Upload folder using huggingface_hub
Browse files- README.md +78 -0
- all_results.json +22 -0
- config.json +72 -0
- eval_results.json +16 -0
- model.safetensors +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +937 -0
- train_results.json +9 -0
- trainer_state.json +941 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
base_model: google-t5/t5-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- glue
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: MNLI
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Text Classification
|
| 16 |
+
type: text-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: GLUE MNLI
|
| 19 |
+
type: glue
|
| 20 |
+
args: mnli
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.8685923515052889
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# MNLI
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on the GLUE MNLI dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.4611
|
| 35 |
+
- Accuracy: 0.8686
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 5e-05
|
| 55 |
+
- train_batch_size: 64
|
| 56 |
+
- eval_batch_size: 64
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 5.0
|
| 61 |
+
|
| 62 |
+
### Training results
|
| 63 |
+
|
| 64 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 65 |
+
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
|
| 66 |
+
| 0.3694 | 1.0 | 12272 | 0.8565 | 0.3870 |
|
| 67 |
+
| 0.303 | 2.0 | 24544 | 0.8651 | 0.3789 |
|
| 68 |
+
| 0.2549 | 3.0 | 36816 | 0.8649 | 0.4213 |
|
| 69 |
+
| 0.2118 | 4.0 | 49088 | 0.8657 | 0.4461 |
|
| 70 |
+
| 0.1733 | 5.0 | 61360 | 0.8659 | 0.4700 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.43.3
|
| 76 |
+
- Pytorch 1.11.0+cu113
|
| 77 |
+
- Datasets 2.20.0
|
| 78 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"epoch_mm": 5.0,
|
| 4 |
+
"eval_accuracy": 0.8658176260825268,
|
| 5 |
+
"eval_accuracy_mm": 0.8685923515052889,
|
| 6 |
+
"eval_loss": 0.4699692726135254,
|
| 7 |
+
"eval_loss_mm": 0.46111756563186646,
|
| 8 |
+
"eval_runtime": 20.1604,
|
| 9 |
+
"eval_runtime_mm": 16.9914,
|
| 10 |
+
"eval_samples": 9815,
|
| 11 |
+
"eval_samples_mm": 9832,
|
| 12 |
+
"eval_samples_per_second": 486.845,
|
| 13 |
+
"eval_samples_per_second_mm": 578.646,
|
| 14 |
+
"eval_steps_per_second": 7.639,
|
| 15 |
+
"eval_steps_per_second_mm": 9.063,
|
| 16 |
+
"total_flos": 2.998178041960627e+17,
|
| 17 |
+
"train_loss": 0.0,
|
| 18 |
+
"train_runtime": 0.2558,
|
| 19 |
+
"train_samples": 392702,
|
| 20 |
+
"train_samples_per_second": 7675471.049,
|
| 21 |
+
"train_steps_per_second": 239859.692
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"finetuning_task": "mnli",
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1",
|
| 19 |
+
"2": "LABEL_2"
|
| 20 |
+
},
|
| 21 |
+
"initializer_factor": 1.0,
|
| 22 |
+
"is_encoder_decoder": true,
|
| 23 |
+
"is_gated_act": false,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"contradiction": 2,
|
| 26 |
+
"entailment": 0,
|
| 27 |
+
"neutral": 1
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_epsilon": 1e-06,
|
| 30 |
+
"model_type": "t5",
|
| 31 |
+
"n_positions": 512,
|
| 32 |
+
"num_decoder_layers": 12,
|
| 33 |
+
"num_heads": 12,
|
| 34 |
+
"num_layers": 12,
|
| 35 |
+
"output_past": true,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"relative_attention_max_distance": 128,
|
| 38 |
+
"relative_attention_num_buckets": 32,
|
| 39 |
+
"task_specific_params": {
|
| 40 |
+
"summarization": {
|
| 41 |
+
"early_stopping": true,
|
| 42 |
+
"length_penalty": 2.0,
|
| 43 |
+
"max_length": 200,
|
| 44 |
+
"min_length": 30,
|
| 45 |
+
"no_repeat_ngram_size": 3,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "summarize: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_de": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to German: "
|
| 54 |
+
},
|
| 55 |
+
"translation_en_to_fr": {
|
| 56 |
+
"early_stopping": true,
|
| 57 |
+
"max_length": 300,
|
| 58 |
+
"num_beams": 4,
|
| 59 |
+
"prefix": "translate English to French: "
|
| 60 |
+
},
|
| 61 |
+
"translation_en_to_ro": {
|
| 62 |
+
"early_stopping": true,
|
| 63 |
+
"max_length": 300,
|
| 64 |
+
"num_beams": 4,
|
| 65 |
+
"prefix": "translate English to Romanian: "
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"torch_dtype": "float32",
|
| 69 |
+
"transformers_version": "4.43.3",
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 32128
