Upload 14 files
Browse files- README.md +83 -1
- all_results.json +13 -0
- config.json +43 -0
- eval_results.json +8 -0
- generation_config.json +15 -0
- image.png +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +944 -0
- train_results.json +8 -0
- trainer_state.json +719 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,85 @@
|
|
| 1 |
---
|
| 2 |
-
license: bsd-3-clause
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: bsd-3-clause
|
| 3 |
+
base_model: pszemraj/long-t5-tglobal-base-16384-book-summary
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: output
|
| 8 |
+
results: []
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
# Model description
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [pszemraj/long-t5-tglobal-base-16384-book-summary](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary) on a custom sample-size dataset.
|
| 15 |
+
The dataset was [kmfoda/booksum](https://huggingface.co/datasets/kmfoda/booksum) fed into GPT3.5-turbo with a finely tuned prompt to output high quality Stable Diffusion prompts.
|
| 16 |
+
The small dataset (less than $10 of OpenAI credits) was roughly 15k entries as a proof of concept.
|
| 17 |
+
|
| 18 |
+
The goal for this model concept was to create a text summarization model that creates decent Stable Diffusion prompts comparable to a human or high-end LLM like GPT-4.
|
| 19 |
+
|
| 20 |
+
Example generations from an excerpt of Hemingway:
|
| 21 |
+
|
| 22 |
+
```
|
| 23 |
+
this model: village in late summer, river and plain, mountains, pebbled boulders, blue water, troops marching, dusty trees, soldiers marching along road, crops rich with fruit trees, battle in the mountains, artillery flashes, cool nights, highly detailed, dramatic lighting
|
| 24 |
+
|
| 25 |
+
gpt-4: desert landscape with camel caravan at sunset, nomad tents, sand dunes, oasis, traditional clothing, dramatic lighting, 8k UHD, highly detailed, masterpiece, digital painting, global illumination
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
This is a VERY rough proof-of-concept model that could be greatly improved by a higher quality dataset and possibly different hyperparameters.
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
Training was completed over 7 epochs with a modified version of the run_summarization.py Huggingface training script.
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0002
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 6
|
| 44 |
+
- total_train_batch_size: 48
|
| 45 |
+
- total_eval_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 7.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 2.453 | 0.28 | 30 | 2.0444 |
|
| 55 |
+
| 2.2692 | 0.56 | 60 | 1.8970 |
|
| 56 |
+
| 2.1485 | 0.84 | 90 | 1.8373 |
|
| 57 |
+
| 2.0469 | 1.12 | 120 | 1.8033 |
|
| 58 |
+
| 1.9954 | 1.4 | 150 | 1.7762 |
|
| 59 |
+
| 1.9778 | 1.68 | 180 | 1.7593 |
|
| 60 |
+
| 1.9536 | 1.96 | 210 | 1.7472 |
|
| 61 |
+
| 1.8524 | 2.24 | 240 | 1.7306 |
|
| 62 |
+
| 1.8438 | 2.52 | 270 | 1.7255 |
|
| 63 |
+
| 1.8436 | 2.8 | 300 | 1.7140 |
|
| 64 |
+
| 1.7765 | 3.08 | 330 | 1.7049 |
|
| 65 |
+
| 1.7537 | 3.36 | 360 | 1.7057 |
|
| 66 |
+
| 1.7328 | 3.64 | 390 | 1.6977 |
|
| 67 |
+
| 1.723 | 3.92 | 420 | 1.6973 |
|
| 68 |
+
| 1.6592 | 4.2 | 450 | 1.7058 |
|
| 69 |
+
