Add files using upload-large-folder tool
Browse files- README.md +101 -0
- added_tokens.json +127 -0
- config.json +33 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +150 -0
- tokenizer_config.json +1163 -0
- trainer_state.json +2182 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: la
|
| 3 |
+
library_name: transformers
|
| 4 |
+
license: cc-by-sa-4.0
|
| 5 |
+
base_model: google/byt5-large
|
| 6 |
+
pipeline_tag: text2text-generation
|
| 7 |
+
tags:
|
| 8 |
+
- latin
|
| 9 |
+
- medieval-latin
|
| 10 |
+
- normalization
|
| 11 |
+
- legal-history
|
| 12 |
+
- digital-humanities
|
| 13 |
+
- ocr-postprocessing
|
| 14 |
+
widget:
|
| 15 |
+
- text: "viiii vt in sabbato sancto ieiunium ante noctis initium non soluatur"
|
| 16 |
+
example_title: "Medieval Legal Latin"
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Medieval Latin Normalizer (ByT5-Large)
|
| 20 |
+
|
| 21 |
+
This model is a **ByT5-Large** transformer fine-tuned to normalize medieval Latin text. It transforms diplomatic transcriptions or noisy HTR/OCR output into a standardized normalized orthography, facilitating better downstream processing such as POS tagging, lemmatization, and linguistic analysis. The model was developed as part of the following research projects **"Embedding the Past"** (LOEWE-Exploration, TU Darmstadt) and **"Burchards Dekret Digital"** (Academy of Sciences and Literature | Mainz).
|
| 22 |
+
|
| 23 |
+
## Model Logic
|
| 24 |
+
Medieval Latin normalization involves handling inconsistent orthography (e.g., `u/v`, `i/j`, or `ae/e` variations) and resolving phonetic spellings common in legal and ecclesiastical manuscripts.
|
| 25 |
+
|
| 26 |
+
By using **ByT5-Large**, the model operates directly on **UTF-8 bytes**. This is a significant advantage for Medieval Latin, as it allows the model to process non-standard characters without the information loss typical of subword tokenizers (like BERT or standard T5).
|
| 27 |
+
|
| 28 |
+
- **Input:** Raw/Diplomatic medieval Latin text.
|
| 29 |
+
- **Output:** Standardized/Normalized Latin text.
|
| 30 |
+
|
| 31 |
+
## Technical Specifications
|
| 32 |
+
- **Architecture:** [ByT5-Large](https://huggingface.co/google/byt5-large) (~1.2B parameters).
|
| 33 |
+
- **Hardware:** Trained on NVIDIA Blackwell GPUs using `bf16` precision and `adamw_torch_fused` optimization.
|
| 34 |
+
- **Training Parameters:**
|
| 35 |
+
- **Learning Rate:** 2e-4
|
| 36 |
+
- **Epochs:** 20
|
| 37 |
+
- **Label Smoothing:** 0.1 (to improve robustness against transcription noise).
|
| 38 |
+
- **Batch Size:** 48.
|
| 39 |
+
|
| 40 |
+
## Performance (Test Set)
|
| 41 |
+
The model was evaluated on a held-out test set (85 samples) from medieval legal corpora:
|
| 42 |
+
|
| 43 |
+
| Metric | Value |
|
| 44 |
+
| :--- | :--- |
|
| 45 |
+
| **Character Error Rate (CER)** | **1.62%** |
|
| 46 |
+
| **Word-Level F1-Score** | **94.12%** |
|
| 47 |
+
| **Evaluation Loss** | 0.143 |
|
| 48 |
+
|
| 49 |
+
## Usage
|
| 50 |
+
You can utilize this model through the Hugging Face `pipeline` API:
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
from transformers import pipeline
|
| 54 |
+
|
| 55 |
+
# Initialize the normalizer
|
| 56 |
+
normalizer = pipeline("text2text-generation", model="mschonhardt/latin-normalizer")
|
| 57 |
+
|
| 58 |
+
# Example input
|
| 59 |
+
raw_text = "viiii vt in sabbato sancto ieiunium ante noctis initium non soluatur"
|
| 60 |
+
result = normalizer(raw_text, max_length=128)
|
| 61 |
+
|
| 62 |
+
print(f"Normalized: {result[0]['generated_text']}")
|
| 63 |
+
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
## Citation
|
| 67 |
+
|
| 68 |
+
If you use this model in your research, please cite:
|
| 69 |
+
|
| 70 |
+
```bibtex
|
| 71 |
+
@software{schonhardt_michael_2026_normalization,
|
| 72 |
+
author = "Schonhardt, Michael",
|
| 73 |
+
title = "Medieval Latin Normalizer",
|
| 74 |
+
year = "2026",
|
| 75 |
+
publisher = "Zenodo",
|
| 76 |
+
doi = "10.5281/zenodo.18416639",
|
| 77 |
+
url = "https://doi.org/10.5281/zenodo.18416639"
|
| 78 |
+
}
|
| 79 |
+
|
| 80 |
+
@article{xue-etal-2022-byt5,
|
| 81 |
+
title = "{B}y{T}5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models",
|
| 82 |
+
author = "Xue, Linting and
|
| 83 |
+
Barua, Aditya and
|
| 84 |
+
Constant, Noah and
|
| 85 |
+
Al-Rfou, Rami and
|
| 86 |
+
Narang, Sharan and
|
| 87 |
+
Kale, Mihir and
|
| 88 |
+
Roberts, Adam and
|
| 89 |
+
Raffel, Colin",
|
| 90 |
+
editor = "Roark, Brian and
|
| 91 |
+
Nenkova, Ani",
|
| 92 |
+
journal = "Transactions of the Association for Computational Linguistics",
|
| 93 |
+
volume = "10",
|
| 94 |
+
year = "2022",
|
| 95 |
+
address = "Cambridge, MA",
|
| 96 |
+
publisher = "MIT Press",
|
| 97 |
+
url = "https://aclanthology.org/2022.tacl-1.17/",
|
| 98 |
+
doi = "10.1162/tacl_a_00461",
|
| 99 |
+
pages = "291--306"}
|
| 100 |
+
|
| 101 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 259,
|
| 3 |
+
"<extra_id_100>": 359,
|
| 4 |
+
"<extra_id_101>": 360,
|
| 5 |
+
"<extra_id_102>": 361,
|
| 6 |
+
"<extra_id_103>": 362,
|
| 7 |
+
"<extra_id_104>": 363,
|
| 8 |
+
"<extra_id_105>": 364,
|
| 9 |
+
"<extra_id_106>": 365,
|
| 10 |
+
"<extra_id_107>": 366,
|
| 11 |
+
"<extra_id_108>": 367,
|
| 12 |
+
"<extra_id_109>": 368,
|
| 13 |
+
"<extra_id_10>": 269,
|
| 14 |
+
"<extra_id_110>": 369,
|
| 15 |
+
"<extra_id_111>": 370,
|
| 16 |
+
"<extra_id_112>": 371,
|
| 17 |
+
"<extra_id_113>": 372,
|
| 18 |
+
"<extra_id_114>": 373,
|
| 19 |
+
"<extra_id_115>": 374,
|
| 20 |
+
"<extra_id_116>": 375,
|
| 21 |
+
"<extra_id_117>": 376,
|
| 22 |
+
"<extra_id_118>": 377,
|
| 23 |
+
"<extra_id_119>": 378,
|
| 24 |
+
"<extra_id_11>": 270,
|
| 25 |
+
"<extra_id_120>": 379,
|
| 26 |
+
"<extra_id_121>": 380,
|
| 27 |
+
"<extra_id_122>": 381,
|
| 28 |
+
"<extra_id_123>": 382,
|
| 29 |
+
"<extra_id_124>": 383,
|
| 30 |
+
"<extra_id_12>": 271,
|
| 31 |
+
"<extra_id_13>": 272,
|
| 32 |
+
"<extra_id_14>": 273,
|
| 33 |
+
"<extra_id_15>": 274,
|
| 34 |
+
"<extra_id_16>": 275,
|
| 35 |
+
"<extra_id_17>": 276,
|
| 36 |
+
"<extra_id_18>": 277,
|
| 37 |
+
"<extra_id_19>": 278,
|
| 38 |
+
"<extra_id_1>": 260,
|
| 39 |
+
"<extra_id_20>": 279,
|
| 40 |
+
"<extra_id_21>": 280,
|
| 41 |
+
"<extra_id_22>": 281,
|
| 42 |
+
"<extra_id_23>": 282,
|
| 43 |
+
"<extra_id_24>": 283,
|
| 44 |
+
"<extra_id_25>": 284,
|
| 45 |
+
"<extra_id_26>": 285,
|
| 46 |
+
"<extra_id_27>": 286,
|
| 47 |
+
"<extra_id_28>": 287,
|
| 48 |
+
"<extra_id_29>": 288,
|
| 49 |
+
"<extra_id_2>": 261,
|
| 50 |
+
"<extra_id_30>": 289,
|
| 51 |
+
"<extra_id_31>": 290,
|
| 52 |
+
"<extra_id_32>": 291,
|
| 53 |
+
"<extra_id_33>": 292,
|
| 54 |
+
"<extra_id_34>": 293,
|
| 55 |
+
"<extra_id_35>": 294,
|
| 56 |
+
"<extra_id_36>": 295,
|
| 57 |
+
"<extra_id_37>": 296,
|
| 58 |
+
"<extra_id_38>": 297,
|
| 59 |
+
"<extra_id_39>": 298,
|
| 60 |
+
"<extra_id_3>": 262,
|
| 61 |
+
"<extra_id_40>": 299,
|
| 62 |
+
"<extra_id_41>": 300,
|
| 63 |
+
"<extra_id_42>": 301,
|
| 64 |
+
"<extra_id_43>": 302,
|
| 65 |
+
"<extra_id_44>": 303,
|
| 66 |
+
"<extra_id_45>": 304,
|
| 67 |
+
"<extra_id_46>": 305,
|
| 68 |
+
"<extra_id_47>": 306,
|
| 69 |
+
"<extra_id_48>": 307,
|
| 70 |
+
"<extra_id_49>": 308,
|
| 71 |
+
"<extra_id_4>": 263,
|
| 72 |
+
"<extra_id_50>": 309,
|
| 73 |
+
"<extra_id_51>": 310,
|
| 74 |
+
"<extra_id_52>": 311,
|
| 75 |
+
"<extra_id_53>": 312,
|
| 76 |
+
"<extra_id_54>": 313,
|
| 77 |
+
"<extra_id_55>": 314,
|
| 78 |
+
"<extra_id_56>": 315,
|
| 79 |
+
"<extra_id_57>": 316,
|
| 80 |
+
"<extra_id_58>": 317,
|
| 81 |
+
"<extra_id_59>": 318,
|
| 82 |
+
"<extra_id_5>": 264,
|
| 83 |
+
"<extra_id_60>": 319,
|
| 84 |
+
"<extra_id_61>": 320,
|
| 85 |
+
"<extra_id_62>": 321,
|
| 86 |
+
"<extra_id_63>": 322,
|
| 87 |
+
"<extra_id_64>": 323,
|
| 88 |
+
"<extra_id_65>": 324,
|
| 89 |
+
"<extra_id_66>": 325,
|
| 90 |
+
"<extra_id_67>": 326,
|
| 91 |
+
"<extra_id_68>": 327,
|
| 92 |
+
"<extra_id_69>": 328,
|
| 93 |
+
"<extra_id_6>": 265,
|
| 94 |
+
"<extra_id_70>": 329,
|
| 95 |
+
"<extra_id_71>": 330,
|
| 96 |
+
"<extra_id_72>": 331,
|
| 97 |
+
"<extra_id_73>": 332,
|
| 98 |
+
"<extra_id_74>": 333,
|
| 99 |
+
"<extra_id_75>": 334,
|
| 100 |
+
"<extra_id_76>": 335,
|
| 101 |
+
"<extra_id_77>": 336,
|
| 102 |
+
"<extra_id_78>": 337,
|
| 103 |
+
"<extra_id_79>": 338,
|
| 104 |
+
"<extra_id_7>": 266,
|
| 105 |
+
"<extra_id_80>": 339,
|
| 106 |
+
"<extra_id_81>": 340,
|
| 107 |
+
"<extra_id_82>": 341,
|
| 108 |
+
"<extra_id_83>": 342,
|
| 109 |
+
"<extra_id_84>": 343,
|
| 110 |
+
"<extra_id_85>": 344,
|
| 111 |
+
"<extra_id_86>": 345,
|
| 112 |
+
"<extra_id_87>": 346,
|
| 113 |
+
"<extra_id_88>": 347,
|
| 114 |
+
"<extra_id_89>": 348,
|
| 115 |
+
"<extra_id_8>": 267,
|
| 116 |
+
"<extra_id_90>": 349,
|
| 117 |
+
"<extra_id_91>": 350,
|
| 118 |
+
"<extra_id_92>": 351,
|
| 119 |
+
"<extra_id_93>": 352,
|
| 120 |
+
"<extra_id_94>": 353,
|
| 121 |
+
"<extra_id_95>": 354,
|
| 122 |
+
"<extra_id_96>": 355,
|
| 123 |
+
"<extra_id_97>": 356,
|
| 124 |
+
"<extra_id_98>": 357,
|
| 125 |
+
"<extra_id_99>": 358,
|
| 126 |
+
"<extra_id_9>": 268
|
| 127 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 3840,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1536,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 16,
|
| 23 |
+
"num_layers": 36,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 30 |
+
"transformers_version": "4.57.6",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 384
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.57.6"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:005949de6d559363bec3846254764b6ee3c766f10c81444da1f3dc967f85f2a2
|
| 3 |
+
size 4912795416
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eab44ef2046e1bdfb96816e7877e73bbeb0159c6ca0568abe6eaeb24b9b7ee68
|
| 3 |
+
size 9825908525
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88f3a10d9c6247faa3d188e5121618bc7a3138568cc4e9c9c55f52106126daa5
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2efd8a83a01ce30e710e01e70684c97fc5098f0cfc80467284ff94ac2ba163d5
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"eos_token": {
|
| 130 |
+
"content": "</s>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": true,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
"pad_token": {
|
| 137 |
+
"content": "<pad>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
"unk_token": {
|
| 144 |
+
"content": "<unk>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
}
|
| 150 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"259": {
|
| 28 |
+
"content": "<extra_id_0>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"260": {
|
| 36 |
+
"content": "<extra_id_1>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"261": {
|
| 44 |
+
"content": "<extra_id_2>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"262": {
|
| 52 |
+
"content": "<extra_id_3>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"263": {
|
| 60 |
+
"content": "<extra_id_4>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"264": {
|
| 68 |
+
"content": "<extra_id_5>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"265": {
|
| 76 |
+
"content": "<extra_id_6>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"266": {
|
| 84 |
+
"content": "<extra_id_7>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"267": {
|
| 92 |
+
"content": "<extra_id_8>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"268": {
|
| 100 |
+
"content": "<extra_id_9>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"269": {
|
| 108 |
+
"content": "<extra_id_10>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"270": {
|
| 116 |
+
"content": "<extra_id_11>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"271": {
|
| 124 |
+
"content": "<extra_id_12>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"272": {
|
| 132 |
+
"content": "<extra_id_13>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"273": {
|
| 140 |
+
"content": "<extra_id_14>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"274": {
|
| 148 |
+
"content": "<extra_id_15>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"275": {
|
| 156 |
+
