Model save
Browse files- README.md +58 -0
- added_tokens.json +130 -0
- all_results.json +8 -0
- chat_template.jinja +2 -0
- config.json +148 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +39 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1191 -0
- train_results.json +8 -0
- trainer_state.json +1375 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: HuggingFaceTB/SmolVLM2-2.2B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: SmolVLM2-2.2B-Instruct-Agentic-GUI
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for SmolVLM2-2.2B-Instruct-Agentic-GUI
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolVLM2-2.2B-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/smolagents/runs/kpx1bopv)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.18.0
|
| 38 |
+
- Transformers: 4.52.3
|
| 39 |
+
- Pytorch: 2.6.0
|
| 40 |
+
- Datasets: 4.0.0
|
| 41 |
+
- Tokenizers: 0.21.2
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<end_of_utterance>": 49279,
|
| 3 |
+
"<fake_token_around_image>": 49189,
|
| 4 |
+
"<global-img>": 49152,
|
| 5 |
+
"<image>": 49190,
|
| 6 |
+
"<row_1_col_1>": 49153,
|
| 7 |
+
"<row_1_col_2>": 49154,
|
| 8 |
+
"<row_1_col_3>": 49155,
|
| 9 |
+
"<row_1_col_4>": 49156,
|
| 10 |
+
"<row_1_col_5>": 49157,
|
| 11 |
+
"<row_1_col_6>": 49158,
|
| 12 |
+
"<row_2_col_1>": 49159,
|
| 13 |
+
"<row_2_col_2>": 49160,
|
| 14 |
+
"<row_2_col_3>": 49161,
|
| 15 |
+
"<row_2_col_4>": 49162,
|
| 16 |
+
"<row_2_col_5>": 49163,
|
| 17 |
+
"<row_2_col_6>": 49164,
|
| 18 |
+
"<row_3_col_1>": 49165,
|
| 19 |
+
"<row_3_col_2>": 49166,
|
| 20 |
+
"<row_3_col_3>": 49167,
|
| 21 |
+
"<row_3_col_4>": 49168,
|
| 22 |
+
"<row_3_col_5>": 49169,
|
| 23 |
+
"<row_3_col_6>": 49170,
|
| 24 |
+
"<row_4_col_1>": 49171,
|
| 25 |
+
"<row_4_col_2>": 49172,
|
| 26 |
+
"<row_4_col_3>": 49173,
|
| 27 |
+
"<row_4_col_4>": 49174,
|
| 28 |
+
"<row_4_col_5>": 49175,
|
| 29 |
+
"<row_4_col_6>": 49176,
|
| 30 |
+
"<row_5_col_1>": 49177,
|
| 31 |
+
"<row_5_col_2>": 49178,
|
| 32 |
+
"<row_5_col_3>": 49179,
|
| 33 |
+
"<row_5_col_4>": 49180,
|
| 34 |
+
"<row_5_col_5>": 49181,
|
| 35 |
+
"<row_5_col_6>": 49182,
|
| 36 |
+
"<row_6_col_1>": 49183,
|
| 37 |
+
"<row_6_col_2>": 49184,
|
| 38 |
+
"<row_6_col_3>": 49185,
|
| 39 |
+
"<row_6_col_4>": 49186,
|
| 40 |
+
"<row_6_col_5>": 49187,
|
| 41 |
+
"<row_6_col_6>": 49188,
|
| 42 |
+
"<|reserved_special_token_0|>": 49191,
|
| 43 |
+
"<|reserved_special_token_10|>": 49201,
|
| 44 |
+
"<|reserved_special_token_11|>": 49202,
|
| 45 |
+
"<|reserved_special_token_12|>": 49203,
|
| 46 |
+
"<|reserved_special_token_13|>": 49204,
|
| 47 |
+
"<|reserved_special_token_14|>": 49205,
|
| 48 |
+
"<|reserved_special_token_15|>": 49206,
|
| 49 |
+
"<|reserved_special_token_16|>": 49207,
|
| 50 |
+
"<|reserved_special_token_17|>": 49208,
|
| 51 |
+
"<|reserved_special_token_18|>": 49209,
|
| 52 |
+
"<|reserved_special_token_19|>": 49210,
|
| 53 |
+
"<|reserved_special_token_1|>": 49192,
|
| 54 |
+
"<|reserved_special_token_20|>": 49211,
|
| 55 |
+
"<|reserved_special_token_21|>": 49212,
|
| 56 |
+
"<|reserved_special_token_22|>": 49213,
|
| 57 |
+
"<|reserved_special_token_23|>": 49214,
|
| 58 |
+
"<|reserved_special_token_24|>": 49215,
|
| 59 |
+
"<|reserved_special_token_25|>": 49216,
|
| 60 |
+
"<|reserved_special_token_26|>": 49217,
|
| 61 |
+
"<|reserved_special_token_27|>": 49218,
|
| 62 |
+
"<|reserved_special_token_28|>": 49219,
|
| 63 |
+
"<|reserved_special_token_29|>": 49220,
|
| 64 |
+
"<|reserved_special_token_2|>": 49193,
|
| 65 |
+
"<|reserved_special_token_30|>": 49221,
|
| 66 |
+
"<|reserved_special_token_31|>": 49222,
|
| 67 |
+
"<|reserved_special_token_32|>": 49223,
|
| 68 |
+
"<|reserved_special_token_33|>": 49224,
|
| 69 |
+
"<|reserved_special_token_34|>": 49225,
|
| 70 |
+
"<|reserved_special_token_35|>": 49226,
|
| 71 |
+
"<|reserved_special_token_36|>": 49227,
|
| 72 |
+
"<|reserved_special_token_37|>": 49228,
|
| 73 |
+
"<|reserved_special_token_38|>": 49229,
|
| 74 |
+
"<|reserved_special_token_39|>": 49230,
|
| 75 |
+
"<|reserved_special_token_3|>": 49194,
|
| 76 |
+
"<|reserved_special_token_40|>": 49231,
|
| 77 |
+
"<|reserved_special_token_41|>": 49232,
|
| 78 |
+
"<|reserved_special_token_42|>": 49233,
|
| 79 |
+
"<|reserved_special_token_43|>": 49234,
|
| 80 |
+
"<|reserved_special_token_44|>": 49235,
|
| 81 |
+
"<|reserved_special_token_45|>": 49236,
|
| 82 |
+
"<|reserved_special_token_46|>": 49237,
|
| 83 |
+
"<|reserved_special_token_47|>": 49238,
|
| 84 |
+
"<|reserved_special_token_48|>": 49239,
|
| 85 |
+
"<|reserved_special_token_49|>": 49240,
|
| 86 |
+
"<|reserved_special_token_4|>": 49195,
|
| 87 |
+
"<|reserved_special_token_50|>": 49241,
|
| 88 |
+
"<|reserved_special_token_51|>": 49242,
|
| 89 |
+
"<|reserved_special_token_52|>": 49243,
|
| 90 |
+
"<|reserved_special_token_53|>": 49244,
|
| 91 |
+
"<|reserved_special_token_54|>": 49245,
|
| 92 |
+
"<|reserved_special_token_55|>": 49246,
|
| 93 |
+
"<|reserved_special_token_56|>": 49247,
|
| 94 |
+
"<|reserved_special_token_57|>": 49248,
|
| 95 |
+
"<|reserved_special_token_58|>": 49249,
|
| 96 |
+
"<|reserved_special_token_59|>": 49250,
|
| 97 |
+
"<|reserved_special_token_5|>": 49196,
|
| 98 |
+
"<|reserved_special_token_60|>": 49251,
|
| 99 |
+
"<|reserved_special_token_61|>": 49252,
|
| 100 |
+
"<|reserved_special_token_62|>": 49253,
|
| 101 |
+
"<|reserved_special_token_63|>": 49254,
|
| 102 |
+
"<|reserved_special_token_64|>": 49255,
|
| 103 |
+
"<|reserved_special_token_65|>": 49256,
|
| 104 |
+
"<|reserved_special_token_66|>": 49257,
|
| 105 |
+
"<|reserved_special_token_67|>": 49258,
|
| 106 |
+
"<|reserved_special_token_68|>": 49259,
|
| 107 |
+
"<|reserved_special_token_69|>": 49260,
|
| 108 |
+
"<|reserved_special_token_6|>": 49197,
|
| 109 |
+
"<|reserved_special_token_70|>": 49261,
|
| 110 |
+
"<|reserved_special_token_71|>": 49262,
|
| 111 |
+
"<|reserved_special_token_72|>": 49263,
|
| 112 |
+
"<|reserved_special_token_73|>": 49264,
|
| 113 |
+
"<|reserved_special_token_74|>": 49265,
|
| 114 |
+
"<|reserved_special_token_75|>": 49266,
|
| 115 |
+
"<|reserved_special_token_76|>": 49267,
|
| 116 |
+
"<|reserved_special_token_77|>": 49268,
|
| 117 |
+
"<|reserved_special_token_78|>": 49269,
|
| 118 |
+
"<|reserved_special_token_79|>": 49270,
|
| 119 |
+
"<|reserved_special_token_7|>": 49198,
|
| 120 |
+
"<|reserved_special_token_80|>": 49271,
|
| 121 |
+
"<|reserved_special_token_81|>": 49272,
|
| 122 |
+
"<|reserved_special_token_82|>": 49273,
|
| 123 |
+
"<|reserved_special_token_83|>": 49274,
|
| 124 |
+
"<|reserved_special_token_84|>": 49275,
|
| 125 |
+
"<|reserved_special_token_85|>": 49276,
|
| 126 |
+
"<|reserved_special_token_86|>": 49277,
|
| 127 |
+
"<|reserved_special_token_87|>": 49278,
|
| 128 |
+
"<|reserved_special_token_8|>": 49199,
|
| 129 |
+
"<|reserved_special_token_9|>": 49200
|
| 130 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 6033817814958080.0,
|
| 3 |
+
"train_loss": 0.6046972061422738,
|
| 4 |
+
"train_runtime": 27367.7567,
|
| 5 |
+
"train_samples": 360252,
|
| 6 |
+
"train_samples_per_second": 13.163,
|
| 7 |
+
"train_steps_per_second": 0.026
|
| 8 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
|
| 2 |
+
{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SmolVLMForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 49190,
|
| 6 |
+
"model_type": "smolvlm",
|
| 7 |
+
"pad_token_id": 128002,
|
| 8 |
+
"scale_factor": 3,
|
| 9 |
+
"text_config": {
|
| 10 |
+
"_flash_attn_2_enabled": true,
|
| 11 |
+
"_name_or_path": "None",
|
| 12 |
+
"architectures": [
|
| 13 |
+
"VLlama3ForCausalLM"
|
| 14 |
+
],
|
| 15 |
+
"attention_bias": false,
|
| 16 |
+
"attention_dropout": 0.0,
|
| 17 |
+
"head_dim": 64,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 2048,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 8192,
|
| 22 |
+
"max_position_embeddings": 8192,
|
| 23 |
+
"mlp_bias": false,
|
| 24 |
+
"model_type": "llama",
|
| 25 |
+
"neftune_noise_alpha": 0.0,
|
| 26 |
+
"num_attention_heads": 32,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"num_key_value_heads": 32,
|
| 29 |
+
"pad_token_id": 2,
|
| 30 |
+
"perceiver_config": {
|
| 31 |
+
"_name_or_path": "",
|
| 32 |
+
"add_cross_attention": false,
|
| 33 |
+
"architectures": null,
|
| 34 |
+
"attention_dropout": 0.0,
|
| 35 |
+
"bad_words_ids": null,
|
| 36 |
+
"begin_suppress_tokens": null,
|
| 37 |
+
"bos_token_id": null,
|
| 38 |
+
"chunk_size_feed_forward": 0,
|
| 39 |
+
"cross_attention_hidden_size": null,
|
| 40 |
+
"decoder_start_token_id": null,
|
| 41 |
+
"diversity_penalty": 0.0,
|
| 42 |
+
"do_sample": false,
|
| 43 |
+
"early_stopping": false,
|
| 44 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 45 |
+
"eos_token_id": null,
|
| 46 |
+
"exponential_decay_length_penalty": null,
|
| 47 |
+
"finetuning_task": null,
|
| 48 |
+
"forced_bos_token_id": null,
|
| 49 |
+
"forced_eos_token_id": null,
|
| 50 |
+
"hidden_act": "silu",
|
| 51 |
+
"id2label": {
|
| 52 |
+
"0": "LABEL_0",
|
| 53 |
+
"1": "LABEL_1"
|
| 54 |
+
},
|
| 55 |
+
"is_decoder": false,
|
| 56 |
+
"is_encoder_decoder": false,
|
| 57 |
+
"label2id": {
|
| 58 |
+
"LABEL_0": 0,
|
| 59 |
+
"LABEL_1": 1
|
| 60 |
+
},
|
| 61 |
+
"length_penalty": 1.0,
|
| 62 |
+
"max_length": 20,
|
| 63 |
+
"min_length": 0,
|
| 64 |
+
"model_type": "vllama3",
|
| 65 |
+
"no_repeat_ngram_size": 0,
|
| 66 |
+
"num_beam_groups": 1,
|
| 67 |
+
"num_beams": 1,
|
| 68 |
+
"num_key_value_heads": 1,
|
| 69 |
+
"num_return_sequences": 1,
|
| 70 |
+
"output_attentions": false,
|
| 71 |
+
"output_hidden_states": false,
|
| 72 |
+
"output_scores": false,
|
| 73 |
+
"pad_token_id": null,
|
| 74 |
+
"prefix": null,
|
| 75 |
+
"problem_type": null,
|
| 76 |
+
"pruned_heads": {},
|
| 77 |
+
"qk_layer_norms_perceiver": false,
|
| 78 |
+
"remove_invalid_values": false,
|
| 79 |
+
"repetition_penalty": 1.0,
|
| 80 |
+
"resampler_depth": 6,
|
| 81 |
+
"resampler_head_dim": 96,
|
| 82 |
+
"resampler_n_heads": 16,
|
| 83 |
+
"resampler_n_latents": 64,
|
| 84 |
+
"return_dict": true,
|
| 85 |
+
"return_dict_in_generate": false,
|
| 86 |
+
"sep_token_id": null,
|
| 87 |
+
"suppress_tokens": null,
|
| 88 |
+
"task_specific_params": null,
|
| 89 |
+
"temperature": 1.0,
|
| 90 |
+
"tf_legacy_loss": false,
|
| 91 |
+
"tie_encoder_decoder": false,
|
| 92 |
+
"tie_word_embeddings": true,