| 1.6563 | 4.48 | 480 | 1.7034 |
|
| 70 |
+
| 1.6443 | 4.76 | 510 | 1.6969 |
|
| 71 |
+
| 1.5782 | 5.04 | 540 | 1.6953 |
|
| 72 |
+
| 1.509 | 5.32 | 570 | 1.7136 |
|
| 73 |
+
| 1.5516 | 5.6 | 600 | 1.7064 |
|
| 74 |
+
| 1.558 | 5.88 | 630 | 1.7045 |
|
| 75 |
+
| 1.5016 | 6.16 | 660 | 1.7182 |
|
| 76 |
+
| 1.5288 | 6.44 | 690 | 1.7111 |
|
| 77 |
+
| 1.4665 | 6.72 | 720 | 1.7030 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.36.0.dev0
|
| 83 |
+
- Pytorch 2.1.1+cu118
|
| 84 |
+
- Datasets 2.15.0
|
| 85 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.99,
|
| 3 |
+
"eval_loss": 1.712321400642395,
|
| 4 |
+
"eval_runtime": 68.3821,
|
| 5 |
+
"eval_samples": 1286,
|
| 6 |
+
"eval_samples_per_second": 18.806,
|
| 7 |
+
"eval_steps_per_second": 2.354,
|
| 8 |
+
"train_loss": 0.7637141177428262,
|
| 9 |
+
"train_runtime": 5381.4192,
|
| 10 |
+
"train_samples": 5143,
|
| 11 |
+
"train_samples_per_second": 6.69,
|
| 12 |
+
"train_steps_per_second": 0.139
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pszemraj/long-t5-tglobal-base-16384-book-summary",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"early_stopping": true,
|
| 13 |
+
"encoder_attention_type": "transient-global",
|
| 14 |
+
"encoder_no_repeat_ngram_size": 4,
|
| 15 |
+
"eos_token_id": 1,
|
| 16 |
+
"feed_forward_proj": "gated-gelu",
|
| 17 |
+
"global_block_size": 16,
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"is_encoder_decoder": true,
|
| 20 |
+
"is_gated_act": true,
|
| 21 |
+
"layer_norm_epsilon": 1e-06,
|
| 22 |
+
"length_penalty": 0.8,
|
| 23 |
+
"local_radius": 127,
|
| 24 |
+
"max_length": 512,
|
| 25 |
+
"min_length": 8,
|
| 26 |
+
"model_type": "longt5",
|
| 27 |
+
"n_positions": 4096,
|
| 28 |
+
"no_repeat_ngram_size": 3,
|
| 29 |
+
"num_beams": 2,
|
| 30 |
+
"num_decoder_layers": 12,
|
| 31 |
+
"num_heads": 12,
|
| 32 |
+
"num_layers": 12,
|
| 33 |
+
"output_past": true,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"relative_attention_max_distance": 128,
|
| 36 |
+
"relative_attention_num_buckets": 32,
|
| 37 |
+
"repetition_penalty": 3.5,
|
| 38 |
+
"tie_word_embeddings": false,
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.36.0.dev0",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 32128
|
| 43 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.99,
|
| 3 |
+
"eval_loss": 1.712321400642395,
|
| 4 |
+
"eval_runtime": 68.3821,
|
| 5 |
+
"eval_samples": 1286,
|
| 6 |
+
"eval_samples_per_second": 18.806,
|
| 7 |
+
"eval_steps_per_second": 2.354
|
| 8 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"encoder_no_repeat_ngram_size": 4,
|
| 6 |
+
"eos_token_id": 1,
|
| 7 |
+
"length_penalty": 0.8,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"min_length": 8,
|
| 10 |
+
"no_repeat_ngram_size": 3,
|
| 11 |
+
"num_beams": 2,
|
| 12 |
+
"pad_token_id": 0,
|
| 13 |
+
"repetition_penalty": 3.5,
|
| 14 |
+
"transformers_version": "4.36.0.dev0"
|
| 15 |
+
}
|
image.png
ADDED
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d93ea98b71aeedf05bd7165365112e99cd103e13799ab7fa403e35d4636f4c4
|
| 3 |
+
size 1187780840
|
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 +1,944 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"max_length": 1024,
|
| 934 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 935 |
+
"pad_to_multiple_of": null,
