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.6454545454545455,
|
| 503 |
+
"grad_norm": 3.076869010925293,
|
| 504 |
+
"learning_rate": 0.0003963414634146342,
|
| 505 |
+
"loss": 1.9654,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6545454545454545,
|
| 510 |
+
"grad_norm": 2.6173629760742188,
|
| 511 |
+
"learning_rate": 0.00039481707317073173,
|
| 512 |
+
"loss": 2.0392,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6636363636363637,
|
| 517 |
+
"grad_norm": 3.449314594268799,
|
| 518 |
+
"learning_rate": 0.0003932926829268293,
|
| 519 |
+
"loss": 2.0893,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.6727272727272727,
|
| 524 |
+
"grad_norm": 2.5918149948120117,
|
| 525 |
+
"learning_rate": 0.00039176829268292685,
|
| 526 |
+
"loss": 1.969,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6818181818181818,
|
| 531 |
+
"grad_norm": 2.780331611633301,
|
| 532 |
+
"learning_rate": 0.0003902439024390244,
|
| 533 |
+
"loss": 2.0783,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6909090909090909,
|
| 538 |
+
"grad_norm": 2.8215320110321045,
|
| 539 |
+
"learning_rate": 0.00038871951219512197,
|
| 540 |
+
"loss": 1.9011,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.7,
|
| 545 |
+
"grad_norm": 2.9159982204437256,
|
| 546 |
+
"learning_rate": 0.00038719512195121953,
|
| 547 |
+
"loss": 1.9432,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7090909090909091,
|
| 552 |
+
"grad_norm": 2.684636116027832,
|
| 553 |
+
"learning_rate": 0.0003856707317073171,
|
| 554 |
+
"loss": 1.9473,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7181818181818181,
|
| 559 |
+
"grad_norm": 2.554502248764038,
|
| 560 |
+
"learning_rate": 0.00038414634146341465,
|
| 561 |
+
"loss": 1.9211,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7272727272727273,
|
| 566 |
+
"grad_norm": 2.93910551071167,
|
| 567 |
+
"learning_rate": 0.0003826219512195122,
|
| 568 |
+
"loss": 1.7052,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7363636363636363,
|
| 573 |
+
"grad_norm": 3.246049165725708,
|
| 574 |
+
"learning_rate": 0.00038109756097560977,
|
| 575 |
+
"loss": 1.9143,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7454545454545455,
|
| 580 |
+
"grad_norm": 2.407006025314331,
|
| 581 |
+
"learning_rate": 0.00037957317073170733,
|
| 582 |
+
"loss": 1.8885,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7545454545454545,
|
| 587 |
+
"grad_norm": 3.0212433338165283,
|
| 588 |
+
"learning_rate": 0.0003780487804878049,
|
| 589 |
+
"loss": 2.2017,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.7636363636363637,
|
| 594 |
+
"grad_norm": 2.7870118618011475,
|
| 595 |
+
"learning_rate": 0.00037652439024390245,
|
| 596 |
+
"loss": 1.8038,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.7727272727272727,
|
| 601 |
+
"grad_norm": 2.3417677879333496,
|
| 602 |
+
"learning_rate": 0.000375,
|
| 603 |
+
"loss": 1.6184,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.7818181818181819,
|
| 608 |
+
"grad_norm": 3.359086036682129,
|
| 609 |
+
"learning_rate": 0.00037347560975609757,
|
| 610 |
+
"loss": 2.3235,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.7909090909090909,
|
| 615 |
+
"grad_norm": 2.854968786239624,
|
| 616 |
+
"learning_rate": 0.0003719512195121951,
|
| 617 |
+
"loss": 1.9161,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8,
|
| 622 |
+
"grad_norm": 3.0338873863220215,
|
| 623 |
+
"learning_rate": 0.0003704268292682927,
|
| 624 |
+
"loss": 2.5778,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.8090909090909091,
|
| 629 |
+
"grad_norm": 2.7215914726257324,
|
| 630 |
+
"learning_rate": 0.00036890243902439025,
|
| 631 |
+
"loss": 2.2668,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8181818181818182,
|
| 636 |
+
"grad_norm": 3.0825934410095215,
|
| 637 |
+
"learning_rate": 0.0003673780487804878,
|
| 638 |
+
"loss": 2.0312,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.8272727272727273,
|
| 643 |
+
"grad_norm": 4.025455951690674,
|
| 644 |
+
"learning_rate": 0.00036585365853658537,
|
| 645 |
+
"loss": 2.0015,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.8363636363636363,
|
| 650 |
+
"grad_norm": 2.394049882888794,
|
| 651 |
+
"learning_rate": 0.0003643292682926829,
|
| 652 |
+
"loss": 1.7331,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.8454545454545455,
|
| 657 |
+
"grad_norm": 3.181750535964966,
|
| 658 |
+
"learning_rate": 0.0003628048780487805,
|
| 659 |
+
"loss": 1.8799,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.8545454545454545,
|
| 664 |
+
"grad_norm": 3.0317776203155518,
|
| 665 |
+
"learning_rate": 0.00036128048780487804,
|
| 666 |
+
"loss": 1.7447,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.8636363636363636,
|
| 671 |
+
"grad_norm": 2.537506341934204,
|
| 672 |
+
"learning_rate": 0.0003597560975609756,
|
| 673 |
+
"loss": 1.5733,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.8727272727272727,
|
| 678 |
+
"grad_norm": 2.7143495082855225,
|
| 679 |
+
"learning_rate": 0.00035823170731707316,
|
| 680 |
+
"loss": 1.7666,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.8818181818181818,
|
| 685 |
+
"grad_norm": 2.9140336513519287,
|
| 686 |
+
"learning_rate": 0.0003567073170731707,
|
| 687 |
+
"loss": 1.5887,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.8909090909090909,
|
| 692 |
+
"grad_norm": 2.7197532653808594,
|
| 693 |
+
"learning_rate": 0.0003551829268292683,
|
| 694 |
+
"loss": 2.0022,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.9,
|
| 699 |
+
"grad_norm": 3.1423003673553467,
|
| 700 |
+
"learning_rate": 0.00035365853658536584,
|
| 701 |
+
"loss": 1.9328,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.9090909090909091,
|
| 706 |
+
"grad_norm": 2.541865110397339,
|
| 707 |
+
"learning_rate": 0.0003521341463414634,
|
| 708 |
+
"loss": 1.7566,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.9181818181818182,
|
| 713 |
+
"grad_norm": 2.9177896976470947,
|
| 714 |
+
"learning_rate": 0.00035060975609756096,
|
| 715 |
+
"loss": 1.7848,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.9272727272727272,
|
| 720 |
+
"grad_norm": 2.671201467514038,
|
| 721 |
+
"learning_rate": 0.0003490853658536585,
|
| 722 |
+
"loss": 2.0213,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9363636363636364,
|
| 727 |
+
"grad_norm": 2.950990676879883,
|
| 728 |
+
"learning_rate": 0.0003475609756097561,
|
| 729 |
+
"loss": 1.8383,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9454545454545454,
|
| 734 |
+
"grad_norm": 2.508028984069824,
|
| 735 |
+
"learning_rate": 0.00034603658536585364,
|
| 736 |
+
"loss": 1.8774,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.9545454545454546,
|
| 741 |
+
"grad_norm": 2.4655253887176514,
|
| 742 |
+
"learning_rate": 0.0003445121951219512,
|
| 743 |
+
"loss": 1.7972,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.9636363636363636,
|
| 748 |
+
"grad_norm": 3.085402727127075,
|
| 749 |
+
"learning_rate": 0.0003429878048780488,
|
| 750 |
+
"loss": 1.8712,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.9727272727272728,
|
| 755 |
+
"grad_norm": 2.305389642715454,
|
| 756 |
+
"learning_rate": 0.0003414634146341464,
|
| 757 |
+
"loss": 1.48,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.9818181818181818,
|
| 762 |
+
"grad_norm": 2.7900662422180176,
|
| 763 |
+
"learning_rate": 0.00033993902439024393,
|
| 764 |
+
"loss": 1.6433,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.990909090909091,
|
| 769 |
+
"grad_norm": 2.7554140090942383,
