Hugging Face's logo

mtzig
/
v4_mistral_lora

PEFT
Safetensors
Generated from Trainer
Model card Files Community
mtzig commited on
Commit
aaedf8c
•
1 Parent(s): 5b084c2

Training in progress, step 100

Browse files
Files changed (8) hide show
  1. README.md +112 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +42 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: peiyi9979/math-shepherd-mistral-7b-prm
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: v4_mistral_lora
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # v4_mistral_lora
20
+
21
+ This model is a fine-tuned version of [peiyi9979/math-shepherd-mistral-7b-prm](https://huggingface.co/peiyi9979/math-shepherd-mistral-7b-prm) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.2886
24
+ - Accuracy: 0.8631
25
+ - Precision: 0.8457
26
+ - Recall: 0.6260
27
+ - F1: 0.7195
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 6
48
+ - eval_batch_size: 8
49
+ - seed: 89234
50
+ - distributed_type: multi-GPU
51
+ - num_devices: 4
52
+ - gradient_accumulation_steps: 3
53
+ - total_train_batch_size: 72
54
+ - total_eval_batch_size: 32
55
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
56
+ - lr_scheduler_type: cosine
57
+ - lr_scheduler_warmup_ratio: 0.1
58
+ - num_epochs: 1
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
63
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
64
+ | No log | 0 | 0 | 0.5995 | 0.7340 | 0.6 | 0.1535 | 0.2445 |
65
+ | 0.7266 | 0.0251 | 20 | 0.5909 | 0.7384 | 0.6232 | 0.1693 | 0.2663 |
66
+ | 0.674 | 0.0502 | 40 | 0.5497 | 0.7517 | 0.6526 | 0.2441 | 0.3553 |
67
+ | 0.5187 | 0.0753 | 60 | 0.4896 | 0.7759 | 0.6409 | 0.4567 | 0.5333 |
68
+ | 0.4811 | 0.1004 | 80 | 0.4410 | 0.7958 | 0.7066 | 0.4646 | 0.5606 |
69
+ | 0.2811 | 0.1255 | 100 | 0.4249 | 0.8102 | 0.7595 | 0.4724 | 0.5825 |
70
+ | 0.2959 | 0.1506 | 120 | 0.3751 | 0.8212 | 0.7674 | 0.5197 | 0.6197 |
71
+ | 0.336 | 0.1757 | 140 | 0.3764 | 0.8278 | 0.8451 | 0.4724 | 0.6061 |
72
+ | 0.3239 | 0.2008 | 160 | 0.3608 | 0.8201 | 0.8421 | 0.4409 | 0.5788 |
73
+ | 0.2767 | 0.2259 | 180 | 0.3362 | 0.8543 | 0.8112 | 0.6260 | 0.7067 |
74
+ | 0.276 | 0.2510 | 200 | 0.3406 | 0.8389 | 0.8462 | 0.5197 | 0.6439 |
75
+ | 0.2715 | 0.2762 | 220 | 0.3223 | 0.8411 | 0.8274 | 0.5472 | 0.6588 |
76
+ | 0.2737 | 0.3013 | 240 | 0.3202 | 0.8521 | 0.8125 | 0.6142 | 0.6996 |
77
+ | 0.3245 | 0.3264 | 260 | 0.3098 | 0.8466 | 0.8249 | 0.5748 | 0.6775 |
78
+ | 0.2868 | 0.3515 | 280 | 0.3159 | 0.8433 | 0.7887 | 0.6024 | 0.6830 |
79
+ | 0.2601 | 0.3766 | 300 | 0.3105 | 0.8587 | 0.7669 | 0.7126 | 0.7388 |
80
+ | 0.2597 | 0.4017 | 320 | 0.3162 | 0.8510 | 0.8362 | 0.5827 | 0.6868 |
81
+ | 0.287 | 0.4268 | 340 | 0.2997 | 0.8532 | 0.8071 | 0.6260 | 0.7051 |
82
+ | 0.3115 | 0.4519 | 360 | 0.3028 | 0.8543 | 0.8315 | 0.6024 | 0.6986 |
83
+ | 0.2654 | 0.4770 | 380 | 0.3008 | 0.8543 | 0.8245 | 0.6102 | 0.7014 |
84
+ | 0.2443 | 0.5021 | 400 | 0.2955 | 0.8565 | 0.8039 | 0.6457 | 0.7162 |
85
+ | 0.2743 | 0.5272 | 420 | 0.3011 | 0.8543 | 0.8389 | 0.5945 | 0.6959 |
86
+ | 0.2248 | 0.5523 | 440 | 0.3031 | 0.8532 | 0.8380 | 0.5906 | 0.6928 |
87
+ | 0.2149 | 0.5774 | 460 | 0.2868 | 0.8609 | 0.7991 | 0.6732 | 0.7308 |
88
+ | 0.1998 | 0.6025 | 480 | 0.2975 | 0.8587 | 0.8316 | 0.6220 | 0.7117 |
89
+ | 0.2459 | 0.6276 | 500 | 0.2978 | 0.8510 | 0.8324 | 0.5866 | 0.6882 |
90
+ | 0.1953 | 0.6527 | 520 | 0.2989 | 0.8576 | 0.8492 | 0.5984 | 0.7021 |
91
+ | 0.3153 | 0.6778 | 540 | 0.2864 | 0.8642 | 0.8359 | 0.6417 | 0.7261 |
92
+ | 0.2172 | 0.7029 | 560 | 0.3190 | 0.8444 | 0.8844 | 0.5118 | 0.6484 |
93
+ | 0.2604 | 0.7280 | 580 | 0.2830 | 0.8687 | 0.8358 | 0.6614 | 0.7385 |
94
+ | 0.2671 | 0.7531 | 600 | 0.2970 | 0.8565 | 0.8523 | 0.5906 | 0.6977 |
95
+ | 0.2049 | 0.7782 | 620 | 0.2862 | 0.8587 | 0.8316 | 0.6220 | 0.7117 |
96
+ | 0.2972 | 0.8033 | 640 | 0.2890 | 0.8609 | 0.8404 | 0.6220 | 0.7149 |
97
+ | 0.1953 | 0.8285 | 660 | 0.2911 | 0.8609 | 0.8441 | 0.6181 | 0.7136 |
98
+ | 0.24 | 0.8536 | 680 | 0.2824 | 0.8653 | 0.8367 | 0.6457 | 0.7289 |
99
+ | 0.282 | 0.8787 | 700 | 0.2860 | 0.8631 | 0.8385 | 0.6339 | 0.7220 |
100
+ | 0.1931 | 0.9038 | 720 | 0.2885 | 0.8620 | 0.8413 | 0.6260 | 0.7178 |
101
+ | 0.2251 | 0.9289 | 740 | 0.2898 | 0.8631 | 0.8457 | 0.6260 | 0.7195 |
102
+ | 0.178 | 0.9540 | 760 | 0.2889 | 0.8631 | 0.8457 | 0.6260 | 0.7195 |
103
+ | 0.2431 | 0.9791 | 780 | 0.2886 | 0.8631 | 0.8457 | 0.6260 | 0.7195 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - PEFT 0.13.2
109
+ - Transformers 4.46.0
110
+ - Pytorch 2.5.1+cu124
111
+ - Datasets 3.1.0
112
+ - Tokenizers 0.20.3
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "peiyi9979/math-shepherd-mistral-7b-prm",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9095ed4f6e46c6233a4e1d1fc457901c76c944734d350942d684fa38cf547bbc
3
+ size 27280152
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6fe80a9dcc4519c6fb861ba85e4443ee8b09e06ef6322583626b2932d2e9e34
3
+ size 5240