|
| 936 |
+
"pad_token": "<pad>",
|
| 937 |
+
"pad_token_type_id": 0,
|
| 938 |
+
"padding_side": "right",
|
| 939 |
+
"stride": 0,
|
| 940 |
+
"tokenizer_class": "T5Tokenizer",
|
| 941 |
+
"truncation_side": "right",
|
| 942 |
+
"truncation_strategy": "longest_first",
|
| 943 |
+
"unk_token": "<unk>"
|
| 944 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.99,
|
| 3 |
+
"train_loss": 0.7637141177428262,
|
| 4 |
+
"train_runtime": 5381.4192,
|
| 5 |
+
"train_samples": 5143,
|
| 6 |
+
"train_samples_per_second": 6.69,
|
| 7 |
+
"train_steps_per_second": 0.139
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,719 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.993779160186625,
|
| 5 |
+
"eval_steps": 30,
|
| 6 |
+
"global_step": 749,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 0.0002,
|
| 14 |
+
"loss": 3.4262,
|
| 15 |
+
"step": 9
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.17,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 2.6518,
|
| 21 |
+
"step": 18
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.25,
|
| 25 |
+
"learning_rate": 0.0002,
|
| 26 |
+
"loss": 2.453,
|
| 27 |
+
"step": 27
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.28,
|
| 31 |
+
"eval_loss": 2.0444083213806152,
|
| 32 |
+
"eval_runtime": 62.6984,
|
| 33 |
+
"eval_samples_per_second": 20.511,
|
| 34 |
+
"eval_steps_per_second": 2.568,
|
| 35 |
+
"step": 30
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.34,
|
| 39 |
+
"learning_rate": 0.0002,
|
| 40 |
+
"loss": 2.3345,
|
| 41 |
+
"step": 36
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.42,
|
| 45 |
+
"learning_rate": 0.0002,
|
| 46 |
+
"loss": 2.3033,
|
| 47 |
+
"step": 45
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.5,
|
| 51 |
+
"learning_rate": 0.0002,
|
| 52 |
+
"loss": 2.2692,
|
| 53 |
+
"step": 54
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.56,
|
| 57 |
+
"eval_loss": 1.8969556093215942,
|
| 58 |
+
"eval_runtime": 68.3363,
|
| 59 |
+
"eval_samples_per_second": 18.819,
|
| 60 |
+
"eval_steps_per_second": 2.356,
|
| 61 |
+
"step": 60
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.59,
|
| 65 |
+
"learning_rate": 0.0002,
|
| 66 |
+
"loss": 2.2294,
|
| 67 |
+
"step": 63
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.67,
|
| 71 |
+
"learning_rate": 0.0002,
|
| 72 |
+
"loss": 2.235,
|
| 73 |
+
"step": 72
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.76,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 2.1576,
|
| 79 |
+
"step": 81
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.84,
|
| 83 |
+
"learning_rate": 0.0002,
|
| 84 |
+
"loss": 2.1485,
|
| 85 |
+
"step": 90
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.84,
|
| 89 |
+
"eval_loss": 1.8373124599456787,
|
| 90 |
+
"eval_runtime": 69.5775,
|
| 91 |
+
"eval_samples_per_second": 18.483,
|
| 92 |
+
"eval_steps_per_second": 2.314,
|
| 93 |
+
"step": 90
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.92,
|
| 97 |
+
"learning_rate": 0.0002,
|
| 98 |
+
"loss": 2.1657,
|
| 99 |
+
"step": 99
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.01,
|
| 103 |
+
"learning_rate": 0.0002,
|
| 104 |
+
"loss": 2.1049,
|
| 105 |
+
"step": 108
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.09,
|
| 109 |
+
"learning_rate": 0.0002,
|