|
| 72 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"epoch_mm": 5.0,
|
| 4 |
+
"eval_accuracy": 0.8658176260825268,
|
| 5 |
+
"eval_accuracy_mm": 0.8685923515052889,
|
| 6 |
+
"eval_loss": 0.4699692726135254,
|
| 7 |
+
"eval_loss_mm": 0.46111756563186646,
|
| 8 |
+
"eval_runtime": 20.1604,
|
| 9 |
+
"eval_runtime_mm": 16.9914,
|
| 10 |
+
"eval_samples": 9815,
|
| 11 |
+
"eval_samples_mm": 9832,
|
| 12 |
+
"eval_samples_per_second": 486.845,
|
| 13 |
+
"eval_samples_per_second_mm": 578.646,
|
| 14 |
+
"eval_steps_per_second": 7.639,
|
| 15 |
+
"eval_steps_per_second_mm": 9.063
|
| 16 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f8a3cedda0c6b6933da4d5f11fef3919dc5154520dda270be87e7d79630c37a
|
| 3 |
+
size 894019788
|
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": "<pad>",
|
| 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": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 2.998178041960627e+17,
|
| 4 |
+
"train_loss": 0.0,
|
| 5 |
+
"train_runtime": 0.2558,
|
| 6 |
+
"train_samples": 392702,
|
| 7 |
+
"train_samples_per_second": 7675471.049,
|
| 8 |
+
"train_steps_per_second": 239859.692
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,941 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8659195109526235,
|
| 3 |
+
"best_model_checkpoint": "output/fine_tuned/t5-base/MNLI/checkpoint-61360",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 61360,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04074315514993481,
|
| 13 |
+
"grad_norm": 6.468524932861328,
|
| 14 |
+
"learning_rate": 4.9796284224250325e-05,
|
| 15 |
+
"loss": 0.8428,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08148631029986962,
|
| 20 |
+
"grad_norm": 4.806485652923584,
|
| 21 |
+
"learning_rate": 4.9592568448500655e-05,
|
| 22 |
+
"loss": 0.59,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12222946544980444,
|
| 27 |
+
"grad_norm": 5.188954830169678,
|
| 28 |
+
"learning_rate": 4.938885267275098e-05,
|
| 29 |
+
"loss": 0.5275,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16297262059973924,
|
| 34 |
+
"grad_norm": 3.7646172046661377,
|
| 35 |
+
"learning_rate": 4.918513689700131e-05,
|
| 36 |
+
"loss": 0.508,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.20371577574967406,
|
| 41 |
+
"grad_norm": 5.518546104431152,
|
| 42 |
+
"learning_rate": 4.898142112125163e-05,
|
| 43 |
+
"loss": 0.4712,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24445893089960888,
|
| 48 |
+
"grad_norm": 4.250612258911133,
|
| 49 |
+
"learning_rate": 4.877770534550195e-05,
|
| 50 |
+
"loss": 0.4501,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28520208604954367,
|
| 55 |
+
"grad_norm": 5.0553812980651855,
|
| 56 |
+
"learning_rate": 4.857398956975228e-05,
|
| 57 |
+
"loss": 0.446,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3259452411994785,
|
| 62 |
+
"grad_norm": 3.5348777770996094,
|
| 63 |
+
"learning_rate": 4.8370273794002606e-05,
|
| 64 |
+
"loss": 0.429,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3666883963494133,
|
| 69 |
+
"grad_norm": 2.972283363342285,
|
| 70 |
+
"learning_rate": 4.8166558018252936e-05,
|
| 71 |
+
"loss": 0.4305,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4074315514993481,
|
| 76 |
+
"grad_norm": 2.9549307823181152,
|
| 77 |
+
"learning_rate": 4.7962842242503265e-05,
|
| 78 |
+
"loss": 0.4194,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44817470664928294,
|
| 83 |
+
"grad_norm": 3.8171303272247314,
|
| 84 |
+
"learning_rate": 4.775912646675359e-05,
|
| 85 |
+
"loss": 0.4122,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48891786179921776,
|
| 90 |
+
"grad_norm": 1.5783547163009644,
|
| 91 |
+
"learning_rate": 4.755541069100392e-05,
|
| 92 |
+
"loss": 0.4059,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5296610169491526,
|
| 97 |
+
"grad_norm": 3.6074378490448,
|
| 98 |
+
"learning_rate": 4.735169491525424e-05,
|
| 99 |
+
"loss": 0.4043,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5704041720990873,
|
| 104 |
+
"grad_norm": 2.160903215408325,
|
| 105 |
+
"learning_rate": 4.7147979139504564e-05,
|
| 106 |
+
"loss": 0.3909,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6111473272490222,
|
| 111 |
+
"grad_norm": 3.1185765266418457,
|
| 112 |
+
"learning_rate": 4.694426336375489e-05,
|
| 113 |
+
"loss": 0.3941,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.651890482398957,