|
| 93 |
+
"tokenizer_class": null,
|
| 94 |
+
"top_k": 50,
|
| 95 |
+
"top_p": 1.0,
|
| 96 |
+
"torch_dtype": null,
|
| 97 |
+
"torchscript": false,
|
| 98 |
+
"transformers_version": "4.46.0",
|
| 99 |
+
"typical_p": 1.0,
|
| 100 |
+
"use_bfloat16": false
|
| 101 |
+
},
|
| 102 |
+
"pixel_shuffle_factor": 3,
|
| 103 |
+
"pretraining_tp": 1,
|
| 104 |
+
"qk_layer_norms": false,
|
| 105 |
+
"rms_norm_eps": 1e-05,
|
| 106 |
+
"rope_scaling": null,
|
| 107 |
+
"rope_theta": 130000,
|
| 108 |
+
"torch_dtype": "bfloat16",
|
| 109 |
+
"transformers.js_config": {
|
| 110 |
+
"kv_cache_dtype": {
|
| 111 |
+
"fp16": "float16",
|
| 112 |
+
"q4f16": "float16"
|
| 113 |
+
}
|
| 114 |
+
},
|
| 115 |
+
"use_cache": true,
|
| 116 |
+
"use_resampler": false,
|
| 117 |
+
"vocab_size": 49280
|
| 118 |
+
},
|
| 119 |
+
"tie_word_embeddings": false,
|
| 120 |
+
"torch_dtype": "bfloat16",
|
| 121 |
+
"transformers_version": "4.52.3",
|
| 122 |
+
"use_cache": false,
|
| 123 |
+
"use_reentrant_checkpointing": false,
|
| 124 |
+
"vision_config": {
|
| 125 |
+
"attention_dropout": 0.0,
|
| 126 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 127 |
+
"hidden_size": 1152,
|
| 128 |
+
"image_size": 384,
|
| 129 |
+
"initializer_range": 0.02,
|
| 130 |
+
"intermediate_size": 4304,
|
| 131 |
+
"layer_norm_eps": 1e-06,
|
| 132 |
+
"max_image_size": {
|
| 133 |
+
"longest_edge": 384
|
| 134 |
+
},
|
| 135 |
+
"model_type": "smolvlm_vision",
|
| 136 |
+
"num_attention_heads": 16,
|
| 137 |
+
"num_channels": 3,
|
| 138 |
+
"num_hidden_layers": 27,
|
| 139 |
+
"patch_size": 14,
|
| 140 |
+
"size": {
|
| 141 |
+
"longest_edge": 1920
|
| 142 |
+
},
|
| 143 |
+
"tie_word_embeddings": false,
|
| 144 |
+
"torch_dtype": "bfloat16",
|
| 145 |
+
"use_base_siglip": false
|
| 146 |
+
},
|
| 147 |
+
"vocab_size": 49280
|
| 148 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 49279,
|
| 5 |
+
"pad_token_id": 2,
|
| 6 |
+
"transformers_version": "4.52.3"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2ec23ca72f97f9878f45d8dc1d660990625fd8640662f3f88c74b2779edf1cc
|
| 3 |
+
size 4493654912
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<fake_token_around_image>",
|
| 4 |
+
"<image>",
|
| 5 |
+
"<end_of_utterance>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<|im_start|>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"end_of_utterance_token": "<end_of_utterance>",
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "<end_of_utterance>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"fake_image_token": "<fake_token_around_image>",
|
| 23 |
+
"global_image_token": "<global-img>",
|
| 24 |
+
"image_token": "<image>",
|
| 25 |
+
"pad_token": {
|
| 26 |
+
"content": "<|im_end|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"unk_token": {
|
| 33 |
+
"content": "<|endoftext|>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
}
|
| 39 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"49152": {
|
| 141 |
+
"content": "<global-img>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"49153": {
|
| 149 |
+
"content": "<row_1_col_1>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"49154": {
|
| 157 |
+
"content": "<row_1_col_2>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"49155": {
|
| 165 |
+
"content": "<row_1_col_3>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"49156": {
|
| 173 |
+
"content": "<row_1_col_4>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"49157": {
|
| 181 |
+
"content": "<row_1_col_5>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"49158": {
|
| 189 |
+
"content": "<row_1_col_6>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"49159": {
|
| 197 |
+
"content": "<row_2_col_1>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"49160": {
|
| 205 |
+
"content": "<row_2_col_2>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"49161": {
|
| 213 |
+
"content": "<row_2_col_3>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"49162": {
|
| 221 |
+
"content": "<row_2_col_4>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"49163": {
|
| 229 |
+
"content": "<row_2_col_5>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"49164": {
|
| 237 |
+
"content": "<row_2_col_6>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"49165": {
|
| 245 |
+
"content": "<row_3_col_1>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"49166": {
|
| 253 |
+
"content": "<row_3_col_2>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"49167": {
|
| 261 |
+
"content": "<row_3_col_3>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"49168": {
|
| 269 |
+
"content": "<row_3_col_4>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"49169": {
|
| 277 |
+
"content": "<row_3_col_5>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"49170": {
|
| 285 |
+
"content": "<row_3_col_6>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"49171": {
|
| 293 |
+
"content": "<row_4_col_1>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"49172": {
|
| 301 |
+
"content": "<row_4_col_2>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"49173": {
|
| 309 |
+
"content": "<row_4_col_3>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"49174": {
|
| 317 |
+
"content": "<row_4_col_4>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"49175": {
|
| 325 |
+
"content": "<row_4_col_5>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"49176": {
|
| 333 |
+
"content": "<row_4_col_6>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"49177": {
|
| 341 |
+
"content": "<row_5_col_1>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"49178": {
|
| 349 |
+
"content": "<row_5_col_2>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"49179": {
|
| 357 |
+
"content": "<row_5_col_3>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"49180": {
|
| 365 |
+
"content": "<row_5_col_4>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"49181": {
|
| 373 |
+
"content": "<row_5_col_5>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"49182": {
|
| 381 |
+
"content": "<row_5_col_6>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"49183": {
|
| 389 |
+
"content": "<row_6_col_1>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"49184": {
|
| 397 |
+
"content": "<row_6_col_2>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"49185": {
|
| 405 |
+
"content": "<row_6_col_3>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"49186": {
|
| 413 |
+
"content": "<row_6_col_4>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"49187": {
|
| 421 |
+
"content": "<row_6_col_5>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"49188": {
|
| 429 |
+
"content": "<row_6_col_6>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"49189": {
|
| 437 |
+
"content": "<fake_token_around_image>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"49190": {
|
| 445 |
+
"content": "<image>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"49191": {
|
| 453 |
+
"content": "<|reserved_special_token_0|>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"49192": {
|
| 461 |
+
"content": "<|reserved_special_token_1|>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"49193": {
|
| 469 |
+
"content": "<|reserved_special_token_2|>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"49194": {
|
| 477 |
+
"content": "<|reserved_special_token_3|>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"49195": {
|
| 485 |
+
"content": "<|reserved_special_token_4|>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"49196": {
|
| 493 |
+
"content": "<|reserved_special_token_5|>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"49197": {
|
| 501 |
+
"content": "<|reserved_special_token_6|>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"49198": {
|
| 509 |
+
"content": "<|reserved_special_token_7|>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"49199": {
|
| 517 |
+
"content": "<|reserved_special_token_8|>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"49200": {
|
| 525 |
+
"content": "<|reserved_special_token_9|>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"49201": {
|
| 533 |
+
"content": "<|reserved_special_token_10|>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"49202": {
|
| 541 |
+
"content": "<|reserved_special_token_11|>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"49203": {
|
| 549 |
+
"content": "<|reserved_special_token_12|>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"49204": {
|
| 557 |
+
"content": "<|reserved_special_token_13|>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"49205": {
|
| 565 |
+
"content": "<|reserved_special_token_14|>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"49206": {
|
| 573 |
+
"content": "<|reserved_special_token_15|>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"49207": {
|
| 581 |
+
"content": "<|reserved_special_token_16|>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"49208": {
|
| 589 |
+
"content": "<|reserved_special_token_17|>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"49209": {
|
| 597 |
+
"content": "<|reserved_special_token_18|>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"49210": {
|
| 605 |
+
"content": "<|reserved_special_token_19|>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"49211": {
|
| 613 |
+
"content": "<|reserved_special_token_20|>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"49212": {
|
| 621 |
+
"content": "<|reserved_special_token_21|>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"49213": {
|
| 629 |
+
"content": "<|reserved_special_token_22|>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"49214": {
|
| 637 |
+
"content": "<|reserved_special_token_23|>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"49215": {
|
| 645 |
+
"content": "<|reserved_special_token_24|>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"49216": {
|
| 653 |
+
"content": "<|reserved_special_token_25|>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"49217": {
|
| 661 |
+
"content": "<|reserved_special_token_26|>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"49218": {
|
| 669 |
+
"content": "<|reserved_special_token_27|>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"49219": {
|
| 677 |
+
"content": "<|reserved_special_token_28|>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"49220": {
|
| 685 |
+
"content": "<|reserved_special_token_29|>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"49221": {
