Hugging Face's logo

chchen
/
MentaLLaMA-chat-7B-PsyCourse-fold10

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
aeb7d8a
·
verified ·
1 Parent(s): caedb62

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-fold10
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-fold10
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: 0.0396
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
+ | 0.8796 | 0.0770 | 50 | 0.6149 |
55
+ | 0.1225 | 0.1539 | 100 | 0.1079 |
56
+ | 0.0896 | 0.2309 | 150 | 0.0615 |
57
+ | 0.0656 | 0.3078 | 200 | 0.0519 |
58
+ | 0.0599 | 0.3848 | 250 | 0.0487 |
59
+ | 0.0559 | 0.4618 | 300 | 0.0453 |
60
+ | 0.047 | 0.5387 | 350 | 0.0427 |
61
+ | 0.0386 | 0.6157 | 400 | 0.0398 |
62
+ | 0.0402 | 0.6926 | 450 | 0.0429 |
63
+ | 0.0525 | 0.7696 | 500 | 0.0384 |
64
+ | 0.0374 | 0.8466 | 550 | 0.0381 |
65
+ | 0.0479 | 0.9235 | 600 | 0.0336 |
66
+ | 0.0464 | 1.0005 | 650 | 0.0337 |
67
+ | 0.0291 | 1.0774 | 700 | 0.0351 |
68
+ | 0.0266 | 1.1544 | 750 | 0.0336 |
69
+ | 0.0268 | 1.2314 | 800 | 0.0323 |
70
+ | 0.0257 | 1.3083 | 850 | 0.0325 |
71
+ | 0.0311 | 1.3853 | 900 | 0.0323 |
72
+ | 0.0345 | 1.4622 | 950 | 0.0317 |
73
+ | 0.0287 | 1.5392 | 1000 | 0.0345 |
74
+ | 0.0333 | 1.6162 | 1050 | 0.0313 |
75
+ | 0.0278 | 1.6931 | 1100 | 0.0314 |
76
+ | 0.0239 | 1.7701 | 1150 | 0.0306 |
77
+ | 0.0346 | 1.8470 | 1200 | 0.0312 |
78
+ | 0.0289 | 1.9240 | 1250 | 0.0301 |
79
+ | 0.0308 | 2.0010 | 1300 | 0.0319 |
80
+ | 0.0176 | 2.0779 | 1350 | 0.0314 |
81
+ | 0.0192 | 2.1549 | 1400 | 0.0312 |
82
+ | 0.0157 | 2.2318 | 1450 | 0.0315 |
83
+ | 0.0227 | 2.3088 | 1500 | 0.0301 |
84
+ | 0.0211 | 2.3858 | 1550 | 0.0305 |
85
+ | 0.0192 | 2.4627 | 1600 | 0.0327 |
86
+ | 0.0215 | 2.5397 | 1650 | 0.0311 |
87
+ | 0.0235 | 2.6166 | 1700 | 0.0297 |
88
+ | 0.0149 | 2.6936 | 1750 | 0.0312 |
89
+ | 0.0206 | 2.7706 | 1800 | 0.0299 |
90
+ | 0.0154 | 2.8475 | 1850 | 0.0318 |
91
+ | 0.0188 | 2.9245 | 1900 | 0.0301 |
92
+ | 0.0198 | 3.0014 | 1950 | 0.0300 |
93
+ | 0.0117 | 3.0784 | 2000 | 0.0322 |
94
+ | 0.0103 | 3.1554 | 2050 | 0.0334 |
95
+ | 0.0158 | 3.2323 | 2100 | 0.0343 |
96
+ | 0.0116 | 3.3093 | 2150 | 0.0330 |
97
+ | 0.0117 | 3.3862 | 2200 | 0.0342 |
98
+ | 0.01 | 3.4632 | 2250 | 0.0345 |
99
+ | 0.0113 | 3.5402 | 2300 | 0.0345 |
100
+ | 0.0111 | 3.6171 | 2350 | 0.0342 |
101
+ | 0.0105 | 3.6941 | 2400 | 0.0351 |
102
+ | 0.0094 | 3.7710 | 2450 | 0.0365 |
103
+ | 0.0144 | 3.8480 | 2500 | 0.0337 |
104
+ | 0.0071 | 3.9250 | 2550 | 0.0341 |
105
+ | 0.0081 | 4.0019 | 2600 | 0.0339 |
106
+ | 0.0051 | 4.0789 | 2650 | 0.0355 |
107
+ | 0.0081 | 4.1558 | 2700 | 0.0364 |
108
+ | 0.0068 | 4.2328 | 2750 | 0.0382 |
109
+ | 0.0055 | 4.3098 | 2800 | 0.0389 |
110
+ | 0.0045 | 4.3867 | 2850 | 0.0386 |
111
+ | 0.0033 | 4.4637 | 2900 | 0.0386 |
112
+ | 0.0031 | 4.5406 | 2950 | 0.0391 |
113
+ | 0.0055 | 4.6176 | 3000 | 0.0393 |
114
+ | 0.0081 | 4.6946 | 3050 | 0.0395 |
115
+ | 0.0034 | 4.7715 | 3100 | 0.0396 |
116
+ | 0.0073 | 4.8485 | 3150 | 0.0396 |
117
+ | 0.0043 | 4.9254 | 3200 | 0.0396 |
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:de8c778864033b3ad09791b585c8bcbebf692269ddafaa46d8a6ae77b22d1a57
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d56e2667b922d7578b15df76f52f69e2c51cb230f6dae66e5f144ff6e698e90
3
  size 80013120