"content": "<extra_id_16>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"276": {
|
| 164 |
+
"content": "<extra_id_17>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"277": {
|
| 172 |
+
"content": "<extra_id_18>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"278": {
|
| 180 |
+
"content": "<extra_id_19>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"279": {
|
| 188 |
+
"content": "<extra_id_20>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"280": {
|
| 196 |
+
"content": "<extra_id_21>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"281": {
|
| 204 |
+
"content": "<extra_id_22>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"282": {
|
| 212 |
+
"content": "<extra_id_23>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"283": {
|
| 220 |
+
"content": "<extra_id_24>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"284": {
|
| 228 |
+
"content": "<extra_id_25>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"285": {
|
| 236 |
+
"content": "<extra_id_26>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"286": {
|
| 244 |
+
"content": "<extra_id_27>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"287": {
|
| 252 |
+
"content": "<extra_id_28>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"288": {
|
| 260 |
+
"content": "<extra_id_29>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"289": {
|
| 268 |
+
"content": "<extra_id_30>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"290": {
|
| 276 |
+
"content": "<extra_id_31>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"291": {
|
| 284 |
+
"content": "<extra_id_32>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"292": {
|
| 292 |
+
"content": "<extra_id_33>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"293": {
|
| 300 |
+
"content": "<extra_id_34>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"294": {
|
| 308 |
+
"content": "<extra_id_35>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"295": {
|
| 316 |
+
"content": "<extra_id_36>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"296": {
|
| 324 |
+
"content": "<extra_id_37>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"297": {
|
| 332 |
+
"content": "<extra_id_38>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"298": {
|
| 340 |
+
"content": "<extra_id_39>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"299": {
|
| 348 |
+
"content": "<extra_id_40>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"300": {
|
| 356 |
+
"content": "<extra_id_41>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"301": {
|
| 364 |
+
"content": "<extra_id_42>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"302": {
|
| 372 |
+
"content": "<extra_id_43>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"303": {
|
| 380 |
+
"content": "<extra_id_44>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"304": {
|
| 388 |
+
"content": "<extra_id_45>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"305": {
|
| 396 |
+
"content": "<extra_id_46>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"306": {
|
| 404 |
+
"content": "<extra_id_47>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"307": {
|
| 412 |
+
"content": "<extra_id_48>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"308": {
|
| 420 |
+
"content": "<extra_id_49>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"309": {
|
| 428 |
+
"content": "<extra_id_50>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"310": {
|
| 436 |
+
"content": "<extra_id_51>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"311": {
|
| 444 |
+
"content": "<extra_id_52>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"312": {
|
| 452 |
+
"content": "<extra_id_53>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"313": {
|
| 460 |
+
"content": "<extra_id_54>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"314": {
|
| 468 |
+
"content": "<extra_id_55>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"315": {
|
| 476 |
+
"content": "<extra_id_56>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"316": {
|
| 484 |
+
"content": "<extra_id_57>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"317": {
|
| 492 |
+
"content": "<extra_id_58>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"318": {
|
| 500 |
+
"content": "<extra_id_59>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"319": {
|
| 508 |
+
"content": "<extra_id_60>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"320": {
|
| 516 |
+
"content": "<extra_id_61>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"321": {
|
| 524 |
+
"content": "<extra_id_62>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"322": {
|
| 532 |
+
"content": "<extra_id_63>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"323": {
|
| 540 |
+
"content": "<extra_id_64>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"324": {
|
| 548 |
+
"content": "<extra_id_65>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"325": {
|
| 556 |
+
"content": "<extra_id_66>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"326": {
|
| 564 |
+
"content": "<extra_id_67>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"327": {
|
| 572 |
+
"content": "<extra_id_68>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"328": {
|
| 580 |
+
"content": "<extra_id_69>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"329": {
|
| 588 |
+
"content": "<extra_id_70>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"330": {
|
| 596 |
+
"content": "<extra_id_71>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"331": {
|
| 604 |
+
"content": "<extra_id_72>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"332": {
|
| 612 |
+
"content": "<extra_id_73>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"333": {
|
| 620 |
+
"content": "<extra_id_74>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"334": {
|
| 628 |
+
"content": "<extra_id_75>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"335": {
|
| 636 |
+
"content": "<extra_id_76>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"336": {
|
| 644 |
+
"content": "<extra_id_77>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"337": {
|
| 652 |
+
"content": "<extra_id_78>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"338": {
|
| 660 |
+
"content": "<extra_id_79>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"339": {
|
| 668 |
+
"content": "<extra_id_80>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"340": {
|
| 676 |
+
"content": "<extra_id_81>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"341": {
|
| 684 |
+
"content": "<extra_id_82>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"342": {
|
| 692 |
+
"content": "<extra_id_83>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"343": {
|
| 700 |
+
"content": "<extra_id_84>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"344": {
|
| 708 |
+
"content": "<extra_id_85>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"345": {
|
| 716 |
+
"content": "<extra_id_86>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"346": {
|
| 724 |
+
"content": "<extra_id_87>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"347": {
|
| 732 |
+
"content": "<extra_id_88>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"348": {
|
| 740 |
+
"content": "<extra_id_89>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"349": {
|
| 748 |
+
"content": "<extra_id_90>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"350": {
|
| 756 |
+
"content": "<extra_id_91>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"351": {
|
| 764 |
+
"content": "<extra_id_92>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"352": {
|
| 772 |
+
"content": "<extra_id_93>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"353": {
|
| 780 |
+
"content": "<extra_id_94>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"354": {
|
| 788 |
+
"content": "<extra_id_95>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"355": {
|
| 796 |
+
"content": "<extra_id_96>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"356": {
|
| 804 |
+
"content": "<extra_id_97>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"357": {
|
| 812 |
+
"content": "<extra_id_98>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"358": {
|
| 820 |
+
"content": "<extra_id_99>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"359": {
|
| 828 |
+
"content": "<extra_id_100>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"360": {
|
| 836 |
+
"content": "<extra_id_101>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"361": {
|
| 844 |
+
"content": "<extra_id_102>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"362": {
|
| 852 |
+
"content": "<extra_id_103>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"363": {
|
| 860 |
+
"content": "<extra_id_104>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"364": {
|
| 868 |
+
"content": "<extra_id_105>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"365": {
|
| 876 |
+
"content": "<extra_id_106>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"366": {
|
| 884 |
+
"content": "<extra_id_107>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"367": {
|
| 892 |
+
"content": "<extra_id_108>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"368": {
|
| 900 |
+
"content": "<extra_id_109>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"369": {
|
| 908 |
+
"content": "<extra_id_110>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"370": {
|
| 916 |
+
"content": "<extra_id_111>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"371": {
|
| 924 |
+
"content": "<extra_id_112>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"372": {
|
| 932 |
+
"content": "<extra_id_113>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"373": {
|
| 940 |
+
"content": "<extra_id_114>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"374": {
|
| 948 |
+
"content": "<extra_id_115>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"375": {
|
| 956 |
+
"content": "<extra_id_116>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"376": {
|
| 964 |
+
"content": "<extra_id_117>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"377": {
|
| 972 |
+
"content": "<extra_id_118>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"378": {
|
| 980 |
+
"content": "<extra_id_119>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"379": {
|
| 988 |
+
"content": "<extra_id_120>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"380": {
|
| 996 |
+
"content": "<extra_id_121>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"381": {
|
| 1004 |
+
"content": "<extra_id_122>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"382": {
|
| 1012 |
+
"content": "<extra_id_123>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"383": {
|
| 1020 |
+
"content": "<extra_id_124>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
}
|
| 1027 |
+
},
|
| 1028 |
+
"additional_special_tokens": [
|
| 1029 |
+
"<extra_id_0>",
|
| 1030 |
+
"<extra_id_1>",
|
| 1031 |
+
"<extra_id_2>",
|
| 1032 |
+
"<extra_id_3>",
|
| 1033 |
+
"<extra_id_4>",
|
| 1034 |
+
"<extra_id_5>",
|
| 1035 |
+
"<extra_id_6>",
|
| 1036 |
+
"<extra_id_7>",
|
| 1037 |
+
"<extra_id_8>",
|
| 1038 |
+
"<extra_id_9>",
|
| 1039 |
+
"<extra_id_10>",
|
| 1040 |
+
"<extra_id_11>",
|
| 1041 |
+
"<extra_id_12>",
|
| 1042 |
+
"<extra_id_13>",
|
| 1043 |
+
"<extra_id_14>",
|
| 1044 |
+
"<extra_id_15>",
|
| 1045 |
+
"<extra_id_16>",
|
| 1046 |
+
"<extra_id_17>",
|
| 1047 |
+
"<extra_id_18>",
|
| 1048 |
+
"<extra_id_19>",
|
| 1049 |
+
"<extra_id_20>",
|
| 1050 |
+
"<extra_id_21>",
|
| 1051 |
+
"<extra_id_22>",
|
| 1052 |
+
"<extra_id_23>",
|
| 1053 |
+
"<extra_id_24>",
|
| 1054 |
+
"<extra_id_25>",
|
| 1055 |
+
"<extra_id_26>",
|
| 1056 |
+
"<extra_id_27>",
|
| 1057 |
+
"<extra_id_28>",
|
| 1058 |
+
"<extra_id_29>",
|
| 1059 |
+
"<extra_id_30>",
|
| 1060 |
+
"<extra_id_31>",
|
| 1061 |
+
"<extra_id_32>",
|
| 1062 |
+
"<extra_id_33>",
|
| 1063 |
+
"<extra_id_34>",
|
| 1064 |
+
"<extra_id_35>",
|
| 1065 |
+
"<extra_id_36>",
|
| 1066 |
+
"<extra_id_37>",
|
| 1067 |
+
"<extra_id_38>",
|
| 1068 |
+
"<extra_id_39>",
|
| 1069 |
+
"<extra_id_40>",
|