|
| 693 |
+
"content": "<|reserved_special_token_30|>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"49222": {
|
| 701 |
+
"content": "<|reserved_special_token_31|>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"49223": {
|
| 709 |
+
"content": "<|reserved_special_token_32|>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"49224": {
|
| 717 |
+
"content": "<|reserved_special_token_33|>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"49225": {
|
| 725 |
+
"content": "<|reserved_special_token_34|>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"49226": {
|
| 733 |
+
"content": "<|reserved_special_token_35|>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"49227": {
|
| 741 |
+
"content": "<|reserved_special_token_36|>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"49228": {
|
| 749 |
+
"content": "<|reserved_special_token_37|>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"49229": {
|
| 757 |
+
"content": "<|reserved_special_token_38|>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"49230": {
|
| 765 |
+
"content": "<|reserved_special_token_39|>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"49231": {
|
| 773 |
+
"content": "<|reserved_special_token_40|>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"49232": {
|
| 781 |
+
"content": "<|reserved_special_token_41|>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"49233": {
|
| 789 |
+
"content": "<|reserved_special_token_42|>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"49234": {
|
| 797 |
+
"content": "<|reserved_special_token_43|>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"49235": {
|
| 805 |
+
"content": "<|reserved_special_token_44|>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"49236": {
|
| 813 |
+
"content": "<|reserved_special_token_45|>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"49237": {
|
| 821 |
+
"content": "<|reserved_special_token_46|>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"49238": {
|
| 829 |
+
"content": "<|reserved_special_token_47|>",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"49239": {
|
| 837 |
+
"content": "<|reserved_special_token_48|>",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
},
|
| 844 |
+
"49240": {
|
| 845 |
+
"content": "<|reserved_special_token_49|>",
|
| 846 |
+
"lstrip": false,
|
| 847 |
+
"normalized": false,
|
| 848 |
+
"rstrip": false,
|
| 849 |
+
"single_word": false,
|
| 850 |
+
"special": true
|
| 851 |
+
},
|
| 852 |
+
"49241": {
|
| 853 |
+
"content": "<|reserved_special_token_50|>",
|
| 854 |
+
"lstrip": false,
|
| 855 |
+
"normalized": false,
|
| 856 |
+
"rstrip": false,
|
| 857 |
+
"single_word": false,
|
| 858 |
+
"special": true
|
| 859 |
+
},
|
| 860 |
+
"49242": {
|
| 861 |
+
"content": "<|reserved_special_token_51|>",
|
| 862 |
+
"lstrip": false,
|
| 863 |
+
"normalized": false,
|
| 864 |
+
"rstrip": false,
|
| 865 |
+
"single_word": false,
|
| 866 |
+
"special": true
|
| 867 |
+
},
|
| 868 |
+
"49243": {
|
| 869 |
+
"content": "<|reserved_special_token_52|>",
|
| 870 |
+
"lstrip": false,
|
| 871 |
+
"normalized": false,
|
| 872 |
+
"rstrip": false,
|
| 873 |
+
"single_word": false,
|
| 874 |
+
"special": true
|
| 875 |
+
},
|
| 876 |
+
"49244": {
|
| 877 |
+
"content": "<|reserved_special_token_53|>",
|
| 878 |
+
"lstrip": false,
|
| 879 |
+
"normalized": false,
|
| 880 |
+
"rstrip": false,
|
| 881 |
+
"single_word": false,
|
| 882 |
+
"special": true
|
| 883 |
+
},
|
| 884 |
+
"49245": {
|
| 885 |
+
"content": "<|reserved_special_token_54|>",
|
| 886 |
+
"lstrip": false,
|
| 887 |
+
"normalized": false,
|
| 888 |
+
"rstrip": false,
|
| 889 |
+
"single_word": false,
|
| 890 |
+
"special": true
|
| 891 |
+
},
|
| 892 |
+
"49246": {
|
| 893 |
+
"content": "<|reserved_special_token_55|>",
|
| 894 |
+
"lstrip": false,
|
| 895 |
+
"normalized": false,
|
| 896 |
+
"rstrip": false,
|
| 897 |
+
"single_word": false,
|
| 898 |
+
"special": true
|
| 899 |
+
},
|
| 900 |
+
"49247": {
|
| 901 |
+
"content": "<|reserved_special_token_56|>",
|
| 902 |
+
"lstrip": false,
|
| 903 |
+
"normalized": false,
|
| 904 |
+
"rstrip": false,
|
| 905 |
+
"single_word": false,
|
| 906 |
+
"special": true
|
| 907 |
+
},
|
| 908 |
+
"49248": {
|
| 909 |
+
"content": "<|reserved_special_token_57|>",
|
| 910 |
+
"lstrip": false,
|
| 911 |
+
"normalized": false,
|
| 912 |
+
"rstrip": false,
|
| 913 |
+
"single_word": false,
|
| 914 |
+
"special": true
|
| 915 |
+
},
|
| 916 |
+
"49249": {
|
| 917 |
+
"content": "<|reserved_special_token_58|>",
|
| 918 |
+
"lstrip": false,
|
| 919 |
+
"normalized": false,
|
| 920 |
+
"rstrip": false,
|
| 921 |
+
"single_word": false,
|
| 922 |
+
"special": true
|
| 923 |
+
},
|
| 924 |
+
"49250": {
|
| 925 |
+
"content": "<|reserved_special_token_59|>",
|
| 926 |
+
"lstrip": false,
|
| 927 |
+
"normalized": false,
|
| 928 |
+
"rstrip": false,
|
| 929 |
+
"single_word": false,
|
| 930 |
+
"special": true
|
| 931 |
+
},
|
| 932 |
+
"49251": {
|
| 933 |
+
"content": "<|reserved_special_token_60|>",
|
| 934 |
+
"lstrip": false,
|
| 935 |
+
"normalized": false,
|
| 936 |
+
"rstrip": false,
|
| 937 |
+
"single_word": false,
|
| 938 |
+
"special": true
|
| 939 |
+
},
|
| 940 |
+
"49252": {
|
| 941 |
+
"content": "<|reserved_special_token_61|>",
|
| 942 |
+
"lstrip": false,
|
| 943 |
+
"normalized": false,
|
| 944 |
+
"rstrip": false,
|
| 945 |
+
"single_word": false,
|
| 946 |
+
"special": true
|
| 947 |
+
},
|
| 948 |
+
"49253": {
|
| 949 |
+
"content": "<|reserved_special_token_62|>",
|
| 950 |
+
"lstrip": false,
|
| 951 |
+
"normalized": false,
|
| 952 |
+
"rstrip": false,
|
| 953 |
+
"single_word": false,
|
| 954 |
+
"special": true
|
| 955 |
+
},
|
| 956 |
+
"49254": {
|
| 957 |
+
"content": "<|reserved_special_token_63|>",
|
| 958 |
+
"lstrip": false,
|
| 959 |
+
"normalized": false,
|
| 960 |
+
"rstrip": false,
|
| 961 |
+
"single_word": false,
|
| 962 |
+
"special": true
|
| 963 |
+
},
|
| 964 |
+
"49255": {
|
| 965 |
+
"content": "<|reserved_special_token_64|>",
|
| 966 |
+
"lstrip": false,
|
| 967 |
+
"normalized": false,
|
| 968 |
+
"rstrip": false,
|
| 969 |
+
"single_word": false,
|
| 970 |
+
"special": true
|
| 971 |
+
},
|
| 972 |
+
"49256": {
|
| 973 |
+
"content": "<|reserved_special_token_65|>",
|
| 974 |
+
"lstrip": false,
|
| 975 |
+
"normalized": false,
|
| 976 |
+
"rstrip": false,
|
| 977 |
+
"single_word": false,
|
| 978 |
+
"special": true
|
| 979 |
+
},
|
| 980 |
+
"49257": {
|
| 981 |
+
"content": "<|reserved_special_token_66|>",
|
| 982 |
+
"lstrip": false,
|
| 983 |
+
"normalized": false,
|
| 984 |
+
"rstrip": false,
|
| 985 |
+
"single_word": false,
|
| 986 |
+
"special": true
|
| 987 |
+
},
|
| 988 |
+
"49258": {
|
| 989 |
+
"content": "<|reserved_special_token_67|>",
|
| 990 |
+
"lstrip": false,
|
| 991 |
+
"normalized": false,
|
| 992 |
+
"rstrip": false,
|
| 993 |
+
"single_word": false,
|
| 994 |
+
"special": true
|
| 995 |
+
},
|
| 996 |
+
"49259": {
|
| 997 |
+
"content": "<|reserved_special_token_68|>",
|
| 998 |
+
"lstrip": false,
|
| 999 |
+
"normalized": false,
|
| 1000 |
+
"rstrip": false,
|
| 1001 |
+
"single_word": false,
|
| 1002 |
+
"special": true
|
| 1003 |
+
},
|
| 1004 |
+
"49260": {
|
| 1005 |
+
"content": "<|reserved_special_token_69|>",
|
| 1006 |
+
"lstrip": false,
|
| 1007 |
+
"normalized": false,
|
| 1008 |
+
"rstrip": false,
|
| 1009 |
+
"single_word": false,
|
| 1010 |
+
"special": true
|
| 1011 |
+
},
|
| 1012 |
+
"49261": {
|
| 1013 |
+
"content": "<|reserved_special_token_70|>",
|
| 1014 |
+
"lstrip": false,
|
| 1015 |
+
"normalized": false,
|
| 1016 |
+
"rstrip": false,
|
| 1017 |
+
"single_word": false,
|
| 1018 |
+
"special": true
|
| 1019 |
+
},
|
| 1020 |
+
"49262": {
|
| 1021 |
+
"content": "<|reserved_special_token_71|>",
|
| 1022 |
+
"lstrip": false,
|
| 1023 |
+
"normalized": false,
|
| 1024 |
+
"rstrip": false,
|
| 1025 |
+
"single_word": false,
|
| 1026 |
+
"special": true
|
| 1027 |
+
},
|
| 1028 |
+
"49263": {
|
| 1029 |
+
"content": "<|reserved_special_token_72|>",
|
| 1030 |
+
"lstrip": false,
|
| 1031 |
+
"normalized": false,
|
| 1032 |
+
"rstrip": false,
|
| 1033 |
+
"single_word": false,
|
| 1034 |
+
"special": true
|
| 1035 |
+
},
|
| 1036 |
+
"49264": {
|
| 1037 |
+
"content": "<|reserved_special_token_73|>",
|
| 1038 |
+
"lstrip": false,
|
| 1039 |
+
"normalized": false,
|
| 1040 |
+
"rstrip": false,
|
| 1041 |
+
"single_word": false,
|
| 1042 |
+
"special": true
|
| 1043 |
+
},
|
| 1044 |
+
"49265": {
|
| 1045 |
+
"content": "<|reserved_special_token_74|>",
|
| 1046 |
+
"lstrip": false,
|
| 1047 |
+
"normalized": false,
|
| 1048 |
+
"rstrip": false,
|
| 1049 |
+
"single_word": false,
|
| 1050 |
+
"special": true
|
| 1051 |
+
},
|
| 1052 |
+
"49266": {
|
| 1053 |
+
"content": "<|reserved_special_token_75|>",
|
| 1054 |
+
"lstrip": false,
|
| 1055 |
+
"normalized": false,
|
| 1056 |
+
"rstrip": false,
|
| 1057 |
+
"single_word": false,
|
| 1058 |
+
"special": true
|
| 1059 |
+
},
|
| 1060 |
+
"49267": {
|
| 1061 |
+
"content": "<|reserved_special_token_76|>",
|
| 1062 |
+
"lstrip": false,
|
| 1063 |
+
"normalized": false,
|
| 1064 |
+
"rstrip": false,
|
| 1065 |
+
"single_word": false,
|
| 1066 |
+
"special": true
|
| 1067 |
+
},
|
| 1068 |
+
"49268": {
|
| 1069 |
+
"content": "<|reserved_special_token_77|>",
|
| 1070 |
+
"lstrip": false,
|
| 1071 |
+
"normalized": false,
|
| 1072 |
+
"rstrip": false,
|
| 1073 |
+
"single_word": false,
|
| 1074 |
+
"special": true
|
| 1075 |
+
},
|
| 1076 |
+
"49269": {
|
| 1077 |
+
"content": "<|reserved_special_token_78|>",
|
| 1078 |
+
"lstrip": false,
|
| 1079 |
+
"normalized": false,
|
| 1080 |
+
"rstrip": false,
|
| 1081 |
+
"single_word": false,
|
| 1082 |
+
"special": true
|
| 1083 |
+
},
|
| 1084 |
+
"49270": {
|
| 1085 |
+
"content": "<|reserved_special_token_79|>",
|
| 1086 |
+
"lstrip": false,
|
| 1087 |
+
"normalized": false,
|
| 1088 |
+
"rstrip": false,
|
| 1089 |
+
"single_word": false,
|
| 1090 |
+
"special": true
|
| 1091 |
+
},
|
| 1092 |
+
"49271": {
|
| 1093 |
+
"content": "<|reserved_special_token_80|>",
|
| 1094 |
+
"lstrip": false,
|
| 1095 |
+
"normalized": false,
|
| 1096 |
+
"rstrip": false,
|
| 1097 |
+
"single_word": false,
|
| 1098 |
+
"special": true
|
| 1099 |
+
},
|
| 1100 |
+
"49272": {
|
| 1101 |
+
"content": "<|reserved_special_token_81|>",