|
| 118 |
+
"grad_norm": 2.998476982116699,
|
| 119 |
+
"learning_rate": 4.6740547588005216e-05,
|
| 120 |
+
"loss": 0.3964,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6926336375488917,
|
| 125 |
+
"grad_norm": 5.319198131561279,
|
| 126 |
+
"learning_rate": 4.6536831812255546e-05,
|
| 127 |
+
"loss": 0.3886,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7333767926988266,
|
| 132 |
+
"grad_norm": 3.9432480335235596,
|
| 133 |
+
"learning_rate": 4.633311603650587e-05,
|
| 134 |
+
"loss": 0.3969,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7741199478487614,
|
| 139 |
+
"grad_norm": 5.180667400360107,
|
| 140 |
+
"learning_rate": 4.612940026075619e-05,
|
| 141 |
+
"loss": 0.3833,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8148631029986962,
|
| 146 |
+
"grad_norm": 3.2222518920898438,
|
| 147 |
+
"learning_rate": 4.592568448500652e-05,
|
| 148 |
+
"loss": 0.3714,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.855606258148631,
|
| 153 |
+
"grad_norm": 3.999013900756836,
|
| 154 |
+
"learning_rate": 4.5721968709256844e-05,
|
| 155 |
+
"loss": 0.3853,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8963494132985659,
|
| 160 |
+
"grad_norm": 3.423118829727173,
|
| 161 |
+
"learning_rate": 4.5518252933507174e-05,
|
| 162 |
+
"loss": 0.3772,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9370925684485006,
|
| 167 |
+
"grad_norm": 3.744582176208496,
|
| 168 |
+
"learning_rate": 4.53145371577575e-05,
|
| 169 |
+
"loss": 0.3753,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9778357235984355,
|
| 174 |
+
"grad_norm": 4.6033806800842285,
|
| 175 |
+
"learning_rate": 4.511082138200782e-05,
|
| 176 |
+
"loss": 0.3694,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"eval_accuracy": 0.8565461029037188,
|
| 182 |
+
"eval_loss": 0.38699737191200256,
|
| 183 |
+
"eval_runtime": 64.7816,
|
| 184 |
+
"eval_samples_per_second": 151.509,
|
| 185 |
+
"eval_steps_per_second": 18.941,
|
| 186 |
+
"step": 12272
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.0185788787483703,
|
| 190 |
+
"grad_norm": 4.516230583190918,
|
| 191 |
+
"learning_rate": 4.490710560625815e-05,
|
| 192 |
+
"loss": 0.3444,
|
| 193 |
+
"step": 12500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.0593220338983051,
|
| 197 |
+
"grad_norm": 4.428933620452881,
|
| 198 |
+
"learning_rate": 4.470338983050847e-05,
|
| 199 |
+
"loss": 0.3135,
|
| 200 |
+
"step": 13000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.1000651890482398,
|
| 204 |
+
"grad_norm": 4.436412334442139,
|
| 205 |
+
"learning_rate": 4.44996740547588e-05,
|
| 206 |
+
"loss": 0.3225,
|
| 207 |
+
"step": 13500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.1408083441981747,
|
| 211 |
+
"grad_norm": 4.193423271179199,
|
| 212 |
+
"learning_rate": 4.429595827900913e-05,
|
| 213 |
+
"loss": 0.3146,
|
| 214 |
+
"step": 14000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.1815514993481095,
|
| 218 |
+
"grad_norm": 4.420684814453125,
|
| 219 |
+
"learning_rate": 4.4092242503259455e-05,
|
| 220 |
+
"loss": 0.3277,
|
| 221 |
+
"step": 14500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.2222946544980444,
|
| 225 |
+
"grad_norm": 2.8461813926696777,
|
| 226 |
+
"learning_rate": 4.3888526727509784e-05,
|
| 227 |
+
"loss": 0.3134,
|
| 228 |
+
"step": 15000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.263037809647979,
|
| 232 |
+
"grad_norm": 2.6924009323120117,
|
| 233 |
+
"learning_rate": 4.368481095176011e-05,
|
| 234 |
+
"loss": 0.3185,
|
| 235 |
+
"step": 15500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.303780964797914,
|
| 239 |
+
"grad_norm": 3.6353909969329834,
|
| 240 |
+
"learning_rate": 4.348109517601043e-05,
|
| 241 |
+
"loss": 0.3166,
|
| 242 |
+
"step": 16000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.3445241199478488,
|
| 246 |
+
"grad_norm": 4.928586959838867,
|
| 247 |
+
"learning_rate": 4.327737940026076e-05,
|
| 248 |
+
"loss": 0.3165,
|
| 249 |
+
"step": 16500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.3852672750977835,
|
| 253 |
+
"grad_norm": 5.045453071594238,
|
| 254 |
+
"learning_rate": 4.307366362451108e-05,
|
| 255 |
+
"loss": 0.3196,
|
| 256 |
+
"step": 17000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.4260104302477183,
|
| 260 |
+
"grad_norm": 2.8752036094665527,
|
| 261 |
+
