Model save
Browse files- README.md +109 -0
- added_tokens.json +24 -0
- all_results.json +9 -0
- config.json +30 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer_config.json +196 -0
- train_results.json +9 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: hZzy/qwen2.5-0.5b-sft-news-IFT
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- expo
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: qwen2.5-0.5b-expo-L2EXPO-W0-noES2-0.1
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhiyuzha-university-of-florida/huggingface/runs/t7vhabyt)
|
17 |
+
# qwen2.5-0.5b-expo-L2EXPO-W0-noES2-0.1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [hZzy/qwen2.5-0.5b-sft-news-IFT](https://huggingface.co/hZzy/qwen2.5-0.5b-sft-news-IFT) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 187.9473
|
22 |
+
- Logps: -88.4162
|
23 |
+
- Logits: -1.2945
|
24 |
+
- Objective: 183.8510
|
25 |
+
- Dpo Loss: 0.6799
|
26 |
+
- Regularize: 0.4168
|
27 |
+
- Ranking Simple: 0.5326
|
28 |
+
- Ranking Idealized: 0.6025
|
29 |
+
- Ranking Idealized Expo: 0.5233
|
30 |
+
- Wo Beta: 15.9953
|
31 |
+
|
32 |
+
## Model description
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Intended uses & limitations
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training and evaluation data
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training procedure
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 1e-06
|
50 |
+
- train_batch_size: 4
|
51 |
+
- eval_batch_size: 4
|
52 |
+
- seed: 42
|
53 |
+
- distributed_type: multi-GPU
|
54 |
+
- num_devices: 3
|
55 |
+
- gradient_accumulation_steps: 12
|
56 |
+
- total_train_batch_size: 144
|
57 |
+
- total_eval_batch_size: 12
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: cosine
|
60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
61 |
+
- num_epochs: 5
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Logps | Logits | Objective | Dpo Loss | Regularize | Ranking Simple | Ranking Idealized | Ranking Idealized Expo | Wo Beta |
|
66 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:-------:|:---------:|:--------:|:----------:|:--------------:|:-----------------:|:----------------------:|:-------:|
|
67 |
+
| 181.5404 | 0.1417 | 50 | 182.3598 | -90.9189 | -1.4233 | 180.3279 | 0.6890 | 0.4088 | 0.5264 | 0.6025 | 0.5233 | 16.2974 |
|
68 |
+
| 156.9096 | 0.2834 | 100 | 181.8641 | -91.4510 | -1.4702 | 180.3150 | 0.6855 | 0.4101 | 0.5316 | 0.6025 | 0.5233 | 16.3731 |
|
69 |
+
| 145.838 | 0.4251 | 150 | 180.6479 | -90.7049 | -1.4504 | 178.1705 | 0.6790 | 0.4023 | 0.5383 | 0.6025 | 0.5233 | 16.5880 |
|
70 |
+
| 140.9398 | 0.5668 | 200 | 184.4987 | -90.3330 | -1.3895 | 181.5451 | 0.6803 | 0.4101 | 0.5326 | 0.6025 | 0.5233 | 16.1415 |
|
71 |
+
| 131.1439 | 0.7085 | 250 | 182.2077 | -91.2246 | -1.4789 | 178.4409 | 0.6797 | 0.4059 | 0.5326 | 0.6025 | 0.5233 | 16.3683 |
|
72 |
+
| 118.3192 | 0.8503 | 300 | 183.4459 | -92.5771 | -1.4552 | 180.4714 | 0.6817 | 0.4123 | 0.5326 | 0.6025 | 0.5233 | 16.4041 |
|
73 |
+
| 108.5029 | 0.9920 | 350 | 183.9593 | -92.1804 | -1.4317 | 180.1151 | 0.6782 | 0.4095 | 0.5321 | 0.6025 | 0.5233 | 16.3367 |
|
74 |
+