| 1070 |
+
"<extra_id_41>",
|
| 1071 |
+
"<extra_id_42>",
|
| 1072 |
+
"<extra_id_43>",
|
| 1073 |
+
"<extra_id_44>",
|
| 1074 |
+
"<extra_id_45>",
|
| 1075 |
+
"<extra_id_46>",
|
| 1076 |
+
"<extra_id_47>",
|
| 1077 |
+
"<extra_id_48>",
|
| 1078 |
+
"<extra_id_49>",
|
| 1079 |
+
"<extra_id_50>",
|
| 1080 |
+
"<extra_id_51>",
|
| 1081 |
+
"<extra_id_52>",
|
| 1082 |
+
"<extra_id_53>",
|
| 1083 |
+
"<extra_id_54>",
|
| 1084 |
+
"<extra_id_55>",
|
| 1085 |
+
"<extra_id_56>",
|
| 1086 |
+
"<extra_id_57>",
|
| 1087 |
+
"<extra_id_58>",
|
| 1088 |
+
"<extra_id_59>",
|
| 1089 |
+
"<extra_id_60>",
|
| 1090 |
+
"<extra_id_61>",
|
| 1091 |
+
"<extra_id_62>",
|
| 1092 |
+
"<extra_id_63>",
|
| 1093 |
+
"<extra_id_64>",
|
| 1094 |
+
"<extra_id_65>",
|
| 1095 |
+
"<extra_id_66>",
|
| 1096 |
+
"<extra_id_67>",
|
| 1097 |
+
"<extra_id_68>",
|
| 1098 |
+
"<extra_id_69>",
|
| 1099 |
+
"<extra_id_70>",
|
| 1100 |
+
"<extra_id_71>",
|
| 1101 |
+
"<extra_id_72>",
|
| 1102 |
+
"<extra_id_73>",
|
| 1103 |
+
"<extra_id_74>",
|
| 1104 |
+
"<extra_id_75>",
|
| 1105 |
+
"<extra_id_76>",
|
| 1106 |
+
"<extra_id_77>",
|
| 1107 |
+
"<extra_id_78>",
|
| 1108 |
+
"<extra_id_79>",
|
| 1109 |
+
"<extra_id_80>",
|
| 1110 |
+
"<extra_id_81>",
|
| 1111 |
+
"<extra_id_82>",
|
| 1112 |
+
"<extra_id_83>",
|
| 1113 |
+
"<extra_id_84>",
|
| 1114 |
+
"<extra_id_85>",
|
| 1115 |
+
"<extra_id_86>",
|
| 1116 |
+
"<extra_id_87>",
|
| 1117 |
+
"<extra_id_88>",
|
| 1118 |
+
"<extra_id_89>",
|
| 1119 |
+
"<extra_id_90>",
|
| 1120 |
+
"<extra_id_91>",
|
| 1121 |
+
"<extra_id_92>",
|
| 1122 |
+
"<extra_id_93>",
|
| 1123 |
+
"<extra_id_94>",
|
| 1124 |
+
"<extra_id_95>",
|
| 1125 |
+
"<extra_id_96>",
|
| 1126 |
+
"<extra_id_97>",
|
| 1127 |
+
"<extra_id_98>",
|
| 1128 |
+
"<extra_id_99>",
|
| 1129 |
+
"<extra_id_100>",
|
| 1130 |
+
"<extra_id_101>",
|
| 1131 |
+
"<extra_id_102>",
|
| 1132 |
+
"<extra_id_103>",
|
| 1133 |
+
"<extra_id_104>",
|
| 1134 |
+
"<extra_id_105>",
|
| 1135 |
+
"<extra_id_106>",
|
| 1136 |
+
"<extra_id_107>",
|
| 1137 |
+
"<extra_id_108>",
|
| 1138 |
+
"<extra_id_109>",
|
| 1139 |
+
"<extra_id_110>",
|
| 1140 |
+
"<extra_id_111>",
|
| 1141 |
+
"<extra_id_112>",
|
| 1142 |
+
"<extra_id_113>",
|
| 1143 |
+
"<extra_id_114>",
|
| 1144 |
+
"<extra_id_115>",
|
| 1145 |
+
"<extra_id_116>",
|
| 1146 |
+
"<extra_id_117>",
|
| 1147 |
+
"<extra_id_118>",
|
| 1148 |
+
"<extra_id_119>",
|
| 1149 |
+
"<extra_id_120>",
|
| 1150 |
+
"<extra_id_121>",
|
| 1151 |
+
"<extra_id_122>",
|
| 1152 |
+
"<extra_id_123>",
|
| 1153 |
+
"<extra_id_124>"
|
| 1154 |
+
],
|
| 1155 |
+
"clean_up_tokenization_spaces": false,
|
| 1156 |
+
"eos_token": "</s>",
|
| 1157 |
+
"extra_ids": 0,
|
| 1158 |
+
"extra_special_tokens": {},
|
| 1159 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1160 |
+
"pad_token": "<pad>",
|
| 1161 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 1162 |
+
"unk_token": "<unk>"
|
| 1163 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1420,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.07042253521126761,
|
| 14 |
+
"grad_norm": 298.37652587890625,
|
| 15 |
+
"learning_rate": 0.00019943661971830986,
|
| 16 |
+
"loss": 32.3915,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.14084507042253522,
|
| 21 |
+
"grad_norm": 93.51129150390625,
|
| 22 |
+
"learning_rate": 0.0001987323943661972,
|
| 23 |
+
"loss": 28.743,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.2112676056338028,
|
| 28 |
+
"grad_norm": 47.780601501464844,
|
| 29 |
+
"learning_rate": 0.00019802816901408452,
|
| 30 |
+
"loss": 25.2619,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.28169014084507044,
|
| 35 |
+
"grad_norm": 50.333736419677734,
|
| 36 |
+
"learning_rate": 0.00019732394366197184,
|
| 37 |
+
"loss": 22.2152,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.352112676056338,
|
| 42 |
+
"grad_norm": 16.70964241027832,
|
| 43 |
+
"learning_rate": 0.00019661971830985917,
|
| 44 |
+
"loss": 18.6695,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4225352112676056,
|
| 49 |
+
"grad_norm": 15.14587688446045,
|
| 50 |
+
"learning_rate": 0.0001959154929577465,
|
| 51 |
+
"loss": 14.7068,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.49295774647887325,
|
| 56 |
+
"grad_norm": 9.351914405822754,
|
| 57 |
+
"learning_rate": 0.00019521126760563382,
|
| 58 |
+
"loss": 8.1565,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5633802816901409,
|
| 63 |
+
"grad_norm": 8.563234329223633,
|
| 64 |
+
"learning_rate": 0.00019450704225352114,
|
| 65 |
+
"loss": 5.4416,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6338028169014085,
|
| 70 |
+
"grad_norm": 6.7714691162109375,
|
| 71 |
+
"learning_rate": 0.00019380281690140847,
|
| 72 |
+
"loss": 5.0701,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.704225352112676,
|
| 77 |
+
"grad_norm": 4.738491535186768,
|
| 78 |
+
"learning_rate": 0.0001930985915492958,
|
| 79 |
+
"loss": 4.6657,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7746478873239436,
|
| 84 |
+
"grad_norm": 5.511097431182861,
|
| 85 |
+
"learning_rate": 0.00019239436619718312,
|
| 86 |
+
"loss": 4.2706,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8450704225352113,
|
| 91 |
+
"grad_norm": 5.683650970458984,
|
| 92 |
+
"learning_rate": 0.00019169014084507045,
|
| 93 |
+
"loss": 3.8374,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.9154929577464789,
|
| 98 |
+
"grad_norm": 4.763166427612305,
|
| 99 |
+
"learning_rate": 0.00019098591549295774,
|
| 100 |
+
"loss": 3.3471,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.9859154929577465,
|
| 105 |
+
"grad_norm": 2.353513240814209,
|
| 106 |
+
"learning_rate": 0.00019028169014084507,
|
| 107 |
+
"loss": 2.9019,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.0,
|
| 112 |
+
"eval_loss": 2.327265977859497,
|
| 113 |
+
"eval_runtime": 1.3559,
|
| 114 |
+
"eval_samples_per_second": 279.528,
|
| 115 |
+
"eval_steps_per_second": 2.213,
|
| 116 |
+
"step": 71
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.056338028169014,
|
| 120 |
+
"grad_norm": 2.5209953784942627,
|
| 121 |
+
"learning_rate": 0.0001895774647887324,
|
| 122 |
+
"loss": 2.5521,
|
| 123 |
+
"step": 75
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.1267605633802817,
|
| 127 |
+
"grad_norm": 0.8227373957633972,
|
| 128 |
+
"learning_rate": 0.00018887323943661972,
|
| 129 |
+
"loss": 2.3236,
|
| 130 |
+
"step": 80
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.1971830985915493,
|
| 134 |
+
"grad_norm": 0.8206098675727844,
|
| 135 |
+
"learning_rate": 0.00018816901408450705,
|
| 136 |
+
"loss": 2.1289,
|
| 137 |
+
"step": 85
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.267605633802817,
|
| 141 |
+
"grad_norm": 0.748960018157959,
|
| 142 |
+
"learning_rate": 0.00018746478873239437,
|
| 143 |
+
"loss": 1.6767,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.3380281690140845,
|
| 148 |
+
"grad_norm": 0.4808853566646576,
|
| 149 |
+
"learning_rate": 0.0001867605633802817,
|
| 150 |
+
"loss": 1.419,
|
| 151 |
+
"step": 95
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.408450704225352,
|
| 155 |
+
"grad_norm": 1.964240312576294,
|
| 156 |
+
"learning_rate": 0.00018605633802816902,
|
| 157 |
+
"loss": 1.3036,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.4788732394366197,
|
| 162 |
+
"grad_norm": 0.2643977403640747,
|
| 163 |
+
"learning_rate": 0.00018535211267605635,
|
| 164 |
+
"loss": 1.2568,
|
| 165 |
+
"step": 105
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.5492957746478875,
|
| 169 |
+
"grad_norm": 0.38880959153175354,
|
| 170 |
+
"learning_rate": 0.00018464788732394367,
|
| 171 |
+
"loss": 1.2002,
|
| 172 |
+
"step": 110
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.619718309859155,
|
| 176 |
+
"grad_norm": 0.22605347633361816,
|
| 177 |
+
"learning_rate": 0.000183943661971831,
|
| 178 |
+
"loss": 1.1694,
|
| 179 |
+
"step": 115
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.6901408450704225,
|
| 183 |
+
"grad_norm": 0.23560728132724762,
|
| 184 |
+
"learning_rate": 0.00018323943661971832,
|
| 185 |
+
"loss": 1.1492,
|
| 186 |
+
"step": 120
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.76056338028169,
|
| 190 |
+
"grad_norm": 0.15073446929454803,
|
| 191 |
+
"learning_rate": 0.00018253521126760565,
|
| 192 |
+
"loss": 1.1263,
|
| 193 |
+
"step": 125
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.8309859154929577,
|
| 197 |
+
"grad_norm": 0.12264095991849899,
|
| 198 |
+
"learning_rate": 0.00018183098591549298,
|
| 199 |
+
"loss": 1.1051,
|
| 200 |
+
"step": 130
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.9014084507042255,
|
| 204 |
+
"grad_norm": 0.1781918853521347,
|
| 205 |
+
"learning_rate": 0.0001811267605633803,
|
| 206 |
+
"loss": 1.0964,
|
| 207 |
+
"step": 135
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.971830985915493,
|
| 211 |
+
"grad_norm": 0.15171071887016296,
|
| 212 |
+
"learning_rate": 0.00018042253521126763,
|
| 213 |
+
"loss": 1.0779,
|
| 214 |
+
"step": 140
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.0,
|
| 218 |
+
"eval_loss": 1.0098963975906372,
|
| 219 |
+
"eval_runtime": 1.3563,
|
| 220 |
+
"eval_samples_per_second": 279.438,
|
| 221 |
+
"eval_steps_per_second": 2.212,
|
| 222 |
+
"step": 142
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.0422535211267605,
|
| 226 |
+
"grad_norm": 0.11982790380716324,
|
| 227 |
+
"learning_rate": 0.00017971830985915495,
|
| 228 |
+
"loss": 1.0746,
|
| 229 |
+
"step": 145
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.112676056338028,
|
| 233 |
+
"grad_norm": 0.11876315623521805,
|
| 234 |
+
"learning_rate": 0.00017901408450704228,
|
| 235 |
+
"loss": 1.0658,
|
| 236 |
+
"step": 150
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.183098591549296,
|
| 240 |
+
"grad_norm": 0.09626977145671844,
|
| 241 |
+
"learning_rate": 0.0001783098591549296,
|
| 242 |
+
"loss": 1.0535,
|
| 243 |
+
"step": 155
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.2535211267605635,
|
| 247 |
+
"grad_norm": 0.11824846267700195,
|
| 248 |
+
"learning_rate": 0.00017760563380281693,
|
| 249 |
+
"loss": 1.0492,
|
| 250 |
+
"step": 160
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.323943661971831,
|
| 254 |
+
"grad_norm": 0.1524844616651535,
|
| 255 |
+
"learning_rate": 0.00017690140845070425,
|
| 256 |
+
"loss": 1.04,
|
| 257 |
+
"step": 165
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.3943661971830985,
|
| 261 |
+
"grad_norm": 0.10610729455947876,
|
| 262 |
+
"learning_rate": 0.00017619718309859158,
|
| 263 |
+
"loss": 1.0355,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.464788732394366,
|
| 268 |
+
"grad_norm": 0.09342360496520996,
|
| 269 |
+
"learning_rate": 0.0001754929577464789,
|
| 270 |
+
"loss": 1.0333,
|
| 271 |
+
"step": 175
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.535211267605634,
|
| 275 |
+
"grad_norm": 0.10479816794395447,
|
| 276 |
+
"learning_rate": 0.0001747887323943662,
|
| 277 |
+
"loss": 1.0318,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.6056338028169015,
|
| 282 |
+
"grad_norm": 0.0711260586977005,
|
| 283 |
+
"learning_rate": 0.00017408450704225353,
|
| 284 |
+
"loss": 1.0241,
|
| 285 |
+
"step": 185
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.676056338028169,
|
| 289 |
+
"grad_norm": 0.11890017986297607,
|
| 290 |
+
"learning_rate": 0.00017338028169014086,
|
| 291 |
+
"loss": 1.0241,
|
| 292 |
+
"step": 190
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.7464788732394365,
|
| 296 |
+
"grad_norm": 0.10851440578699112,
|
| 297 |
+
"learning_rate": 0.00017267605633802818,
|
| 298 |
+
"loss": 1.018,
|
| 299 |
+
"step": 195
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.816901408450704,
|
| 303 |
+
"grad_norm": 0.1457432061433792,
|
| 304 |
+
"learning_rate": 0.0001719718309859155,
|
| 305 |
+
"loss": 1.0149,
|
| 306 |
+
"step": 200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.887323943661972,
|
| 310 |
+
"grad_norm": 0.0658695176243782,
|
| 311 |
+
"learning_rate": 0.00017126760563380283,
|
| 312 |
+
"loss": 1.0093,
|
| 313 |
+
"step": 205
