Hugging Face's logo

mtzig
/
v3_mistral_balance1_lora

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
mtzig commited on
Commit
e3b9cab
·
verified ·
1 Parent(s): b8bed13

Model save

Browse files
Files changed (3) hide show
  1. README.md +111 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: v3_mistral_balance1_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
+ # v3_mistral_balance1_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: 0.0130
24
+ - Accuracy: 0.9980
25
+ - Precision: 0.9818
26
+ - Recall: 0.9474
27
+ - F1: 0.9643
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: 8
48
+ - eval_batch_size: 8
49
+ - seed: 8569382
50
+ - distributed_type: multi-GPU
51
+ - num_devices: 4
52
+ - gradient_accumulation_steps: 2
53
+ - total_train_batch_size: 64
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 | 0.3256 | 0.9369 | 0.1429 | 0.2456 | 0.1806 |
65
+ | 0.4529 | 0.0258 | 20 | 0.2883 | 0.9484 | 0.1493 | 0.1754 | 0.1613 |
66
+ | 0.2483 | 0.0515 | 40 | 0.1461 | 0.9672 | 0.2 | 0.0526 | 0.0833 |
67
+ | 0.1622 | 0.0773 | 60 | 0.1080 | 0.9687 | 0.35 | 0.1228 | 0.1818 |
68
+ | 0.1243 | 0.1031 | 80 | 0.0879 | 0.9697 | 0.4524 | 0.3333 | 0.3838 |
69
+ | 0.0678 | 0.1289 | 100 | 0.0700 | 0.9692 | 0.4719 | 0.7368 | 0.5753 |
70
+ | 0.0301 | 0.1546 | 120 | 0.0474 | 0.9836 | 0.65 | 0.9123 | 0.7591 |
71
+ | 0.0105 | 0.1804 | 140 | 0.0342 | 0.9911 | 0.8421 | 0.8421 | 0.8421 |
72
+ | 0.041 | 0.2062 | 160 | 0.0333 | 0.9926 | 0.875 | 0.8596 | 0.8673 |
73
+ | 0.0291 | 0.2320 | 180 | 0.0268 | 0.9930 | 0.8308 | 0.9474 | 0.8852 |
74
+ | 0.0366 | 0.2577 | 200 | 0.0262 | 0.9916 | 0.7941 | 0.9474 | 0.864 |
75
+ | 0.0133 | 0.2835 | 220 | 0.0206 | 0.9921 | 0.8154 | 0.9298 | 0.8689 |
76
+ | 0.0075 | 0.3093 | 240 | 0.0188 | 0.9955 | 0.9444 | 0.8947 | 0.9189 |
77
+ | 0.0036 | 0.3351 | 260 | 0.0168 | 0.9945 | 0.9107 | 0.8947 | 0.9027 |
78
+ | 0.0081 | 0.3608 | 280 | 0.0182 | 0.9960 | 0.9153 | 0.9474 | 0.9310 |
79
+ | 0.0155 | 0.3866 | 300 | 0.0145 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
80
+ | 0.0075 | 0.4124 | 320 | 0.0165 | 0.9975 | 0.9643 | 0.9474 | 0.9558 |
81
+ | 0.0033 | 0.4381 | 340 | 0.0139 | 0.9975 | 0.9643 | 0.9474 | 0.9558 |
82
+ | 0.01 | 0.4639 | 360 | 0.0136 | 0.9970 | 0.9474 | 0.9474 | 0.9474 |
83
+ | 0.0018 | 0.4897 | 380 | 0.0146 | 0.9970 | 0.9474 | 0.9474 | 0.9474 |
84
+ | 0.0006 | 0.5155 | 400 | 0.0138 | 0.9975 | 0.9815 | 0.9298 | 0.9550 |
85
+ | 0.003 | 0.5412 | 420 | 0.0135 | 0.9965 | 0.9310 | 0.9474 | 0.9391 |
86
+ | 0.0035 | 0.5670 | 440 | 0.0141 | 0.9965 | 0.9808 | 0.8947 | 0.9358 |
87
+ | 0.0024 | 0.5928 | 460 | 0.0148 | 0.9965 | 0.9808 | 0.8947 | 0.9358 |
88
+ | 0.0203 | 0.6186 | 480 | 0.0136 | 0.9970 | 0.9474 | 0.9474 | 0.9474 |
89
+ | 0.0293 | 0.6443 | 500 | 0.0164 | 0.9970 | 0.9811 | 0.9123 | 0.9455 |
90
+ | 0.0078 | 0.6701 | 520 | 0.0149 | 0.9970 | 0.9474 | 0.9474 | 0.9474 |
91
+ | 0.0291 | 0.6959 | 540 | 0.0147 | 0.9975 | 0.9643 | 0.9474 | 0.9558 |
92
+ | 0.0119 | 0.7216 | 560 | 0.0136 | 0.9970 | 0.9474 | 0.9474 | 0.9474 |
93
+ | 0.002 | 0.7474 | 580 | 0.0138 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
94
+ | 0.0009 | 0.7732 | 600 | 0.0140 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
95
+ | 0.0022 | 0.7990 | 620 | 0.0134 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
96
+ | 0.0149 | 0.8247 | 640 | 0.0136 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
97
+ | 0.0397 | 0.8505 | 660 | 0.0140 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
98
+ | 0.0058 | 0.8763 | 680 | 0.0135 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
99
+ | 0.0153 | 0.9021 | 700 | 0.0132 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
100
+ | 0.0122 | 0.9278 | 720 | 0.0132 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
101
+ | 0.0276 | 0.9536 | 740 | 0.0132 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
102
+ | 0.0042 | 0.9794 | 760 | 0.0130 | 0.9980 | 0.9818 | 0.9474 | 0.9643 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - PEFT 0.13.2
108
+ - Transformers 4.46.0
109
+ - Pytorch 2.5.1+cu124
110
+ - Datasets 3.1.0
111
+ - 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:ab31fea01bedcebcf45f2e0dc4aa971341a3aa82a62c7ed554987fcf96657a69
3
+ size 27280152