| 104.6813 | 1.1337 | 400 | 183.8759 | -89.7261 | -1.3930 | 180.2840 | 0.6801 | 0.4094 | 0.5311 | 0.6025 | 0.5233 | 16.2209 |
|
75 |
+
| 90.5585 | 1.2754 | 450 | 184.0673 | -91.2037 | -1.3663 | 180.6296 | 0.6795 | 0.4105 | 0.5357 | 0.6025 | 0.5233 | 16.2889 |
|
76 |
+
| 91.2372 | 1.4171 | 500 | 185.7194 | -89.4298 | -1.3281 | 180.8790 | 0.6782 | 0.4110 | 0.5347 | 0.6025 | 0.5233 | 16.0443 |
|
77 |
+
| 85.7307 | 1.5588 | 550 | 186.2241 | -91.6866 | -1.3683 | 182.1382 | 0.6799 | 0.4147 | 0.5336 | 0.6025 | 0.5233 | 16.1863 |
|
78 |
+
| 79.9458 | 1.7005 | 600 | 186.2137 | -91.0847 | -1.3519 | 181.8686 | 0.6794 | 0.4135 | 0.5373 | 0.6025 | 0.5233 | 16.1060 |
|
79 |
+
| 86.7578 | 1.8422 | 650 | 186.7196 | -89.4070 | -1.3403 | 182.4970 | 0.6797 | 0.4141 | 0.5316 | 0.6025 | 0.5233 | 16.0270 |
|
80 |
+
| 76.2665 | 1.9839 | 700 | 186.2802 | -89.5857 | -1.3223 | 182.3933 | 0.6800 | 0.4136 | 0.5311 | 0.6025 | 0.5233 | 16.1117 |
|
81 |
+
| 65.1575 | 2.1256 | 750 | 188.1571 | -90.2454 | -1.3253 | 184.2076 | 0.6806 | 0.4179 | 0.5321 | 0.6025 | 0.5233 | 15.9179 |
|
82 |
+
| 66.0375 | 2.2674 | 800 | 186.7221 | -88.5874 | -1.3137 | 181.9355 | 0.6781 | 0.4137 | 0.5336 | 0.6025 | 0.5233 | 15.9879 |
|
83 |
+
| 55.6773 | 2.4091 | 850 | 189.5397 | -88.2689 | -1.3112 | 185.2096 | 0.6809 | 0.4203 | 0.5300 | 0.6025 | 0.5233 | 15.9311 |
|
84 |
+
| 54.3682 | 2.5508 | 900 | 188.2381 | -88.3611 | -1.3259 | 184.1678 | 0.6793 | 0.4167 | 0.5311 | 0.6025 | 0.5233 | 15.9680 |
|
85 |
+
| 50.3775 | 2.6925 | 950 | 189.5419 | -88.8005 | -1.3091 | 185.0044 | 0.6802 | 0.4183 | 0.5331 | 0.6025 | 0.5233 | 15.9986 |
|
86 |
+
| 45.9449 | 2.8342 | 1000 | 187.7079 | -87.8148 | -1.2990 | 183.5676 | 0.6792 | 0.4161 | 0.5300 | 0.6025 | 0.5233 | 15.9960 |
|
87 |
+
| 49.0003 | 2.9759 | 1050 | 188.0040 | -88.3004 | -1.2778 | 184.0016 | 0.6792 | 0.4173 | 0.5342 | 0.6025 | 0.5233 | 16.0403 |
|
88 |
+
| 40.2428 | 3.1176 | 1100 | 188.7166 | -88.6470 | -1.2988 | 184.3815 | 0.6801 | 0.4181 | 0.5326 | 0.6025 | 0.5233 | 15.9981 |
|
89 |
+
| 37.177 | 3.2593 | 1150 | 188.2563 | -87.9239 | -1.2843 | 184.3351 | 0.6804 | 0.4183 | 0.5357 | 0.6025 | 0.5233 | 16.0123 |
|
90 |
+
| 34.9809 | 3.4010 | 1200 | 189.1705 | -88.1129 | -1.2900 | 184.8718 | 0.6806 | 0.4193 | 0.5326 | 0.6025 | 0.5233 | 15.9531 |
|
91 |
+
| 34.073 | 3.5427 | 1250 | 188.2203 | -88.5617 | -1.2892 | 184.1966 | 0.6802 | 0.4177 | 0.5336 | 0.6025 | 0.5233 | 16.0022 |
|
92 |
+
| 28.4565 | 3.6845 | 1300 | 188.3189 | -88.0836 | -1.2942 | 184.1293 | 0.6803 | 0.4178 | 0.5331 | 0.6025 | 0.5233 | 16.0081 |
|
93 |
+
| 27.4636 | 3.8262 | 1350 | 188.3022 | -88.4586 | -1.2973 | 184.2191 | 0.6803 | 0.4178 | 0.5321 | 0.6025 | 0.5233 | 15.9996 |
|
94 |
+
| 27.3902 | 3.9679 | 1400 | 187.9691 | -88.3135 | -1.2974 | 183.7816 | 0.6798 | 0.4168 | 0.5321 | 0.6025 | 0.5233 | 15.9788 |
|
95 |
+
| 21.2906 | 4.1096 | 1450 | 187.8985 | -88.1212 | -1.2976 | 183.6546 | 0.6796 | 0.4164 | 0.5321 | 0.6025 | 0.5233 | 15.9853 |
|
96 |
+
| 19.8787 | 4.2513 | 1500 | 188.0825 | -88.3078 | -1.2942 | 183.8684 | 0.6799 | 0.4169 | 0.5321 | 0.6025 | 0.5233 | 15.9839 |
|
97 |
+
| 18.4741 | 4.3930 | 1550 | 188.0407 | -88.4855 | -1.2951 | 184.0446 | 0.6802 | 0.4173 | 0.5326 | 0.6025 | 0.5233 | 15.9950 |
|
98 |
+