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.9577464788732395,
|
| 317 |
+
"grad_norm": 0.09453574568033218,
|
| 318 |
+
"learning_rate": 0.00017056338028169016,
|
| 319 |
+
"loss": 1.0081,
|
| 320 |
+
"step": 210
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.0,
|
| 324 |
+
"eval_loss": 0.9575695395469666,
|
| 325 |
+
"eval_runtime": 1.3565,
|
| 326 |
+
"eval_samples_per_second": 279.401,
|
| 327 |
+
"eval_steps_per_second": 2.212,
|
| 328 |
+
"step": 213
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.028169014084507,
|
| 332 |
+
"grad_norm": 0.13185155391693115,
|
| 333 |
+
"learning_rate": 0.00016985915492957746,
|
| 334 |
+
"loss": 1.0059,
|
| 335 |
+
"step": 215
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.0985915492957745,
|
| 339 |
+
"grad_norm": 0.10181483626365662,
|
| 340 |
+
"learning_rate": 0.00016915492957746478,
|
| 341 |
+
"loss": 0.9993,
|
| 342 |
+
"step": 220
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.169014084507042,
|
| 346 |
+
"grad_norm": 0.07031014561653137,
|
| 347 |
+
"learning_rate": 0.0001684507042253521,
|
| 348 |
+
"loss": 1.0002,
|
| 349 |
+
"step": 225
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.23943661971831,
|
| 353 |
+
"grad_norm": 0.08129975944757462,
|
| 354 |
+
"learning_rate": 0.00016774647887323943,
|
| 355 |
+
"loss": 0.9966,
|
| 356 |
+
"step": 230
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.3098591549295775,
|
| 360 |
+
"grad_norm": 0.061685919761657715,
|
| 361 |
+
"learning_rate": 0.00016704225352112676,
|
| 362 |
+
"loss": 0.9986,
|
| 363 |
+
"step": 235
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.380281690140845,
|
| 367 |
+
"grad_norm": 0.10376816242933273,
|
| 368 |
+
"learning_rate": 0.00016633802816901408,
|
| 369 |
+
"loss": 0.9914,
|
| 370 |
+
"step": 240
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.4507042253521125,
|
| 374 |
+
"grad_norm": 0.16595374047756195,
|
| 375 |
+
"learning_rate": 0.0001656338028169014,
|
| 376 |
+
"loss": 0.9944,
|
| 377 |
+
"step": 245
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.52112676056338,
|
| 381 |
+
"grad_norm": 0.0959262102842331,
|
| 382 |
+
"learning_rate": 0.00016492957746478873,
|
| 383 |
+
"loss": 0.99,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.591549295774648,
|
| 388 |
+
"grad_norm": 0.04954326152801514,
|
| 389 |
+
"learning_rate": 0.00016422535211267606,
|
| 390 |
+
"loss": 0.9887,
|
| 391 |
+
"step": 255
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 3.6619718309859155,
|
| 395 |
+
"grad_norm": 0.09042917937040329,
|
| 396 |
+
"learning_rate": 0.00016352112676056339,
|
| 397 |
+
"loss": 0.989,
|
| 398 |
+
"step": 260
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.732394366197183,
|
| 402 |
+
"grad_norm": 0.1556464284658432,
|
| 403 |
+
"learning_rate": 0.0001628169014084507,
|
| 404 |
+
"loss": 0.9914,
|
| 405 |
+
"step": 265
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.802816901408451,
|
| 409 |
+
"grad_norm": 0.0660383403301239,
|
| 410 |
+
"learning_rate": 0.00016211267605633804,
|
| 411 |
+
"loss": 0.9874,
|
| 412 |
+
"step": 270
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 3.873239436619718,
|
| 416 |
+
"grad_norm": 0.08755503594875336,
|
| 417 |
+
"learning_rate": 0.00016140845070422536,
|
| 418 |
+
"loss": 0.9823,
|
| 419 |
+
"step": 275
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.943661971830986,
|
| 423 |
+
"grad_norm": 0.07488470524549484,
|
| 424 |
+
"learning_rate": 0.0001607042253521127,
|
| 425 |
+
"loss": 0.9846,
|
| 426 |
+
"step": 280
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 4.0,
|
| 430 |
+
"eval_loss": 0.9477686285972595,
|
| 431 |
+
"eval_runtime": 1.356,
|
| 432 |
+
"eval_samples_per_second": 279.49,
|
| 433 |
+
"eval_steps_per_second": 2.212,
|
| 434 |
+
"step": 284
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.014084507042254,
|
| 438 |
+
"grad_norm": 0.0663798451423645,
|
| 439 |
+
"learning_rate": 0.00016,
|
| 440 |
+
"loss": 0.9813,
|
| 441 |
+
"step": 285
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.084507042253521,
|
| 445 |
+
"grad_norm": 0.07960853725671768,
|
| 446 |
+
"learning_rate": 0.00015929577464788734,
|
| 447 |
+
"loss": 0.9834,
|
| 448 |
+
"step": 290
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.154929577464789,
|
| 452 |
+
"grad_norm": 0.0459803082048893,
|
| 453 |
+
"learning_rate": 0.00015859154929577466,
|
| 454 |
+
"loss": 0.9813,
|
| 455 |
+
"step": 295
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.225352112676056,
|
| 459 |
+
"grad_norm": 1.369140386581421,
|
| 460 |
+
"learning_rate": 0.00015788732394366196,
|
| 461 |
+
"loss": 0.9847,
|
| 462 |
+
"step": 300
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.295774647887324,
|
| 466 |
+
"grad_norm": 5.1048102378845215,
|
| 467 |
+
"learning_rate": 0.0001571830985915493,
|
| 468 |
+
"loss": 0.9825,
|
| 469 |
+
"step": 305
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 4.366197183098592,
|
| 473 |
+
"grad_norm": 0.722586452960968,
|
| 474 |
+
"learning_rate": 0.00015647887323943661,
|
| 475 |
+
"loss": 0.9782,
|
| 476 |
+
"step": 310
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.436619718309859,
|
| 480 |
+
"grad_norm": 0.11551281064748764,
|
| 481 |
+
"learning_rate": 0.00015577464788732394,
|
| 482 |
+
"loss": 0.9775,
|
| 483 |
+
"step": 315
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.507042253521127,
|
| 487 |
+
"grad_norm": 0.07706153392791748,
|
| 488 |
+
"learning_rate": 0.00015507042253521126,
|
| 489 |
+
"loss": 0.9765,
|
| 490 |
+
"step": 320
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.577464788732394,
|
| 494 |
+
"grad_norm": 0.13360825181007385,
|
| 495 |
+
"learning_rate": 0.0001543661971830986,
|
| 496 |
+
"loss": 0.9825,
|
| 497 |
+
"step": 325
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.647887323943662,
|
| 501 |
+
"grad_norm": 0.0996808111667633,
|
| 502 |
+
"learning_rate": 0.00015366197183098592,
|
| 503 |
+
"loss": 0.9755,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.71830985915493,
|
| 508 |
+
"grad_norm": 0.064101941883564,
|
| 509 |
+
"learning_rate": 0.00015295774647887324,
|
| 510 |
+
"loss": 0.9747,
|
| 511 |
+
"step": 335
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.788732394366197,
|
| 515 |
+
"grad_norm": 0.0587599016726017,
|
| 516 |
+
"learning_rate": 0.00015225352112676057,
|
| 517 |
+
"loss": 0.9762,
|
| 518 |
+
"step": 340
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.859154929577465,
|
| 522 |
+
"grad_norm": 0.08781857788562775,
|
| 523 |
+
"learning_rate": 0.0001515492957746479,
|
| 524 |
+
"loss": 0.9725,
|
| 525 |
+
"step": 345
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.929577464788732,
|
| 529 |
+
"grad_norm": 0.09201648831367493,
|
| 530 |
+
"learning_rate": 0.00015084507042253522,
|
| 531 |
+
"loss": 0.9751,
|
| 532 |
+
"step": 350
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.0,
|
| 536 |
+
"grad_norm": 0.07896555215120316,
|
| 537 |
+
"learning_rate": 0.00015014084507042254,
|
| 538 |
+
"loss": 0.974,
|
| 539 |
+
"step": 355
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.0,
|
| 543 |
+
"eval_loss": 0.9434144496917725,
|
| 544 |
+
"eval_runtime": 1.3282,
|
| 545 |
+
"eval_samples_per_second": 285.356,
|
| 546 |
+
"eval_steps_per_second": 2.259,
|
| 547 |
+
"step": 355
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.070422535211268,
|
| 551 |
+
"grad_norm": 0.06868085265159607,
|
| 552 |
+
"learning_rate": 0.00014943661971830987,
|
| 553 |
+
"loss": 0.9773,
|
| 554 |
+
"step": 360
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 5.140845070422535,
|
| 558 |
+
"grad_norm": 0.06904036551713943,
|
| 559 |
+
"learning_rate": 0.0001487323943661972,
|
| 560 |
+
"loss": 0.9724,
|
| 561 |
+
"step": 365
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 5.211267605633803,
|
| 565 |
+
"grad_norm": 0.05451333895325661,
|
| 566 |
+
"learning_rate": 0.00014802816901408452,
|
| 567 |
+
"loss": 0.9716,
|
| 568 |
+
"step": 370
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.28169014084507,
|
| 572 |
+
"grad_norm": 0.08863852173089981,
|
| 573 |
+
"learning_rate": 0.00014732394366197185,
|
| 574 |
+
"loss": 0.9692,
|
| 575 |
+
"step": 375
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.352112676056338,
|
| 579 |
+
"grad_norm": 0.06055117025971413,
|
| 580 |
+
"learning_rate": 0.00014661971830985917,
|
| 581 |
+
"loss": 0.9713,
|
| 582 |
+
"step": 380
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 5.422535211267606,
|
| 586 |
+
"grad_norm": 0.10994315892457962,
|
| 587 |
+
"learning_rate": 0.0001459154929577465,
|
| 588 |
+
"loss": 0.9707,
|
| 589 |
+
"step": 385
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.492957746478873,
|
| 593 |
+
"grad_norm": 0.09731490910053253,
|
| 594 |
+
"learning_rate": 0.00014521126760563382,
|
| 595 |
+
"loss": 0.9694,
|
| 596 |
+
"step": 390
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 5.563380281690141,
|
| 600 |
+
"grad_norm": 0.05324326828122139,
|
| 601 |
+
"learning_rate": 0.00014450704225352115,
|
| 602 |
+
"loss": 0.9666,
|
| 603 |
+
"step": 395
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.633802816901408,
|
| 607 |
+
"grad_norm": 0.05008189380168915,
|
| 608 |
+
"learning_rate": 0.00014380281690140847,
|
| 609 |
+
"loss": 0.9672,
|
| 610 |
+
"step": 400
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 5.704225352112676,
|
| 614 |
+
"grad_norm": 0.0279605221003294,
|
| 615 |
+
"learning_rate": 0.0001430985915492958,
|
| 616 |
+
"loss": 0.9676,
|
| 617 |
+
"step": 405
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.774647887323944,
|
| 621 |
+
"grad_norm": 0.0670681744813919,
|
| 622 |
+
"learning_rate": 0.00014239436619718312,
|
| 623 |
+
"loss": 0.9654,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.845070422535211,
|
| 628 |
+
"grad_norm": 0.04129045829176903,
|
| 629 |
+
"learning_rate": 0.00014169014084507045,
|
| 630 |
+
"loss": 0.9659,
|
| 631 |
+
"step": 415
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 5.915492957746479,
|
| 635 |
+
"grad_norm": 0.04552697390317917,
|
| 636 |
+
"learning_rate": 0.00014098591549295775,
|
| 637 |
+
"loss": 0.9675,
|
| 638 |
+
"step": 420
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 5.985915492957746,
|
| 642 |
+
"grad_norm": 0.05515826866030693,
|
| 643 |
+
"learning_rate": 0.00014028169014084507,
|
| 644 |
+
"loss": 0.967,
|
| 645 |
+
"step": 425
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 6.0,
|
| 649 |
+
"eval_loss": 0.9389934539794922,
|
| 650 |
+
"eval_runtime": 1.3536,
|
| 651 |
+
"eval_samples_per_second": 279.994,
|
| 652 |
+
"eval_steps_per_second": 2.216,
|
| 653 |
+
"step": 426
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 6.056338028169014,
|
| 657 |
+
"grad_norm": 0.060634512454271317,
|
| 658 |
+
"learning_rate": 0.0001395774647887324,
|
| 659 |
+
"loss": 0.9661,
|
| 660 |
+
"step": 430
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 6.126760563380282,
|
| 664 |
+
"grad_norm": 0.035951510071754456,
|
| 665 |
+
"learning_rate": 0.00013887323943661972,
|
| 666 |
+
"loss": 0.9673,
|
| 667 |
+
"step": 435
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 6.197183098591549,
|
| 671 |
+
"grad_norm": 0.07630197703838348,
|
| 672 |
+
"learning_rate": 0.00013816901408450705,
|
| 673 |
+
"loss": 0.969,
|
| 674 |
+
"step": 440
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.267605633802817,
|
| 678 |
+
"grad_norm": 0.048709649592638016,
|
| 679 |
+
"learning_rate": 0.00013746478873239438,
|
| 680 |
+
"loss": 0.9605,
|
| 681 |
+
"step": 445
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.338028169014084,
|
| 685 |
+
"grad_norm": 0.08284774422645569,
|
| 686 |
+
"learning_rate": 0.0001367605633802817,
|
| 687 |
+
"loss": 0.9647,
|
| 688 |
+
"step": 450
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 6.408450704225352,
|
| 692 |
+
"grad_norm": 0.10234501212835312,
|
| 693 |
+
"learning_rate": 0.00013605633802816903,
|
| 694 |
+
"loss": 0.9649,
|
| 695 |
+
"step": 455
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 6.47887323943662,
|
| 699 |
