Hugging Face's logo

chchen
/
MentaLLaMA-chat-7B-PsyCourse-fold8

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
15973dd
·
verified ·
1 Parent(s): 3338017

Model save

Browse files
Files changed (2) hide show
  1. README.md +127 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold8
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-fold8
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: 0.0443
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
+ | 0.8816 | 0.0758 | 50 | 0.6521 |
55
+ | 0.1876 | 0.1516 | 100 | 0.1201 |
56
+ | 0.0847 | 0.2275 | 150 | 0.0709 |
57
+ | 0.0547 | 0.3033 | 200 | 0.0595 |
58
+ | 0.05 | 0.3791 | 250 | 0.0510 |
59
+ | 0.0566 | 0.4549 | 300 | 0.0494 |
60
+ | 0.057 | 0.5308 | 350 | 0.0461 |
61
+ | 0.0323 | 0.6066 | 400 | 0.0422 |
62
+ | 0.0331 | 0.6824 | 450 | 0.0393 |
63
+ | 0.0339 | 0.7582 | 500 | 0.0405 |
64
+ | 0.0432 | 0.8340 | 550 | 0.0383 |
65
+ | 0.0332 | 0.9099 | 600 | 0.0361 |
66
+ | 0.0458 | 0.9857 | 650 | 0.0381 |
67
+ | 0.0281 | 1.0615 | 700 | 0.0368 |
68
+ | 0.0222 | 1.1373 | 750 | 0.0382 |
69
+ | 0.0272 | 1.2132 | 800 | 0.0346 |
70
+ | 0.0303 | 1.2890 | 850 | 0.0352 |
71
+ | 0.0318 | 1.3648 | 900 | 0.0358 |
72
+ | 0.0233 | 1.4406 | 950 | 0.0353 |
73
+ | 0.0263 | 1.5164 | 1000 | 0.0349 |
74
+ | 0.0381 | 1.5923 | 1050 | 0.0354 |
75
+ | 0.0267 | 1.6681 | 1100 | 0.0319 |
76
+ | 0.0335 | 1.7439 | 1150 | 0.0320 |
77
+ | 0.0228 | 1.8197 | 1200 | 0.0320 |
78
+ | 0.0311 | 1.8956 | 1250 | 0.0313 |
79
+ | 0.0228 | 1.9714 | 1300 | 0.0314 |
80
+ | 0.0157 | 2.0472 | 1350 | 0.0321 |
81
+ | 0.0129 | 2.1230 | 1400 | 0.0316 |
82
+ | 0.0208 | 2.1988 | 1450 | 0.0330 |
83
+ | 0.0191 | 2.2747 | 1500 | 0.0325 |
84
+ | 0.0189 | 2.3505 | 1550 | 0.0325 |
85
+ | 0.0161 | 2.4263 | 1600 | 0.0325 |
86
+ | 0.0164 | 2.5021 | 1650 | 0.0356 |
87
+ | 0.0144 | 2.5780 | 1700 | 0.0338 |
88
+ | 0.0211 | 2.6538 | 1750 | 0.0328 |
89
+ | 0.0195 | 2.7296 | 1800 | 0.0322 |
90
+ | 0.0148 | 2.8054 | 1850 | 0.0338 |
91
+ | 0.0249 | 2.8812 | 1900 | 0.0327 |
92
+ | 0.0152 | 2.9571 | 1950 | 0.0320 |
93
+ | 0.0136 | 3.0329 | 2000 | 0.0329 |
94
+ | 0.009 | 3.1087 | 2050 | 0.0341 |
95
+ | 0.0089 | 3.1845 | 2100 | 0.0367 |
96
+ | 0.0127 | 3.2604 | 2150 | 0.0364 |
97
+ | 0.0119 | 3.3362 | 2200 | 0.0358 |
98
+ | 0.0118 | 3.4120 | 2250 | 0.0358 |
99
+ | 0.0084 | 3.4878 | 2300 | 0.0371 |
100
+ | 0.0137 | 3.5636 | 2350 | 0.0365 |
101
+ | 0.0093 | 3.6395 | 2400 | 0.0364 |
102
+ | 0.0095 | 3.7153 | 2450 | 0.0359 |
103
+ | 0.0102 | 3.7911 | 2500 | 0.0381 |
104
+ | 0.0137 | 3.8669 | 2550 | 0.0384 |
105
+ | 0.01 | 3.9428 | 2600 | 0.0376 |
106
+ | 0.0058 | 4.0186 | 2650 | 0.0389 |
107
+ | 0.0071 | 4.0944 | 2700 | 0.0407 |
108
+ | 0.0051 | 4.1702 | 2750 | 0.0414 |
109
+ | 0.0077 | 4.2460 | 2800 | 0.0419 |
110
+ | 0.0039 | 4.3219 | 2850 | 0.0424 |
111
+ | 0.002 | 4.3977 | 2900 | 0.0429 |
112
+ | 0.0036 | 4.4735 | 2950 | 0.0433 |
113
+ | 0.0083 | 4.5493 | 3000 | 0.0439 |
114
+ | 0.0049 | 4.6252 | 3050 | 0.0439 |
115
+ | 0.0033 | 4.7010 | 3100 | 0.0443 |
116
+ | 0.0034 | 4.7768 | 3150 | 0.0443 |
117
+ | 0.0038 | 4.8526 | 3200 | 0.0442 |
118
+ | 0.0029 | 4.9284 | 3250 | 0.0443 |
119
+
120
+
121
+ ### Framework versions
122
+
123
+ - PEFT 0.12.0
124
+ - Transformers 4.46.1
125
+ - Pytorch 2.5.1+cu124
126
+ - Datasets 3.1.0
127
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd095430e52e9f6b9623b83512b7685378cc280c908ab042840b9fc948dcef85
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b2abf54e78336331fb0979a7a4f74f46f511a37cdcecae56727f044fa56721
3
  size 80013120