| 20.4794 | 4.5347 | 1600 | 187.9061 | -88.4381 | -1.2950 | 183.8276 | 0.6799 | 0.4168 | 0.5331 | 0.6025 | 0.5233 | 16.0004 |
|
99 |
+
| 17.2115 | 4.6764 | 1650 | 187.9504 | -88.4174 | -1.2938 | 183.8566 | 0.6798 | 0.4168 | 0.5326 | 0.6025 | 0.5233 | 15.9942 |
|
100 |
+
| 16.5799 | 4.8181 | 1700 | 187.9360 | -88.4220 | -1.2946 | 183.8405 | 0.6799 | 0.4168 | 0.5326 | 0.6025 | 0.5233 | 15.9963 |
|
101 |
+
| 16.689 | 4.9598 | 1750 | 187.9473 | -88.4162 | -1.2945 | 183.8510 | 0.6799 | 0.4168 | 0.5326 | 0.6025 | 0.5233 | 15.9953 |
|
102 |
+
|
103 |
+
|
104 |
+
### Framework versions
|
105 |
+
|
106 |
+
- Transformers 4.42.0
|
107 |
+
- Pytorch 2.3.0+cu121
|
108 |
+
- Datasets 3.2.0
|
109 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.988190836088805,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 67.88850653388283,
|
5 |
+
"train_runtime": 74214.1269,
|
6 |
+
"train_samples": 50802,
|
7 |
+
"train_samples_per_second": 3.423,
|
8 |
+
"train_steps_per_second": 0.024
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hZzy/qwen2.5-0.5b-sft-news-IFT",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151644,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 896,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4864,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 24,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 14,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"pad_token_id": 151645,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": 32768,
|
23 |
+
"tie_word_embeddings": true,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.42.0",
|
26 |
+
"use_cache": false,
|
27 |
+
"use_mrope": false,
|
28 |
+
"use_sliding_window": false,
|
29 |
+
"vocab_size": 151665
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151644,
|
3 |
+
"eos_token_id": 151645,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"pad_token_id": 151645,
|
6 |
+
"transformers_version": "4.42.0"
|
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 sha256:496d62e8af42ba74cd83db1decaa2a43ab903c57d05316f8d67d90d4cf96fbba
|
3 |
+
size 1975192208
|
special_tokens_map.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|im_start|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
}
|
27 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>"
|
185 |
+
],
|
186 |
+
"bos_token": "<|im_start|>",
|
187 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
188 |
+
"clean_up_tokenization_spaces": false,
|
189 |
+
"eos_token": "<|im_end|>",
|
190 |
+
"errors": "replace",
|
191 |
+
"model_max_length": 2048,
|
192 |
+
"pad_token": "<|im_end|>",
|
193 |
+
"split_special_tokens": false,
|
194 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
195 |
+
"unk_token": null
|
196 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.988190836088805,
|
3 |
+
"total_flos": 0.0,
|
4 |
+
"train_loss": 67.88850653388283,
|
5 |
+
"train_runtime": 74214.1269,
|
6 |
+
"train_samples": 50802,
|
7 |
+
"train_samples_per_second": 3.423,
|
8 |
+
"train_steps_per_second": 0.024
|
9 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9828540f5fb5867f6f4b488ca7015d00075a1d89a889015dd40d4996b667991a
|
3 |
+
size 8120
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|