"learning_rate": 4.286994784876141e-05,
|
| 262 |
+
"loss": 0.3232,
|
| 263 |
+
"step": 17500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.4667535853976532,
|
| 267 |
+
"grad_norm": 2.486584424972534,
|
| 268 |
+
"learning_rate": 4.2666232073011735e-05,
|
| 269 |
+
"loss": 0.3153,
|
| 270 |
+
"step": 18000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.5074967405475879,
|
| 274 |
+
"grad_norm": 3.719909429550171,
|
| 275 |
+
"learning_rate": 4.2462516297262065e-05,
|
| 276 |
+
"loss": 0.3149,
|
| 277 |
+
"step": 18500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.548239895697523,
|
| 281 |
+
"grad_norm": 2.8027002811431885,
|
| 282 |
+
"learning_rate": 4.225880052151239e-05,
|
| 283 |
+
"loss": 0.3176,
|
| 284 |
+
"step": 19000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.5889830508474576,
|
| 288 |
+
"grad_norm": 5.058602333068848,
|
| 289 |
+
"learning_rate": 4.205508474576271e-05,
|
| 290 |
+
"loss": 0.3148,
|
| 291 |
+
"step": 19500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.6297262059973925,
|
| 295 |
+
"grad_norm": 3.070186138153076,
|
| 296 |
+
"learning_rate": 4.185136897001304e-05,
|
| 297 |
+
"loss": 0.3154,
|
| 298 |
+
"step": 20000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.6704693611473274,
|
| 302 |
+
"grad_norm": 3.288327932357788,
|
| 303 |
+
"learning_rate": 4.164765319426336e-05,
|
| 304 |
+
"loss": 0.3175,
|
| 305 |
+
"step": 20500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.711212516297262,
|
| 309 |
+
"grad_norm": 3.934622049331665,
|
| 310 |
+
"learning_rate": 4.144393741851369e-05,
|
| 311 |
+
"loss": 0.3127,
|
| 312 |
+
"step": 21000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.7519556714471969,
|
| 316 |
+
"grad_norm": 4.4335737228393555,
|
| 317 |
+
"learning_rate": 4.1240221642764016e-05,
|
| 318 |
+
"loss": 0.312,
|
| 319 |
+
"step": 21500
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.7926988265971318,
|
| 323 |
+
"grad_norm": 2.0218756198883057,
|
| 324 |
+
"learning_rate": 4.103650586701434e-05,
|
| 325 |
+
"loss": 0.31,
|
| 326 |
+
"step": 22000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.8334419817470664,
|
| 330 |
+
"grad_norm": 3.1556270122528076,
|
| 331 |
+
"learning_rate": 4.0832790091264675e-05,
|
| 332 |
+
"loss": 0.3203,
|
| 333 |
+
"step": 22500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.8741851368970013,
|
| 337 |
+
"grad_norm": 4.388118267059326,
|
| 338 |
+
"learning_rate": 4.0629074315515e-05,
|
| 339 |
+
"loss": 0.3099,
|
| 340 |
+
"step": 23000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.9149282920469362,
|
| 344 |
+
"grad_norm": 1.511881709098816,
|
| 345 |
+
"learning_rate": 4.042535853976532e-05,
|
| 346 |
+
"loss": 0.3148,
|
| 347 |
+
"step": 23500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.9556714471968708,
|
| 351 |
+
"grad_norm": 1.853653073310852,
|
| 352 |
+
"learning_rate": 4.022164276401565e-05,
|
| 353 |
+
"loss": 0.3095,
|
| 354 |
+
"step": 24000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.996414602346806,
|
| 358 |
+
"grad_norm": 1.6253551244735718,
|
| 359 |
+
"learning_rate": 4.0017926988265974e-05,
|
| 360 |
+
"loss": 0.303,
|
| 361 |
+
"step": 24500
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.0,
|
| 365 |
+
"eval_accuracy": 0.8651044319918492,
|
| 366 |
+
"eval_loss": 0.37888792157173157,
|
| 367 |
+
"eval_runtime": 27.9558,
|
| 368 |
+
"eval_samples_per_second": 351.09,
|
| 369 |
+
"eval_steps_per_second": 43.891,
|
| 370 |
+
"step": 24544
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.0371577574967406,
|
| 374 |
+
"grad_norm": 3.7835922241210938,
|
| 375 |
+
"learning_rate": 3.98142112125163e-05,
|
| 376 |
+
"loss": 0.2552,
|
| 377 |
+
"step": 25000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.077900912646675,
|
| 381 |
+
"grad_norm": 3.147528886795044,
|
| 382 |
+
"learning_rate": 3.9610495436766626e-05,
|
| 383 |
+
"loss": 0.2401,
|
| 384 |
+
"step": 25500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.1186440677966103,
|
| 388 |
+
"grad_norm": 4.904528617858887,
|
| 389 |
+
"learning_rate": 3.940677966101695e-05,
|
| 390 |
+
"loss": 0.253,
|
| 391 |
+
"step": 26000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.159387222946545,
|
| 395 |
+
"grad_norm": 5.313526630401611,
|
| 396 |
+
"learning_rate": 3.920306388526728e-05,
|
| 397 |
+
"loss": 0.256,
|