| 110 |
+
"loss": 2.0469,
|
| 111 |
+
"step": 117
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.12,
|
| 115 |
+
"eval_loss": 1.8033325672149658,
|
| 116 |
+
"eval_runtime": 69.7392,
|
| 117 |
+
"eval_samples_per_second": 18.44,
|
| 118 |
+
"eval_steps_per_second": 2.309,
|
| 119 |
+
"step": 120
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.18,
|
| 123 |
+
"learning_rate": 0.0002,
|
| 124 |
+
"loss": 2.003,
|
| 125 |
+
"step": 126
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.26,
|
| 129 |
+
"learning_rate": 0.0002,
|
| 130 |
+
"loss": 1.9928,
|
| 131 |
+
"step": 135
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.34,
|
| 135 |
+
"learning_rate": 0.0002,
|
| 136 |
+
"loss": 1.9954,
|
| 137 |
+
"step": 144
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.4,
|
| 141 |
+
"eval_loss": 1.7761518955230713,
|
| 142 |
+
"eval_runtime": 68.9976,
|
| 143 |
+
"eval_samples_per_second": 18.638,
|
| 144 |
+
"eval_steps_per_second": 2.333,
|
| 145 |
+
"step": 150
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.43,
|
| 149 |
+
"learning_rate": 0.0002,
|
| 150 |
+
"loss": 1.9571,
|
| 151 |
+
"step": 153
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.51,
|
| 155 |
+
"learning_rate": 0.0002,
|
| 156 |
+
"loss": 2.0011,
|
| 157 |
+
"step": 162
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.6,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 1.983,
|
| 163 |
+
"step": 171
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.68,
|
| 167 |
+
"learning_rate": 0.0002,
|
| 168 |
+
"loss": 1.9778,
|
| 169 |
+
"step": 180
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.68,
|
| 173 |
+
"eval_loss": 1.7592827081680298,
|
| 174 |
+
"eval_runtime": 71.1717,
|
| 175 |
+
"eval_samples_per_second": 18.069,
|
| 176 |
+
"eval_steps_per_second": 2.262,
|
| 177 |
+
"step": 180
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.76,
|
| 181 |
+
"learning_rate": 0.0002,
|
| 182 |
+
"loss": 1.9624,
|
| 183 |
+
"step": 189
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.85,
|
| 187 |
+
"learning_rate": 0.0002,
|
| 188 |
+
"loss": 1.9384,
|
| 189 |
+
"step": 198
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.93,
|
| 193 |
+
"learning_rate": 0.0002,
|
| 194 |
+
"loss": 1.9536,
|
| 195 |
+
"step": 207
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.96,
|
| 199 |
+
"eval_loss": 1.7472261190414429,
|
| 200 |
+
"eval_runtime": 68.6137,
|
| 201 |
+
"eval_samples_per_second": 18.743,
|
| 202 |
+
"eval_steps_per_second": 2.346,
|
| 203 |
+
"step": 210
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.02,
|
| 207 |
+
"learning_rate": 0.0002,
|
| 208 |
+
"loss": 1.9249,
|
| 209 |
+
"step": 216
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.1,
|
| 213 |
+
"learning_rate": 0.0002,
|
| 214 |
+
"loss": 1.8604,
|
| 215 |
+
"step": 225
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.18,
|
| 219 |
+
"learning_rate": 0.0002,
|
| 220 |
+
"loss": 1.8524,
|
| 221 |
+
"step": 234
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.24,
|
| 225 |
+
"eval_loss": 1.730584740638733,
|
| 226 |
+
"eval_runtime": 68.1311,
|
| 227 |
+
"eval_samples_per_second": 18.875,
|
| 228 |
+
"eval_steps_per_second": 2.363,
|
| 229 |
+
"step": 240
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.27,
|
| 233 |
+