|
| 770 |
+
"learning_rate": 0.0003384146341463415,
|
| 771 |
+
"loss": 2.2131,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.0,
|
| 776 |
+
"grad_norm": 2.8607048988342285,
|
| 777 |
+
"learning_rate": 0.00033689024390243905,
|
| 778 |
+
"loss": 2.062,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.0,
|
| 783 |
+
"eval_f1": 0.8911,
|
| 784 |
+
"eval_gen_len": 49.7273,
|
| 785 |
+
"eval_loss": 1.8471709489822388,
|
| 786 |
+
"eval_precision": 0.8897,
|
| 787 |
+
"eval_recall": 0.8927,
|
| 788 |
+
"eval_rouge1": 0.4633,
|
| 789 |
+
"eval_rouge2": 0.2177,
|
| 790 |
+
"eval_rougeL": 0.3919,
|
| 791 |
+
"eval_rougeLsum": 0.428,
|
| 792 |
+
"eval_runtime": 46.8612,
|
| 793 |
+
"eval_samples_per_second": 2.347,
|
| 794 |
+
"eval_steps_per_second": 0.299,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.009090909090909,
|
| 799 |
+
"grad_norm": 2.5493690967559814,
|
| 800 |
+
"learning_rate": 0.0003353658536585366,
|
| 801 |
+
"loss": 1.9424,
|
| 802 |
+
"step": 111
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.018181818181818,
|
| 806 |
+
"grad_norm": 2.030336618423462,
|
| 807 |
+
"learning_rate": 0.00033384146341463417,
|
| 808 |
+
"loss": 1.4907,
|
| 809 |
+
"step": 112
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.0272727272727273,
|
| 813 |
+
"grad_norm": 2.3484795093536377,
|
| 814 |
+
"learning_rate": 0.00033231707317073173,
|
| 815 |
+
"loss": 1.8514,
|
| 816 |
+
"step": 113
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.0363636363636364,
|
| 820 |
+
"grad_norm": 3.1272692680358887,
|
| 821 |
+
"learning_rate": 0.0003307926829268293,
|
| 822 |
+
"loss": 2.2966,
|
| 823 |
+
"step": 114
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.0454545454545454,
|
| 827 |
+
"grad_norm": 2.4133095741271973,
|
| 828 |
+
"learning_rate": 0.00032926829268292685,
|
| 829 |
+
"loss": 1.5813,
|
| 830 |
+
"step": 115
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.0545454545454545,
|
| 834 |
+
"grad_norm": 2.597964286804199,
|
| 835 |
+
"learning_rate": 0.0003277439024390244,
|
| 836 |
+
"loss": 1.9743,
|
| 837 |
+
"step": 116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.0636363636363637,
|
| 841 |
+
"grad_norm": 2.755969524383545,
|
| 842 |
+
"learning_rate": 0.00032621951219512197,
|
| 843 |
+
"loss": 1.4676,
|
| 844 |
+
"step": 117
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.0727272727272728,
|
| 848 |
+
"grad_norm": 2.3715810775756836,
|
| 849 |
+
"learning_rate": 0.00032469512195121953,
|
| 850 |
+
"loss": 1.9406,
|
| 851 |
+
"step": 118
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.0818181818181818,
|
| 855 |
+
"grad_norm": 2.3229820728302,
|
| 856 |
+
"learning_rate": 0.0003231707317073171,
|
| 857 |
+
"loss": 1.9787,
|
| 858 |
+
"step": 119
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.0909090909090908,
|
| 862 |
+
"grad_norm": 2.724597215652466,
|
| 863 |
+
"learning_rate": 0.00032164634146341465,
|
| 864 |
+
"loss": 2.1574,
|
| 865 |
+
"step": 120
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.1,
|
| 869 |
+
"grad_norm": 3.342278242111206,
|
| 870 |
+
"learning_rate": 0.0003201219512195122,
|
| 871 |
+
"loss": 1.8255,
|
| 872 |
+
"step": 121
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.1090909090909091,
|
| 876 |
+
"grad_norm": 2.4172379970550537,
|
| 877 |
+
"learning_rate": 0.00031859756097560977,
|
| 878 |
+
"loss": 1.7576,
|
| 879 |
+
"step": 122
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.1181818181818182,
|
| 883 |
+
"grad_norm": 3.158111095428467,
|
| 884 |
+
"learning_rate": 0.00031707317073170733,
|
| 885 |
+
"loss": 1.9855,
|
| 886 |
+
"step": 123
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.1272727272727272,
|
| 890 |
+
"grad_norm": 2.9254257678985596,
|
| 891 |
+
"learning_rate": 0.0003155487804878049,
|
| 892 |
+
"loss": 2.0363,
|
| 893 |
+
"step": 124
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 1.1363636363636362,
|
| 897 |
+
"grad_norm": 2.5448672771453857,
|
| 898 |
+
"learning_rate": 0.00031402439024390245,
|
| 899 |
+
"loss": 1.8373,
|
| 900 |
+
"step": 125
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 1.1454545454545455,
|
| 904 |
+
"grad_norm": 2.693936347961426,
|
| 905 |
+
"learning_rate": 0.0003125,
|
| 906 |
+
"loss": 1.8654,
|
| 907 |
+
"step": 126
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 1.1545454545454545,
|
| 911 |
+
"grad_norm": 2.5871312618255615,
|
| 912 |
+
"learning_rate": 0.00031097560975609757,
|
| 913 |
+
"loss": 1.7372,
|
| 914 |
+
"step": 127
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.1636363636363636,
|
| 918 |
+
"grad_norm": 2.709867000579834,
|
| 919 |
+
"learning_rate": 0.0003094512195121951,
|
| 920 |
+
"loss": 1.8044,
|
| 921 |
+
"step": 128
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.1727272727272728,
|
| 925 |
+
"grad_norm": 2.741077423095703,
|
| 926 |
+
"learning_rate": 0.0003079268292682927,
|
| 927 |
+
"loss": 1.9361,
|
| 928 |
+
"step": 129
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.1818181818181819,
|
| 932 |
+
"grad_norm": 2.9570066928863525,
|
| 933 |
+
"learning_rate": 0.00030640243902439024,
|
| 934 |
+
"loss": 2.0666,
|
| 935 |
+
"step": 130
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.190909090909091,
|
| 939 |
+
"grad_norm": 2.356640100479126,
|
| 940 |
+
"learning_rate": 0.0003048780487804878,
|
| 941 |
+
"loss": 1.7525,
|
| 942 |
+
"step": 131
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 1.2,
|
| 946 |
+
"grad_norm": 2.7299695014953613,
|
| 947 |
+
"learning_rate": 0.00030335365853658536,
|
| 948 |
+
"loss": 1.8064,
|
| 949 |
+
"step": 132
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 1.209090909090909,
|
| 953 |
+
"grad_norm": 2.3065450191497803,
|
| 954 |
+
"learning_rate": 0.0003018292682926829,
|
| 955 |
+
"loss": 1.652,
|
| 956 |
+
"step": 133
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 1.2181818181818183,
|
| 960 |
+
"grad_norm": 2.8539586067199707,
|
| 961 |
+
"learning_rate": 0.0003003048780487805,
|
| 962 |
+
"loss": 1.8285,
|
| 963 |
+
"step": 134
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.2272727272727273,
|
| 967 |
+
"grad_norm": 2.843475580215454,
|
| 968 |
+
"learning_rate": 0.00029878048780487804,
|
| 969 |
+
"loss": 1.9938,
|
| 970 |
+
"step": 135
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.2363636363636363,
|
| 974 |
+
"grad_norm": 2.547865390777588,
|
| 975 |
+
"learning_rate": 0.0002972560975609756,
|
| 976 |
+
"loss": 1.9472,
|
| 977 |
+
"step": 136
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.2454545454545454,
|
| 981 |
+
"grad_norm": 2.1262078285217285,
|
| 982 |
+
"learning_rate": 0.00029573170731707316,
|
| 983 |
+
"loss": 1.3486,
|
| 984 |
+
"step": 137
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.2545454545454544,
|
| 988 |
+
"grad_norm": 2.93005633354187,
|
| 989 |
+
"learning_rate": 0.0002942073170731707,
|
| 990 |
+
"loss": 1.5797,
|
| 991 |
+
"step": 138
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.2636363636363637,
|
| 995 |
+
"grad_norm": 2.5727319717407227,
|
| 996 |
+
"learning_rate": 0.0002926829268292683,
|
| 997 |
+
"loss": 1.8976,
|
| 998 |
+
"step": 139
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.2727272727272727,
|
| 1002 |
+
"grad_norm": 3.29372501373291,
|
| 1003 |
+
"learning_rate": 0.00029115853658536584,
|
| 1004 |
+
"loss": 1.9751,
|
| 1005 |
+
"step": 140
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.2818181818181817,
|
| 1009 |
+