| 398 |
+
"step": 26500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.2001303780964796,
|
| 402 |
+
"grad_norm": 1.7792415618896484,
|
| 403 |
+
"learning_rate": 3.89993481095176e-05,
|
| 404 |
+
"loss": 0.2486,
|
| 405 |
+
"step": 27000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.2408735332464147,
|
| 409 |
+
"grad_norm": 5.110089302062988,
|
| 410 |
+
"learning_rate": 3.879563233376793e-05,
|
| 411 |
+
"loss": 0.2411,
|
| 412 |
+
"step": 27500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.2816166883963493,
|
| 416 |
+
"grad_norm": 2.6529006958007812,
|
| 417 |
+
"learning_rate": 3.8591916558018254e-05,
|
| 418 |
+
"loss": 0.2588,
|
| 419 |
+
"step": 28000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.322359843546284,
|
| 423 |
+
"grad_norm": 5.450090408325195,
|
| 424 |
+
"learning_rate": 3.838820078226858e-05,
|
| 425 |
+
"loss": 0.2424,
|
| 426 |
+
"step": 28500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.363102998696219,
|
| 430 |
+
"grad_norm": 3.4213919639587402,
|
| 431 |
+
"learning_rate": 3.818448500651891e-05,
|
| 432 |
+
"loss": 0.2546,
|
| 433 |
+
"step": 29000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.4038461538461537,
|
| 437 |
+
"grad_norm": 4.965076923370361,
|
| 438 |
+
"learning_rate": 3.798076923076923e-05,
|
| 439 |
+
"loss": 0.2519,
|
| 440 |
+
"step": 29500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.444589308996089,
|
| 444 |
+
"grad_norm": 3.764460802078247,
|
| 445 |
+
"learning_rate": 3.777705345501956e-05,
|
| 446 |
+
"loss": 0.2529,
|
| 447 |
+
"step": 30000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.4853324641460235,
|
| 451 |
+
"grad_norm": 3.033212184906006,
|
| 452 |
+
"learning_rate": 3.757333767926988e-05,
|
| 453 |
+
"loss": 0.2559,
|
| 454 |
+
"step": 30500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.526075619295958,
|
| 458 |
+
"grad_norm": 2.535740613937378,
|
| 459 |
+
"learning_rate": 3.7369621903520205e-05,
|
| 460 |
+
"loss": 0.2587,
|
| 461 |
+
"step": 31000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.5668187744458932,
|
| 465 |
+
"grad_norm": 3.642535448074341,
|
| 466 |
+
"learning_rate": 3.716590612777054e-05,
|
| 467 |
+
"loss": 0.2509,
|
| 468 |
+
"step": 31500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.607561929595828,
|
| 472 |
+
"grad_norm": 5.233695030212402,
|
| 473 |
+
"learning_rate": 3.6962190352020865e-05,
|
| 474 |
+
"loss": 0.2471,
|
| 475 |
+
"step": 32000
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.648305084745763,
|
| 479 |
+
"grad_norm": 4.331786155700684,
|
| 480 |
+
"learning_rate": 3.675847457627119e-05,
|
| 481 |
+
"loss": 0.2569,
|
| 482 |
+
"step": 32500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.6890482398956976,
|
| 486 |
+
"grad_norm": 3.5510385036468506,
|
| 487 |
+
"learning_rate": 3.655475880052152e-05,
|
| 488 |
+
"loss": 0.2518,
|
| 489 |
+
"step": 33000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.7297913950456323,
|
| 493 |
+
"grad_norm": 4.476876258850098,
|
| 494 |
+
"learning_rate": 3.635104302477184e-05,
|
| 495 |
+
"loss": 0.2596,
|
| 496 |
+
"step": 33500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.770534550195567,
|
| 500 |
+
"grad_norm": 1.7541571855545044,
|
| 501 |
+
"learning_rate": 3.614732724902217e-05,
|
| 502 |
+
"loss": 0.2674,
|
| 503 |
+
"step": 34000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.811277705345502,
|
| 507 |
+
"grad_norm": 5.406097412109375,
|
| 508 |
+
"learning_rate": 3.594361147327249e-05,
|
| 509 |
+
"loss": 0.2611,
|
| 510 |
+
"step": 34500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.8520208604954367,
|
| 514 |
+
"grad_norm": 3.6985819339752197,
|
| 515 |
+
"learning_rate": 3.5739895697522816e-05,
|
| 516 |
+
"loss": 0.2485,
|
| 517 |
+
"step": 35000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.8927640156453718,
|
| 521 |
+
"grad_norm": 5.607602596282959,
|
| 522 |
+
"learning_rate": 3.5536179921773145e-05,
|
| 523 |
+
"loss": 0.2529,
|
| 524 |
+
"step": 35500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.9335071707953064,
|
| 528 |
+
"grad_norm": 2.735818862915039,
|
| 529 |
+
"learning_rate": 3.533246414602347e-05,
|
| 530 |
+
"loss": 0.2545,
|
| 531 |
+
"step": 36000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.974250325945241,
|
| 535 |
+
"grad_norm": 4.402085781097412,
|
| 536 |
+