+
"grad_norm": 0.07582994550466537,
|
| 700 |
+
"learning_rate": 0.00013535211267605635,
|
| 701 |
+
"loss": 0.9637,
|
| 702 |
+
"step": 460
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 6.549295774647887,
|
| 706 |
+
"grad_norm": 0.032033782452344894,
|
| 707 |
+
"learning_rate": 0.00013464788732394368,
|
| 708 |
+
"loss": 0.9616,
|
| 709 |
+
"step": 465
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 6.619718309859155,
|
| 713 |
+
"grad_norm": 0.029730021953582764,
|
| 714 |
+
"learning_rate": 0.000133943661971831,
|
| 715 |
+
"loss": 0.961,
|
| 716 |
+
"step": 470
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 6.690140845070422,
|
| 720 |
+
"grad_norm": 0.036565788090229034,
|
| 721 |
+
"learning_rate": 0.00013323943661971833,
|
| 722 |
+
"loss": 0.9613,
|
| 723 |
+
"step": 475
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 6.76056338028169,
|
| 727 |
+
"grad_norm": 0.046678755432367325,
|
| 728 |
+
"learning_rate": 0.00013253521126760565,
|
| 729 |
+
"loss": 0.9631,
|
| 730 |
+
"step": 480
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 6.830985915492958,
|
| 734 |
+
"grad_norm": 0.11235543340444565,
|
| 735 |
+
"learning_rate": 0.00013183098591549295,
|
| 736 |
+
"loss": 0.9617,
|
| 737 |
+
"step": 485
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 6.901408450704225,
|
| 741 |
+
"grad_norm": 0.04812972992658615,
|
| 742 |
+
"learning_rate": 0.00013112676056338028,
|
| 743 |
+
"loss": 0.9599,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 6.971830985915493,
|
| 748 |
+
"grad_norm": 0.05159539356827736,
|
| 749 |
+
"learning_rate": 0.0001304225352112676,
|
| 750 |
+
"loss": 0.9622,
|
| 751 |
+
"step": 495
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 7.0,
|
| 755 |
+
"eval_loss": 0.938995361328125,
|
| 756 |
+
"eval_runtime": 1.3575,
|
| 757 |
+
"eval_samples_per_second": 279.181,
|
| 758 |
+
"eval_steps_per_second": 2.21,
|
| 759 |
+
"step": 497
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 7.042253521126761,
|
| 763 |
+
"grad_norm": 0.046111464500427246,
|
| 764 |
+
"learning_rate": 0.00012971830985915493,
|
| 765 |
+
"loss": 0.9592,
|
| 766 |
+
"step": 500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 7.112676056338028,
|
| 770 |
+
"grad_norm": 0.09057960659265518,
|
| 771 |
+
"learning_rate": 0.00012901408450704226,
|
| 772 |
+
"loss": 0.9605,
|
| 773 |
+
"step": 505
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 7.183098591549296,
|
| 777 |
+
"grad_norm": 0.06652987748384476,
|
| 778 |
+
"learning_rate": 0.00012830985915492958,
|
| 779 |
+
"loss": 0.9595,
|
| 780 |
+
"step": 510
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 7.253521126760563,
|
| 784 |
+
"grad_norm": 0.05949646607041359,
|
| 785 |
+
"learning_rate": 0.0001276056338028169,
|
| 786 |
+
"loss": 0.9586,
|
| 787 |
+
"step": 515
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 7.323943661971831,
|
| 791 |
+
"grad_norm": 0.04339510202407837,
|
| 792 |
+
"learning_rate": 0.00012690140845070423,
|
| 793 |
+
"loss": 0.9594,
|
| 794 |
+
"step": 520
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 7.394366197183099,
|
| 798 |
+
"grad_norm": 0.06728670001029968,
|
| 799 |
+
"learning_rate": 0.00012619718309859156,
|
| 800 |
+
"loss": 0.9613,
|
| 801 |
+
"step": 525
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 7.464788732394366,
|
| 805 |
+
"grad_norm": 0.03795556724071503,
|
| 806 |
+
"learning_rate": 0.00012549295774647888,
|
| 807 |
+
"loss": 0.9563,
|
| 808 |
+
"step": 530
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 7.535211267605634,
|
| 812 |
+
"grad_norm": 0.0375334694981575,
|
| 813 |
+
"learning_rate": 0.00012478873239436618,
|
| 814 |
+
"loss": 0.9601,
|
| 815 |
+
"step": 535
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 7.605633802816901,
|
| 819 |
+
"grad_norm": 0.057856108993291855,
|
| 820 |
+
"learning_rate": 0.0001240845070422535,
|
| 821 |
+
"loss": 0.9616,
|
| 822 |
+
"step": 540
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 7.676056338028169,
|
| 826 |
+
"grad_norm": 0.03536657989025116,
|
| 827 |
+
"learning_rate": 0.00012338028169014083,
|
| 828 |
+
"loss": 0.9557,
|
| 829 |
+
"step": 545
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 7.746478873239437,
|
| 833 |
+
"grad_norm": 0.05437963828444481,
|
| 834 |
+
"learning_rate": 0.00012267605633802816,
|
| 835 |
+
"loss": 0.9596,
|
| 836 |
+
"step": 550
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 7.816901408450704,
|
| 840 |
+
"grad_norm": 0.0574585422873497,
|
| 841 |
+
"learning_rate": 0.0001219718309859155,
|
| 842 |
+
"loss": 0.9583,
|
| 843 |
+
"step": 555
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 7.887323943661972,
|
| 847 |
+
"grad_norm": 0.0447322279214859,
|
| 848 |
+
"learning_rate": 0.00012126760563380282,
|
| 849 |
+
"loss": 0.9599,
|
| 850 |
+
"step": 560
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 7.957746478873239,
|
| 854 |
+
"grad_norm": 0.06250979751348495,
|
| 855 |
+
"learning_rate": 0.00012056338028169015,
|
| 856 |
+
"loss": 0.9581,
|
| 857 |
+
"step": 565
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 8.0,
|
| 861 |
+
"eval_loss": 0.9374349117279053,
|
| 862 |
+
"eval_runtime": 1.356,
|
| 863 |
+
"eval_samples_per_second": 279.498,
|
| 864 |
+
"eval_steps_per_second": 2.212,
|
| 865 |
+
"step": 568
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 8.028169014084508,
|
| 869 |
+
"grad_norm": 0.02564265951514244,
|
| 870 |
+
"learning_rate": 0.00011985915492957746,
|
| 871 |
+
"loss": 0.9574,
|
| 872 |
+
"step": 570
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 8.098591549295774,
|
| 876 |
+
"grad_norm": 0.047478966414928436,
|
| 877 |
+
"learning_rate": 0.00011915492957746479,
|
| 878 |
+
"loss": 0.9538,
|
| 879 |
+
"step": 575
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 8.169014084507042,
|
| 883 |
+
"grad_norm": 0.04486701637506485,
|
| 884 |
+
"learning_rate": 0.00011845070422535211,
|
| 885 |
+
"loss": 0.957,
|
| 886 |
+
"step": 580
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 8.23943661971831,
|
| 890 |
+
"grad_norm": 0.03243768587708473,
|
| 891 |
+
"learning_rate": 0.00011774647887323944,
|
| 892 |
+
"loss": 0.9549,
|
| 893 |
+
"step": 585
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 8.309859154929578,
|
| 897 |
+
"grad_norm": 0.023309363052248955,
|
| 898 |
+
"learning_rate": 0.00011704225352112676,
|
| 899 |
+
"loss": 0.9552,
|
| 900 |
+
"step": 590
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 8.380281690140846,
|
| 904 |
+
"grad_norm": 0.06186755374073982,
|
| 905 |
+
"learning_rate": 0.00011633802816901409,
|
| 906 |
+
"loss": 0.956,
|
| 907 |
+
"step": 595
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 8.450704225352112,
|
| 911 |
+
"grad_norm": 0.033569905906915665,
|
| 912 |
+
"learning_rate": 0.00011563380281690141,
|
| 913 |
+
"loss": 0.9558,
|
| 914 |
+
"step": 600
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 8.52112676056338,
|
| 918 |
+
"grad_norm": 0.02437894605100155,
|
| 919 |
+
"learning_rate": 0.00011492957746478874,
|
| 920 |
+
"loss": 0.9539,
|
| 921 |
+
"step": 605
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 8.591549295774648,
|
| 925 |
+
"grad_norm": 0.0500415675342083,
|
| 926 |
+
"learning_rate": 0.00011422535211267606,
|
| 927 |
+
"loss": 0.9567,
|
| 928 |
+
"step": 610
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 8.661971830985916,
|
| 932 |
+
"grad_norm": 0.03755724057555199,
|
| 933 |
+
"learning_rate": 0.00011352112676056339,
|
| 934 |
+
"loss": 0.9561,
|
| 935 |
+
"step": 615
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 8.732394366197184,
|
| 939 |
+
"grad_norm": 0.06001519784331322,
|
| 940 |
+
"learning_rate": 0.00011281690140845072,
|
| 941 |
+
"loss": 0.9587,
|
| 942 |
+
"step": 620
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 8.80281690140845,
|
| 946 |
+
"grad_norm": 0.03620074316859245,
|
| 947 |
+
"learning_rate": 0.00011211267605633804,
|
| 948 |
+
"loss": 0.9541,
|
| 949 |
+
"step": 625
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 8.873239436619718,
|
| 953 |
+
"grad_norm": 0.052633192390203476,
|
| 954 |
+
"learning_rate": 0.00011140845070422537,
|
| 955 |
+
"loss": 0.9552,
|
| 956 |
+
"step": 630
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 8.943661971830986,
|
| 960 |
+
"grad_norm": 0.06923436373472214,
|
| 961 |
+
"learning_rate": 0.00011070422535211269,
|
| 962 |
+
"loss": 0.9562,
|
| 963 |
+
"step": 635
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 9.0,
|
| 967 |
+
"eval_loss": 0.9356324672698975,
|
| 968 |
+
"eval_runtime": 1.356,
|
| 969 |
+
"eval_samples_per_second": 279.507,
|
| 970 |
+
"eval_steps_per_second": 2.212,
|
| 971 |
+
"step": 639
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 9.014084507042254,
|
| 975 |
+
"grad_norm": 0.030308526009321213,
|
| 976 |
+
"learning_rate": 0.00011000000000000002,
|
| 977 |
+
"loss": 0.9567,
|
| 978 |
+
"step": 640
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 9.084507042253522,
|
| 982 |
+
"grad_norm": 0.04463675990700722,
|
| 983 |
+
"learning_rate": 0.00010929577464788734,
|
| 984 |
+
"loss": 0.9534,
|
| 985 |
+
"step": 645
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 9.154929577464788,
|
| 989 |
+
"grad_norm": 0.07801490277051926,
|
| 990 |
+
"learning_rate": 0.00010859154929577467,
|
| 991 |
+
"loss": 0.9532,
|
| 992 |
+
"step": 650
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 9.225352112676056,
|
| 996 |
+
"grad_norm": 0.07350599020719528,
|
| 997 |
+
"learning_rate": 0.00010788732394366197,
|
| 998 |
+
"loss": 0.9573,
|
| 999 |
+
"step": 655
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 9.295774647887324,
|
| 1003 |
+
"grad_norm": 0.04489121586084366,
|
| 1004 |
+
"learning_rate": 0.00010718309859154929,
|
| 1005 |
+
"loss": 0.9529,
|
| 1006 |
+
"step": 660
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 9.366197183098592,
|
| 1010 |
+
"grad_norm": 0.03186199814081192,
|
| 1011 |
+
"learning_rate": 0.00010647887323943662,
|
| 1012 |
+
"loss": 0.9547,
|
| 1013 |
+
"step": 665
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 9.43661971830986,
|
| 1017 |
+
"grad_norm": 0.050086986273527145,
|
| 1018 |
+
"learning_rate": 0.00010577464788732394,
|
| 1019 |
+
"loss": 0.9537,
|
| 1020 |
+
"step": 670
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 9.507042253521126,
|
| 1024 |
+
"grad_norm": 0.037186432629823685,
|
| 1025 |
+
"learning_rate": 0.00010507042253521127,
|
| 1026 |
+
"loss": 0.9526,
|
| 1027 |
+
"step": 675
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 9.577464788732394,
|
| 1031 |
+
"grad_norm": 0.07604589313268661,
|
| 1032 |
+
"learning_rate": 0.0001043661971830986,
|
| 1033 |
+
"loss": 0.9548,
|
| 1034 |
+
"step": 680
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 9.647887323943662,
|
| 1038 |
+
"grad_norm": 0.0647517517209053,
|
| 1039 |
+
"learning_rate": 0.00010366197183098592,
|
| 1040 |
+
"loss": 0.9565,
|
| 1041 |
+
"step": 685
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 9.71830985915493,
|
| 1045 |
+
"grad_norm": 0.0681651309132576,
|
| 1046 |
+
"learning_rate": 0.00010295774647887325,
|
| 1047 |
+
"loss": 0.9533,
|
| 1048 |
+
"step": 690
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 9.788732394366198,
|
| 1052 |
+
"grad_norm": 0.04616454616189003,
|
| 1053 |
+
"learning_rate": 0.00010225352112676057,
|
| 1054 |
+
"loss": 0.9529,
|
| 1055 |
+
"step": 695
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 9.859154929577464,
|
| 1059 |
+
"grad_norm": 0.029675917699933052,
|
| 1060 |
+
"learning_rate": 0.0001015492957746479,
|
| 1061 |
+
"loss": 0.9521,
|
| 1062 |
+
"step": 700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 9.929577464788732,
|
| 1066 |
+
"grad_norm": 0.025709936395287514,
|
| 1067 |
+
"learning_rate": 0.00010084507042253521,
|
| 1068 |
+
"loss": 0.9494,
|
| 1069 |
+
"step": 705
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 10.0,
|
| 1073 |
+
"grad_norm": 0.02850981615483761,
|
| 1074 |
+
"learning_rate": 0.00010014084507042253,
|
| 1075 |
+
"loss": 0.9522,
