Hugging Face's logo

chchen
/
MentaLLaMA-chat-7B-PsyCourse-fold2

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
056b1ed
·
verified ·
1 Parent(s): ec215e2

Model save

Browse files
Files changed (2) hide show
  1. README.md +126 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: klyang/MentaLLaMA-chat-7B-hf
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: MentaLLaMA-chat-7B-PsyCourse-fold2
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
+ # MentaLLaMA-chat-7B-PsyCourse-fold2
17
+
18
+ This model is a fine-tuned version of [klyang/MentaLLaMA-chat-7B-hf](https://huggingface.co/klyang/MentaLLaMA-chat-7B-hf) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0407
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 16
44
+ - total_train_batch_size: 16
45
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 5.0
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.7519 | 0.0775 | 50 | 0.6389 |
55
+ | 0.1485 | 0.1550 | 100 | 0.1124 |
56
+ | 0.074 | 0.2326 | 150 | 0.0650 |
57
+ | 0.0655 | 0.3101 | 200 | 0.0619 |
58
+ | 0.0598 | 0.3876 | 250 | 0.0512 |
59
+ | 0.0414 | 0.4651 | 300 | 0.0449 |
60
+ | 0.0427 | 0.5426 | 350 | 0.0414 |
61
+ | 0.0471 | 0.6202 | 400 | 0.0387 |
62
+ | 0.0433 | 0.6977 | 450 | 0.0362 |
63
+ | 0.0432 | 0.7752 | 500 | 0.0353 |
64
+ | 0.0445 | 0.8527 | 550 | 0.0353 |
65
+ | 0.0529 | 0.9302 | 600 | 0.0353 |
66
+ | 0.0313 | 1.0078 | 650 | 0.0318 |
67
+ | 0.0301 | 1.0853 | 700 | 0.0322 |
68
+ | 0.0289 | 1.1628 | 750 | 0.0338 |
69
+ | 0.0267 | 1.2403 | 800 | 0.0314 |
70
+ | 0.0314 | 1.3178 | 850 | 0.0317 |
71
+ | 0.0382 | 1.3953 | 900 | 0.0327 |
72
+ | 0.0354 | 1.4729 | 950 | 0.0320 |
73
+ | 0.0265 | 1.5504 | 1000 | 0.0321 |
74
+ | 0.0301 | 1.6279 | 1050 | 0.0333 |
75
+ | 0.0262 | 1.7054 | 1100 | 0.0312 |
76
+ | 0.0273 | 1.7829 | 1150 | 0.0306 |
77
+ | 0.0283 | 1.8605 | 1200 | 0.0297 |
78
+ | 0.0381 | 1.9380 | 1250 | 0.0299 |
79
+ | 0.0207 | 2.0155 | 1300 | 0.0294 |
80
+ | 0.0163 | 2.0930 | 1350 | 0.0329 |
81
+ | 0.0236 | 2.1705 | 1400 | 0.0311 |
82
+ | 0.0191 | 2.2481 | 1450 | 0.0310 |
83
+ | 0.0243 | 2.3256 | 1500 | 0.0308 |
84
+ | 0.0165 | 2.4031 | 1550 | 0.0327 |
85
+ | 0.0224 | 2.4806 | 1600 | 0.0329 |
86
+ | 0.0289 | 2.5581 | 1650 | 0.0319 |
87
+ | 0.014 | 2.6357 | 1700 | 0.0316 |
88
+ | 0.0182 | 2.7132 | 1750 | 0.0334 |
89
+ | 0.0175 | 2.7907 | 1800 | 0.0298 |
90
+ | 0.0218 | 2.8682 | 1850 | 0.0297 |
91
+ | 0.018 | 2.9457 | 1900 | 0.0289 |
92
+ | 0.01 | 3.0233 | 1950 | 0.0309 |
93
+ | 0.0109 | 3.1008 | 2000 | 0.0338 |
94
+ | 0.0076 | 3.1783 | 2050 | 0.0347 |
95
+ | 0.0087 | 3.2558 | 2100 | 0.0358 |
96
+ | 0.0092 | 3.3333 | 2150 | 0.0323 |
97
+ | 0.0078 | 3.4109 | 2200 | 0.0331 |
98
+ | 0.0109 | 3.4884 | 2250 | 0.0356 |
99
+ | 0.0137 | 3.5659 | 2300 | 0.0360 |
100
+ | 0.013 | 3.6434 | 2350 | 0.0350 |
101
+ | 0.0133 | 3.7209 | 2400 | 0.0353 |
102
+ | 0.0068 | 3.7984 | 2450 | 0.0357 |
103
+ | 0.012 | 3.8760 | 2500 | 0.0348 |
104
+ | 0.0088 | 3.9535 | 2550 | 0.0344 |
105
+ | 0.0066 | 4.0310 | 2600 | 0.0346 |
106
+ | 0.0052 | 4.1085 | 2650 | 0.0361 |
107
+ | 0.008 | 4.1860 | 2700 | 0.0374 |
108
+ | 0.0062 | 4.2636 | 2750 | 0.0383 |
109
+ | 0.005 | 4.3411 | 2800 | 0.0386 |
110
+ | 0.004 | 4.4186 | 2850 | 0.0395 |
111
+ | 0.0075 | 4.4961 | 2900 | 0.0400 |
112
+ | 0.003 | 4.5736 | 2950 | 0.0402 |
113
+ | 0.0066 | 4.6512 | 3000 | 0.0405 |
114
+ | 0.005 | 4.7287 | 3050 | 0.0406 |
115
+ | 0.0067 | 4.8062 | 3100 | 0.0407 |
116
+ | 0.0067 | 4.8837 | 3150 | 0.0407 |
117
+ | 0.006 | 4.9612 | 3200 | 0.0407 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - PEFT 0.12.0
123
+ - Transformers 4.46.1
124
+ - Pytorch 2.5.1+cu124
125
+ - Datasets 3.1.0
126
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d324917c2a79b3bb15e438d5bed774273b33b065135e3a80e20d2fc3045781ee
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5a7fb5eedc53d9f81a6d53a28a2b925d78a629fc9a21e3716881fb885e8697
3
  size 80013120