"learning_rate": 3.51287483702738e-05,
|
| 537 |
+
"loss": 0.2549,
|
| 538 |
+
"step": 36500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.0,
|
| 542 |
+
"eval_accuracy": 0.8649006622516556,
|
| 543 |
+
"eval_loss": 0.4213252663612366,
|
| 544 |
+
"eval_runtime": 27.4712,
|
| 545 |
+
"eval_samples_per_second": 357.283,
|
| 546 |
+
"eval_steps_per_second": 44.665,
|
| 547 |
+
"step": 36816
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 3.014993481095176,
|
| 551 |
+
"grad_norm": 2.6076323986053467,
|
| 552 |
+
"learning_rate": 3.492503259452412e-05,
|
| 553 |
+
"loss": 0.2432,
|
| 554 |
+
"step": 37000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.055736636245111,
|
| 558 |
+
"grad_norm": 5.72471284866333,
|
| 559 |
+
"learning_rate": 3.4721316818774444e-05,
|
| 560 |
+
"loss": 0.2004,
|
| 561 |
+
"step": 37500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.0964797913950455,
|
| 565 |
+
"grad_norm": 2.282419443130493,
|
| 566 |
+
"learning_rate": 3.451760104302477e-05,
|
| 567 |
+
"loss": 0.1961,
|
| 568 |
+
"step": 38000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.1372229465449806,
|
| 572 |
+
"grad_norm": 6.373399257659912,
|
| 573 |
+
"learning_rate": 3.4313885267275096e-05,
|
| 574 |
+
"loss": 0.2047,
|
| 575 |
+
"step": 38500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.1779661016949152,
|
| 579 |
+
"grad_norm": 3.3030478954315186,
|
| 580 |
+
"learning_rate": 3.4110169491525426e-05,
|
| 581 |
+
"loss": 0.2051,
|
| 582 |
+
"step": 39000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.21870925684485,
|
| 586 |
+
"grad_norm": 3.459233283996582,
|
| 587 |
+
"learning_rate": 3.390645371577575e-05,
|
| 588 |
+
"loss": 0.2026,
|
| 589 |
+
"step": 39500
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.259452411994785,
|
| 593 |
+
"grad_norm": 6.500429153442383,
|
| 594 |
+
"learning_rate": 3.370273794002607e-05,
|
| 595 |
+
"loss": 0.1989,
|
| 596 |
+
"step": 40000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.3001955671447196,
|
| 600 |
+
"grad_norm": 2.9848804473876953,
|
| 601 |
+
"learning_rate": 3.349902216427641e-05,
|
| 602 |
+
"loss": 0.2092,
|
| 603 |
+
"step": 40500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.3409387222946547,
|
| 607 |
+
"grad_norm": 6.0977091789245605,
|
| 608 |
+
"learning_rate": 3.329530638852673e-05,
|
| 609 |
+
"loss": 0.2062,
|
| 610 |
+
"step": 41000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 3.3816818774445894,
|
| 614 |
+
"grad_norm": 6.147849082946777,
|
| 615 |
+
"learning_rate": 3.3091590612777054e-05,
|
| 616 |
+
"loss": 0.2065,
|
| 617 |
+
"step": 41500
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.422425032594524,
|
| 621 |
+
"grad_norm": 4.928431034088135,
|
| 622 |
+
"learning_rate": 3.2887874837027384e-05,
|
| 623 |
+
"loss": 0.2044,
|
| 624 |
+
"step": 42000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 3.463168187744459,
|
| 628 |
+
"grad_norm": 5.093155860900879,
|
| 629 |
+
"learning_rate": 3.2684159061277707e-05,
|
| 630 |
+
"loss": 0.2134,
|
| 631 |
+
"step": 42500
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 3.5039113428943938,
|
| 635 |
+
"grad_norm": 3.0888853073120117,
|
| 636 |
+
"learning_rate": 3.2480443285528036e-05,
|
| 637 |
+
"loss": 0.2114,
|
| 638 |
+
"step": 43000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.5446544980443284,
|
| 642 |
+
"grad_norm": 4.273815155029297,
|
| 643 |
+
"learning_rate": 3.227672750977836e-05,
|
| 644 |
+
"loss": 0.2122,
|
| 645 |
+
"step": 43500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.5853976531942635,
|
| 649 |
+
"grad_norm": 5.846683025360107,
|
| 650 |
+
"learning_rate": 3.207301173402868e-05,
|
| 651 |
+
"loss": 0.2053,
|
| 652 |
+
"step": 44000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.626140808344198,
|
| 656 |
+
"grad_norm": 6.744229316711426,
|
| 657 |
+
"learning_rate": 3.186929595827901e-05,
|
| 658 |
+
"loss": 0.2141,
|
| 659 |
+
"step": 44500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.666883963494133,
|
| 663 |
+
"grad_norm": 6.070234775543213,
|
| 664 |
+
"learning_rate": 3.1665580182529335e-05,
|
| 665 |
+
"loss": 0.2108,
|
| 666 |
+
"step": 45000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 3.707627118644068,
|
| 670 |
+
"grad_norm": 4.892887115478516,
|
| 671 |
+
"learning_rate": 3.1461864406779664e-05,
|
| 672 |
+