"grad_norm": NaN,
|
| 1010 |
+
"learning_rate": 0.00029115853658536584,
|
| 1011 |
+
"loss": 1.9404,
|
| 1012 |
+
"step": 141
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.290909090909091,
|
| 1016 |
+
"grad_norm": 2.868084669113159,
|
| 1017 |
+
"learning_rate": 0.0002896341463414634,
|
| 1018 |
+
"loss": 1.5832,
|
| 1019 |
+
"step": 142
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.3,
|
| 1023 |
+
"grad_norm": 2.792365312576294,
|
| 1024 |
+
"learning_rate": 0.00028810975609756096,
|
| 1025 |
+
"loss": 2.0512,
|
| 1026 |
+
"step": 143
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.309090909090909,
|
| 1030 |
+
"grad_norm": 2.333376169204712,
|
| 1031 |
+
"learning_rate": 0.0002865853658536585,
|
| 1032 |
+
"loss": 1.5019,
|
| 1033 |
+
"step": 144
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.3181818181818181,
|
| 1037 |
+
"grad_norm": 3.5344386100769043,
|
| 1038 |
+
"learning_rate": 0.0002850609756097561,
|
| 1039 |
+
"loss": 2.0819,
|
| 1040 |
+
"step": 145
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.3272727272727272,
|
| 1044 |
+
"grad_norm": 2.7761566638946533,
|
| 1045 |
+
"learning_rate": 0.00028353658536585364,
|
| 1046 |
+
"loss": 1.8773,
|
| 1047 |
+
"step": 146
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 1.3363636363636364,
|
| 1051 |
+
"grad_norm": 2.796036720275879,
|
| 1052 |
+
"learning_rate": 0.0002820121951219512,
|
| 1053 |
+
"loss": 1.8373,
|
| 1054 |
+
"step": 147
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.3454545454545455,
|
| 1058 |
+
"grad_norm": 3.2006378173828125,
|
| 1059 |
+
"learning_rate": 0.0002804878048780488,
|
| 1060 |
+
"loss": 2.0195,
|
| 1061 |
+
"step": 148
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.3545454545454545,
|
| 1065 |
+
"grad_norm": 3.6497931480407715,
|
| 1066 |
+
"learning_rate": 0.00027896341463414637,
|
| 1067 |
+
"loss": 1.7754,
|
| 1068 |
+
"step": 149
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.3636363636363638,
|
| 1072 |
+
"grad_norm": 3.0451290607452393,
|
| 1073 |
+
"learning_rate": 0.00027743902439024393,
|
| 1074 |
+
"loss": 1.6708,
|
| 1075 |
+
"step": 150
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 1.3727272727272728,
|
| 1079 |
+
"grad_norm": 3.2684431076049805,
|
| 1080 |
+
"learning_rate": 0.0002759146341463415,
|
| 1081 |
+
"loss": 2.0718,
|
| 1082 |
+
"step": 151
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.3818181818181818,
|
| 1086 |
+
"grad_norm": 2.6152052879333496,
|
| 1087 |
+
"learning_rate": 0.00027439024390243905,
|
| 1088 |
+
"loss": 1.87,
|
| 1089 |
+
"step": 152
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.3909090909090909,
|
| 1093 |
+
"grad_norm": 2.713304281234741,
|
| 1094 |
+
"learning_rate": 0.0002728658536585366,
|
| 1095 |
+
"loss": 1.707,
|
| 1096 |
+
"step": 153
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.4,
|
| 1100 |
+
"grad_norm": 2.6585283279418945,
|
| 1101 |
+
"learning_rate": 0.00027134146341463417,
|
| 1102 |
+
"loss": 1.8551,
|
| 1103 |
+
"step": 154
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.4090909090909092,
|
| 1107 |
+
"grad_norm": 2.903383255004883,
|
| 1108 |
+
"learning_rate": 0.00026981707317073173,
|
| 1109 |
+
"loss": 1.9101,
|
| 1110 |
+
"step": 155
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.4181818181818182,
|
| 1114 |
+
"grad_norm": 2.6489484310150146,
|
| 1115 |
+
"learning_rate": 0.0002682926829268293,
|
| 1116 |
+
"loss": 1.8333,
|
| 1117 |
+
"step": 156
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.4272727272727272,
|
| 1121 |
+
"grad_norm": 3.004567861557007,
|
| 1122 |
+
"learning_rate": 0.00026676829268292685,
|
| 1123 |
+
"loss": 1.4886,
|
| 1124 |
+
"step": 157
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.4363636363636363,
|
| 1128 |
+
"grad_norm": 2.774327278137207,
|
| 1129 |
+
"learning_rate": 0.0002652439024390244,
|
| 1130 |
+
"loss": 1.8893,
|
| 1131 |
+
"step": 158
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.4454545454545453,
|
| 1135 |
+
"grad_norm": 2.8652050495147705,
|
| 1136 |
+
"learning_rate": 0.00026371951219512197,
|
| 1137 |
+
"loss": 1.8702,
|
| 1138 |
+
"step": 159
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.4545454545454546,
|
| 1142 |
+
"grad_norm": 2.2331173419952393,
|
| 1143 |
+
"learning_rate": 0.00026219512195121953,
|
| 1144 |
+
"loss": 1.9589,
|
| 1145 |
+
"step": 160
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.4636363636363636,
|
| 1149 |
+
"grad_norm": 2.5273420810699463,
|
| 1150 |
+
"learning_rate": 0.0002606707317073171,
|
| 1151 |
+
"loss": 1.7515,
|
| 1152 |
+
"step": 161
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.4727272727272727,
|
| 1156 |
+
"grad_norm": 3.0862534046173096,
|
| 1157 |
+
"learning_rate": 0.00025914634146341465,
|
| 1158 |
+
"loss": 1.4377,
|
| 1159 |
+
"step": 162
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 1.481818181818182,
|
| 1163 |
+
"grad_norm": 3.167388677597046,
|
| 1164 |
+
"learning_rate": 0.0002576219512195122,
|
| 1165 |
+
"loss": 2.2095,
|
| 1166 |
+
"step": 163
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.490909090909091,
|
| 1170 |
+
"grad_norm": 2.9668028354644775,
|
| 1171 |
+
"learning_rate": 0.00025609756097560977,
|
| 1172 |
+
"loss": 1.7428,
|
| 1173 |
+
"step": 164
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.5,
|
| 1177 |
+
"grad_norm": 2.4375245571136475,
|
| 1178 |
+
"learning_rate": 0.0002545731707317073,
|
| 1179 |
+
"loss": 1.392,
|
| 1180 |
+
"step": 165
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 1.509090909090909,
|
| 1184 |
+
"grad_norm": 2.71293568611145,
|
| 1185 |
+
"learning_rate": 0.0002530487804878049,
|
| 1186 |
+
"loss": 1.9706,
|
| 1187 |
+
"step": 166
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 1.518181818181818,
|
| 1191 |
+
"grad_norm": 2.6570401191711426,
|
| 1192 |
+
"learning_rate": 0.00025152439024390245,
|
| 1193 |
+
"loss": 1.8777,
|
| 1194 |
+
"step": 167
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.5272727272727273,
|
| 1198 |
+
"grad_norm": 2.379110813140869,
|
| 1199 |
+
"learning_rate": 0.00025,
|
| 1200 |
+
"loss": 1.4582,
|
| 1201 |
+
"step": 168
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.5363636363636364,
|
| 1205 |
+
"grad_norm": 3.0288100242614746,
|
| 1206 |
+
"learning_rate": 0.00024847560975609756,
|
| 1207 |
+
"loss": 1.9216,
|
| 1208 |
+
"step": 169
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.5454545454545454,
|
| 1212 |
+
"grad_norm": 2.574794054031372,
|
| 1213 |
+
"learning_rate": 0.0002469512195121951,
|
| 1214 |
+
"loss": 1.5392,
|
| 1215 |
+
"step": 170
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 1.5545454545454547,
|
| 1219 |
+
"grad_norm": 2.8772997856140137,
|
| 1220 |
+
"learning_rate": 0.0002454268292682927,
|
| 1221 |
+
"loss": 1.8662,
|
| 1222 |
+
"step": 171
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 1.5636363636363635,
|
| 1226 |
+
"grad_norm": 3.186906099319458,
|
| 1227 |
+
"learning_rate": 0.00024390243902439024,
|
| 1228 |
+
"loss": 1.7958,
|
| 1229 |
+
"step": 172
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.5727272727272728,
|
| 1233 |
+
"grad_norm": 2.5595905780792236,
|
| 1234 |
+
"learning_rate": 0.0002423780487804878,
|
| 1235 |
+
"loss": 1.6044,
|
| 1236 |
+
"step": 173
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.5818181818181818,
|
| 1240 |
+
"grad_norm": 2.952155828475952,
|
| 1241 |
+
"learning_rate": 0.00024085365853658536,
|
| 1242 |
+
"loss": 1.9509,