|
| 1102 |
+
"lstrip": false,
|
| 1103 |
+
"normalized": false,
|
| 1104 |
+
"rstrip": false,
|
| 1105 |
+
"single_word": false,
|
| 1106 |
+
"special": true
|
| 1107 |
+
},
|
| 1108 |
+
"49273": {
|
| 1109 |
+
"content": "<|reserved_special_token_82|>",
|
| 1110 |
+
"lstrip": false,
|
| 1111 |
+
"normalized": false,
|
| 1112 |
+
"rstrip": false,
|
| 1113 |
+
"single_word": false,
|
| 1114 |
+
"special": true
|
| 1115 |
+
},
|
| 1116 |
+
"49274": {
|
| 1117 |
+
"content": "<|reserved_special_token_83|>",
|
| 1118 |
+
"lstrip": false,
|
| 1119 |
+
"normalized": false,
|
| 1120 |
+
"rstrip": false,
|
| 1121 |
+
"single_word": false,
|
| 1122 |
+
"special": true
|
| 1123 |
+
},
|
| 1124 |
+
"49275": {
|
| 1125 |
+
"content": "<|reserved_special_token_84|>",
|
| 1126 |
+
"lstrip": false,
|
| 1127 |
+
"normalized": false,
|
| 1128 |
+
"rstrip": false,
|
| 1129 |
+
"single_word": false,
|
| 1130 |
+
"special": true
|
| 1131 |
+
},
|
| 1132 |
+
"49276": {
|
| 1133 |
+
"content": "<|reserved_special_token_85|>",
|
| 1134 |
+
"lstrip": false,
|
| 1135 |
+
"normalized": false,
|
| 1136 |
+
"rstrip": false,
|
| 1137 |
+
"single_word": false,
|
| 1138 |
+
"special": true
|
| 1139 |
+
},
|
| 1140 |
+
"49277": {
|
| 1141 |
+
"content": "<|reserved_special_token_86|>",
|
| 1142 |
+
"lstrip": false,
|
| 1143 |
+
"normalized": false,
|
| 1144 |
+
"rstrip": false,
|
| 1145 |
+
"single_word": false,
|
| 1146 |
+
"special": true
|
| 1147 |
+
},
|
| 1148 |
+
"49278": {
|
| 1149 |
+
"content": "<|reserved_special_token_87|>",
|
| 1150 |
+
"lstrip": false,
|
| 1151 |
+
"normalized": false,
|
| 1152 |
+
"rstrip": false,
|
| 1153 |
+
"single_word": false,
|
| 1154 |
+
"special": true
|
| 1155 |
+
},
|
| 1156 |
+
"49279": {
|
| 1157 |
+
"content": "<end_of_utterance>",
|
| 1158 |
+
"lstrip": false,
|
| 1159 |
+
"normalized": false,
|
| 1160 |
+
"rstrip": false,
|
| 1161 |
+
"single_word": false,
|
| 1162 |
+
"special": true
|
| 1163 |
+
}
|
| 1164 |
+
},
|
| 1165 |
+
"additional_special_tokens": [
|
| 1166 |
+
"<fake_token_around_image>",
|
| 1167 |
+
"<image>",
|
| 1168 |
+
"<end_of_utterance>"
|
| 1169 |
+
],
|
| 1170 |
+
"bos_token": "<|im_start|>",
|
| 1171 |
+
"clean_up_tokenization_spaces": false,
|
| 1172 |
+
"end_of_utterance_token": "<end_of_utterance>",
|
| 1173 |
+
"eos_token": "<end_of_utterance>",
|
| 1174 |
+
"extra_special_tokens": {
|
| 1175 |
+
"end_of_utterance_token": "<end_of_utterance>",
|
| 1176 |
+
"fake_image_token": "<fake_token_around_image>",
|
| 1177 |
+
"global_image_token": "<global-img>",
|
| 1178 |
+
"image_token": "<image>"
|
| 1179 |
+
},
|
| 1180 |
+
"fake_image_token": "<fake_token_around_image>",
|
| 1181 |
+
"global_image_token": "<global-img>",
|
| 1182 |
+
"image_token": "<image>",
|
| 1183 |
+
"legacy": false,
|
| 1184 |
+
"model_max_length": 16384,
|
| 1185 |
+
"pad_token": "<|im_end|>",
|
| 1186 |
+
"processor_class": "SmolVLMProcessor",
|
| 1187 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 1188 |
+
"truncation_side": "left",
|
| 1189 |
+
"unk_token": "<|endoftext|>",
|
| 1190 |
+
"vocab_size": 49152
|
| 1191 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"total_flos": 6033817814958080.0,
|
| 3 |
+
"train_loss": 0.6046972061422738,
|
| 4 |
+
"train_runtime": 27367.7567,
|
| 5 |
+
"train_samples": 360252,
|
| 6 |
+
"train_samples_per_second": 13.163,
|
| 7 |
+
"train_steps_per_second": 0.026
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 704,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007106057914372002,
|
| 14 |
+
"grad_norm": 50.32903949504469,
|
| 15 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 16 |
+
"loss": 4.3632,
|
| 17 |
+
"mean_token_accuracy": 0.441570908203721,
|
| 18 |
+
"num_tokens": 5473393.0,
|
| 19 |
+
"step": 5
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.014212115828744005,
|
| 23 |
+
"grad_norm": 14.807993883918904,
|
| 24 |
+
"learning_rate": 8.181818181818183e-06,
|
| 25 |
+
"loss": 3.1394,
|
| 26 |
+
"mean_token_accuracy": 0.49803002886474135,
|
| 27 |
+
"num_tokens": 10986730.0,
|
| 28 |
+
"step": 10
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.021318173743116006,
|
| 32 |
+
"grad_norm": 5.124010397941281,
|
| 33 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 34 |
+
"loss": 1.5984,
|
| 35 |
+
"mean_token_accuracy": 0.6562768064439297,
|
| 36 |
+
"num_tokens": 16504629.0,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02842423165748801,
|
| 41 |
+
"grad_norm": 2.392040251927866,
|
| 42 |
+
"learning_rate": 1.7272727272727274e-05,
|
| 43 |
+
"loss": 1.0563,
|
| 44 |
+
"mean_token_accuracy": 0.7480768047273159,
|
| 45 |
+
"num_tokens": 22018554.0,
|
| 46 |
+
"step": 20
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.03553028957186001,
|
| 50 |
+
"grad_norm": 3.2881890911900955,
|
| 51 |
+
"learning_rate": 1.999961805535155e-05,
|
| 52 |
+
"loss": 0.8892,
|
| 53 |
+
"mean_token_accuracy": 0.7724978730082512,
|
| 54 |
+
"num_tokens": 27528237.0,
|
| 55 |
+
"step": 25
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.04263634748623201,
|
| 59 |
+
"grad_norm": 3.296418319427866,
|
| 60 |
+
"learning_rate": 1.9995321550350065e-05,
|
| 61 |
+
"loss": 0.7968,
|
| 62 |
+
"mean_token_accuracy": 0.7858201645314693,
|
| 63 |
+
"num_tokens": 33059234.0,
|
| 64 |
+
"step": 30
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.04974240540060401,
|
| 68 |
+
"grad_norm": 2.650113760947062,
|
| 69 |
+
"learning_rate": 1.998625339625423e-05,
|
| 70 |
+
"loss": 0.7639,
|
| 71 |
+
"mean_token_accuracy": 0.7874479472637177,
|
| 72 |
+
"num_tokens": 38579238.0,
|
| 73 |
+
"step": 35
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.05684846331497602,
|
| 77 |
+
"grad_norm": 0.8030808619999289,
|
| 78 |
+
"learning_rate": 1.9972418403347817e-05,
|
| 79 |
+
"loss": 0.7136,
|
| 80 |
+
"mean_token_accuracy": 0.7952406644821167,
|
| 81 |
+
"num_tokens": 44087596.0,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.06395452122934801,
|
| 86 |
+
"grad_norm": 0.38079517614839553,
|
| 87 |
+
"learning_rate": 1.9953823910527057e-05,
|
| 88 |
+
"loss": 0.6781,
|
| 89 |
+
"mean_token_accuracy": 0.8054998718202114,
|
| 90 |
+
"num_tokens": 49589200.0,
|
| 91 |
+
"step": 45
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.07106057914372002,
|
| 95 |
+
"grad_norm": 0.35060604680564306,
|
| 96 |
+
"learning_rate": 1.993047978140764e-05,
|
| 97 |
+
"loss": 0.6594,
|
| 98 |
+
"mean_token_accuracy": 0.8087423123419285,
|
| 99 |
+
"num_tokens": 55106291.0,
|
| 100 |
+
"step": 50
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07816663705809203,
|
| 104 |
+
"grad_norm": 0.4403926191014202,
|
| 105 |
+
"learning_rate": 1.9902398399092494e-05,
|
| 106 |
+
"loss": 0.6293,
|
| 107 |
+
"mean_token_accuracy": 0.8166272558271885,
|
| 108 |
+
"num_tokens": 60615746.0,
|
| 109 |
+
"step": 55
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.08527269497246402,
|
| 113 |
+
"grad_norm": 0.4059804779836136,
|
| 114 |
+
"learning_rate": 1.9869594659603032e-05,
|
| 115 |
+
"loss": 0.633,
|
| 116 |
+
"mean_token_accuracy": 0.8155130945146084,
|
| 117 |
+
"num_tokens": 66132359.0,
|
| 118 |
+
"step": 60
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.09237875288683603,
|
| 122 |
+
"grad_norm": 0.35058497488520535,
|
| 123 |
+
"learning_rate": 1.9832085963977445e-05,
|
| 124 |
+
"loss": 0.6263,
|
| 125 |
+
"mean_token_accuracy": 0.8166398376226425,
|
| 126 |
+
"num_tokens": 71655901.0,
|
| 127 |
+
"step": 65
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.09948481080120802,
|
| 131 |
+
"grad_norm": 0.3514975941052687,
|
| 132 |
+
"learning_rate": 1.978989220904016e-05,
|
| 133 |
+
"loss": 0.6166,
|
| 134 |
+
"mean_token_accuracy": 0.817786256223917,
|
| 135 |
+
"num_tokens": 77177506.0,
|
| 136 |
+
"step": 70
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.10659086871558003,
|
| 140 |
+
"grad_norm": 0.3305576165553241,
|
| 141 |
+
"learning_rate": 1.9743035776847377e-05,
|
| 142 |
+
"loss": 0.6112,
|
| 143 |
+
"mean_token_accuracy": 0.8196637347340584,
|
| 144 |
+
"num_tokens": 82719853.0,
|
| 145 |
+
"step": 75
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.11369692662995204,
|
| 149 |
+
"grad_norm": 0.338564559273819,
|
| 150 |
+
"learning_rate": 1.9691541522814327e-05,
|
| 151 |
+
"loss": 0.5925,
|
| 152 |
+
"mean_token_accuracy": 0.823684225231409,
|
| 153 |
+
"num_tokens": 88237466.0,
|
| 154 |
+
"step": 80
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.12080298454432403,
|
| 158 |
+
"grad_norm": 0.3094787313199236,
|
| 159 |
+
"learning_rate": 1.963543676253048e-05,
|
| 160 |
+
"loss": 0.6006,
|
| 161 |
+
"mean_token_accuracy": 0.8217748202383518,
|
| 162 |
+
"num_tokens": 93758651.0,
|
| 163 |
+
"step": 85
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12790904245869603,
|
| 167 |
+
"grad_norm": 0.3244755207573469,
|
| 168 |
+
"learning_rate": 1.9574751257269748e-05,
|
| 169 |
+
"loss": 0.5922,
|
| 170 |
+
"mean_token_accuracy": 0.8233424670994282,
|
| 171 |
+
"num_tokens": 99280369.0,
|
| 172 |
+
"step": 90
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.13501510037306805,
|
| 176 |
+
"grad_norm": 0.37452298605350337,
|
| 177 |
+
"learning_rate": 1.950951719820335e-05,
|
| 178 |
+
"loss": 0.586,
|
| 179 |
+
"mean_token_accuracy": 0.825210265815258,
|
| 180 |
+
"num_tokens": 104773871.0,
|
| 181 |
+
"step": 95
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.14212115828744004,
|
| 185 |
+
"grad_norm": 0.3637562399439702,
|
| 186 |
+
"learning_rate": 1.9439769189323727e-05,
|
| 187 |
+
"loss": 0.5942,
|
| 188 |
+
"mean_token_accuracy": 0.8233202829957008,
|
| 189 |
+
"num_tokens": 110286415.0,
|
| 190 |
+
"step": 100
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.14212115828744004,
|
| 194 |
+
"eval_loss": 0.5650674104690552,
|
| 195 |
+
"eval_mean_token_accuracy": 0.8260843633559712,
|
| 196 |
+
"eval_num_tokens": 110286415.0,
|
| 197 |
+
"eval_runtime": 149.0036,
|
| 198 |
+
"eval_samples_per_second": 24.422,
|
| 199 |
+
"eval_steps_per_second": 0.765,
|
| 200 |
+
"step": 100
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.14922721620181204,
|
| 204 |
+
"grad_norm": 0.34962576562336867,
|
| 205 |
+
"learning_rate": 1.9365544229088517e-05,
|
| 206 |
+
"loss": 0.5897,
|
| 207 |
+
"mean_token_accuracy": 0.8245358660817146,
|
| 208 |
+
"num_tokens": 115819384.0,
|
| 209 |
+
"step": 105