"learning_rate": 0.0002,
|
| 234 |
+
"loss": 1.8442,
|
| 235 |
+
"step": 243
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.35,
|
| 239 |
+
"learning_rate": 0.0002,
|
| 240 |
+
"loss": 1.8647,
|
| 241 |
+
"step": 252
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.44,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 1.8218,
|
| 247 |
+
"step": 261
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.52,
|
| 251 |
+
"learning_rate": 0.0002,
|
| 252 |
+
"loss": 1.8438,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.52,
|
| 257 |
+
"eval_loss": 1.7255065441131592,
|
| 258 |
+
"eval_runtime": 67.2395,
|
| 259 |
+
"eval_samples_per_second": 19.126,
|
| 260 |
+
"eval_steps_per_second": 2.394,
|
| 261 |
+
"step": 270
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.6,
|
| 265 |
+
"learning_rate": 0.0002,
|
| 266 |
+
"loss": 1.8491,
|
| 267 |
+
"step": 279
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.69,
|
| 271 |
+
"learning_rate": 0.0002,
|
| 272 |
+
"loss": 1.8304,
|
| 273 |
+
"step": 288
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.77,
|
| 277 |
+
"learning_rate": 0.0002,
|
| 278 |
+
"loss": 1.8436,
|
| 279 |
+
"step": 297
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.8,
|
| 283 |
+
"eval_loss": 1.7139911651611328,
|
| 284 |
+
"eval_runtime": 70.3499,
|
| 285 |
+
"eval_samples_per_second": 18.28,
|
| 286 |
+
"eval_steps_per_second": 2.289,
|
| 287 |
+
"step": 300
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.86,
|
| 291 |
+
"learning_rate": 0.0002,
|
| 292 |
+
"loss": 1.8039,
|
| 293 |
+
"step": 306
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.94,
|
| 297 |
+
"learning_rate": 0.0002,
|
| 298 |
+
"loss": 1.8255,
|
| 299 |
+
"step": 315
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.02,
|
| 303 |
+
"learning_rate": 0.0002,
|
| 304 |
+
"loss": 1.7765,
|
| 305 |
+
"step": 324
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.08,
|
| 309 |
+
"eval_loss": 1.7048661708831787,
|
| 310 |
+
"eval_runtime": 70.1678,
|
| 311 |
+
"eval_samples_per_second": 18.328,
|
| 312 |
+
"eval_steps_per_second": 2.295,
|
| 313 |
+
"step": 330
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.11,
|
| 317 |
+
"learning_rate": 0.0002,
|
| 318 |
+
"loss": 1.7546,
|
| 319 |
+
"step": 333
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 3.19,
|
| 323 |
+
"learning_rate": 0.0002,
|
| 324 |
+
"loss": 1.7389,
|
| 325 |
+
"step": 342
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.28,
|
| 329 |
+
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 1.7248,
|
| 331 |
+
"step": 351
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.36,
|
| 335 |
+
"learning_rate": 0.0002,
|
| 336 |
+
"loss": 1.7537,
|
| 337 |
+
"step": 360
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.36,
|
| 341 |
+
"eval_loss": 1.7056528329849243,
|
| 342 |
+
"eval_runtime": 70.6453,
|
| 343 |
+
"eval_samples_per_second": 18.204,
|
| 344 |
+
"eval_steps_per_second": 2.279,
|
| 345 |
+
"step": 360
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.44,
|
| 349 |
+
"learning_rate": 0.0002,
|
| 350 |
+
"loss": 1.7234,
|
| 351 |
+
"step": 369
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.53,
|
| 355 |
+
"learning_rate": 0.0002,
|
| 356 |
+
"loss": 1.7208,
|
| 357 |
+
"step": 378