|
| 1076 |
+
"step": 710
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 10.0,
|
| 1080 |
+
"eval_loss": 0.9344412684440613,
|
| 1081 |
+
"eval_runtime": 1.3287,
|
| 1082 |
+
"eval_samples_per_second": 285.24,
|
| 1083 |
+
"eval_steps_per_second": 2.258,
|
| 1084 |
+
"step": 710
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 10.070422535211268,
|
| 1088 |
+
"grad_norm": 0.05556517466902733,
|
| 1089 |
+
"learning_rate": 9.943661971830986e-05,
|
| 1090 |
+
"loss": 0.9529,
|
| 1091 |
+
"step": 715
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 10.140845070422536,
|
| 1095 |
+
"grad_norm": 0.06735611706972122,
|
| 1096 |
+
"learning_rate": 9.873239436619719e-05,
|
| 1097 |
+
"loss": 0.9531,
|
| 1098 |
+
"step": 720
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 10.211267605633802,
|
| 1102 |
+
"grad_norm": 0.05679089203476906,
|
| 1103 |
+
"learning_rate": 9.802816901408451e-05,
|
| 1104 |
+
"loss": 0.9511,
|
| 1105 |
+
"step": 725
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 10.28169014084507,
|
| 1109 |
+
"grad_norm": 0.09331786632537842,
|
| 1110 |
+
"learning_rate": 9.732394366197184e-05,
|
| 1111 |
+
"loss": 0.9509,
|
| 1112 |
+
"step": 730
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 10.352112676056338,
|
| 1116 |
+
"grad_norm": 0.06282954663038254,
|
| 1117 |
+
"learning_rate": 9.661971830985916e-05,
|
| 1118 |
+
"loss": 0.952,
|
| 1119 |
+
"step": 735
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 10.422535211267606,
|
| 1123 |
+
"grad_norm": 0.06508725136518478,
|
| 1124 |
+
"learning_rate": 9.591549295774649e-05,
|
| 1125 |
+
"loss": 0.9534,
|
| 1126 |
+
"step": 740
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 10.492957746478874,
|
| 1130 |
+
"grad_norm": 0.041396528482437134,
|
| 1131 |
+
"learning_rate": 9.52112676056338e-05,
|
| 1132 |
+
"loss": 0.9537,
|
| 1133 |
+
"step": 745
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 10.56338028169014,
|
| 1137 |
+
"grad_norm": 0.04602223262190819,
|
| 1138 |
+
"learning_rate": 9.450704225352112e-05,
|
| 1139 |
+
"loss": 0.951,
|
| 1140 |
+
"step": 750
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 10.633802816901408,
|
| 1144 |
+
"grad_norm": 0.03372340276837349,
|
| 1145 |
+
"learning_rate": 9.380281690140845e-05,
|
| 1146 |
+
"loss": 0.9498,
|
| 1147 |
+
"step": 755
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 10.704225352112676,
|
| 1151 |
+
"grad_norm": 0.03808495029807091,
|
| 1152 |
+
"learning_rate": 9.309859154929578e-05,
|
| 1153 |
+
"loss": 0.9504,
|
| 1154 |
+
"step": 760
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 10.774647887323944,
|
| 1158 |
+
"grad_norm": 0.027203522622585297,
|
| 1159 |
+
"learning_rate": 9.23943661971831e-05,
|
| 1160 |
+
"loss": 0.9514,
|
| 1161 |
+
"step": 765
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 10.845070422535212,
|
| 1165 |
+
"grad_norm": 0.03273136168718338,
|
| 1166 |
+
"learning_rate": 9.169014084507043e-05,
|
| 1167 |
+
"loss": 0.9496,
|
| 1168 |
+
"step": 770
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 10.915492957746478,
|
| 1172 |
+
"grad_norm": 0.03632248193025589,
|
| 1173 |
+
"learning_rate": 9.098591549295775e-05,
|
| 1174 |
+
"loss": 0.9518,
|
| 1175 |
+
"step": 775
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 10.985915492957746,
|
| 1179 |
+
"grad_norm": 0.04196527600288391,
|
| 1180 |
+
"learning_rate": 9.028169014084508e-05,
|
| 1181 |
+
"loss": 0.9493,
|
| 1182 |
+
"step": 780
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 11.0,
|
| 1186 |
+
"eval_loss": 0.9340574145317078,
|
| 1187 |
+
"eval_runtime": 1.3554,
|
| 1188 |
+
"eval_samples_per_second": 279.624,
|
| 1189 |
+
"eval_steps_per_second": 2.213,
|
| 1190 |
+
"step": 781
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 11.056338028169014,
|
| 1194 |
+
"grad_norm": 0.02801569737493992,
|
| 1195 |
+
"learning_rate": 8.95774647887324e-05,
|
| 1196 |
+
"loss": 0.9506,
|
| 1197 |
+
"step": 785
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 11.126760563380282,
|
| 1201 |
+
"grad_norm": 0.07875282317399979,
|
| 1202 |
+
"learning_rate": 8.887323943661973e-05,
|
| 1203 |
+
"loss": 0.9527,
|
| 1204 |
+
"step": 790
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 11.19718309859155,
|
| 1208 |
+
"grad_norm": 0.06978793442249298,
|
| 1209 |
+
"learning_rate": 8.816901408450705e-05,
|
| 1210 |
+
"loss": 0.9513,
|
| 1211 |
+
"step": 795
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 11.267605633802816,
|
| 1215 |
+
"grad_norm": 0.05102715268731117,
|
| 1216 |
+
"learning_rate": 8.746478873239437e-05,
|
| 1217 |
+
"loss": 0.9493,
|
| 1218 |
+
"step": 800
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 11.338028169014084,
|
| 1222 |
+
"grad_norm": 0.037087179720401764,
|
| 1223 |
+
"learning_rate": 8.676056338028169e-05,
|
| 1224 |
+
"loss": 0.9482,
|
| 1225 |
+
"step": 805
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 11.408450704225352,
|
| 1229 |
+
"grad_norm": 0.026025516912341118,
|
| 1230 |
+
"learning_rate": 8.605633802816902e-05,
|
| 1231 |
+
"loss": 0.9499,
|
| 1232 |
+
"step": 810
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 11.47887323943662,
|
| 1236 |
+
"grad_norm": 0.046463027596473694,
|
| 1237 |
+
"learning_rate": 8.535211267605634e-05,
|
| 1238 |
+
"loss": 0.9526,
|
| 1239 |
+
"step": 815
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 11.549295774647888,
|
| 1243 |
+
"grad_norm": 0.03885842487215996,
|
| 1244 |
+
"learning_rate": 8.464788732394367e-05,
|
| 1245 |
+
"loss": 0.9508,
|
| 1246 |
+
"step": 820
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 11.619718309859154,
|
| 1250 |
+
"grad_norm": 0.042792994529008865,
|
| 1251 |
+
"learning_rate": 8.3943661971831e-05,
|
| 1252 |
+
"loss": 0.9491,
|
| 1253 |
+
"step": 825
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 11.690140845070422,
|
| 1257 |
+
"grad_norm": 0.040800243616104126,
|
| 1258 |
+
"learning_rate": 8.323943661971832e-05,
|
| 1259 |
+
"loss": 0.9502,
|
| 1260 |
+
"step": 830
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 11.76056338028169,
|
| 1264 |
+
"grad_norm": 0.04244118928909302,
|
| 1265 |
+
"learning_rate": 8.253521126760565e-05,
|
| 1266 |
+
"loss": 0.9463,
|
| 1267 |
+
"step": 835
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 11.830985915492958,
|
| 1271 |
+
"grad_norm": 0.027077561244368553,
|
| 1272 |
+
"learning_rate": 8.183098591549296e-05,
|
| 1273 |
+
"loss": 0.9486,
|
| 1274 |
+
"step": 840
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 11.901408450704226,
|
| 1278 |
+
"grad_norm": 0.0710897371172905,
|
| 1279 |
+
"learning_rate": 8.112676056338028e-05,
|
| 1280 |
+
"loss": 0.9498,
|
| 1281 |
+
"step": 845
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 11.971830985915492,
|
| 1285 |
+
"grad_norm": 0.027009285986423492,
|
| 1286 |
+
"learning_rate": 8.042253521126761e-05,
|
| 1287 |
+
"loss": 0.9492,
|
| 1288 |
+
"step": 850
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 12.0,
|
| 1292 |
+
"eval_loss": 0.934472382068634,
|
| 1293 |
+
"eval_runtime": 1.3559,
|
| 1294 |
+
"eval_samples_per_second": 279.512,
|
| 1295 |
+
"eval_steps_per_second": 2.212,
|
| 1296 |
+
"step": 852
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 12.04225352112676,
|
| 1300 |
+
"grad_norm": 0.027241826057434082,
|
| 1301 |
+
"learning_rate": 7.971830985915493e-05,
|
| 1302 |
+
"loss": 0.9485,
|
| 1303 |
+
"step": 855
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 12.112676056338028,
|
| 1307 |
+
"grad_norm": 17.60222816467285,
|
| 1308 |
+
"learning_rate": 7.901408450704225e-05,
|
| 1309 |
+
"loss": 0.9505,
|
| 1310 |
+
"step": 860
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 12.183098591549296,
|
| 1314 |
+
"grad_norm": 0.04522601515054703,
|
| 1315 |
+
"learning_rate": 7.830985915492957e-05,
|
| 1316 |
+
"loss": 0.9511,
|
| 1317 |
+
"step": 865
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 12.253521126760564,
|
| 1321 |
+
"grad_norm": 0.0453733466565609,
|
| 1322 |
+
"learning_rate": 7.76056338028169e-05,
|
| 1323 |
+
"loss": 0.9488,
|
| 1324 |
+
"step": 870
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 12.323943661971832,
|
| 1328 |
+
"grad_norm": 0.04800290986895561,
|
| 1329 |
+
"learning_rate": 7.690140845070422e-05,
|
| 1330 |
+
"loss": 0.9484,
|
| 1331 |
+
"step": 875
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 12.394366197183098,
|
| 1335 |
+
"grad_norm": 0.056329064071178436,
|
| 1336 |
+
"learning_rate": 7.619718309859155e-05,
|
| 1337 |
+
"loss": 0.9488,
|
| 1338 |
+
"step": 880
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 12.464788732394366,
|
| 1342 |
+
"grad_norm": 0.04998723790049553,
|
| 1343 |
+
"learning_rate": 7.549295774647887e-05,
|
| 1344 |
+
"loss": 0.9491,
|
| 1345 |
+
"step": 885
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 12.535211267605634,
|
| 1349 |
+
"grad_norm": 0.024647079408168793,
|
| 1350 |
+
"learning_rate": 7.47887323943662e-05,
|
| 1351 |
+
"loss": 0.9474,
|
| 1352 |
+
"step": 890
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 12.605633802816902,
|
| 1356 |
+
"grad_norm": 0.06089835241436958,
|
| 1357 |
+
"learning_rate": 7.408450704225352e-05,
|
| 1358 |
+
"loss": 0.9487,
|
| 1359 |
+
"step": 895
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 12.676056338028168,
|
| 1363 |
+
"grad_norm": 0.07820327579975128,
|
| 1364 |
+
"learning_rate": 7.338028169014085e-05,
|
| 1365 |
+
"loss": 0.9486,
|
| 1366 |
+
"step": 900
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 12.746478873239436,
|
| 1370 |
+
"grad_norm": 0.03777018189430237,
|
| 1371 |
+
"learning_rate": 7.267605633802818e-05,
|
| 1372 |
+
"loss": 0.9483,
|
| 1373 |
+
"step": 905
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 12.816901408450704,
|
| 1377 |
+
"grad_norm": 0.038660142570734024,
|
| 1378 |
+
"learning_rate": 7.19718309859155e-05,
|
| 1379 |
+
"loss": 0.9478,
|
| 1380 |
+
"step": 910
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 12.887323943661972,
|
| 1384 |
+
"grad_norm": 0.028829969465732574,
|
| 1385 |
+
"learning_rate": 7.126760563380283e-05,
|
| 1386 |
+
"loss": 0.9471,
|
| 1387 |
+
"step": 915
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 12.95774647887324,
|
| 1391 |
+
"grad_norm": 0.02644144371151924,
|
| 1392 |
+
"learning_rate": 7.056338028169014e-05,
|
| 1393 |
+
"loss": 0.9493,
|
| 1394 |
+
"step": 920
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 13.0,
|
| 1398 |
+
"eval_loss": 0.9329857230186462,
|
| 1399 |
+
"eval_runtime": 1.3566,
|
| 1400 |
+
"eval_samples_per_second": 279.384,
|
| 1401 |
+
"eval_steps_per_second": 2.211,
|
| 1402 |
+
"step": 923
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 13.028169014084508,
|
| 1406 |
+
"grad_norm": 0.027125298976898193,
|
| 1407 |
+
"learning_rate": 6.985915492957746e-05,
|
| 1408 |
+
"loss": 0.948,
|
| 1409 |
+
"step": 925
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 13.098591549295774,
|
| 1413 |
+
"grad_norm": 0.025396650657057762,
|
| 1414 |
+
"learning_rate": 6.915492957746479e-05,
|
| 1415 |
+
"loss": 0.9485,
|
| 1416 |
+
"step": 930
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 13.169014084507042,
|
| 1420 |
+
"grad_norm": 0.039986852556467056,
|
| 1421 |
+
"learning_rate": 6.845070422535212e-05,
|
| 1422 |
+
"loss": 0.948,
|
| 1423 |
+
"step": 935
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 13.23943661971831,
|
| 1427 |
+
"grad_norm": 0.04669572040438652,
|
| 1428 |
+
"learning_rate": 6.774647887323944e-05,
|
| 1429 |
+
"loss": 0.9484,
|
| 1430 |
+
"step": 940
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 13.309859154929578,
|
| 1434 |
+
"grad_norm": 0.05597477778792381,
|
| 1435 |
+
"learning_rate": 6.704225352112677e-05,
|
| 1436 |
+
"loss": 0.9492,
|
| 1437 |
+
"step": 945
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 13.380281690140846,
|
| 1441 |
+
"grad_norm": 0.03363762050867081,
|
| 1442 |
+
"learning_rate": 6.633802816901409e-05,
|
| 1443 |
+
"loss": 0.9479,
|
| 1444 |
+
"step": 950
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 13.450704225352112,
