Hugging Face's logo

mtzig
/
v3c_llama_lora

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
mtzig commited on
Commit
ae49d2f
·
verified ·
1 Parent(s): 1ee29ea

Model save

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mtzig/prm800k_llama_debug_full
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: v3c_llama_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
+ # v3c_llama_lora
20
+
21
+ This model is a fine-tuned version of [mtzig/prm800k_llama_debug_full](https://huggingface.co/mtzig/prm800k_llama_debug_full) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.4195
24
+ - Accuracy: 0.8128
25
+ - Precision: 0.7778
26
+ - Recall: 0.42
27
+ - F1: 0.5455
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: 4
48
+ - eval_batch_size: 4
49
+ - seed: 765837
50
+ - distributed_type: multi-GPU
51
+ - num_devices: 4
52
+ - gradient_accumulation_steps: 4
53
+ - total_train_batch_size: 64
54
+ - total_eval_batch_size: 16
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 | 0.6173 | 0.7487 | 1.0 | 0.06 | 0.1132 |
65
+ | 0.3808 | 0.0492 | 40 | 0.5695 | 0.7487 | 0.8 | 0.08 | 0.1455 |
66
+ | 0.3036 | 0.0984 | 80 | 0.4816 | 0.7647 | 0.6364 | 0.28 | 0.3889 |
67
+ | 0.305 | 0.1476 | 120 | 0.4852 | 0.8021 | 0.7241 | 0.42 | 0.5316 |
68
+ | 0.256 | 0.1967 | 160 | 0.4328 | 0.8021 | 0.7826 | 0.36 | 0.4932 |
69
+ | 0.2062 | 0.2459 | 200 | 0.4699 | 0.7861 | 0.75 | 0.3 | 0.4286 |
70
+ | 0.2004 | 0.2951 | 240 | 0.4480 | 0.7807 | 0.7143 | 0.3 | 0.4225 |
71
+ | 0.2241 | 0.3443 | 280 | 0.4449 | 0.7807 | 0.7143 | 0.3 | 0.4225 |
72
+ | 0.1505 | 0.3935 | 320 | 0.4088 | 0.8182 | 0.75 | 0.48 | 0.5854 |
73
+ | 0.1752 | 0.4427 | 360 | 0.4386 | 0.7861 | 0.75 | 0.3 | 0.4286 |
74
+ | 0.2382 | 0.4919 | 400 | 0.4186 | 0.8128 | 0.7778 | 0.42 | 0.5455 |
75
+ | 0.238 | 0.5410 | 440 | 0.4313 | 0.7914 | 0.7391 | 0.34 | 0.4658 |
76
+ | 0.1448 | 0.5902 | 480 | 0.4161 | 0.8128 | 0.7778 | 0.42 | 0.5455 |
77
+ | 0.2096 | 0.6394 | 520 | 0.4251 | 0.7968 | 0.75 | 0.36 | 0.4865 |
78
+ | 0.204 | 0.6886 | 560 | 0.4413 | 0.7914 | 0.7391 | 0.34 | 0.4658 |
79
+ | 0.1545 | 0.7378 | 600 | 0.4312 | 0.7968 | 0.75 | 0.36 | 0.4865 |
80
+ | 0.1883 | 0.7870 | 640 | 0.4288 | 0.8021 | 0.76 | 0.38 | 0.5067 |
81
+ | 0.2403 | 0.8362 | 680 | 0.4288 | 0.8021 | 0.76 | 0.38 | 0.5067 |
82
+ | 0.1937 | 0.8853 | 720 | 0.4245 | 0.8021 | 0.76 | 0.38 | 0.5067 |
83
+ | 0.164 | 0.9345 | 760 | 0.4182 | 0.8075 | 0.7692 | 0.4 | 0.5263 |
84
+ | 0.2185 | 0.9837 | 800 | 0.4195 | 0.8128 | 0.7778 | 0.42 | 0.5455 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - PEFT 0.13.2
90
+ - Transformers 4.46.3
91
+ - Pytorch 2.5.1+cu124
92
+ - Datasets 3.1.0
93
+ - Tokenizers 0.20.3