|
| 1243 |
+
"step": 174
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 1.5909090909090908,
|
| 1247 |
+
"grad_norm": 2.6648874282836914,
|
| 1248 |
+
"learning_rate": 0.00023932926829268292,
|
| 1249 |
+
"loss": 1.8644,
|
| 1250 |
+
"step": 175
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.6,
|
| 1254 |
+
"grad_norm": 2.649273157119751,
|
| 1255 |
+
"learning_rate": 0.00023780487804878048,
|
| 1256 |
+
"loss": 1.9846,
|
| 1257 |
+
"step": 176
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.6090909090909091,
|
| 1261 |
+
"grad_norm": 3.196133852005005,
|
| 1262 |
+
"learning_rate": 0.00023628048780487804,
|
| 1263 |
+
"loss": 1.689,
|
| 1264 |
+
"step": 177
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.6181818181818182,
|
| 1268 |
+
"grad_norm": 2.5493838787078857,
|
| 1269 |
+
"learning_rate": 0.0002347560975609756,
|
| 1270 |
+
"loss": 1.6899,
|
| 1271 |
+
"step": 178
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.6272727272727274,
|
| 1275 |
+
"grad_norm": 4.60580587387085,
|
| 1276 |
+
"learning_rate": 0.0002332317073170732,
|
| 1277 |
+
"loss": 1.8183,
|
| 1278 |
+
"step": 179
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.6363636363636362,
|
| 1282 |
+
"grad_norm": 2.7253472805023193,
|
| 1283 |
+
"learning_rate": 0.00023170731707317075,
|
| 1284 |
+
"loss": 1.7829,
|
| 1285 |
+
"step": 180
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.6454545454545455,
|
| 1289 |
+
"grad_norm": 2.9373483657836914,
|
| 1290 |
+
"learning_rate": 0.0002301829268292683,
|
| 1291 |
+
"loss": 1.7837,
|
| 1292 |
+
"step": 181
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.6545454545454545,
|
| 1296 |
+
"grad_norm": 2.4897494316101074,
|
| 1297 |
+
"learning_rate": 0.00022865853658536587,
|
| 1298 |
+
"loss": 1.4675,
|
| 1299 |
+
"step": 182
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.6636363636363636,
|
| 1303 |
+
"grad_norm": 2.3043053150177,
|
| 1304 |
+
"learning_rate": 0.00022713414634146343,
|
| 1305 |
+
"loss": 1.5805,
|
| 1306 |
+
"step": 183
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.6727272727272728,
|
| 1310 |
+
"grad_norm": 3.0130205154418945,
|
| 1311 |
+
"learning_rate": 0.00022560975609756099,
|
| 1312 |
+
"loss": 2.1577,
|
| 1313 |
+
"step": 184
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.6818181818181817,
|
| 1317 |
+
"grad_norm": 3.0861997604370117,
|
| 1318 |
+
"learning_rate": 0.00022408536585365855,
|
| 1319 |
+
"loss": 2.011,
|
| 1320 |
+
"step": 185
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.690909090909091,
|
| 1324 |
+
"grad_norm": 2.6685359477996826,
|
| 1325 |
+
"learning_rate": 0.0002225609756097561,
|
| 1326 |
+
"loss": 1.9333,
|
| 1327 |
+
"step": 186
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.7,
|
| 1331 |
+
"grad_norm": 2.309566020965576,
|
| 1332 |
+
"learning_rate": 0.00022103658536585367,
|
| 1333 |
+
"loss": 1.7602,
|
| 1334 |
+
"step": 187
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.709090909090909,
|
| 1338 |
+
"grad_norm": 2.686500072479248,
|
| 1339 |
+
"learning_rate": 0.00021951219512195122,
|
| 1340 |
+
"loss": 1.9934,
|
| 1341 |
+
"step": 188
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.7181818181818183,
|
| 1345 |
+
"grad_norm": 2.0740697383880615,
|
| 1346 |
+
"learning_rate": 0.00021798780487804878,
|
| 1347 |
+
"loss": 1.3903,
|
| 1348 |
+
"step": 189
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.7272727272727273,
|
| 1352 |
+
"grad_norm": 2.9675910472869873,
|
| 1353 |
+
"learning_rate": 0.00021646341463414634,
|
| 1354 |
+
"loss": 1.8017,
|
| 1355 |
+
"step": 190
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.7363636363636363,
|
| 1359 |
+
"grad_norm": 2.5559232234954834,
|
| 1360 |
+
"learning_rate": 0.0002149390243902439,
|
| 1361 |
+
"loss": 1.8526,
|
| 1362 |
+
"step": 191
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.7454545454545456,
|
| 1366 |
+
"grad_norm": 3.0341475009918213,
|
| 1367 |
+
"learning_rate": 0.00021341463414634146,
|
| 1368 |
+
"loss": 1.9374,
|
| 1369 |
+
"step": 192
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 1.7545454545454544,
|
| 1373 |
+
"grad_norm": 2.351853609085083,
|
| 1374 |
+
"learning_rate": 0.00021189024390243902,
|
| 1375 |
+
"loss": 1.695,
|
| 1376 |
+
"step": 193
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.7636363636363637,
|
| 1380 |
+
"grad_norm": 2.8605730533599854,
|
| 1381 |
+
"learning_rate": 0.00021036585365853658,
|
| 1382 |
+
"loss": 2.1981,
|
| 1383 |
+
"step": 194
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 1.7727272727272727,
|
| 1387 |
+
"grad_norm": 2.4615988731384277,
|
| 1388 |
+
"learning_rate": 0.00020884146341463414,
|
| 1389 |
+
"loss": 1.8249,
|
| 1390 |
+
"step": 195
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.7818181818181817,
|
| 1394 |
+
"grad_norm": 2.9569573402404785,
|
| 1395 |
+
"learning_rate": 0.0002073170731707317,
|
| 1396 |
+
"loss": 2.0083,
|
| 1397 |
+
"step": 196
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.790909090909091,
|
| 1401 |
+
"grad_norm": 2.4674253463745117,
|
| 1402 |
+
"learning_rate": 0.00020579268292682926,
|
| 1403 |
+
"loss": 1.4235,
|
| 1404 |
+
"step": 197
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.8,
|
| 1408 |
+
"grad_norm": 2.693068027496338,
|
| 1409 |
+
"learning_rate": 0.00020426829268292682,
|
| 1410 |
+
"loss": 2.0025,
|
| 1411 |
+
"step": 198
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 1.809090909090909,
|
| 1415 |
+
"grad_norm": 2.6479923725128174,
|
| 1416 |
+
"learning_rate": 0.0002027439024390244,
|
| 1417 |
+
"loss": 1.8531,
|
| 1418 |
+
"step": 199
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.8181818181818183,
|
| 1422 |
+
"grad_norm": 2.5726828575134277,
|
| 1423 |
+
"learning_rate": 0.00020121951219512197,
|
| 1424 |
+
"loss": 1.9046,
|
| 1425 |
+
"step": 200
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.8272727272727272,
|
| 1429 |
+
"grad_norm": 2.286144971847534,
|
| 1430 |
+
"learning_rate": 0.00019969512195121953,
|
| 1431 |
+
"loss": 1.8147,
|
| 1432 |
+
"step": 201
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 1.8363636363636364,
|
| 1436 |
+
"grad_norm": 2.4627556800842285,
|
| 1437 |
+
"learning_rate": 0.0001981707317073171,
|
| 1438 |
+
"loss": 1.7151,
|
| 1439 |
+
"step": 202
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.8454545454545455,
|
| 1443 |
+
"grad_norm": 2.3641176223754883,
|
| 1444 |
+
"learning_rate": 0.00019664634146341465,
|
| 1445 |
+
"loss": 1.6279,
|
| 1446 |
+
"step": 203
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 1.8545454545454545,
|
| 1450 |
+
"grad_norm": 2.3488380908966064,
|
| 1451 |
+
"learning_rate": 0.0001951219512195122,
|
| 1452 |
+
"loss": 1.7368,
|
| 1453 |
+
"step": 204
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 1.8636363636363638,
|
| 1457 |
+
"grad_norm": 2.626936435699463,
|
| 1458 |
+
"learning_rate": 0.00019359756097560977,
|
| 1459 |
+
"loss": 1.6347,
|
| 1460 |
+
"step": 205
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.8727272727272726,
|
| 1464 |
+
"grad_norm": 2.7492589950561523,
|
| 1465 |
+
"learning_rate": 0.00019207317073170733,
|
| 1466 |
+
"loss": 1.8449,
|
| 1467 |
+
"step": 206
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.8818181818181818,
|
| 1471 |
+
"grad_norm": 2.2747907638549805,
|
| 1472 |
+
"learning_rate": 0.00019054878048780488,
|
| 1473 |
+
"loss": 1.669,
|
| 1474 |
+
"step": 207
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.8909090909090909,