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.61,
|
| 361 |
+
"learning_rate": 0.0002,
|
| 362 |
+
"loss": 1.7328,
|
| 363 |
+
"step": 387
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.64,
|
| 367 |
+
"eval_loss": 1.6977263689041138,
|
| 368 |
+
"eval_runtime": 61.7073,
|
| 369 |
+
"eval_samples_per_second": 20.84,
|
| 370 |
+
"eval_steps_per_second": 2.609,
|
| 371 |
+
"step": 390
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.7,
|
| 375 |
+
"learning_rate": 0.0002,
|
| 376 |
+
"loss": 1.7231,
|
| 377 |
+
"step": 396
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.78,
|
| 381 |
+
"learning_rate": 0.0002,
|
| 382 |
+
"loss": 1.7424,
|
| 383 |
+
"step": 405
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.87,
|
| 387 |
+
"learning_rate": 0.0002,
|
| 388 |
+
"loss": 1.723,
|
| 389 |
+
"step": 414
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.92,
|
| 393 |
+
"eval_loss": 1.6972527503967285,
|
| 394 |
+
"eval_runtime": 69.7095,
|
| 395 |
+
"eval_samples_per_second": 18.448,
|
| 396 |
+
"eval_steps_per_second": 2.31,
|
| 397 |
+
"step": 420
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 3.95,
|
| 401 |
+
"learning_rate": 0.0002,
|
| 402 |
+
"loss": 1.6888,
|
| 403 |
+
"step": 423
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 4.04,
|
| 407 |
+
"learning_rate": 0.0002,
|
| 408 |
+
"loss": 1.6847,
|
| 409 |
+
"step": 432
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.12,
|
| 413 |
+
"learning_rate": 0.0002,
|
| 414 |
+
"loss": 1.6702,
|
| 415 |
+
"step": 441
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.2,
|
| 419 |
+
"learning_rate": 0.0002,
|
| 420 |
+
"loss": 1.6592,
|
| 421 |
+
"step": 450
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 4.2,
|
| 425 |
+
"eval_loss": 1.7057932615280151,
|
| 426 |
+
"eval_runtime": 71.3257,
|
| 427 |
+
"eval_samples_per_second": 18.03,
|
| 428 |
+
"eval_steps_per_second": 2.257,
|
| 429 |
+
"step": 450
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 4.29,
|
| 433 |
+
"learning_rate": 0.0002,
|
| 434 |
+
"loss": 1.6158,
|
| 435 |
+
"step": 459
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.37,
|
| 439 |
+
"learning_rate": 0.0002,
|
| 440 |
+
"loss": 1.6684,
|
| 441 |
+
"step": 468
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.46,
|
| 445 |
+
"learning_rate": 0.0002,
|
| 446 |
+
"loss": 1.6563,
|
| 447 |
+
"step": 477
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.48,
|
| 451 |
+
"eval_loss": 1.703405499458313,
|
| 452 |
+
"eval_runtime": 67.5168,
|
| 453 |
+
"eval_samples_per_second": 19.047,
|
| 454 |
+
"eval_steps_per_second": 2.385,
|
| 455 |
+
"step": 480
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.54,
|
| 459 |
+
"learning_rate": 0.0002,
|
| 460 |
+
"loss": 1.6111,
|
| 461 |
+
"step": 486
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.62,
|
| 465 |
+
"learning_rate": 0.0002,
|
| 466 |
+
"loss": 1.6514,
|
| 467 |
+
"step": 495
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.71,
|
| 471 |
+
"learning_rate": 0.0002,
|
| 472 |
+
"loss": 1.6443,
|
| 473 |
+
"step": 504
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.76,
|
| 477 |
+
"eval_loss": 1.6969022750854492,
|
| 478 |
+
"eval_runtime": 68.7108,
|
| 479 |
+
"eval_samples_per_second": 18.716,
|
| 480 |
+
"eval_steps_per_second": 2.343,
|