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.15633327411618406,
|
| 213 |
+
"grad_norm": 0.32080702182710497,
|
| 214 |
+
"learning_rate": 1.9286881690794425e-05,
|
| 215 |
+
"loss": 0.5795,
|
| 216 |
+
"mean_token_accuracy": 0.827671080827713,
|
| 217 |
+
"num_tokens": 121352740.0,
|
| 218 |
+
"step": 110
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.16343933203055605,
|
| 222 |
+
"grad_norm": 0.3302528447867004,
|
| 223 |
+
"learning_rate": 1.9203823301691272e-05,
|
| 224 |
+
"loss": 0.5898,
|
| 225 |
+
"mean_token_accuracy": 0.8234031349420547,
|
| 226 |
+
"num_tokens": 126898367.0,
|
| 227 |
+
"step": 115
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.17054538994492804,
|
| 231 |
+
"grad_norm": 0.344422613860792,
|
| 232 |
+
"learning_rate": 1.9116413120847425e-05,
|
| 233 |
+
"loss": 0.5803,
|
| 234 |
+
"mean_token_accuracy": 0.8264414891600609,
|
| 235 |
+
"num_tokens": 132422935.0,
|
| 236 |
+
"step": 120
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.17765144785930007,
|
| 240 |
+
"grad_norm": 0.31498034575502054,
|
| 241 |
+
"learning_rate": 1.902469751577826e-05,
|
| 242 |
+
"loss": 0.5736,
|
| 243 |
+
"mean_token_accuracy": 0.8282143533229828,
|
| 244 |
+
"num_tokens": 137934164.0,
|
| 245 |
+
"step": 125
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.18475750577367206,
|
| 249 |
+
"grad_norm": 0.29607953526948433,
|
| 250 |
+
"learning_rate": 1.892872513785008e-05,
|
| 251 |
+
"loss": 0.5625,
|
| 252 |
+
"mean_token_accuracy": 0.8306705243885517,
|
| 253 |
+
"num_tokens": 143442236.0,
|
| 254 |
+
"step": 130
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.19186356368804405,
|
| 258 |
+
"grad_norm": 0.33026938357250507,
|
| 259 |
+
"learning_rate": 1.88285468964726e-05,
|
| 260 |
+
"loss": 0.5674,
|
| 261 |
+
"mean_token_accuracy": 0.8293713837862015,
|
| 262 |
+
"num_tokens": 148967668.0,
|
| 263 |
+
"step": 135
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.19896962160241605,
|
| 267 |
+
"grad_norm": 0.3098906923396821,
|
| 268 |
+
"learning_rate": 1.872421593209355e-05,
|
| 269 |
+
"loss": 0.5625,
|
| 270 |
+
"mean_token_accuracy": 0.8305731259286404,
|
| 271 |
+
"num_tokens": 154497475.0,
|
| 272 |
+
"step": 140
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.20607567951678807,
|
| 276 |
+
"grad_norm": 0.39805146321076146,
|
| 277 |
+
"learning_rate": 1.861578758800989e-05,
|
| 278 |
+
"loss": 0.569,
|
| 279 |
+
"mean_token_accuracy": 0.8292202673852443,
|
| 280 |
+
"num_tokens": 160003170.0,
|
| 281 |
+
"step": 145
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.21318173743116006,
|
| 285 |
+
"grad_norm": 0.314641318728057,
|
| 286 |
+
"learning_rate": 1.8503319381010414e-05,
|
| 287 |
+
"loss": 0.5632,
|
| 288 |
+
"mean_token_accuracy": 0.8299683950841427,
|
| 289 |
+
"num_tokens": 165528828.0,
|
| 290 |
+
"step": 150
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.22028779534553206,
|
| 294 |
+
"grad_norm": 0.31172255219458456,
|
| 295 |
+
"learning_rate": 1.8386870970865488e-05,
|
| 296 |
+
"loss": 0.5561,
|
| 297 |
+
"mean_token_accuracy": 0.8317106999456882,
|
| 298 |
+
"num_tokens": 171050241.0,
|
| 299 |
+
"step": 155
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.22739385325990408,
|
| 303 |
+
"grad_norm": 0.3316716520690995,
|
| 304 |
+
"learning_rate": 1.8266504128679988e-05,
|
| 305 |
+
"loss": 0.5572,
|
| 306 |
+
"mean_token_accuracy": 0.8323395892977714,
|
| 307 |
+
"num_tokens": 176567106.0,
|
| 308 |
+
"step": 160
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.23449991117427607,
|
| 312 |
+
"grad_norm": 0.3018790729986631,
|
| 313 |
+
"learning_rate": 1.814228270412624e-05,
|
| 314 |
+
"loss": 0.5717,
|
| 315 |
+
"mean_token_accuracy": 0.8280466146767139,
|
| 316 |
+
"num_tokens": 182090185.0,
|
| 317 |
+
"step": 165
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.24160596908864806,
|
| 321 |
+
"grad_norm": 0.3340485136656981,
|
| 322 |
+
"learning_rate": 1.8014272591574405e-05,
|
| 323 |
+
"loss": 0.5666,
|
| 324 |
+
"mean_token_accuracy": 0.8296592086553574,
|
| 325 |
+
"num_tokens": 187606737.0,
|
| 326 |
+
"step": 170
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.2487120270030201,
|
| 330 |
+
"grad_norm": 0.31420140799198965,
|
| 331 |
+
"learning_rate": 1.7882541695138224e-05,
|
| 332 |
+
"loss": 0.5521,
|
| 333 |
+
"mean_token_accuracy": 0.8335933439433575,
|
| 334 |
+
"num_tokens": 193124335.0,
|
| 335 |
+
"step": 175
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.25581808491739205,
|
| 339 |
+
"grad_norm": 0.3354458879208076,
|
| 340 |
+
"learning_rate": 1.7747159892654646e-05,
|
| 341 |
+
"loss": 0.5509,
|
| 342 |
+
"mean_token_accuracy": 0.8328722730278969,
|
| 343 |
+
"num_tokens": 198639349.0,
|
| 344 |
+
"step": 180
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.2629241428317641,
|
| 348 |
+
"grad_norm": 0.3022133339191553,
|
| 349 |
+
"learning_rate": 1.7608198998616533e-05,
|
| 350 |
+
"loss": 0.5573,
|
| 351 |
+
"mean_token_accuracy": 0.8310446247458458,
|
| 352 |
+
"num_tokens": 204194484.0,
|
| 353 |
+
"step": 185
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2700302007461361,
|
| 357 |
+
"grad_norm": 0.3224922846056182,
|
| 358 |
+
"learning_rate": 1.7465732726077993e-05,
|
| 359 |
+
"loss": 0.5535,
|
| 360 |
+
"mean_token_accuracy": 0.8318519063293934,
|
| 361 |
+
"num_tokens": 209683141.0,
|
| 362 |
+
"step": 190
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.27713625866050806,
|
| 366 |
+
"grad_norm": 0.29765302794192444,
|
| 367 |
+
"learning_rate": 1.731983664755264e-05,
|
| 368 |
+
"loss": 0.5569,
|
| 369 |
+
"mean_token_accuracy": 0.8318051770329475,
|
| 370 |
+
"num_tokens": 215203256.0,
|
| 371 |
+
"step": 195
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.2842423165748801,
|
| 375 |
+
"grad_norm": 0.3410703478926894,
|
| 376 |
+
"learning_rate": 1.717058815492548e-05,
|
| 377 |
+
"loss": 0.5569,
|
| 378 |
+
"mean_token_accuracy": 0.8310887739062309,
|
| 379 |
+
"num_tokens": 220715591.0,
|
| 380 |
+
"step": 200
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2842423165748801,
|
| 384 |
+
"eval_loss": 0.5341136455535889,
|
| 385 |
+
"eval_mean_token_accuracy": 0.833399682714228,
|
| 386 |
+
"eval_num_tokens": 220715591.0,
|
| 387 |
+
"eval_runtime": 149.5883,
|
| 388 |
+
"eval_samples_per_second": 24.327,
|
| 389 |
+
"eval_steps_per_second": 0.762,
|
| 390 |
+
"step": 200
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.2913483744892521,
|
| 394 |
+
"grad_norm": 0.2886034985645996,
|
| 395 |
+
"learning_rate": 1.701806641839967e-05,
|
| 396 |
+
"loss": 0.5567,
|
| 397 |
+
"mean_token_accuracy": 0.8324723578989506,
|
| 398 |
+
"num_tokens": 226242581.0,
|
| 399 |
+
"step": 205
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.29845443240362407,
|
| 403 |
+
"grad_norm": 0.28843151859178723,
|
| 404 |
+
"learning_rate": 1.6862352344500004e-05,
|
| 405 |
+
"loss": 0.5558,
|
| 406 |
+
"mean_token_accuracy": 0.8317767918109894,
|
| 407 |
+
"num_tokens": 231752698.0,
|
| 408 |
+
"step": 210
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3055604903179961,
|
| 412 |
+
"grad_norm": 0.2942105037955124,
|
| 413 |
+
"learning_rate": 1.6703528533155283e-05,
|
| 414 |
+
"loss": 0.5512,
|
| 415 |
+
"mean_token_accuracy": 0.8333536356687545,
|
| 416 |
+
"num_tokens": 237265750.0,
|
| 417 |
+
"step": 215
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.3126665482323681,
|
| 421 |
+
"grad_norm": 0.29970782334352336,
|
| 422 |
+
"learning_rate": 1.6541679233882477e-05,
|
| 423 |
+
"loss": 0.5467,
|
| 424 |
+
"mean_token_accuracy": 0.8344343066215515,
|
| 425 |
+
"num_tokens": 242787815.0,
|
| 426 |
+
"step": 220
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.3197726061467401,
|
| 430 |
+
"grad_norm": 0.29759819742183974,
|
| 431 |
+
"learning_rate": 1.63768903010958e-05,
|
| 432 |
+
"loss": 0.55,
|
| 433 |
+
"mean_token_accuracy": 0.8330938413739204,
|
| 434 |
+
"num_tokens": 248325122.0,
|
| 435 |
+
"step": 225
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.3268786640611121,
|
| 439 |
+
"grad_norm": 0.2920108536684172,
|
| 440 |
+
"learning_rate": 1.6209249148564437e-05,
|
| 441 |
+
"loss": 0.5453,
|
| 442 |
+
"mean_token_accuracy": 0.8345815449953079,
|
| 443 |
+
"num_tokens": 253826880.0,
|
| 444 |
+
"step": 230
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3339847219754841,
|
| 448 |
+
"grad_norm": 0.29667699234937334,
|
| 449 |
+
"learning_rate": 1.603884470304318e-05,
|
| 450 |
+
"loss": 0.5578,
|
| 451 |
+
"mean_token_accuracy": 0.8316668353974819,
|
| 452 |
+
"num_tokens": 259356528.0,
|
| 453 |
+
"step": 235
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.3410907798898561,
|
| 457 |
+
"grad_norm": 0.2867819840469066,
|
| 458 |
+
"learning_rate": 1.5865767357100383e-05,
|
| 459 |
+
"loss": 0.5394,
|
| 460 |
+
"mean_token_accuracy": 0.8358893245458603,
|
| 461 |
+
"num_tokens": 264887477.0,
|
| 462 |
+
"step": 240
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.3481968378042281,
|
| 466 |
+
"grad_norm": 0.332209143957244,
|
| 467 |
+
"learning_rate": 1.5690108921168428e-05,
|
| 468 |
+
"loss": 0.5456,
|
| 469 |
+
"mean_token_accuracy": 0.8347376808524132,
|
| 470 |
+
"num_tokens": 270408845.0,
|
| 471 |
+
"step": 245
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.35530289571860013,
|
| 475 |
+
"grad_norm": 0.330011762312303,
|
| 476 |
+
"learning_rate": 1.5511962574842073e-05,
|
| 477 |
+
"loss": 0.5446,
|
| 478 |
+
"mean_token_accuracy": 0.8345297470688819,
|
| 479 |
+
"num_tokens": 275923409.0,
|
| 480 |
+
"step": 250
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.3624089536329721,
|
| 484 |
+
"grad_norm": 0.31031497830420174,
|
| 485 |
+
"learning_rate": 1.5331422817450485e-05,
|
| 486 |
+
"loss": 0.5478,
|
| 487 |
+
"mean_token_accuracy": 0.8336269296705723,
|
| 488 |
+
"num_tokens": 281456923.0,
|
| 489 |
+
"step": 255
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3695150115473441,
|
| 493 |
+
"grad_norm": 0.2918876682786512,
|
| 494 |
+
"learning_rate": 1.5148585417929212e-05,
|
| 495 |
+
"loss": 0.5438,
|
| 496 |
+
"mean_token_accuracy": 0.8351672604680062,
|
| 497 |
+
"num_tokens": 286973486.0,
|
| 498 |
+
"step": 260
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.37662106946171614,
|
| 502 |
+
"grad_norm": 0.3365818739495239,
|
| 503 |
+
"learning_rate": 1.4963547364018711e-05,