|
| 1478 |
+
"grad_norm": 2.540228843688965,
|
| 1479 |
+
"learning_rate": 0.00018902439024390244,
|
| 1480 |
+
"loss": 1.6892,
|
| 1481 |
+
"step": 208
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.9,
|
| 1485 |
+
"grad_norm": 2.521294593811035,
|
| 1486 |
+
"learning_rate": 0.0001875,
|
| 1487 |
+
"loss": 1.7682,
|
| 1488 |
+
"step": 209
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 1.9090909090909092,
|
| 1492 |
+
"grad_norm": 2.7691824436187744,
|
| 1493 |
+
"learning_rate": 0.00018597560975609756,
|
| 1494 |
+
"loss": 1.7694,
|
| 1495 |
+
"step": 210
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 1.9181818181818182,
|
| 1499 |
+
"grad_norm": 2.7531917095184326,
|
| 1500 |
+
"learning_rate": 0.00018445121951219512,
|
| 1501 |
+
"loss": 1.7217,
|
| 1502 |
+
"step": 211
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.9272727272727272,
|
| 1506 |
+
"grad_norm": 2.3607912063598633,
|
| 1507 |
+
"learning_rate": 0.00018292682926829268,
|
| 1508 |
+
"loss": 1.9776,
|
| 1509 |
+
"step": 212
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.9363636363636365,
|
| 1513 |
+
"grad_norm": 2.737658739089966,
|
| 1514 |
+
"learning_rate": 0.00018140243902439024,
|
| 1515 |
+
"loss": 1.7351,
|
| 1516 |
+
"step": 213
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.9454545454545453,
|
| 1520 |
+
"grad_norm": 2.491176128387451,
|
| 1521 |
+
"learning_rate": 0.0001798780487804878,
|
| 1522 |
+
"loss": 1.7922,
|
| 1523 |
+
"step": 214
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.9545454545454546,
|
| 1527 |
+
"grad_norm": 2.4534223079681396,
|
| 1528 |
+
"learning_rate": 0.00017835365853658536,
|
| 1529 |
+
"loss": 1.8887,
|
| 1530 |
+
"step": 215
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.9636363636363636,
|
| 1534 |
+
"grad_norm": 3.2689099311828613,
|
| 1535 |
+
"learning_rate": 0.00017682926829268292,
|
| 1536 |
+
"loss": 2.1455,
|
| 1537 |
+
"step": 216
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.9727272727272727,
|
| 1541 |
+
"grad_norm": 2.444859743118286,
|
| 1542 |
+
"learning_rate": 0.00017530487804878048,
|
| 1543 |
+
"loss": 1.6893,
|
| 1544 |
+
"step": 217
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.981818181818182,
|
| 1548 |
+
"grad_norm": 2.3944003582000732,
|
| 1549 |
+
"learning_rate": 0.00017378048780487804,
|
| 1550 |
+
"loss": 1.4158,
|
| 1551 |
+
"step": 218
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.990909090909091,
|
| 1555 |
+
"grad_norm": 2.8656787872314453,
|
| 1556 |
+
"learning_rate": 0.0001722560975609756,
|
| 1557 |
+
"loss": 2.1827,
|
| 1558 |
+
"step": 219
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.0,
|
| 1562 |
+
"grad_norm": 2.836941719055176,
|
| 1563 |
+
"learning_rate": 0.0001707317073170732,
|
| 1564 |
+
"loss": 1.7853,
|
| 1565 |
+
"step": 220
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.0,
|
| 1569 |
+
"eval_f1": 0.8953,
|
| 1570 |
+
"eval_gen_len": 49.4273,
|
| 1571 |
+
"eval_loss": 1.8119523525238037,
|
| 1572 |
+
"eval_precision": 0.8945,
|
| 1573 |
+
"eval_recall": 0.8963,
|
| 1574 |
+
"eval_rouge1": 0.4633,
|
| 1575 |
+
"eval_rouge2": 0.2203,
|
| 1576 |
+
"eval_rougeL": 0.3941,
|
| 1577 |
+
"eval_rougeLsum": 0.4285,
|
| 1578 |
+
"eval_runtime": 47.0298,
|
| 1579 |
+
"eval_samples_per_second": 2.339,
|
| 1580 |
+
"eval_steps_per_second": 0.298,
|
| 1581 |
+
"step": 220
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 2.0090909090909093,
|
| 1585 |
+
"grad_norm": 2.421740770339966,
|
| 1586 |
+
"learning_rate": 0.00016920731707317075,
|
| 1587 |
+
"loss": 1.3819,
|
| 1588 |
+
"step": 221
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 2.018181818181818,
|
| 1592 |
+
"grad_norm": 2.5827627182006836,
|
| 1593 |
+
"learning_rate": 0.0001676829268292683,
|
| 1594 |
+
"loss": 1.7222,
|
| 1595 |
+
"step": 222
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 2.0272727272727273,
|
| 1599 |
+
"grad_norm": 2.4553208351135254,
|
| 1600 |
+
"learning_rate": 0.00016615853658536587,
|
| 1601 |
+
"loss": 1.7625,
|
| 1602 |
+
"step": 223
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 2.036363636363636,
|
| 1606 |
+
"grad_norm": 2.6801366806030273,
|
| 1607 |
+
"learning_rate": 0.00016463414634146343,
|
| 1608 |
+
"loss": 1.6591,
|
| 1609 |
+
"step": 224
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 2.0454545454545454,
|
| 1613 |
+
"grad_norm": 2.8583321571350098,
|
| 1614 |
+
"learning_rate": 0.00016310975609756098,
|
| 1615 |
+
"loss": 1.8691,
|
| 1616 |
+
"step": 225
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 2.0545454545454547,
|
| 1620 |
+
"grad_norm": 2.8577945232391357,
|
| 1621 |
+
"learning_rate": 0.00016158536585365854,
|
| 1622 |
+
"loss": 2.2397,
|
| 1623 |
+
"step": 226
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 2.0636363636363635,
|
| 1627 |
+
"grad_norm": 2.5665602684020996,
|
| 1628 |
+
"learning_rate": 0.0001600609756097561,
|
| 1629 |
+
"loss": 1.6606,
|
| 1630 |
+
"step": 227
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 2.0727272727272728,
|
| 1634 |
+
"grad_norm": 2.4023563861846924,
|
| 1635 |
+
"learning_rate": 0.00015853658536585366,
|
| 1636 |
+
"loss": 1.6621,
|
| 1637 |
+
"step": 228
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 2.081818181818182,
|
| 1641 |
+
"grad_norm": 2.426421880722046,
|
| 1642 |
+
"learning_rate": 0.00015701219512195122,
|
| 1643 |
+
"loss": 1.5207,
|
| 1644 |
+
"step": 229
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 2.090909090909091,
|
| 1648 |
+
"grad_norm": 2.462782382965088,
|
| 1649 |
+
"learning_rate": 0.00015548780487804878,
|
| 1650 |
+
"loss": 1.6258,
|
| 1651 |
+
"step": 230
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 2.1,
|
| 1655 |
+
"grad_norm": 2.5428097248077393,
|
| 1656 |
+
"learning_rate": 0.00015396341463414634,
|
| 1657 |
+
"loss": 1.4525,
|
| 1658 |
+
"step": 231
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 2.109090909090909,
|
| 1662 |
+
"grad_norm": 2.179856538772583,
|
| 1663 |
+
"learning_rate": 0.0001524390243902439,
|
| 1664 |
+
"loss": 1.3824,
|
| 1665 |
+
"step": 232
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 2.118181818181818,
|
| 1669 |
+
"grad_norm": 2.4684817790985107,
|
| 1670 |
+
"learning_rate": 0.00015091463414634146,
|
| 1671 |
+
"loss": 1.5785,
|
| 1672 |
+
"step": 233
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 2.1272727272727274,
|
| 1676 |
+
"grad_norm": 2.5517914295196533,
|
| 1677 |
+
"learning_rate": 0.00014939024390243902,
|
| 1678 |
+
"loss": 1.5097,
|
| 1679 |
+
"step": 234
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 2.1363636363636362,
|
| 1683 |
+
"grad_norm": 2.6141982078552246,
|
| 1684 |
+
"learning_rate": 0.00014786585365853658,
|
| 1685 |
+
"loss": 1.4524,
|
| 1686 |
+
"step": 235
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 2.1454545454545455,
|
| 1690 |
+
"grad_norm": 2.820064067840576,
|
| 1691 |
+
"learning_rate": 0.00014634146341463414,
|
| 1692 |
+
"loss": 1.8698,
|
| 1693 |
+
"step": 236
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 2.1545454545454543,
|
| 1697 |
+
"grad_norm": 2.5539379119873047,
|
| 1698 |
+
"learning_rate": 0.0001448170731707317,
|
| 1699 |
+
"loss": 1.5742,
|
| 1700 |
+
"step": 237
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 2.1636363636363636,
|
| 1704 |
+
"grad_norm": 2.738567352294922,
|
| 1705 |
+
"learning_rate": 0.00014329268292682926,
|
| 1706 |
+
"loss": 1.6458,
|
| 1707 |
+
"step": 238