| 481 |
+
"step": 510
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 4.79,
|
| 485 |
+
"learning_rate": 0.0002,
|
| 486 |
+
"loss": 1.6255,
|
| 487 |
+
"step": 513
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 4.88,
|
| 491 |
+
"learning_rate": 0.0002,
|
| 492 |
+
"loss": 1.6563,
|
| 493 |
+
"step": 522
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 4.96,
|
| 497 |
+
"learning_rate": 0.0002,
|
| 498 |
+
"loss": 1.617,
|
| 499 |
+
"step": 531
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 5.04,
|
| 503 |
+
"learning_rate": 0.0002,
|
| 504 |
+
"loss": 1.5782,
|
| 505 |
+
"step": 540
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 5.04,
|
| 509 |
+
"eval_loss": 1.6952643394470215,
|
| 510 |
+
"eval_runtime": 68.1803,
|
| 511 |
+
"eval_samples_per_second": 18.862,
|
| 512 |
+
"eval_steps_per_second": 2.361,
|
| 513 |
+
"step": 540
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 5.13,
|
| 517 |
+
"learning_rate": 0.0002,
|
| 518 |
+
"loss": 1.5834,
|
| 519 |
+
"step": 549
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.21,
|
| 523 |
+
"learning_rate": 0.0002,
|
| 524 |
+
"loss": 1.5956,
|
| 525 |
+
"step": 558
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 5.3,
|
| 529 |
+
"learning_rate": 0.0002,
|
| 530 |
+
"loss": 1.509,
|
| 531 |
+
"step": 567
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 5.32,
|
| 535 |
+
"eval_loss": 1.7135779857635498,
|
| 536 |
+
"eval_runtime": 68.335,
|
| 537 |
+
"eval_samples_per_second": 18.819,
|
| 538 |
+
"eval_steps_per_second": 2.356,
|
| 539 |
+
"step": 570
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.38,
|
| 543 |
+
"learning_rate": 0.0002,
|
| 544 |
+
"loss": 1.5999,
|
| 545 |
+
"step": 576
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 5.46,
|
| 549 |
+
"learning_rate": 0.0002,
|
| 550 |
+
"loss": 1.5743,
|
| 551 |
+
"step": 585
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 5.55,
|
| 555 |
+
"learning_rate": 0.0002,
|
| 556 |
+
"loss": 1.5516,
|
| 557 |
+
"step": 594
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 5.6,
|
| 561 |
+
"eval_loss": 1.7064013481140137,
|
| 562 |
+
"eval_runtime": 69.1824,
|
| 563 |
+
"eval_samples_per_second": 18.589,
|
| 564 |
+
"eval_steps_per_second": 2.327,
|
| 565 |
+
"step": 600
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 5.63,
|
| 569 |
+
"learning_rate": 0.0002,
|
| 570 |
+
"loss": 1.5623,
|
| 571 |
+
"step": 603
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 5.72,
|
| 575 |
+
"learning_rate": 0.0002,
|
| 576 |
+
"loss": 1.5476,
|
| 577 |
+
"step": 612
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 5.8,
|
| 581 |
+
"learning_rate": 0.0002,
|
| 582 |
+
"loss": 1.5587,
|
| 583 |
+
"step": 621
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 5.88,
|
| 587 |
+
"learning_rate": 0.0002,
|
| 588 |
+
"loss": 1.558,
|
| 589 |
+
"step": 630
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.88,
|
| 593 |
+
"eval_loss": 1.7045198678970337,
|
| 594 |
+
"eval_runtime": 69.0953,
|
| 595 |
+
"eval_samples_per_second": 18.612,
|
| 596 |
+
"eval_steps_per_second": 2.33,
|
| 597 |
+
"step": 630
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 5.97,
|
| 601 |
+
"learning_rate": 0.0002,
|
| 602 |
+
"loss": 1.5317,
|
| 603 |
+
"step": 639