|
| 504 |
+
"loss": 0.541,
|
| 505 |
+
"mean_token_accuracy": 0.8354949586093425,
|
| 506 |
+
"num_tokens": 292479427.0,
|
| 507 |
+
"step": 265
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3837271273760881,
|
| 511 |
+
"grad_norm": 0.293893859709652,
|
| 512 |
+
"learning_rate": 1.477640681081632e-05,
|
| 513 |
+
"loss": 0.5436,
|
| 514 |
+
"mean_token_accuracy": 0.8349400483071804,
|
| 515 |
+
"num_tokens": 298006653.0,
|
| 516 |
+
"step": 270
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.39083318529046013,
|
| 520 |
+
"grad_norm": 0.2944189536488024,
|
| 521 |
+
"learning_rate": 1.4587263028709013e-05,
|
| 522 |
+
"loss": 0.5401,
|
| 523 |
+
"mean_token_accuracy": 0.8359036639332771,
|
| 524 |
+
"num_tokens": 303515961.0,
|
| 525 |
+
"step": 275
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.3979392432048321,
|
| 529 |
+
"grad_norm": 0.3027989379324982,
|
| 530 |
+
"learning_rate": 1.4396216350714512e-05,
|
| 531 |
+
"loss": 0.5421,
|
| 532 |
+
"mean_token_accuracy": 0.8354827515780926,
|
| 533 |
+
"num_tokens": 309030348.0,
|
| 534 |
+
"step": 280
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4050453011192041,
|
| 538 |
+
"grad_norm": 0.2978819457639701,
|
| 539 |
+
"learning_rate": 1.4203368119258759e-05,
|
| 540 |
+
"loss": 0.538,
|
| 541 |
+
"mean_token_accuracy": 0.8356474481523037,
|
| 542 |
+
"num_tokens": 314557830.0,
|
| 543 |
+
"step": 285
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.41215135903357614,
|
| 547 |
+
"grad_norm": 0.3149386649352245,
|
| 548 |
+
"learning_rate": 1.4008820632417906e-05,
|
| 549 |
+
"loss": 0.5339,
|
| 550 |
+
"mean_token_accuracy": 0.8371641159057617,
|
| 551 |
+
"num_tokens": 320080082.0,
|
| 552 |
+
"step": 290
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.4192574169479481,
|
| 556 |
+
"grad_norm": 0.3059908505846885,
|
| 557 |
+
"learning_rate": 1.381267708965339e-05,
|
| 558 |
+
"loss": 0.5379,
|
| 559 |
+
"mean_token_accuracy": 0.8365371204912663,
|
| 560 |
+
"num_tokens": 325602548.0,
|
| 561 |
+
"step": 295
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.4263634748623201,
|
| 565 |
+
"grad_norm": 0.3021029670481725,
|
| 566 |
+
"learning_rate": 1.3615041537068831e-05,
|
| 567 |
+
"loss": 0.5462,
|
| 568 |
+
"mean_token_accuracy": 0.8336855717003345,
|
| 569 |
+
"num_tokens": 331139258.0,
|
| 570 |
+
"step": 300
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4263634748623201,
|
| 574 |
+
"eval_loss": 0.5192646980285645,
|
| 575 |
+
"eval_mean_token_accuracy": 0.8369944780542139,
|
| 576 |
+
"eval_num_tokens": 331139258.0,
|
| 577 |
+
"eval_runtime": 150.4327,
|
| 578 |
+
"eval_samples_per_second": 24.19,
|
| 579 |
+
"eval_steps_per_second": 0.758,
|
| 580 |
+
"step": 300
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.43346953277669215,
|
| 584 |
+
"grad_norm": 0.3062091073612256,
|
| 585 |
+
"learning_rate": 1.3416018812217866e-05,
|
| 586 |
+
"loss": 0.5441,
|
| 587 |
+
"mean_token_accuracy": 0.8341693080961704,
|
| 588 |
+
"num_tokens": 336661954.0,
|
| 589 |
+
"step": 305
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.4405755906910641,
|
| 593 |
+
"grad_norm": 0.2877765065298344,
|
| 594 |
+
"learning_rate": 1.3215714488492121e-05,
|
| 595 |
+
"loss": 0.5288,
|
| 596 |
+
"mean_token_accuracy": 0.838797652721405,
|
| 597 |
+
"num_tokens": 342190308.0,
|
| 598 |
+
"step": 310
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.44768164860543613,
|
| 602 |
+
"grad_norm": 0.2986822105588957,
|
| 603 |
+
"learning_rate": 1.3014234819118846e-05,
|
| 604 |
+
"loss": 0.5269,
|
| 605 |
+
"mean_token_accuracy": 0.8390726670622826,
|
| 606 |
+
"num_tokens": 347716991.0,
|
| 607 |
+
"step": 315
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.45478770651980815,
|
| 611 |
+
"grad_norm": 0.28753831464660323,
|
| 612 |
+
"learning_rate": 1.2811686680797942e-05,
|
| 613 |
+
"loss": 0.54,
|
| 614 |
+
"mean_token_accuracy": 0.8348217740654945,
|
| 615 |
+
"num_tokens": 353240462.0,
|
| 616 |
+
"step": 320
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.4618937644341801,
|
| 620 |
+
"grad_norm": 0.3189321553532571,
|
| 621 |
+
"learning_rate": 1.2608177517008268e-05,
|
| 622 |
+
"loss": 0.5316,
|
| 623 |
+
"mean_token_accuracy": 0.8373772338032722,
|
| 624 |
+
"num_tokens": 358757193.0,
|
| 625 |
+
"step": 325
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.46899982234855214,
|
| 629 |
+
"grad_norm": 0.2740676502206635,
|
| 630 |
+
"learning_rate": 1.240381528101327e-05,
|
| 631 |
+
"loss": 0.5245,
|
| 632 |
+
"mean_token_accuracy": 0.8392882093787193,
|
| 633 |
+
"num_tokens": 364274287.0,
|
| 634 |
+
"step": 330
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.47610588026292416,
|
| 638 |
+
"grad_norm": 0.29826705795684294,
|
| 639 |
+
"learning_rate": 1.2198708378596198e-05,
|
| 640 |
+
"loss": 0.5201,
|
| 641 |
+
"mean_token_accuracy": 0.8405162297189236,
|
| 642 |
+
"num_tokens": 369781348.0,
|
| 643 |
+
"step": 335
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.48321193817729613,
|
| 647 |
+
"grad_norm": 0.2810861157555765,
|
| 648 |
+
"learning_rate": 1.19929656105553e-05,
|
| 649 |
+
"loss": 0.5252,
|
| 650 |
+
"mean_token_accuracy": 0.838694840669632,
|
| 651 |
+
"num_tokens": 375291603.0,
|
| 652 |
+
"step": 340
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.49031799609166815,
|
| 656 |
+
"grad_norm": 0.28476568743444564,
|
| 657 |
+
"learning_rate": 1.1786696114989455e-05,
|
| 658 |
+
"loss": 0.5264,
|
| 659 |
+
"mean_token_accuracy": 0.839257051050663,
|
| 660 |
+
"num_tokens": 380805085.0,
|
| 661 |
+
"step": 345
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4974240540060402,
|
| 665 |
+
"grad_norm": 0.2977392563082,
|
| 666 |
+
"learning_rate": 1.1580009309404887e-05,
|
| 667 |
+
"loss": 0.5276,
|
| 668 |
+
"mean_token_accuracy": 0.8389153242111206,
|
| 669 |
+
"num_tokens": 386334037.0,
|
| 670 |
+
"step": 350
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.5045301119204122,
|
| 674 |
+
"grad_norm": 0.3033446749891465,
|
| 675 |
+
"learning_rate": 1.1373014832673661e-05,
|
| 676 |
+
"loss": 0.5298,
|
| 677 |
+
"mean_token_accuracy": 0.8390403784811497,
|
| 678 |
+
"num_tokens": 391841580.0,
|
| 679 |
+
"step": 355
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.5116361698347841,
|
| 683 |
+
"grad_norm": 0.3969220524710466,
|
| 684 |
+
"learning_rate": 1.1165822486874773e-05,
|
| 685 |
+
"loss": 0.5229,
|
| 686 |
+
"mean_token_accuracy": 0.8393726870417595,
|
| 687 |
+
"num_tokens": 397371651.0,
|
| 688 |
+
"step": 360
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5187422277491561,
|
| 692 |
+
"grad_norm": 0.30559826647342453,
|
| 693 |
+
"learning_rate": 1.0958542179048637e-05,
|
| 694 |
+
"loss": 0.5244,
|
| 695 |
+
"mean_token_accuracy": 0.8402129337191582,
|
| 696 |
+
"num_tokens": 402867415.0,
|
| 697 |
+
"step": 365
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.5258482856635281,
|
| 701 |
+
"grad_norm": 0.3494017728215535,
|
| 702 |
+
"learning_rate": 1.0751283862895914e-05,
|
| 703 |
+
"loss": 0.5361,
|
| 704 |
+
"mean_token_accuracy": 0.8366998687386513,
|
| 705 |
+
"num_tokens": 408390957.0,
|
| 706 |
+
"step": 370
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.5329543435779002,
|
| 710 |
+
"grad_norm": 0.353265195510961,
|
| 711 |
+
"learning_rate": 1.0544157480451586e-05,
|
| 712 |
+
"loss": 0.534,
|
| 713 |
+
"mean_token_accuracy": 0.8368604250252247,
|
| 714 |
+
"num_tokens": 413913149.0,
|
| 715 |
+
"step": 375
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.5400604014922722,
|
| 719 |
+
"grad_norm": 0.2611354161191268,
|
| 720 |
+
"learning_rate": 1.033727290376522e-05,
|
| 721 |
+
"loss": 0.5361,
|
| 722 |
+
"mean_token_accuracy": 0.836609935760498,
|
| 723 |
+
"num_tokens": 419431562.0,
|
| 724 |
+
"step": 380
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.5471664594066442,
|
| 728 |
+
"grad_norm": 0.2872728729171679,
|
| 729 |
+
"learning_rate": 1.013073987661834e-05,
|
| 730 |
+
"loss": 0.5338,
|
| 731 |
+
"mean_token_accuracy": 0.8370331548154354,
|
| 732 |
+
"num_tokens": 424955146.0,
|
| 733 |
+
"step": 385
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.5542725173210161,
|
| 737 |
+
"grad_norm": 0.28934761011723314,
|
| 738 |
+
"learning_rate": 9.924667956309862e-06,
|
| 739 |
+
"loss": 0.5251,
|
| 740 |
+
"mean_token_accuracy": 0.8398349188268185,
|
| 741 |
+
"num_tokens": 430476718.0,
|
| 742 |
+
"step": 390
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.5613785752353881,
|
| 746 |
+
"grad_norm": 0.28067537969678,
|
| 747 |
+
"learning_rate": 9.719166455540437e-06,
|
| 748 |
+
"loss": 0.5304,
|
| 749 |
+
"mean_token_accuracy": 0.8381435446441173,
|
| 750 |
+
"num_tokens": 435994507.0,
|
| 751 |
+
"step": 395
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5684846331497602,
|
| 755 |
+
"grad_norm": 0.3568751332581294,
|
| 756 |
+
"learning_rate": 9.51434438442655e-06,
|
| 757 |
+
"loss": 0.5293,
|
| 758 |
+
"mean_token_accuracy": 0.8387467741966248,
|
| 759 |
+
"num_tokens": 441515444.0,
|
| 760 |
+
"step": 400
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.5684846331497602,
|
| 764 |
+
"eval_loss": 0.5093328356742859,
|
| 765 |
+
"eval_mean_token_accuracy": 0.8396573615701575,
|
| 766 |
+
"eval_num_tokens": 441515444.0,
|
| 767 |
+
"eval_runtime": 150.3037,
|
| 768 |
+
"eval_samples_per_second": 24.211,
|
| 769 |
+
"eval_steps_per_second": 0.758,
|
| 770 |
+
"step": 400
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.5755906910641322,
|
| 774 |
+
"grad_norm": 0.2802098035879255,
|
| 775 |
+
"learning_rate": 9.310310392675132e-06,
|
| 776 |
+
"loss": 0.5167,
|
| 777 |
+
"mean_token_accuracy": 0.8414627239108086,
|
| 778 |
+
"num_tokens": 447005744.0,
|
| 779 |
+
"step": 405
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.5826967489785042,
|
| 783 |
+
"grad_norm": 0.2668144948670277,
|
| 784 |
+
"learning_rate": 9.107172711949324e-06,
|
| 785 |
+
"loss": 0.5323,
|
| 786 |
+
"mean_token_accuracy": 0.836710449308157,
|
| 787 |
+
"num_tokens": 452533510.0,
|
| 788 |
+
"step": 410
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.5898028068928762,
|
| 792 |
+
"grad_norm": 0.282320393535823,
|
| 793 |
+
"learning_rate": 8.905039098456049e-06,
|
| 794 |
+
"loss": 0.5237,
|
| 795 |
+
"mean_token_accuracy": 0.8391933210194111,
|
| 796 |
+
"num_tokens": 458057489.0,
|