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 2.172727272727273,
|
| 1711 |
+
"grad_norm": 2.583866834640503,
|
| 1712 |
+
"learning_rate": 0.00014176829268292682,
|
| 1713 |
+
"loss": 1.7928,
|
| 1714 |
+
"step": 239
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 2.1818181818181817,
|
| 1718 |
+
"grad_norm": 2.7706844806671143,
|
| 1719 |
+
"learning_rate": 0.0001402439024390244,
|
| 1720 |
+
"loss": 2.1484,
|
| 1721 |
+
"step": 240
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 2.190909090909091,
|
| 1725 |
+
"grad_norm": 2.333019495010376,
|
| 1726 |
+
"learning_rate": 0.00013871951219512197,
|
| 1727 |
+
"loss": 1.4385,
|
| 1728 |
+
"step": 241
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 2.2,
|
| 1732 |
+
"grad_norm": 2.4395415782928467,
|
| 1733 |
+
"learning_rate": 0.00013719512195121953,
|
| 1734 |
+
"loss": 1.1418,
|
| 1735 |
+
"step": 242
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 2.209090909090909,
|
| 1739 |
+
"grad_norm": 2.8756039142608643,
|
| 1740 |
+
"learning_rate": 0.00013567073170731709,
|
| 1741 |
+
"loss": 2.121,
|
| 1742 |
+
"step": 243
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 2.2181818181818183,
|
| 1746 |
+
"grad_norm": 2.7827882766723633,
|
| 1747 |
+
"learning_rate": 0.00013414634146341464,
|
| 1748 |
+
"loss": 1.829,
|
| 1749 |
+
"step": 244
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 2.227272727272727,
|
| 1753 |
+
"grad_norm": 2.5495877265930176,
|
| 1754 |
+
"learning_rate": 0.0001326219512195122,
|
| 1755 |
+
"loss": 1.8662,
|
| 1756 |
+
"step": 245
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 2.2363636363636363,
|
| 1760 |
+
"grad_norm": 2.831456422805786,
|
| 1761 |
+
"learning_rate": 0.00013109756097560976,
|
| 1762 |
+
"loss": 1.9483,
|
| 1763 |
+
"step": 246
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 2.2454545454545456,
|
| 1767 |
+
"grad_norm": 3.0142741203308105,
|
| 1768 |
+
"learning_rate": 0.00012957317073170732,
|
| 1769 |
+
"loss": 1.7868,
|
| 1770 |
+
"step": 247
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 2.2545454545454544,
|
| 1774 |
+
"grad_norm": 2.723198652267456,
|
| 1775 |
+
"learning_rate": 0.00012804878048780488,
|
| 1776 |
+
"loss": 1.7103,
|
| 1777 |
+
"step": 248
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 2.2636363636363637,
|
| 1781 |
+
"grad_norm": 3.161470890045166,
|
| 1782 |
+
"learning_rate": 0.00012652439024390244,
|
| 1783 |
+
"loss": 1.8972,
|
| 1784 |
+
"step": 249
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 2.2727272727272725,
|
| 1788 |
+
"grad_norm": 2.5970962047576904,
|
| 1789 |
+
"learning_rate": 0.000125,
|
| 1790 |
+
"loss": 2.1127,
|
| 1791 |
+
"step": 250
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 2.2818181818181817,
|
| 1795 |
+
"grad_norm": 2.5795202255249023,
|
| 1796 |
+
"learning_rate": 0.00012347560975609756,
|
| 1797 |
+
"loss": 1.3795,
|
| 1798 |
+
"step": 251
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 2.290909090909091,
|
| 1802 |
+
"grad_norm": 2.3511993885040283,
|
| 1803 |
+
"learning_rate": 0.00012195121951219512,
|
| 1804 |
+
"loss": 1.2534,
|
| 1805 |
+
"step": 252
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 2.3,
|
| 1809 |
+
"grad_norm": 2.6542067527770996,
|
| 1810 |
+
"learning_rate": 0.00012042682926829268,
|
| 1811 |
+
"loss": 1.6894,
|
| 1812 |
+
"step": 253
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 2.309090909090909,
|
| 1816 |
+
"grad_norm": 4.014543533325195,
|
| 1817 |
+
"learning_rate": 0.00011890243902439024,
|
| 1818 |
+
"loss": 1.9333,
|
| 1819 |
+
"step": 254
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 2.3181818181818183,
|
| 1823 |
+
"grad_norm": 2.828244924545288,
|
| 1824 |
+
"learning_rate": 0.0001173780487804878,
|
| 1825 |
+
"loss": 1.7024,
|
| 1826 |
+
"step": 255
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 2.327272727272727,
|
| 1830 |
+
"grad_norm": 2.9751951694488525,
|
| 1831 |
+
"learning_rate": 0.00011585365853658537,
|
| 1832 |
+
"loss": 1.7545,
|
| 1833 |
+
"step": 256
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 2.3363636363636364,
|
| 1837 |
+
"grad_norm": 2.876709461212158,
|
| 1838 |
+
"learning_rate": 0.00011432926829268293,
|
| 1839 |
+
"loss": 2.1827,
|
| 1840 |
+
"step": 257
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 2.3454545454545457,
|
| 1844 |
+
"grad_norm": 3.0717837810516357,
|
| 1845 |
+
"learning_rate": 0.00011280487804878049,
|
| 1846 |
+
"loss": 1.5924,
|
| 1847 |
+
"step": 258
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 2.3545454545454545,
|
| 1851 |
+
"grad_norm": 2.5759644508361816,
|
| 1852 |
+
"learning_rate": 0.00011128048780487805,
|
| 1853 |
+
"loss": 1.8342,
|
| 1854 |
+
"step": 259
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 2.3636363636363638,
|
| 1858 |
+
"grad_norm": 2.3989076614379883,
|
| 1859 |
+
"learning_rate": 0.00010975609756097561,
|
| 1860 |
+
"loss": 1.8479,
|
| 1861 |
+
"step": 260
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 2.3727272727272726,
|
| 1865 |
+
"grad_norm": 2.9248263835906982,
|
| 1866 |
+
"learning_rate": 0.00010823170731707317,
|
| 1867 |
+
"loss": 1.5602,
|
| 1868 |
+
"step": 261
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 2.381818181818182,
|
| 1872 |
+
"grad_norm": 2.715651512145996,
|
| 1873 |
+
"learning_rate": 0.00010670731707317073,
|
| 1874 |
+
"loss": 1.5377,
|
| 1875 |
+
"step": 262
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 2.390909090909091,
|
| 1879 |
+
"grad_norm": 2.504502534866333,
|
| 1880 |
+
"learning_rate": 0.00010518292682926829,
|
| 1881 |
+
"loss": 1.2146,
|
| 1882 |
+
"step": 263
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 2.4,
|
| 1886 |
+
"grad_norm": 2.516601085662842,
|
| 1887 |
+
"learning_rate": 0.00010365853658536585,
|
| 1888 |
+
"loss": 1.7834,
|
| 1889 |
+
"step": 264
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 2.409090909090909,
|
| 1893 |
+
"grad_norm": 2.362786293029785,
|
| 1894 |
+
"learning_rate": 0.00010213414634146341,
|
| 1895 |
+
"loss": 1.5664,
|
| 1896 |
+
"step": 265
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 2.418181818181818,
|
| 1900 |
+
"grad_norm": 2.057528257369995,
|
| 1901 |
+
"learning_rate": 0.00010060975609756098,
|
| 1902 |
+
"loss": 1.5126,
|
| 1903 |
+
"step": 266
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 2.4272727272727272,
|
| 1907 |
+
"grad_norm": 2.4843454360961914,
|
| 1908 |
+
"learning_rate": 9.908536585365854e-05,
|
| 1909 |
+
"loss": 1.883,
|
| 1910 |
+
"step": 267
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 2.4363636363636365,
|
| 1914 |
+
"grad_norm": 2.3680319786071777,
|
| 1915 |
+
"learning_rate": 9.75609756097561e-05,
|
| 1916 |
+
"loss": 1.521,
|
| 1917 |
+
"step": 268
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 2.4454545454545453,
|
| 1921 |
+
"grad_norm": 2.7291035652160645,
|
| 1922 |
+
"learning_rate": 9.603658536585366e-05,
|
| 1923 |
+
"loss": 1.7955,
|
| 1924 |
+
"step": 269
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 2.4545454545454546,
|
| 1928 |
+
"grad_norm": 2.395080327987671,
|
| 1929 |
+
"learning_rate": 9.451219512195122e-05,
|
| 1930 |
+
"loss": 1.7271,
|
| 1931 |
+
"step": 270
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 2.463636363636364,
|
| 1935 |
+
"grad_norm": 2.8394501209259033,
|
| 1936 |
+
"learning_rate": 9.298780487804878e-05,
|
| 1937 |
+
"loss": 1.5939,
|
| 1938 |
+
"step": 271
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 2.4727272727272727,