|
| 1448 |
+
"grad_norm": 0.0501028336584568,
|
| 1449 |
+
"learning_rate": 6.563380281690142e-05,
|
| 1450 |
+
"loss": 0.9472,
|
| 1451 |
+
"step": 955
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 13.52112676056338,
|
| 1455 |
+
"grad_norm": 0.02368428371846676,
|
| 1456 |
+
"learning_rate": 6.492957746478874e-05,
|
| 1457 |
+
"loss": 0.9473,
|
| 1458 |
+
"step": 960
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 13.591549295774648,
|
| 1462 |
+
"grad_norm": 0.024430401623249054,
|
| 1463 |
+
"learning_rate": 6.422535211267607e-05,
|
| 1464 |
+
"loss": 0.9461,
|
| 1465 |
+
"step": 965
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 13.661971830985916,
|
| 1469 |
+
"grad_norm": 0.036314696073532104,
|
| 1470 |
+
"learning_rate": 6.35211267605634e-05,
|
| 1471 |
+
"loss": 0.9469,
|
| 1472 |
+
"step": 970
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 13.732394366197184,
|
| 1476 |
+
"grad_norm": 0.03353135287761688,
|
| 1477 |
+
"learning_rate": 6.28169014084507e-05,
|
| 1478 |
+
"loss": 0.9468,
|
| 1479 |
+
"step": 975
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 13.80281690140845,
|
| 1483 |
+
"grad_norm": 0.0263178963214159,
|
| 1484 |
+
"learning_rate": 6.211267605633803e-05,
|
| 1485 |
+
"loss": 0.9484,
|
| 1486 |
+
"step": 980
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 13.873239436619718,
|
| 1490 |
+
"grad_norm": 0.06421630084514618,
|
| 1491 |
+
"learning_rate": 6.140845070422536e-05,
|
| 1492 |
+
"loss": 0.9481,
|
| 1493 |
+
"step": 985
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 13.943661971830986,
|
| 1497 |
+
"grad_norm": 0.03617294877767563,
|
| 1498 |
+
"learning_rate": 6.0704225352112676e-05,
|
| 1499 |
+
"loss": 0.9467,
|
| 1500 |
+
"step": 990
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 14.0,
|
| 1504 |
+
"eval_loss": 0.9325685501098633,
|
| 1505 |
+
"eval_runtime": 1.3557,
|
| 1506 |
+
"eval_samples_per_second": 279.559,
|
| 1507 |
+
"eval_steps_per_second": 2.213,
|
| 1508 |
+
"step": 994
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 14.014084507042254,
|
| 1512 |
+
"grad_norm": 0.05025329068303108,
|
| 1513 |
+
"learning_rate": 6e-05,
|
| 1514 |
+
"loss": 0.9447,
|
| 1515 |
+
"step": 995
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 14.084507042253522,
|
| 1519 |
+
"grad_norm": 0.03912140801548958,
|
| 1520 |
+
"learning_rate": 5.929577464788733e-05,
|
| 1521 |
+
"loss": 0.9468,
|
| 1522 |
+
"step": 1000
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 14.154929577464788,
|
| 1526 |
+
"grad_norm": 0.030682148411870003,
|
| 1527 |
+
"learning_rate": 5.859154929577465e-05,
|
| 1528 |
+
"loss": 0.9454,
|
| 1529 |
+
"step": 1005
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 14.225352112676056,
|
| 1533 |
+
"grad_norm": 0.06476651132106781,
|
| 1534 |
+
"learning_rate": 5.788732394366198e-05,
|
| 1535 |
+
"loss": 0.946,
|
| 1536 |
+
"step": 1010
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 14.295774647887324,
|
| 1540 |
+
"grad_norm": 0.01931784488260746,
|
| 1541 |
+
"learning_rate": 5.71830985915493e-05,
|
| 1542 |
+
"loss": 0.9458,
|
| 1543 |
+
"step": 1015
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 14.366197183098592,
|
| 1547 |
+
"grad_norm": 0.030390406027436256,
|
| 1548 |
+
"learning_rate": 5.647887323943662e-05,
|
| 1549 |
+
"loss": 0.9464,
|
| 1550 |
+
"step": 1020
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 14.43661971830986,
|
| 1554 |
+
"grad_norm": 0.060740068554878235,
|
| 1555 |
+
"learning_rate": 5.577464788732395e-05,
|
| 1556 |
+
"loss": 0.9459,
|
| 1557 |
+
"step": 1025
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 14.507042253521126,
|
| 1561 |
+
"grad_norm": 0.034336596727371216,
|
| 1562 |
+
"learning_rate": 5.5070422535211273e-05,
|
| 1563 |
+
"loss": 0.9454,
|
| 1564 |
+
"step": 1030
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 14.577464788732394,
|
| 1568 |
+
"grad_norm": 0.04022248461842537,
|
| 1569 |
+
"learning_rate": 5.43661971830986e-05,
|
| 1570 |
+
"loss": 0.9459,
|
| 1571 |
+
"step": 1035
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 14.647887323943662,
|
| 1575 |
+
"grad_norm": 0.03897751495242119,
|
| 1576 |
+
"learning_rate": 5.366197183098591e-05,
|
| 1577 |
+
"loss": 0.948,
|
| 1578 |
+
"step": 1040
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 14.71830985915493,
|
| 1582 |
+
"grad_norm": 0.017990631982684135,
|
| 1583 |
+
"learning_rate": 5.2957746478873237e-05,
|
| 1584 |
+
"loss": 0.9461,
|
| 1585 |
+
"step": 1045
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 14.788732394366198,
|
| 1589 |
+
"grad_norm": 0.04828361049294472,
|
| 1590 |
+
"learning_rate": 5.225352112676056e-05,
|
| 1591 |
+
"loss": 0.9473,
|
| 1592 |
+
"step": 1050
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 14.859154929577464,
|
| 1596 |
+
"grad_norm": 0.040516018867492676,
|
| 1597 |
+
"learning_rate": 5.154929577464789e-05,
|
| 1598 |
+
"loss": 0.9466,
|
| 1599 |
+
"step": 1055
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 14.929577464788732,
|
| 1603 |
+
"grad_norm": 0.023633386939764023,
|
| 1604 |
+
"learning_rate": 5.084507042253521e-05,
|
| 1605 |
+
"loss": 0.9483,
|
| 1606 |
+
"step": 1060
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 15.0,
|
| 1610 |
+
"grad_norm": 0.03356311842799187,
|
| 1611 |
+
"learning_rate": 5.014084507042254e-05,
|
| 1612 |
+
"loss": 0.9433,
|
| 1613 |
+
"step": 1065
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 15.0,
|
| 1617 |
+
"eval_loss": 0.9321981072425842,
|
| 1618 |
+
"eval_runtime": 1.3288,
|
| 1619 |
+
"eval_samples_per_second": 285.221,
|
| 1620 |
+
"eval_steps_per_second": 2.258,
|
| 1621 |
+
"step": 1065
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 15.070422535211268,
|
| 1625 |
+
"grad_norm": 0.031062249094247818,
|
| 1626 |
+
"learning_rate": 4.9436619718309864e-05,
|
| 1627 |
+
"loss": 0.9449,
|
| 1628 |
+
"step": 1070
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 15.140845070422536,
|
| 1632 |
+
"grad_norm": 0.03606761246919632,
|
| 1633 |
+
"learning_rate": 4.873239436619719e-05,
|
| 1634 |
+
"loss": 0.9452,
|
| 1635 |
+
"step": 1075
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 15.211267605633802,
|
| 1639 |
+
"grad_norm": 0.03723893314599991,
|
| 1640 |
+
"learning_rate": 4.8028169014084515e-05,
|
| 1641 |
+
"loss": 0.9495,
|
| 1642 |
+
"step": 1080
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 15.28169014084507,
|
| 1646 |
+
"grad_norm": 0.022561002522706985,
|
| 1647 |
+
"learning_rate": 4.7323943661971834e-05,
|
| 1648 |
+
"loss": 0.9451,
|
| 1649 |
+
"step": 1085
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 15.352112676056338,
|
| 1653 |
+
"grad_norm": 0.03934817761182785,
|
| 1654 |
+
"learning_rate": 4.661971830985915e-05,
|
| 1655 |
+
"loss": 0.9465,
|
| 1656 |
+
"step": 1090
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 15.422535211267606,
|
| 1660 |
+
"grad_norm": 0.021020477637648582,
|
| 1661 |
+
"learning_rate": 4.591549295774648e-05,
|
| 1662 |
+
"loss": 0.9458,
|
| 1663 |
+
"step": 1095
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 15.492957746478874,
|
| 1667 |
+
"grad_norm": 0.029691854491829872,
|
| 1668 |
+
"learning_rate": 4.5211267605633804e-05,
|
| 1669 |
+
"loss": 0.9464,
|
| 1670 |
+
"step": 1100
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 15.56338028169014,
|
| 1674 |
+
"grad_norm": 0.030643166974186897,
|
| 1675 |
+
"learning_rate": 4.450704225352113e-05,
|
| 1676 |
+
"loss": 0.9438,
|
| 1677 |
+
"step": 1105
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 15.633802816901408,
|
| 1681 |
+
"grad_norm": 0.0261048823595047,
|
| 1682 |
+
"learning_rate": 4.3802816901408455e-05,
|
| 1683 |
+
"loss": 0.9442,
|
| 1684 |
+
"step": 1110
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 15.704225352112676,
|
| 1688 |
+
"grad_norm": 0.04185587912797928,
|
| 1689 |
+
"learning_rate": 4.3098591549295774e-05,
|
| 1690 |
+
"loss": 0.9455,
|
| 1691 |
+
"step": 1115
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 15.774647887323944,
|
| 1695 |
+
"grad_norm": 0.03181832283735275,
|
| 1696 |
+
"learning_rate": 4.23943661971831e-05,
|
| 1697 |
+
"loss": 0.9452,
|
| 1698 |
+
"step": 1120
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 15.845070422535212,
|
| 1702 |
+
"grad_norm": 0.017347080633044243,
|
| 1703 |
+
"learning_rate": 4.1690140845070425e-05,
|
| 1704 |
+
"loss": 0.9445,
|
| 1705 |
+
"step": 1125
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 15.915492957746478,
|
| 1709 |
+
"grad_norm": 0.0175313837826252,
|
| 1710 |
+
"learning_rate": 4.098591549295775e-05,
|
| 1711 |
+
"loss": 0.9462,
|
| 1712 |
+
"step": 1130
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 15.985915492957746,
|
| 1716 |
+
"grad_norm": 0.016237597912549973,
|
| 1717 |
+
"learning_rate": 4.0281690140845076e-05,
|
| 1718 |
+
"loss": 0.9441,
|
| 1719 |
+
"step": 1135
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 16.0,
|
| 1723 |
+
"eval_loss": 0.932042121887207,
|
| 1724 |
+
"eval_runtime": 1.3559,
|
| 1725 |
+
"eval_samples_per_second": 279.512,
|
| 1726 |
+
"eval_steps_per_second": 2.212,
|
| 1727 |
+
"step": 1136
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 16.056338028169016,
|
| 1731 |
+
"grad_norm": 0.02838326431810856,
|
| 1732 |
+
"learning_rate": 3.9577464788732395e-05,
|
| 1733 |
+
"loss": 0.9443,
|
| 1734 |
+
"step": 1140
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 16.12676056338028,
|
| 1738 |
+
"grad_norm": 0.03755342960357666,
|
| 1739 |
+
"learning_rate": 3.887323943661972e-05,
|
| 1740 |
+
"loss": 0.9448,
|
| 1741 |
+
"step": 1145
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 16.197183098591548,
|
| 1745 |
+
"grad_norm": 0.019139522686600685,
|
| 1746 |
+
"learning_rate": 3.8169014084507046e-05,
|
| 1747 |
+
"loss": 0.945,
|
| 1748 |
+
"step": 1150
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 16.267605633802816,
|
| 1752 |
+
"grad_norm": 0.029503419995307922,
|
| 1753 |
+
"learning_rate": 3.746478873239437e-05,
|
| 1754 |
+
"loss": 0.9437,
|
| 1755 |
+
"step": 1155
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 16.338028169014084,
|
| 1759 |
+
"grad_norm": 0.02175034210085869,
|
| 1760 |
+
"learning_rate": 3.676056338028169e-05,
|
| 1761 |
+
"loss": 0.9458,
|
| 1762 |
+
"step": 1160
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 16.408450704225352,
|
| 1766 |
+
"grad_norm": 0.041107743978500366,
|
| 1767 |
+
"learning_rate": 3.6056338028169015e-05,
|
| 1768 |
+
"loss": 0.9462,
|
| 1769 |
+
"step": 1165
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 16.47887323943662,
|
| 1773 |
+
"grad_norm": 0.03304363787174225,
|
| 1774 |
+
"learning_rate": 3.5352112676056334e-05,
|
| 1775 |
+
"loss": 0.9456,
|
| 1776 |
+
"step": 1170
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 16.549295774647888,
|
| 1780 |
+
"grad_norm": 0.02730601467192173,
|
| 1781 |
+
"learning_rate": 3.464788732394366e-05,
|
| 1782 |
+
"loss": 0.9447,
|
| 1783 |
+
"step": 1175
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 16.619718309859156,
|
| 1787 |
+
"grad_norm": 0.03291373327374458,
|
| 1788 |
+
"learning_rate": 3.3943661971830985e-05,
|
| 1789 |
+
"loss": 0.9452,
|
| 1790 |
+
"step": 1180
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 16.690140845070424,
|
| 1794 |
+
"grad_norm": 0.023141978308558464,
|
| 1795 |
+
"learning_rate": 3.323943661971831e-05,
|
| 1796 |
+
"loss": 0.9437,
|
| 1797 |
+
"step": 1185
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 16.760563380281692,
|
| 1801 |
+
"grad_norm": 0.02332274429500103,
|
| 1802 |
+
"learning_rate": 3.2535211267605636e-05,
|
| 1803 |
+
"loss": 0.9438,
|
| 1804 |
+
"step": 1190
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 16.830985915492956,
|
| 1808 |
+
"grad_norm": 0.050522513687610626,
|
| 1809 |
+
"learning_rate": 3.183098591549296e-05,
|
| 1810 |
+
"loss": 0.9437,
|
| 1811 |
+
"step": 1195
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 16.901408450704224,
|
| 1815 |
+
"grad_norm": 0.02046947181224823,
|
| 1816 |
+