| 797 |
+
"step": 415
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.5969088648072481,
|
| 801 |
+
"grad_norm": 0.2623104974680133,
|
| 802 |
+
"learning_rate": 8.704016775785742e-06,
|
| 803 |
+
"loss": 0.5282,
|
| 804 |
+
"mean_token_accuracy": 0.8383334554731846,
|
| 805 |
+
"num_tokens": 463589349.0,
|
| 806 |
+
"step": 420
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.6040149227216202,
|
| 810 |
+
"grad_norm": 0.28075733994367397,
|
| 811 |
+
"learning_rate": 8.50421237803464e-06,
|
| 812 |
+
"loss": 0.5226,
|
| 813 |
+
"mean_token_accuracy": 0.8393978834152221,
|
| 814 |
+
"num_tokens": 469104113.0,
|
| 815 |
+
"step": 425
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6111209806359922,
|
| 819 |
+
"grad_norm": 0.28552247132295744,
|
| 820 |
+
"learning_rate": 8.30573189323978e-06,
|
| 821 |
+
"loss": 0.5161,
|
| 822 |
+
"mean_token_accuracy": 0.8426251098513603,
|
| 823 |
+
"num_tokens": 474604196.0,
|
| 824 |
+
"step": 430
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.6182270385503642,
|
| 828 |
+
"grad_norm": 0.2792007208746605,
|
| 829 |
+
"learning_rate": 8.108680607156669e-06,
|
| 830 |
+
"loss": 0.5307,
|
| 831 |
+
"mean_token_accuracy": 0.8380370497703552,
|
| 832 |
+
"num_tokens": 480124231.0,
|
| 833 |
+
"step": 435
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.6253330964647362,
|
| 837 |
+
"grad_norm": 0.2876628277081085,
|
| 838 |
+
"learning_rate": 7.913163047409533e-06,
|
| 839 |
+
"loss": 0.5235,
|
| 840 |
+
"mean_token_accuracy": 0.839199036359787,
|
| 841 |
+
"num_tokens": 485642165.0,
|
| 842 |
+
"step": 440
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.6324391543791081,
|
| 846 |
+
"grad_norm": 0.27864846137064453,
|
| 847 |
+
"learning_rate": 7.719282928043688e-06,
|
| 848 |
+
"loss": 0.5248,
|
| 849 |
+
"mean_token_accuracy": 0.8390684366226197,
|
| 850 |
+
"num_tokens": 491149290.0,
|
| 851 |
+
"step": 445
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.6395452122934802,
|
| 855 |
+
"grad_norm": 0.28373247762189147,
|
| 856 |
+
"learning_rate": 7.527143094509492e-06,
|
| 857 |
+
"loss": 0.5234,
|
| 858 |
+
"mean_token_accuracy": 0.8402359418570995,
|
| 859 |
+
"num_tokens": 496664600.0,
|
| 860 |
+
"step": 450
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.6466512702078522,
|
| 864 |
+
"grad_norm": 0.26738376755844384,
|
| 865 |
+
"learning_rate": 7.336845469107061e-06,
|
| 866 |
+
"loss": 0.5229,
|
| 867 |
+
"mean_token_accuracy": 0.839232936501503,
|
| 868 |
+
"num_tokens": 502162941.0,
|
| 869 |
+
"step": 455
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.6537573281222242,
|
| 873 |
+
"grad_norm": 0.3006774536256795,
|
| 874 |
+
"learning_rate": 7.148490996920661e-06,
|
| 875 |
+
"loss": 0.5253,
|
| 876 |
+
"mean_token_accuracy": 0.8390106722712517,
|
| 877 |
+
"num_tokens": 507685810.0,
|
| 878 |
+
"step": 460
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.6608633860365962,
|
| 882 |
+
"grad_norm": 0.26836022137138205,
|
| 883 |
+
"learning_rate": 6.9621795922714805e-06,
|
| 884 |
+
"loss": 0.5218,
|
| 885 |
+
"mean_token_accuracy": 0.8404779210686684,
|
| 886 |
+
"num_tokens": 513196397.0,
|
| 887 |
+
"step": 465
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.6679694439509682,
|
| 891 |
+
"grad_norm": 0.26829584881370205,
|
| 892 |
+
"learning_rate": 6.778010085717202e-06,
|
| 893 |
+
"loss": 0.5209,
|
| 894 |
+
"mean_token_accuracy": 0.8410870231688022,
|
| 895 |
+
"num_tokens": 518716947.0,
|
| 896 |
+
"step": 470
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.6750755018653402,
|
| 900 |
+
"grad_norm": 0.2707573848559289,
|
| 901 |
+
"learning_rate": 6.596080171626409e-06,
|
| 902 |
+
"loss": 0.5239,
|
| 903 |
+
"mean_token_accuracy": 0.8392590440809726,
|
| 904 |
+
"num_tokens": 524218898.0,
|
| 905 |
+
"step": 475
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.6821815597797122,
|
| 909 |
+
"grad_norm": 0.2739664325900379,
|
| 910 |
+
"learning_rate": 6.416486356355769e-06,
|
| 911 |
+
"loss": 0.5306,
|
| 912 |
+
"mean_token_accuracy": 0.8375619657337665,
|
| 913 |
+
"num_tokens": 529729639.0,
|
| 914 |
+
"step": 480
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.6892876176940842,
|
| 918 |
+
"grad_norm": 0.2868769682396871,
|
| 919 |
+
"learning_rate": 6.239323907057342e-06,
|
| 920 |
+
"loss": 0.5276,
|
| 921 |
+
"mean_token_accuracy": 0.8388026498258114,
|
| 922 |
+
"num_tokens": 535240450.0,
|
| 923 |
+
"step": 485
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.6963936756084562,
|
| 927 |
+
"grad_norm": 0.27945127177338197,
|
| 928 |
+
"learning_rate": 6.064686801143271e-06,
|
| 929 |
+
"loss": 0.5096,
|
| 930 |
+
"mean_token_accuracy": 0.8433919370174408,
|
| 931 |
+
"num_tokens": 540730386.0,
|
| 932 |
+
"step": 490
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.7034997335228282,
|
| 936 |
+
"grad_norm": 0.2797688763148102,
|
| 937 |
+
"learning_rate": 5.892667676434633e-06,
|
| 938 |
+
"loss": 0.5176,
|
| 939 |
+
"mean_token_accuracy": 0.8411184750497341,
|
| 940 |
+
"num_tokens": 546264785.0,
|
| 941 |
+
"step": 495
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.7106057914372003,
|
| 945 |
+
"grad_norm": 0.29234119222810084,
|
| 946 |
+
"learning_rate": 5.723357782020867e-06,
|
| 947 |
+
"loss": 0.5154,
|
| 948 |
+
"mean_token_accuracy": 0.8415673337876797,
|
| 949 |
+
"num_tokens": 551771408.0,
|
| 950 |
+
"step": 500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.7106057914372003,
|
| 954 |
+
"eval_loss": 0.5027303099632263,
|
| 955 |
+
"eval_mean_token_accuracy": 0.8409134248892466,
|
| 956 |
+
"eval_num_tokens": 551771408.0,
|
| 957 |
+
"eval_runtime": 150.6202,
|
| 958 |
+
"eval_samples_per_second": 24.16,
|
| 959 |
+
"eval_steps_per_second": 0.757,
|
| 960 |
+
"step": 500
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.7177118493515722,
|
| 964 |
+
"grad_norm": 0.28402079440718836,
|
| 965 |
+
"learning_rate": 5.556846929855857e-06,
|
| 966 |
+
"loss": 0.5133,
|
| 967 |
+
"mean_token_accuracy": 0.8421028688549995,
|
| 968 |
+
"num_tokens": 557283870.0,
|
| 969 |
+
"step": 505
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7248179072659442,
|
| 973 |
+
"grad_norm": 0.2831441468283664,
|
| 974 |
+
"learning_rate": 5.393223447116409e-06,
|
| 975 |
+
"loss": 0.5278,
|
| 976 |
+
"mean_token_accuracy": 0.8389511182904243,
|
| 977 |
+
"num_tokens": 562803110.0,
|
| 978 |
+
"step": 510
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.7319239651803162,
|
| 982 |
+
"grad_norm": 0.37193795016606795,
|
| 983 |
+
"learning_rate": 5.232574129348278e-06,
|
| 984 |
+
"loss": 0.5168,
|
| 985 |
+
"mean_token_accuracy": 0.8417807504534721,
|
| 986 |
+
"num_tokens": 568320103.0,
|
| 987 |
+
"step": 515
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.7390300230946882,
|
| 991 |
+
"grad_norm": 0.27764965119819857,
|
| 992 |
+
"learning_rate": 5.0749841944247e-06,
|
| 993 |
+
"loss": 0.5274,
|
| 994 |
+
"mean_token_accuracy": 0.8377346590161323,
|
| 995 |
+
"num_tokens": 573851289.0,
|
| 996 |
+
"step": 520
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7461360810090603,
|
| 1000 |
+
"grad_norm": 0.46925453686500695,
|
| 1001 |
+
"learning_rate": 4.92053723734182e-06,
|
| 1002 |
+
"loss": 0.525,
|
| 1003 |
+
"mean_token_accuracy": 0.8391022063791752,
|
| 1004 |
+
"num_tokens": 579354449.0,
|
| 1005 |
+
"step": 525
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.7532421389234323,
|
| 1009 |
+
"grad_norm": 0.28343319532373823,
|
| 1010 |
+
"learning_rate": 4.769315185874951e-06,
|
| 1011 |
+
"loss": 0.5215,
|
| 1012 |
+
"mean_token_accuracy": 0.840414184331894,
|
| 1013 |
+
"num_tokens": 584875200.0,
|
| 1014 |
+
"step": 530
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.7603481968378042,
|
| 1018 |
+
"grad_norm": 0.32287063748249534,
|
| 1019 |
+
"learning_rate": 4.621398257119266e-06,
|
| 1020 |
+
"loss": 0.5198,
|
| 1021 |
+
"mean_token_accuracy": 0.840663468837738,
|
| 1022 |
+
"num_tokens": 590401576.0,
|
| 1023 |
+
"step": 535
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.7674542547521762,
|
| 1027 |
+
"grad_norm": 0.3396523052676484,
|
| 1028 |
+
"learning_rate": 4.476864914937923e-06,
|
| 1029 |
+
"loss": 0.5132,
|
| 1030 |
+
"mean_token_accuracy": 0.8424190938472748,
|
| 1031 |
+
"num_tokens": 595916751.0,
|
| 1032 |
+
"step": 540
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.7745603126665482,
|
| 1036 |
+
"grad_norm": 0.275059324923501,
|
| 1037 |
+
"learning_rate": 4.335791828340183e-06,
|
| 1038 |
+
"loss": 0.5229,
|
| 1039 |
+
"mean_token_accuracy": 0.8403938293457032,
|
| 1040 |
+
"num_tokens": 601460941.0,
|
| 1041 |
+
"step": 545
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.7816663705809203,
|
| 1045 |
+
"grad_norm": 0.26807372924267187,
|
| 1046 |
+
"learning_rate": 4.1982538308116775e-06,
|
| 1047 |
+
"loss": 0.5178,
|
| 1048 |
+
"mean_token_accuracy": 0.8396266974508763,
|
| 1049 |
+
"num_tokens": 606975325.0,
|
| 1050 |
+
"step": 550
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.7887724284952923,
|
| 1054 |
+
"grad_norm": 0.3385442872306829,
|
| 1055 |
+
"learning_rate": 4.064323880618279e-06,
|
| 1056 |
+
"loss": 0.5207,
|
| 1057 |
+
"mean_token_accuracy": 0.8411053366959095,
|
| 1058 |
+
"num_tokens": 612497721.0,
|
| 1059 |
+
"step": 555
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.7958784864096642,
|
| 1063 |
+
"grad_norm": 0.28005130030507386,
|
| 1064 |
+
"learning_rate": 3.934073022104759e-06,
|
| 1065 |
+
"loss": 0.517,
|
| 1066 |
+
"mean_token_accuracy": 0.8412538655102253,
|
| 1067 |
+
"num_tokens": 618029589.0,
|
| 1068 |
+
"step": 560
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.8029845443240362,
|
| 1072 |
+
"grad_norm": 0.29164566017921,
|
| 1073 |
+
"learning_rate": 3.807570348008672e-06,
|
| 1074 |
+
"loss": 0.5173,
|
| 1075 |
+
"mean_token_accuracy": 0.8412310920655728,
|
| 1076 |
+
"num_tokens": 623561843.0,
|
| 1077 |
+
"step": 565
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.8100906022384082,
|
| 1081 |
+
"grad_norm": 0.27485579792509013,
|
| 1082 |
+
"learning_rate": 3.684882962809484e-06,
|
| 1083 |
+
"loss": 0.5247,
|
| 1084 |
+
"mean_token_accuracy": 0.839312057942152,
|
| 1085 |
+
"num_tokens": 629091377.0,
|
| 1086 |
+
"step": 570
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.8171966601527803,
|
| 1090 |
+
"grad_norm": 0.27816784714201154,