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 6.05,
|
| 607 |
+
"learning_rate": 0.0002,
|
| 608 |
+
"loss": 1.5192,
|
| 609 |
+
"step": 648
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 6.14,
|
| 613 |
+
"learning_rate": 0.0002,
|
| 614 |
+
"loss": 1.5016,
|
| 615 |
+
"step": 657
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 6.16,
|
| 619 |
+
"eval_loss": 1.718214750289917,
|
| 620 |
+
"eval_runtime": 68.4195,
|
| 621 |
+
"eval_samples_per_second": 18.796,
|
| 622 |
+
"eval_steps_per_second": 2.353,
|
| 623 |
+
"step": 660
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 6.22,
|
| 627 |
+
"learning_rate": 0.0002,
|
| 628 |
+
"loss": 1.5243,
|
| 629 |
+
"step": 666
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 6.3,
|
| 633 |
+
"learning_rate": 0.0002,
|
| 634 |
+
"loss": 1.4374,
|
| 635 |
+
"step": 675
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 6.39,
|
| 639 |
+
"learning_rate": 0.0002,
|
| 640 |
+
"loss": 1.5288,
|
| 641 |
+
"step": 684
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 6.44,
|
| 645 |
+
"eval_loss": 1.7111074924468994,
|
| 646 |
+
"eval_runtime": 68.9961,
|
| 647 |
+
"eval_samples_per_second": 18.639,
|
| 648 |
+
"eval_steps_per_second": 2.333,
|
| 649 |
+
"step": 690
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 6.47,
|
| 653 |
+
"learning_rate": 0.0002,
|
| 654 |
+
"loss": 1.4874,
|
| 655 |
+
"step": 693
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 6.56,
|
| 659 |
+
"learning_rate": 0.0002,
|
| 660 |
+
"loss": 1.4725,
|
| 661 |
+
"step": 702
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 6.64,
|
| 665 |
+
"learning_rate": 0.0002,
|
| 666 |
+
"loss": 1.5042,
|
| 667 |
+
"step": 711
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 6.72,
|
| 671 |
+
"learning_rate": 0.0002,
|
| 672 |
+
"loss": 1.4665,
|
| 673 |
+
"step": 720
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 6.72,
|
| 677 |
+
"eval_loss": 1.7030370235443115,
|
| 678 |
+
"eval_runtime": 67.7732,
|
| 679 |
+
"eval_samples_per_second": 18.975,
|
| 680 |
+
"eval_steps_per_second": 2.376,
|
| 681 |
+
"step": 720
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.81,
|
| 685 |
+
"learning_rate": 0.0002,
|
| 686 |
+
"loss": 1.4698,
|
| 687 |
+
"step": 729
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 6.89,
|
| 691 |
+
"learning_rate": 0.0002,
|
| 692 |
+
"loss": 1.5119,
|
| 693 |
+
"step": 738
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 6.98,
|
| 697 |
+
"learning_rate": 0.0002,
|
| 698 |
+
"loss": 1.4489,
|
| 699 |
+
"step": 747
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 6.99,
|
| 703 |
+
"step": 749,
|
| 704 |
+
"total_flos": 5.022814063873229e+16,
|
| 705 |
+
"train_loss": 0.7637141177428262,
|
| 706 |
+
"train_runtime": 5381.4192,
|
| 707 |
+
"train_samples_per_second": 6.69,
|
| 708 |
+
"train_steps_per_second": 0.139
|
| 709 |
+
}
|
| 710 |
+
],
|
| 711 |
+
"logging_steps": 9,
|
| 712 |
+
"max_steps": 749,
|
| 713 |
+
"num_input_tokens_seen": 0,
|
| 714 |
+
"num_train_epochs": 7,
|
| 715 |
+
"save_steps": 43,
|
| 716 |
+
"total_flos": 5.022814063873229e+16,
|
| 717 |
+
"trial_name": null,
|
| 718 |
+
"trial_params": null
|
| 719 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a77b03d99224205f3fe9393136030acb9b050983d90dbe091600821513cb3b6c
|
| 3 |
+
size 6328
|