|
| 1942 |
+
"grad_norm": 2.4888384342193604,
|
| 1943 |
+
"learning_rate": 9.146341463414634e-05,
|
| 1944 |
+
"loss": 1.282,
|
| 1945 |
+
"step": 272
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 2.481818181818182,
|
| 1949 |
+
"grad_norm": 2.417750835418701,
|
| 1950 |
+
"learning_rate": 8.99390243902439e-05,
|
| 1951 |
+
"loss": 1.4742,
|
| 1952 |
+
"step": 273
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 2.4909090909090907,
|
| 1956 |
+
"grad_norm": 2.7631969451904297,
|
| 1957 |
+
"learning_rate": 8.841463414634146e-05,
|
| 1958 |
+
"loss": 1.7823,
|
| 1959 |
+
"step": 274
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 2.5,
|
| 1963 |
+
"grad_norm": 2.7598719596862793,
|
| 1964 |
+
"learning_rate": 8.689024390243902e-05,
|
| 1965 |
+
"loss": 1.7852,
|
| 1966 |
+
"step": 275
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 2.509090909090909,
|
| 1970 |
+
"grad_norm": 2.4489023685455322,
|
| 1971 |
+
"learning_rate": 8.53658536585366e-05,
|
| 1972 |
+
"loss": 1.4942,
|
| 1973 |
+
"step": 276
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 2.518181818181818,
|
| 1977 |
+
"grad_norm": 2.320030927658081,
|
| 1978 |
+
"learning_rate": 8.384146341463415e-05,
|
| 1979 |
+
"loss": 1.5197,
|
| 1980 |
+
"step": 277
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 2.5272727272727273,
|
| 1984 |
+
"grad_norm": 2.592423677444458,
|
| 1985 |
+
"learning_rate": 8.231707317073171e-05,
|
| 1986 |
+
"loss": 1.7495,
|
| 1987 |
+
"step": 278
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.536363636363636,
|
| 1991 |
+
"grad_norm": 2.7762107849121094,
|
| 1992 |
+
"learning_rate": 8.079268292682927e-05,
|
| 1993 |
+
"loss": 1.9257,
|
| 1994 |
+
"step": 279
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.5454545454545454,
|
| 1998 |
+
"grad_norm": 2.527858018875122,
|
| 1999 |
+
"learning_rate": 7.926829268292683e-05,
|
| 2000 |
+
"loss": 1.5523,
|
| 2001 |
+
"step": 280
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 2.5545454545454547,
|
| 2005 |
+
"grad_norm": 3.0844714641571045,
|
| 2006 |
+
"learning_rate": 7.774390243902439e-05,
|
| 2007 |
+
"loss": 1.5701,
|
| 2008 |
+
"step": 281
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 2.5636363636363635,
|
| 2012 |
+
"grad_norm": 2.9077203273773193,
|
| 2013 |
+
"learning_rate": 7.621951219512195e-05,
|
| 2014 |
+
"loss": 1.4133,
|
| 2015 |
+
"step": 282
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 2.5727272727272728,
|
| 2019 |
+
"grad_norm": 3.1426498889923096,
|
| 2020 |
+
"learning_rate": 7.469512195121951e-05,
|
| 2021 |
+
"loss": 1.6216,
|
| 2022 |
+
"step": 283
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 2.581818181818182,
|
| 2026 |
+
"grad_norm": 3.0162813663482666,
|
| 2027 |
+
"learning_rate": 7.317073170731707e-05,
|
| 2028 |
+
"loss": 1.6784,
|
| 2029 |
+
"step": 284
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 2.590909090909091,
|
| 2033 |
+
"grad_norm": 2.502703905105591,
|
| 2034 |
+
"learning_rate": 7.164634146341463e-05,
|
| 2035 |
+
"loss": 1.6971,
|
| 2036 |
+
"step": 285
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 2.6,
|
| 2040 |
+
"grad_norm": 2.4731063842773438,
|
| 2041 |
+
"learning_rate": 7.01219512195122e-05,
|
| 2042 |
+
"loss": 1.4637,
|
| 2043 |
+
"step": 286
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 2.6090909090909093,
|
| 2047 |
+
"grad_norm": 2.648430109024048,
|
| 2048 |
+
"learning_rate": 6.859756097560976e-05,
|
| 2049 |
+
"loss": 1.5027,
|
| 2050 |
+
"step": 287
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 2.618181818181818,
|
| 2054 |
+
"grad_norm": 3.18878173828125,
|
| 2055 |
+
"learning_rate": 6.707317073170732e-05,
|
| 2056 |
+
"loss": 1.8242,
|
| 2057 |
+
"step": 288
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 2.6272727272727274,
|
| 2061 |
+
"grad_norm": 2.5465493202209473,
|
| 2062 |
+
"learning_rate": 6.554878048780488e-05,
|
| 2063 |
+
"loss": 1.4872,
|
| 2064 |
+
"step": 289
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 2.6363636363636362,
|
| 2068 |
+
"grad_norm": 2.4700820446014404,
|
| 2069 |
+
"learning_rate": 6.402439024390244e-05,
|
| 2070 |
+
"loss": 1.7537,
|
| 2071 |
+
"step": 290
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 2.6454545454545455,
|
| 2075 |
+
"grad_norm": 3.4680936336517334,
|
| 2076 |
+
"learning_rate": 6.25e-05,
|
| 2077 |
+
"loss": 1.8912,
|
| 2078 |
+
"step": 291
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 2.6545454545454543,
|
| 2082 |
+
"grad_norm": 3.104785442352295,
|
| 2083 |
+
"learning_rate": 6.097560975609756e-05,
|
| 2084 |
+
"loss": 2.276,
|
| 2085 |
+
"step": 292
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 2.6636363636363636,
|
| 2089 |
+
"grad_norm": 3.0287201404571533,
|
| 2090 |
+
"learning_rate": 5.945121951219512e-05,
|
| 2091 |
+
"loss": 1.6728,
|
| 2092 |
+
"step": 293
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 2.672727272727273,
|
| 2096 |
+
"grad_norm": 2.384228229522705,
|
| 2097 |
+
"learning_rate": 5.792682926829269e-05,
|
| 2098 |
+
"loss": 1.6343,
|
| 2099 |
+
"step": 294
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 2.6818181818181817,
|
| 2103 |
+
"grad_norm": 2.866724967956543,
|
| 2104 |
+
"learning_rate": 5.6402439024390247e-05,
|
| 2105 |
+
"loss": 2.0956,
|
| 2106 |
+
"step": 295
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 2.690909090909091,
|
| 2110 |
+
"grad_norm": 2.9918506145477295,
|
| 2111 |
+
"learning_rate": 5.4878048780487806e-05,
|
| 2112 |
+
"loss": 1.7989,
|
| 2113 |
+
"step": 296
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 2.7,
|
| 2117 |
+
"grad_norm": 2.5096092224121094,
|
| 2118 |
+
"learning_rate": 5.3353658536585366e-05,
|
| 2119 |
+
"loss": 1.6828,
|
| 2120 |
+
"step": 297
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 2.709090909090909,
|
| 2124 |
+
"grad_norm": 2.7829229831695557,
|
| 2125 |
+
"learning_rate": 5.1829268292682925e-05,
|
| 2126 |
+
"loss": 1.4211,
|
| 2127 |
+
"step": 298
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 2.7181818181818183,
|
| 2131 |
+
"grad_norm": 2.250296115875244,
|
| 2132 |
+
"learning_rate": 5.030487804878049e-05,
|
| 2133 |
+
"loss": 1.4267,
|
| 2134 |
+
"step": 299
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 2.7272727272727275,
|
| 2138 |
+
"grad_norm": 3.163660764694214,
|
| 2139 |
+
"learning_rate": 4.878048780487805e-05,
|
| 2140 |
+
"loss": 2.1689,
|
| 2141 |
+
"step": 300
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 2.7363636363636363,
|
| 2145 |
+
"grad_norm": 2.386986255645752,
|
| 2146 |
+
"learning_rate": 4.725609756097561e-05,
|
| 2147 |
+
"loss": 1.4535,
|
| 2148 |
+
"step": 301
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 2.7454545454545456,
|
| 2152 |
+
"grad_norm": 2.807040214538574,
|
| 2153 |
+
"learning_rate": 4.573170731707317e-05,
|
| 2154 |
+
"loss": 1.5864,
|
| 2155 |
+
"step": 302
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 2.7545454545454544,
|
| 2159 |
+
"grad_norm": 3.6512951850891113,
|
| 2160 |
+
"learning_rate": 4.420731707317073e-05,
|
| 2161 |
+
"loss": 1.6136,
|
| 2162 |
+
"step": 303
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 2.7636363636363637,
|
| 2166 |
+
"grad_norm": 2.888395071029663,
|
| 2167 |
+
"learning_rate": 4.26829268292683e-05,
|
| 2168 |
+
"loss": 1.5037,
|
| 2169 |
+
"step": 304
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 2.7727272727272725,
|
| 2173 |
+
"grad_norm": 2.2506160736083984,