|
| 1091 |
+
"learning_rate": 3.5660759471324037e-06,
|
| 1092 |
+
"loss": 0.5226,
|
| 1093 |
+
"mean_token_accuracy": 0.8401588529348374,
|
| 1094 |
+
"num_tokens": 634600764.0,
|
| 1095 |
+
"step": 575
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.8243027180671523,
|
| 1099 |
+
"grad_norm": 0.40137187990535683,
|
| 1100 |
+
"learning_rate": 3.451212323225786e-06,
|
| 1101 |
+
"loss": 0.5136,
|
| 1102 |
+
"mean_token_accuracy": 0.8420207679271698,
|
| 1103 |
+
"num_tokens": 640105985.0,
|
| 1104 |
+
"step": 580
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.8314087759815243,
|
| 1108 |
+
"grad_norm": 0.277470349562551,
|
| 1109 |
+
"learning_rate": 3.340353021530409e-06,
|
| 1110 |
+
"loss": 0.5147,
|
| 1111 |
+
"mean_token_accuracy": 0.8408644467592239,
|
| 1112 |
+
"num_tokens": 645630496.0,
|
| 1113 |
+
"step": 585
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.8385148338958962,
|
| 1117 |
+
"grad_norm": 0.2915696671499121,
|
| 1118 |
+
"learning_rate": 3.2335568483583708e-06,
|
| 1119 |
+
"loss": 0.5102,
|
| 1120 |
+
"mean_token_accuracy": 0.8447316095232964,
|
| 1121 |
+
"num_tokens": 651136302.0,
|
| 1122 |
+
"step": 590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8456208918102682,
|
| 1126 |
+
"grad_norm": 0.31523011648160176,
|
| 1127 |
+
"learning_rate": 3.1308804546987615e-06,
|
| 1128 |
+
"loss": 0.5241,
|
| 1129 |
+
"mean_token_accuracy": 0.8398886010050773,
|
| 1130 |
+
"num_tokens": 656667592.0,
|
| 1131 |
+
"step": 595
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.8527269497246402,
|
| 1135 |
+
"grad_norm": 0.2715441398857633,
|
| 1136 |
+
"learning_rate": 3.0323783061666307e-06,
|
| 1137 |
+
"loss": 0.5154,
|
| 1138 |
+
"mean_token_accuracy": 0.8416090242564678,
|
| 1139 |
+
"num_tokens": 662182702.0,
|
| 1140 |
+
"step": 600
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.8527269497246402,
|
| 1144 |
+
"eval_loss": 0.49905067682266235,
|
| 1145 |
+
"eval_mean_token_accuracy": 0.8420795897642771,
|
| 1146 |
+
"eval_num_tokens": 662182702.0,
|
| 1147 |
+
"eval_runtime": 150.127,
|
| 1148 |
+
"eval_samples_per_second": 24.239,
|
| 1149 |
+
"eval_steps_per_second": 0.759,
|
| 1150 |
+
"step": 600
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.8598330076390123,
|
| 1154 |
+
"grad_norm": 0.4459191186579175,
|
| 1155 |
+
"learning_rate": 2.9381026541112145e-06,
|
| 1156 |
+
"loss": 0.5176,
|
| 1157 |
+
"mean_token_accuracy": 0.8410927847027778,
|
| 1158 |
+
"num_tokens": 667713320.0,
|
| 1159 |
+
"step": 605
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 0.8669390655533843,
|
| 1163 |
+
"grad_norm": 0.2700680983325809,
|
| 1164 |
+
"learning_rate": 2.848103507898745e-06,
|
| 1165 |
+
"loss": 0.5204,
|
| 1166 |
+
"mean_token_accuracy": 0.8398772545158864,
|
| 1167 |
+
"num_tokens": 673241578.0,
|
| 1168 |
+
"step": 610
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.8740451234677563,
|
| 1172 |
+
"grad_norm": 0.3027315294815319,
|
| 1173 |
+
"learning_rate": 2.7624286083845187e-06,
|
| 1174 |
+
"loss": 0.5152,
|
| 1175 |
+
"mean_token_accuracy": 0.8407413326203823,
|
| 1176 |
+
"num_tokens": 678761901.0,
|
| 1177 |
+
"step": 615
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.8811511813821282,
|
| 1181 |
+
"grad_norm": 0.35742788068442477,
|
| 1182 |
+
"learning_rate": 2.6811234025883457e-06,
|
| 1183 |
+
"loss": 0.5104,
|
| 1184 |
+
"mean_token_accuracy": 0.8433315142989158,
|
| 1185 |
+
"num_tokens": 684294891.0,
|
| 1186 |
+
"step": 620
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8882572392965002,
|
| 1190 |
+
"grad_norm": 0.29102667879601235,
|
| 1191 |
+
"learning_rate": 2.604231019586761e-06,
|
| 1192 |
+
"loss": 0.5141,
|
| 1193 |
+
"mean_token_accuracy": 0.8427356474101544,
|
| 1194 |
+
"num_tokens": 689811922.0,
|
| 1195 |
+
"step": 625
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.8953632972108723,
|
| 1199 |
+
"grad_norm": 0.27752275928788533,
|
| 1200 |
+
"learning_rate": 2.5317922476348194e-06,
|
| 1201 |
+
"loss": 0.5165,
|
| 1202 |
+
"mean_token_accuracy": 0.8411040998995304,
|
| 1203 |
+
"num_tokens": 695336104.0,
|
| 1204 |
+
"step": 630
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 0.9024693551252443,
|
| 1208 |
+
"grad_norm": 0.3055065438673597,
|
| 1209 |
+
"learning_rate": 2.4638455125296043e-06,
|
| 1210 |
+
"loss": 0.5184,
|
| 1211 |
+
"mean_token_accuracy": 0.8411155760288238,
|
| 1212 |
+
"num_tokens": 700859085.0,
|
| 1213 |
+
"step": 635
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9095754130396163,
|
| 1217 |
+
"grad_norm": 0.2832455318439677,
|
| 1218 |
+
"learning_rate": 2.400426857226914e-06,
|
| 1219 |
+
"loss": 0.5116,
|
| 1220 |
+
"mean_token_accuracy": 0.8422174222767354,
|
| 1221 |
+
"num_tokens": 706390161.0,
|
| 1222 |
+
"step": 640
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.9166814709539882,
|
| 1226 |
+
"grad_norm": 0.2887928206874307,
|
| 1227 |
+
"learning_rate": 2.3415699227219517e-06,
|
| 1228 |
+
"loss": 0.5234,
|
| 1229 |
+
"mean_token_accuracy": 0.8393123477697373,
|
| 1230 |
+
"num_tokens": 711902275.0,
|
| 1231 |
+
"step": 645
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.9237875288683602,
|
| 1235 |
+
"grad_norm": 0.28711313316509707,
|
| 1236 |
+
"learning_rate": 2.2873059302041627e-06,
|
| 1237 |
+
"loss": 0.514,
|
| 1238 |
+
"mean_token_accuracy": 0.8423109248280525,
|
| 1239 |
+
"num_tokens": 717419225.0,
|
| 1240 |
+
"step": 650
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.9308935867827323,
|
| 1244 |
+
"grad_norm": 0.2736325147914108,
|
| 1245 |
+
"learning_rate": 2.2376636644956656e-06,
|
| 1246 |
+
"loss": 0.5109,
|
| 1247 |
+
"mean_token_accuracy": 0.8425532042980194,
|
| 1248 |
+
"num_tokens": 722935006.0,
|
| 1249 |
+
"step": 655
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.9379996446971043,
|
| 1253 |
+
"grad_norm": 0.30955429096645193,
|
| 1254 |
+
"learning_rate": 2.192669458782096e-06,
|
| 1255 |
+
"loss": 0.5197,
|
| 1256 |
+
"mean_token_accuracy": 0.8405652604997158,
|
| 1257 |
+
"num_tokens": 728439084.0,
|
| 1258 |
+
"step": 660
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.9451057026114763,
|
| 1262 |
+
"grad_norm": 0.265130214896546,
|
| 1263 |
+
"learning_rate": 2.1523471806439205e-06,
|
| 1264 |
+
"loss": 0.5281,
|
| 1265 |
+
"mean_token_accuracy": 0.8385866686701775,
|
| 1266 |
+
"num_tokens": 733969356.0,
|
| 1267 |
+
"step": 665
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 0.9522117605258483,
|
| 1271 |
+
"grad_norm": 0.3128163738373232,
|
| 1272 |
+
"learning_rate": 2.1167182193956738e-06,
|
| 1273 |
+
"loss": 0.5099,
|
| 1274 |
+
"mean_token_accuracy": 0.843552653491497,
|
| 1275 |
+
"num_tokens": 739459750.0,
|
| 1276 |
+
"step": 670
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.9593178184402202,
|
| 1280 |
+
"grad_norm": 0.2766118277915724,
|
| 1281 |
+
"learning_rate": 2.0858014747397952e-06,
|
| 1282 |
+
"loss": 0.5183,
|
| 1283 |
+
"mean_token_accuracy": 0.8413214348256588,
|
| 1284 |
+
"num_tokens": 744974432.0,
|
| 1285 |
+
"step": 675
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.9664238763545923,
|
| 1289 |
+
"grad_norm": 0.2848391339478646,
|
| 1290 |
+
"learning_rate": 2.0596133467411213e-06,
|
| 1291 |
+
"loss": 0.5109,
|
| 1292 |
+
"mean_token_accuracy": 0.8428529247641563,
|
| 1293 |
+
"num_tokens": 750470988.0,
|
| 1294 |
+
"step": 680
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.9735299342689643,
|
| 1298 |
+
"grad_norm": 0.26348775943038943,
|
| 1299 |
+
"learning_rate": 2.0381677271273177e-06,
|
| 1300 |
+
"loss": 0.5149,
|
| 1301 |
+
"mean_token_accuracy": 0.8410044960677624,
|
| 1302 |
+
"num_tokens": 756002818.0,
|
| 1303 |
+
"step": 685
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.9806359921833363,
|
| 1307 |
+
"grad_norm": 0.2695158145512426,
|
| 1308 |
+
"learning_rate": 2.0214759919198904e-06,
|
| 1309 |
+
"loss": 0.5089,
|
| 1310 |
+
"mean_token_accuracy": 0.8422830864787102,
|
| 1311 |
+
"num_tokens": 761498903.0,
|
| 1312 |
+
"step": 690
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.9877420500977083,
|
| 1316 |
+
"grad_norm": 0.2833155672506133,
|
| 1317 |
+
"learning_rate": 2.0095469953996724e-06,
|
| 1318 |
+
"loss": 0.5174,
|
| 1319 |
+
"mean_token_accuracy": 0.8406875729560852,
|
| 1320 |
+
"num_tokens": 767022510.0,
|
| 1321 |
+
"step": 695
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.9948481080120803,
|
| 1325 |
+
"grad_norm": 0.28210706359667653,
|
| 1326 |
+
"learning_rate": 2.002387065409989e-06,
|
| 1327 |
+
"loss": 0.5208,
|
| 1328 |
+
"mean_token_accuracy": 0.8403361722826957,
|
| 1329 |
+
"num_tokens": 772560079.0,
|
| 1330 |
+
"step": 700
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.9948481080120803,
|
| 1334 |
+
"eval_loss": 0.4970676302909851,
|
| 1335 |
+
"eval_mean_token_accuracy": 0.8422517065416303,
|
| 1336 |
+
"eval_num_tokens": 772560079.0,
|
| 1337 |
+
"eval_runtime": 150.3658,
|
| 1338 |
+
"eval_samples_per_second": 24.201,
|
| 1339 |
+
"eval_steps_per_second": 0.758,
|
| 1340 |
+
"step": 700
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.0,
|
| 1344 |
+
"mean_token_accuracy": 0.8405463315289596,
|
| 1345 |
+
"num_tokens": 776561265.0,
|
| 1346 |
+
"step": 704,
|
| 1347 |
+
"total_flos": 6033817814958080.0,
|
| 1348 |
+
"train_loss": 0.6046972061422738,
|
| 1349 |
+
"train_runtime": 27367.7567,
|
| 1350 |
+
"train_samples_per_second": 13.163,
|
| 1351 |
+
"train_steps_per_second": 0.026
|
| 1352 |
+
}
|
| 1353 |
+
],
|
| 1354 |
+
"logging_steps": 5,
|
| 1355 |
+
"max_steps": 704,
|
| 1356 |
+
"num_input_tokens_seen": 0,
|
| 1357 |
+
"num_train_epochs": 1,
|
| 1358 |
+
"save_steps": 1,
|
| 1359 |
+
"stateful_callbacks": {
|
| 1360 |
+
"TrainerControl": {
|
| 1361 |
+
"args": {
|
| 1362 |
+
"should_epoch_stop": false,
|
| 1363 |
+
"should_evaluate": false,
|
| 1364 |
+
"should_log": false,
|
| 1365 |
+
"should_save": true,
|
| 1366 |
+
"should_training_stop": true
|
| 1367 |
+
},
|
| 1368 |
+
"attributes": {}
|
| 1369 |
+
}
|
| 1370 |
+
},
|
| 1371 |
+
"total_flos": 6033817814958080.0,
|
| 1372 |
+
"train_batch_size": 4,
|
| 1373 |
+
"trial_name": null,
|
| 1374 |
+
"trial_params": null
|
| 1375 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96991165b944d5dfac1abbaf5319a838d82645c656f8e09ff3b117be706be012
|
| 3 |
+
size 7416
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|