"loss": 0.2067,
|
| 673 |
+
"step": 45500
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 3.7483702737940026,
|
| 677 |
+
"grad_norm": 2.861110210418701,
|
| 678 |
+
"learning_rate": 3.125814863102999e-05,
|
| 679 |
+
"loss": 0.2022,
|
| 680 |
+
"step": 46000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 3.7891134289439377,
|
| 684 |
+
"grad_norm": 5.521021842956543,
|
| 685 |
+
"learning_rate": 3.105443285528031e-05,
|
| 686 |
+
"loss": 0.2119,
|
| 687 |
+
"step": 46500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.8298565840938723,
|
| 691 |
+
"grad_norm": 4.308606147766113,
|
| 692 |
+
"learning_rate": 3.085071707953064e-05,
|
| 693 |
+
"loss": 0.2101,
|
| 694 |
+
"step": 47000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 3.870599739243807,
|
| 698 |
+
"grad_norm": 5.6051025390625,
|
| 699 |
+
"learning_rate": 3.064700130378096e-05,
|
| 700 |
+
"loss": 0.2179,
|
| 701 |
+
"step": 47500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 3.9113428943937416,
|
| 705 |
+
"grad_norm": 2.6445212364196777,
|
| 706 |
+
"learning_rate": 3.044328552803129e-05,
|
| 707 |
+
"loss": 0.2174,
|
| 708 |
+
"step": 48000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 3.9520860495436767,
|
| 712 |
+
"grad_norm": 2.7666218280792236,
|
| 713 |
+
"learning_rate": 3.0239569752281615e-05,
|
| 714 |
+
"loss": 0.2021,
|
| 715 |
+
"step": 48500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 3.9928292046936114,
|
| 719 |
+
"grad_norm": 4.770074844360352,
|
| 720 |
+
"learning_rate": 3.003585397653194e-05,
|
| 721 |
+
"loss": 0.2118,
|
| 722 |
+
"step": 49000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 4.0,
|
| 726 |
+
"eval_accuracy": 0.86571574121243,
|
| 727 |
+
"eval_loss": 0.44608649611473083,
|
| 728 |
+
"eval_runtime": 27.5189,
|
| 729 |
+
"eval_samples_per_second": 356.663,
|
| 730 |
+
"eval_steps_per_second": 44.587,
|
| 731 |
+
"step": 49088
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 4.0335723598435465,
|
| 735 |
+
"grad_norm": 1.6207386255264282,
|
| 736 |
+
"learning_rate": 2.983213820078227e-05,
|
| 737 |
+
"loss": 0.1697,
|
| 738 |
+
"step": 49500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 4.074315514993481,
|
| 742 |
+
"grad_norm": 3.2992472648620605,
|
| 743 |
+
"learning_rate": 2.9628422425032598e-05,
|
| 744 |
+
"loss": 0.1552,
|
| 745 |
+
"step": 50000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 4.115058670143416,
|
| 749 |
+
"grad_norm": 5.406311511993408,
|
| 750 |
+
"learning_rate": 2.9424706649282924e-05,
|
| 751 |
+
"loss": 0.1705,
|
| 752 |
+
"step": 50500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 4.15580182529335,
|
| 756 |
+
"grad_norm": 3.330251455307007,
|
| 757 |
+
"learning_rate": 2.922099087353325e-05,
|
| 758 |
+
"loss": 0.1669,
|
| 759 |
+
"step": 51000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 4.196544980443286,
|
| 763 |
+
"grad_norm": 9.146599769592285,
|
| 764 |
+
"learning_rate": 2.9017275097783576e-05,
|
| 765 |
+
"loss": 0.1614,
|
| 766 |
+
"step": 51500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 4.237288135593221,
|
| 770 |
+
"grad_norm": 3.782498598098755,
|
| 771 |
+
"learning_rate": 2.88135593220339e-05,
|
| 772 |
+
"loss": 0.167,
|
| 773 |
+
"step": 52000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 4.278031290743155,
|
| 777 |
+
"grad_norm": 3.704604387283325,
|
| 778 |
+
"learning_rate": 2.8609843546284226e-05,
|
| 779 |
+
"loss": 0.171,
|
| 780 |
+
"step": 52500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 4.31877444589309,
|
| 784 |
+
"grad_norm": 4.229913234710693,
|
| 785 |
+
"learning_rate": 2.8406127770534552e-05,
|
| 786 |
+
"loss": 0.1752,
|
| 787 |
+
"step": 53000
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 4.3595176010430245,
|
| 791 |
+
"grad_norm": 5.513256549835205,
|
| 792 |
+
"learning_rate": 2.8202411994784878e-05,
|
| 793 |
+
"loss": 0.1688,
|
| 794 |
+
"step": 53500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 4.400260756192959,
|
| 798 |
+
"grad_norm": 3.369919776916504,
|
| 799 |
+
"learning_rate": 2.7998696219035204e-05,
|
| 800 |
+
"loss": 0.17,
|
| 801 |
+
"step": 54000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 4.441003911342895,
|
| 805 |
+
"grad_norm": 6.391170978546143,
|
| 806 |
+
"learning_rate": 2.7794980443285527e-05,
|
| 807 |
+
"loss": 0.1663,
|
| 808 |
+