"learning_rate": 3.112676056338028e-05,
|
| 1817 |
+
"loss": 0.9453,
|
| 1818 |
+
"step": 1200
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 16.971830985915492,
|
| 1822 |
+
"grad_norm": 0.06999664008617401,
|
| 1823 |
+
"learning_rate": 3.0422535211267606e-05,
|
| 1824 |
+
"loss": 0.9453,
|
| 1825 |
+
"step": 1205
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 17.0,
|
| 1829 |
+
"eval_loss": 0.9319289326667786,
|
| 1830 |
+
"eval_runtime": 1.3556,
|
| 1831 |
+
"eval_samples_per_second": 279.59,
|
| 1832 |
+
"eval_steps_per_second": 2.213,
|
| 1833 |
+
"step": 1207
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 17.04225352112676,
|
| 1837 |
+
"grad_norm": 0.027964303269982338,
|
| 1838 |
+
"learning_rate": 2.971830985915493e-05,
|
| 1839 |
+
"loss": 0.9437,
|
| 1840 |
+
"step": 1210
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 17.112676056338028,
|
| 1844 |
+
"grad_norm": 0.021849192678928375,
|
| 1845 |
+
"learning_rate": 2.9014084507042254e-05,
|
| 1846 |
+
"loss": 0.9451,
|
| 1847 |
+
"step": 1215
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 17.183098591549296,
|
| 1851 |
+
"grad_norm": 0.06382541358470917,
|
| 1852 |
+
"learning_rate": 2.830985915492958e-05,
|
| 1853 |
+
"loss": 0.9446,
|
| 1854 |
+
"step": 1220
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 17.253521126760564,
|
| 1858 |
+
"grad_norm": 0.018395431339740753,
|
| 1859 |
+
"learning_rate": 2.7605633802816905e-05,
|
| 1860 |
+
"loss": 0.9449,
|
| 1861 |
+
"step": 1225
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 17.323943661971832,
|
| 1865 |
+
"grad_norm": 0.02647424302995205,
|
| 1866 |
+
"learning_rate": 2.6901408450704224e-05,
|
| 1867 |
+
"loss": 0.943,
|
| 1868 |
+
"step": 1230
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 17.3943661971831,
|
| 1872 |
+
"grad_norm": 0.053954143077135086,
|
| 1873 |
+
"learning_rate": 2.619718309859155e-05,
|
| 1874 |
+
"loss": 0.9451,
|
| 1875 |
+
"step": 1235
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 17.464788732394368,
|
| 1879 |
+
"grad_norm": 0.03957201540470123,
|
| 1880 |
+
"learning_rate": 2.5492957746478875e-05,
|
| 1881 |
+
"loss": 0.9448,
|
| 1882 |
+
"step": 1240
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 17.535211267605632,
|
| 1886 |
+
"grad_norm": 0.0455038957297802,
|
| 1887 |
+
"learning_rate": 2.47887323943662e-05,
|
| 1888 |
+
"loss": 0.9441,
|
| 1889 |
+
"step": 1245
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 17.6056338028169,
|
| 1893 |
+
"grad_norm": 0.03737751021981239,
|
| 1894 |
+
"learning_rate": 2.4084507042253522e-05,
|
| 1895 |
+
"loss": 0.9469,
|
| 1896 |
+
"step": 1250
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 17.676056338028168,
|
| 1900 |
+
"grad_norm": 0.038107406347990036,
|
| 1901 |
+
"learning_rate": 2.3380281690140845e-05,
|
| 1902 |
+
"loss": 0.9445,
|
| 1903 |
+
"step": 1255
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 17.746478873239436,
|
| 1907 |
+
"grad_norm": 0.04548390954732895,
|
| 1908 |
+
"learning_rate": 2.267605633802817e-05,
|
| 1909 |
+
"loss": 0.9451,
|
| 1910 |
+
"step": 1260
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 17.816901408450704,
|
| 1914 |
+
"grad_norm": 0.03373611345887184,
|
| 1915 |
+
"learning_rate": 2.1971830985915496e-05,
|
| 1916 |
+
"loss": 0.9438,
|
| 1917 |
+
"step": 1265
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 17.887323943661972,
|
| 1921 |
+
"grad_norm": 0.029089247807860374,
|
| 1922 |
+
"learning_rate": 2.1267605633802818e-05,
|
| 1923 |
+
"loss": 0.9435,
|
| 1924 |
+
"step": 1270
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 17.95774647887324,
|
| 1928 |
+
"grad_norm": 0.027908792719244957,
|
| 1929 |
+
"learning_rate": 2.0563380281690143e-05,
|
| 1930 |
+
"loss": 0.9433,
|
| 1931 |
+
"step": 1275
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 18.0,
|
| 1935 |
+
"eval_loss": 0.9321526885032654,
|
| 1936 |
+
"eval_runtime": 1.3562,
|
| 1937 |
+
"eval_samples_per_second": 279.464,
|
| 1938 |
+
"eval_steps_per_second": 2.212,
|
| 1939 |
+
"step": 1278
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 18.028169014084508,
|
| 1943 |
+
"grad_norm": 0.038007136434316635,
|
| 1944 |
+
"learning_rate": 1.9859154929577465e-05,
|
| 1945 |
+
"loss": 0.9433,
|
| 1946 |
+
"step": 1280
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 18.098591549295776,
|
| 1950 |
+
"grad_norm": 0.055055730044841766,
|
| 1951 |
+
"learning_rate": 1.9154929577464788e-05,
|
| 1952 |
+
"loss": 0.9444,
|
| 1953 |
+
"step": 1285
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 18.169014084507044,
|
| 1957 |
+
"grad_norm": 0.024233724921941757,
|
| 1958 |
+
"learning_rate": 1.8450704225352113e-05,
|
| 1959 |
+
"loss": 0.9448,
|
| 1960 |
+
"step": 1290
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 18.239436619718308,
|
| 1964 |
+
"grad_norm": 0.02525465376675129,
|
| 1965 |
+
"learning_rate": 1.774647887323944e-05,
|
| 1966 |
+
"loss": 0.9452,
|
| 1967 |
+
"step": 1295
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 18.309859154929576,
|
| 1971 |
+
"grad_norm": 0.03696692734956741,
|
| 1972 |
+
"learning_rate": 1.704225352112676e-05,
|
| 1973 |
+
"loss": 0.9451,
|
| 1974 |
+
"step": 1300
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 18.380281690140844,
|
| 1978 |
+
"grad_norm": 0.012775393202900887,
|
| 1979 |
+
"learning_rate": 1.6338028169014086e-05,
|
| 1980 |
+
"loss": 0.9424,
|
| 1981 |
+
"step": 1305
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 18.450704225352112,
|
| 1985 |
+
"grad_norm": 0.04282708466053009,
|
| 1986 |
+
"learning_rate": 1.5633802816901412e-05,
|
| 1987 |
+
"loss": 0.9439,
|
| 1988 |
+
"step": 1310
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 18.52112676056338,
|
| 1992 |
+
"grad_norm": 0.026728734374046326,
|
| 1993 |
+
"learning_rate": 1.4929577464788732e-05,
|
| 1994 |
+
"loss": 0.9432,
|
| 1995 |
+
"step": 1315
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 18.591549295774648,
|
| 1999 |
+
"grad_norm": 0.038278259336948395,
|
| 2000 |
+
"learning_rate": 1.4225352112676058e-05,
|
| 2001 |
+
"loss": 0.9437,
|
| 2002 |
+
"step": 1320
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 18.661971830985916,
|
| 2006 |
+
"grad_norm": 0.0476648211479187,
|
| 2007 |
+
"learning_rate": 1.352112676056338e-05,
|
| 2008 |
+
"loss": 0.9442,
|
| 2009 |
+
"step": 1325
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 18.732394366197184,
|
| 2013 |
+
"grad_norm": 0.017152875661849976,
|
| 2014 |
+
"learning_rate": 1.2816901408450704e-05,
|
| 2015 |
+
"loss": 0.9439,
|
| 2016 |
+
"step": 1330
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 18.802816901408452,
|
| 2020 |
+
"grad_norm": 0.02195524424314499,
|
| 2021 |
+
"learning_rate": 1.211267605633803e-05,
|
| 2022 |
+
"loss": 0.9441,
|
| 2023 |
+
"step": 1335
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 18.87323943661972,
|
| 2027 |
+
"grad_norm": 0.03179704770445824,
|
| 2028 |
+
"learning_rate": 1.1408450704225353e-05,
|
| 2029 |
+
"loss": 0.944,
|
| 2030 |
+
"step": 1340
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 18.943661971830984,
|
| 2034 |
+
"grad_norm": 0.01666986383497715,
|
| 2035 |
+
"learning_rate": 1.0704225352112677e-05,
|
| 2036 |
+
"loss": 0.9436,
|
| 2037 |
+
"step": 1345
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 19.0,
|
| 2041 |
+
"eval_loss": 0.9319114685058594,
|
| 2042 |
+
"eval_runtime": 1.3555,
|
| 2043 |
+
"eval_samples_per_second": 279.596,
|
| 2044 |
+
"eval_steps_per_second": 2.213,
|
| 2045 |
+
"step": 1349
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 19.014084507042252,
|
| 2049 |
+
"grad_norm": 0.027670254930853844,
|
| 2050 |
+
"learning_rate": 1e-05,
|
| 2051 |
+
"loss": 0.9441,
|
| 2052 |
+
"step": 1350
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 19.08450704225352,
|
| 2056 |
+
"grad_norm": 0.05388191342353821,
|
| 2057 |
+
"learning_rate": 9.295774647887325e-06,
|
| 2058 |
+
"loss": 0.9445,
|
| 2059 |
+
"step": 1355
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 19.154929577464788,
|
| 2063 |
+
"grad_norm": 0.02966221235692501,
|
| 2064 |
+
"learning_rate": 8.591549295774648e-06,
|
| 2065 |
+
"loss": 0.9432,
|
| 2066 |
+
"step": 1360
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 19.225352112676056,
|
| 2070 |
+
"grad_norm": 0.02553911693394184,
|
| 2071 |
+
"learning_rate": 7.887323943661972e-06,
|
| 2072 |
+
"loss": 0.9434,
|
| 2073 |
+
"step": 1365
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 19.295774647887324,
|
| 2077 |
+
"grad_norm": 0.03100278414785862,
|
| 2078 |
+
"learning_rate": 7.183098591549296e-06,
|
| 2079 |
+
"loss": 0.9438,
|
| 2080 |
+
"step": 1370
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 19.366197183098592,
|
| 2084 |
+
"grad_norm": 0.03018755465745926,
|
| 2085 |
+
"learning_rate": 6.47887323943662e-06,
|
| 2086 |
+
"loss": 0.9442,
|
| 2087 |
+
"step": 1375
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 19.43661971830986,
|
| 2091 |
+
"grad_norm": 0.019777249544858932,
|
| 2092 |
+
"learning_rate": 5.774647887323944e-06,
|
| 2093 |
+
"loss": 0.9438,
|
| 2094 |
+
"step": 1380
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 19.507042253521128,
|
| 2098 |
+
"grad_norm": 0.036921270191669464,
|
| 2099 |
+
"learning_rate": 5.070422535211268e-06,
|
| 2100 |
+
"loss": 0.9435,
|
| 2101 |
+
"step": 1385
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 19.577464788732396,
|
| 2105 |
+
"grad_norm": 0.038511138409376144,
|
| 2106 |
+
"learning_rate": 4.3661971830985915e-06,
|
| 2107 |
+
"loss": 0.9442,
|
| 2108 |
+
"step": 1390
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 19.647887323943664,
|
| 2112 |
+
"grad_norm": 0.03045705333352089,
|
| 2113 |
+
"learning_rate": 3.6619718309859158e-06,
|
| 2114 |
+
"loss": 0.9443,
|
| 2115 |
+
"step": 1395
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 19.718309859154928,
|
| 2119 |
+
"grad_norm": 0.037487465888261795,
|
| 2120 |
+
"learning_rate": 2.9577464788732396e-06,
|
| 2121 |
+
"loss": 0.9435,
|
| 2122 |
+
"step": 1400
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 19.788732394366196,
|
| 2126 |
+
"grad_norm": 0.022748373448848724,
|
| 2127 |
+
"learning_rate": 2.2535211267605635e-06,
|
| 2128 |
+
"loss": 0.9439,
|
| 2129 |
+
"step": 1405
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 19.859154929577464,
|
| 2133 |
+
"grad_norm": 0.037895116955041885,
|
| 2134 |
+
"learning_rate": 1.5492957746478875e-06,
|
| 2135 |
+
"loss": 0.9438,
|
| 2136 |
+
"step": 1410
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 19.929577464788732,
|
| 2140 |
+
"grad_norm": 0.02999270148575306,
|
| 2141 |
+
"learning_rate": 8.450704225352112e-07,
|
| 2142 |
+
"loss": 0.9429,
|
| 2143 |
+
"step": 1415
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 20.0,
|
| 2147 |
+
"grad_norm": 0.03205498680472374,
|
| 2148 |
+
"learning_rate": 1.4084507042253522e-07,
|
| 2149 |
+
"loss": 0.9441,
|
| 2150 |
+
"step": 1420
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 20.0,
|
| 2154 |
+
"eval_loss": 0.931971549987793,
|
| 2155 |
+
"eval_runtime": 1.3285,
|
| 2156 |
+
"eval_samples_per_second": 285.277,
|
| 2157 |
+
"eval_steps_per_second": 2.258,
|
| 2158 |
+
"step": 1420
|
| 2159 |
+
}
|
| 2160 |
+
],
|
| 2161 |
+
"logging_steps": 5,
|
| 2162 |
+
"max_steps": 1420,
|
| 2163 |
+
"num_input_tokens_seen": 0,
|
| 2164 |
+
"num_train_epochs": 20,
|
| 2165 |
+
"save_steps": 500,
|
| 2166 |
+
"stateful_callbacks": {
|
| 2167 |
+
"TrainerControl": {
|
| 2168 |
+
"args": {
|
| 2169 |
+
"should_epoch_stop": false,
|
| 2170 |
+
"should_evaluate": false,
|
| 2171 |
+
"should_log": false,
|
| 2172 |
+
"should_save": true,
|
| 2173 |
+
"should_training_stop": true
|
| 2174 |
+
},
|
| 2175 |
+
"attributes": {}
|
| 2176 |
+
}
|
| 2177 |
+
},
|
| 2178 |
+
"total_flos": 6.424179214123008e+16,
|
| 2179 |
+
"train_batch_size": 48,
|
| 2180 |
+
"trial_name": null,
|
| 2181 |
+
"trial_params": null
|
| 2182 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:041f2ee6df165b5d22004b622affcf417f382986127d7a972adaf8f8946ea8ed
|
| 3 |
+
size 6033
|