|
| 2174 |
+
"learning_rate": 4.1158536585365856e-05,
|
| 2175 |
+
"loss": 1.2207,
|
| 2176 |
+
"step": 305
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 2.7818181818181817,
|
| 2180 |
+
"grad_norm": 2.5099334716796875,
|
| 2181 |
+
"learning_rate": 3.9634146341463416e-05,
|
| 2182 |
+
"loss": 1.6804,
|
| 2183 |
+
"step": 306
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 2.790909090909091,
|
| 2187 |
+
"grad_norm": 2.87251615524292,
|
| 2188 |
+
"learning_rate": 3.8109756097560976e-05,
|
| 2189 |
+
"loss": 1.8993,
|
| 2190 |
+
"step": 307
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 2.8,
|
| 2194 |
+
"grad_norm": 2.648142099380493,
|
| 2195 |
+
"learning_rate": 3.6585365853658535e-05,
|
| 2196 |
+
"loss": 1.5677,
|
| 2197 |
+
"step": 308
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 2.809090909090909,
|
| 2201 |
+
"grad_norm": 3.0312211513519287,
|
| 2202 |
+
"learning_rate": 3.50609756097561e-05,
|
| 2203 |
+
"loss": 2.1024,
|
| 2204 |
+
"step": 309
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 2.8181818181818183,
|
| 2208 |
+
"grad_norm": 2.32504940032959,
|
| 2209 |
+
"learning_rate": 3.353658536585366e-05,
|
| 2210 |
+
"loss": 1.498,
|
| 2211 |
+
"step": 310
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 2.827272727272727,
|
| 2215 |
+
"grad_norm": 2.7433340549468994,
|
| 2216 |
+
"learning_rate": 3.201219512195122e-05,
|
| 2217 |
+
"loss": 2.0186,
|
| 2218 |
+
"step": 311
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 2.8363636363636364,
|
| 2222 |
+
"grad_norm": 2.5491738319396973,
|
| 2223 |
+
"learning_rate": 3.048780487804878e-05,
|
| 2224 |
+
"loss": 1.5459,
|
| 2225 |
+
"step": 312
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 2.8454545454545457,
|
| 2229 |
+
"grad_norm": 3.0771000385284424,
|
| 2230 |
+
"learning_rate": 2.8963414634146343e-05,
|
| 2231 |
+
"loss": 1.8847,
|
| 2232 |
+
"step": 313
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 2.8545454545454545,
|
| 2236 |
+
"grad_norm": 2.719658851623535,
|
| 2237 |
+
"learning_rate": 2.7439024390243903e-05,
|
| 2238 |
+
"loss": 1.6282,
|
| 2239 |
+
"step": 314
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 2.8636363636363638,
|
| 2243 |
+
"grad_norm": 2.6213059425354004,
|
| 2244 |
+
"learning_rate": 2.5914634146341463e-05,
|
| 2245 |
+
"loss": 1.3235,
|
| 2246 |
+
"step": 315
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 2.8727272727272726,
|
| 2250 |
+
"grad_norm": 2.4952800273895264,
|
| 2251 |
+
"learning_rate": 2.4390243902439026e-05,
|
| 2252 |
+
"loss": 1.6865,
|
| 2253 |
+
"step": 316
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 2.881818181818182,
|
| 2257 |
+
"grad_norm": 2.896984577178955,
|
| 2258 |
+
"learning_rate": 2.2865853658536585e-05,
|
| 2259 |
+
"loss": 1.5933,
|
| 2260 |
+
"step": 317
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 2.8909090909090907,
|
| 2264 |
+
"grad_norm": 2.54345965385437,
|
| 2265 |
+
"learning_rate": 2.134146341463415e-05,
|
| 2266 |
+
"loss": 1.9299,
|
| 2267 |
+
"step": 318
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 2.9,
|
| 2271 |
+
"grad_norm": 2.8932416439056396,
|
| 2272 |
+
"learning_rate": 1.9817073170731708e-05,
|
| 2273 |
+
"loss": 2.0065,
|
| 2274 |
+
"step": 319
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 2.909090909090909,
|
| 2278 |
+
"grad_norm": 2.6085596084594727,
|
| 2279 |
+
"learning_rate": 1.8292682926829268e-05,
|
| 2280 |
+
"loss": 1.3924,
|
| 2281 |
+
"step": 320
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 2.918181818181818,
|
| 2285 |
+
"grad_norm": 2.9155259132385254,
|
| 2286 |
+
"learning_rate": 1.676829268292683e-05,
|
| 2287 |
+
"loss": 2.0032,
|
| 2288 |
+
"step": 321
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 2.9272727272727272,
|
| 2292 |
+
"grad_norm": 2.5170652866363525,
|
| 2293 |
+
"learning_rate": 1.524390243902439e-05,
|
| 2294 |
+
"loss": 1.3955,
|
| 2295 |
+
"step": 322
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 2.9363636363636365,
|
| 2299 |
+
"grad_norm": 2.5169925689697266,
|
| 2300 |
+
"learning_rate": 1.3719512195121952e-05,
|
| 2301 |
+
"loss": 1.5228,
|
| 2302 |
+
"step": 323
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 2.9454545454545453,
|
| 2306 |
+
"grad_norm": 2.683560848236084,
|
| 2307 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 2308 |
+
"loss": 1.6762,
|
| 2309 |
+
"step": 324
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 2.9545454545454546,
|
| 2313 |
+
"grad_norm": 2.675593614578247,
|
| 2314 |
+
"learning_rate": 1.0670731707317074e-05,
|
| 2315 |
+
"loss": 1.6192,
|
| 2316 |
+
"step": 325
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 2.963636363636364,
|
| 2320 |
+
"grad_norm": 2.860233783721924,
|
| 2321 |
+
"learning_rate": 9.146341463414634e-06,
|
| 2322 |
+
"loss": 1.9632,
|
| 2323 |
+
"step": 326
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 2.9727272727272727,
|
| 2327 |
+
"grad_norm": 2.5503525733947754,
|
| 2328 |
+
"learning_rate": 7.621951219512195e-06,
|
| 2329 |
+
"loss": 1.4166,
|
| 2330 |
+
"step": 327
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 2.981818181818182,
|
| 2334 |
+
"grad_norm": 2.5347251892089844,
|
| 2335 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 2336 |
+
"loss": 1.4993,
|
| 2337 |
+
"step": 328
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 2.990909090909091,
|
| 2341 |
+
"grad_norm": 2.628443479537964,
|
| 2342 |
+
"learning_rate": 4.573170731707317e-06,
|
| 2343 |
+
"loss": 1.4424,
|
| 2344 |
+
"step": 329
|
| 2345 |
+
},
|
| 2346 |
+
{
|
| 2347 |
+
"epoch": 3.0,
|
| 2348 |
+
"grad_norm": 2.5161614418029785,
|
| 2349 |
+
"learning_rate": 3.0487804878048782e-06,
|
| 2350 |
+
"loss": 1.5952,
|
| 2351 |
+
"step": 330
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 3.0,
|
| 2355 |
+
"eval_f1": 0.8942,
|
| 2356 |
+
"eval_gen_len": 49.4091,
|
| 2357 |
+
"eval_loss": 1.7933717966079712,
|
| 2358 |
+
"eval_precision": 0.8941,
|
| 2359 |
+
"eval_recall": 0.8945,
|
| 2360 |
+
"eval_rouge1": 0.4708,
|
| 2361 |
+
"eval_rouge2": 0.2246,
|
| 2362 |
+
"eval_rougeL": 0.3984,
|
| 2363 |
+
"eval_rougeLsum": 0.4357,
|
| 2364 |
+
"eval_runtime": 47.9405,
|
| 2365 |
+
"eval_samples_per_second": 2.295,
|
| 2366 |
+
"eval_steps_per_second": 0.292,
|
| 2367 |
+
"step": 330
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 3.0,
|
| 2371 |
+
"step": 330,
|
| 2372 |
+
"total_flos": 2506179136462848.0,
|
| 2373 |
+
"train_loss": 1.8787952170227513,
|
| 2374 |
+
"train_runtime": 633.4063,
|
| 2375 |
+
"train_samples_per_second": 4.163,
|
| 2376 |
+
"train_steps_per_second": 0.521
|
| 2377 |
+
}
|
| 2378 |
+
],
|
| 2379 |
+
"logging_steps": 1,
|
| 2380 |
+
"max_steps": 330,
|
| 2381 |
+
"num_input_tokens_seen": 0,
|
| 2382 |
+
"num_train_epochs": 3,
|
| 2383 |
+
"save_steps": 500,
|
| 2384 |
+
"stateful_callbacks": {
|
| 2385 |
+
"TrainerControl": {
|
| 2386 |
+
"args": {
|
| 2387 |
+
"should_epoch_stop": false,
|
| 2388 |
+
"should_evaluate": false,
|
| 2389 |
+
"should_log": false,
|
| 2390 |
+
"should_save": true,
|
| 2391 |
+
"should_training_stop": true
|
| 2392 |
+
},
|
| 2393 |
+
"attributes": {}
|
| 2394 |
+
}
|
| 2395 |
+
},
|
| 2396 |
+
"total_flos": 2506179136462848.0,
|
| 2397 |
+
"train_batch_size": 8,
|
| 2398 |
+
"trial_name": null,
|
| 2399 |
+
"trial_params": null
|
| 2400 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd29122046c1ee570d0e318f04e7039880cdec1822e726a17732c7b8ecd88b54
|
| 3 |
+
size 5432
|