"step": 54500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 4.481747066492829,
|
| 812 |
+
"grad_norm": 3.2502150535583496,
|
| 813 |
+
"learning_rate": 2.7591264667535854e-05,
|
| 814 |
+
"loss": 0.1729,
|
| 815 |
+
"step": 55000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 4.522490221642764,
|
| 819 |
+
"grad_norm": 2.424835443496704,
|
| 820 |
+
"learning_rate": 2.738754889178618e-05,
|
| 821 |
+
"loss": 0.1733,
|
| 822 |
+
"step": 55500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 4.563233376792699,
|
| 826 |
+
"grad_norm": 2.813887119293213,
|
| 827 |
+
"learning_rate": 2.7183833116036506e-05,
|
| 828 |
+
"loss": 0.1653,
|
| 829 |
+
"step": 56000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 4.603976531942633,
|
| 833 |
+
"grad_norm": 9.048973083496094,
|
| 834 |
+
"learning_rate": 2.6980117340286833e-05,
|
| 835 |
+
"loss": 0.1755,
|
| 836 |
+
"step": 56500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 4.644719687092568,
|
| 840 |
+
"grad_norm": 4.4565558433532715,
|
| 841 |
+
"learning_rate": 2.6776401564537155e-05,
|
| 842 |
+
"loss": 0.1717,
|
| 843 |
+
"step": 57000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.6854628422425035,
|
| 847 |
+
"grad_norm": 1.3312770128250122,
|
| 848 |
+
"learning_rate": 2.6572685788787482e-05,
|
| 849 |
+
"loss": 0.1664,
|
| 850 |
+
"step": 57500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 4.726205997392438,
|
| 854 |
+
"grad_norm": 7.608250617980957,
|
| 855 |
+
"learning_rate": 2.6368970013037815e-05,
|
| 856 |
+
"loss": 0.1687,
|
| 857 |
+
"step": 58000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.766949152542373,
|
| 861 |
+
"grad_norm": 4.287994861602783,
|
| 862 |
+
"learning_rate": 2.6165254237288138e-05,
|
| 863 |
+
"loss": 0.1757,
|
| 864 |
+
"step": 58500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 4.8076923076923075,
|
| 868 |
+
"grad_norm": 3.2377748489379883,
|
| 869 |
+
"learning_rate": 2.5961538461538464e-05,
|
| 870 |
+
"loss": 0.1746,
|
| 871 |
+
"step": 59000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 4.848435462842242,
|
| 875 |
+
"grad_norm": 6.194840431213379,
|
| 876 |
+
"learning_rate": 2.575782268578879e-05,
|
| 877 |
+
"loss": 0.1655,
|
| 878 |
+
"step": 59500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.889178617992178,
|
| 882 |
+
"grad_norm": 3.546142339706421,
|
| 883 |
+
"learning_rate": 2.5554106910039117e-05,
|
| 884 |
+
"loss": 0.1799,
|
| 885 |
+
"step": 60000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 4.929921773142112,
|
| 889 |
+
"grad_norm": 7.121952533721924,
|
| 890 |
+
"learning_rate": 2.5350391134289443e-05,
|
| 891 |
+
"loss": 0.1683,
|
| 892 |
+
"step": 60500
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.970664928292047,
|
| 896 |
+
"grad_norm": 4.6492838859558105,
|
| 897 |
+
"learning_rate": 2.5146675358539766e-05,
|
| 898 |
+
"loss": 0.1733,
|
| 899 |
+
"step": 61000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 5.0,
|
| 903 |
+
"eval_accuracy": 0.8659195109526235,
|
| 904 |
+
"eval_loss": 0.46997779607772827,
|
| 905 |
+
"eval_runtime": 27.6271,
|
| 906 |
+
"eval_samples_per_second": 355.267,
|
| 907 |
+
"eval_steps_per_second": 44.413,
|
| 908 |
+
"step": 61360
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 5.0,
|
| 912 |
+
"step": 61360,
|
| 913 |
+
"total_flos": 2.998178041960627e+17,
|
| 914 |
+
"train_loss": 0.0,
|
| 915 |
+
"train_runtime": 0.2558,
|
| 916 |
+
"train_samples_per_second": 7675471.049,
|
| 917 |
+
"train_steps_per_second": 239859.692
|
| 918 |
+
}
|
| 919 |
+
],
|
| 920 |
+
"logging_steps": 500,
|
| 921 |
+
"max_steps": 61360,
|
| 922 |
+
"num_input_tokens_seen": 0,
|
| 923 |
+
"num_train_epochs": 5,
|
| 924 |
+
"save_steps": 500,
|
| 925 |
+
"stateful_callbacks": {
|
| 926 |
+
"TrainerControl": {
|
| 927 |
+
"args": {
|
| 928 |
+
"should_epoch_stop": false,
|
| 929 |
+
"should_evaluate": false,
|
| 930 |
+
"should_log": false,
|
| 931 |
+
"should_save": true,
|
| 932 |
+
"should_training_stop": false
|
| 933 |
+
},
|
| 934 |
+
"attributes": {}
|
| 935 |
+
}
|
| 936 |
+
},
|
| 937 |
+
"total_flos": 2.998178041960627e+17,
|
| 938 |
+
"train_batch_size": 32,
|
| 939 |
+
"trial_name": null,
|
| 940 |
+
"trial_params": null
|
| 941 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15c214fb78026b2d0c9676c8c7d906470b5c8d644c2e4238a9ae9d05f5bb12f3
|
| 3 |
+
size 4783
|