Hugging Face's logo

chchen
/
MentaLLaMA-chat-7B-PsyCourse-fold5

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
ef7bff1
·
verified ·
1 Parent(s): dc4fb68

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-fold5
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-fold5
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: 0.0391
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
+ | 0.8836 | 0.0758 | 50 | 0.6510 |
55
+ | 0.1276 | 0.1517 | 100 | 0.1150 |
56
+ | 0.0848 | 0.2275 | 150 | 0.0731 |
57
+ | 0.0545 | 0.3033 | 200 | 0.0569 |
58
+ | 0.0542 | 0.3791 | 250 | 0.0499 |
59
+ | 0.0466 | 0.4550 | 300 | 0.0510 |
60
+ | 0.0517 | 0.5308 | 350 | 0.0468 |
61
+ | 0.058 | 0.6066 | 400 | 0.0456 |
62
+ | 0.0521 | 0.6825 | 450 | 0.0405 |
63
+ | 0.0317 | 0.7583 | 500 | 0.0382 |
64
+ | 0.0281 | 0.8341 | 550 | 0.0390 |
65
+ | 0.0388 | 0.9100 | 600 | 0.0388 |
66
+ | 0.0459 | 0.9858 | 650 | 0.0355 |
67
+ | 0.0277 | 1.0616 | 700 | 0.0368 |
68
+ | 0.0342 | 1.1374 | 750 | 0.0369 |
69
+ | 0.0323 | 1.2133 | 800 | 0.0337 |
70
+ | 0.0257 | 1.2891 | 850 | 0.0351 |
71
+ | 0.0218 | 1.3649 | 900 | 0.0346 |
72
+ | 0.0266 | 1.4408 | 950 | 0.0377 |
73
+ | 0.0344 | 1.5166 | 1000 | 0.0322 |
74
+ | 0.0244 | 1.5924 | 1050 | 0.0315 |
75
+ | 0.0227 | 1.6682 | 1100 | 0.0332 |
76
+ | 0.0243 | 1.7441 | 1150 | 0.0318 |
77
+ | 0.03 | 1.8199 | 1200 | 0.0311 |
78
+ | 0.0307 | 1.8957 | 1250 | 0.0295 |
79
+ | 0.0344 | 1.9716 | 1300 | 0.0305 |
80
+ | 0.0214 | 2.0474 | 1350 | 0.0307 |
81
+ | 0.0178 | 2.1232 | 1400 | 0.0320 |
82
+ | 0.0167 | 2.1991 | 1450 | 0.0321 |
83
+ | 0.0115 | 2.2749 | 1500 | 0.0325 |
84
+ | 0.0192 | 2.3507 | 1550 | 0.0318 |
85
+ | 0.0233 | 2.4265 | 1600 | 0.0327 |
86
+ | 0.0108 | 2.5024 | 1650 | 0.0340 |
87
+ | 0.0256 | 2.5782 | 1700 | 0.0315 |
88
+ | 0.019 | 2.6540 | 1750 | 0.0300 |
89
+ | 0.0205 | 2.7299 | 1800 | 0.0302 |
90
+ | 0.0197 | 2.8057 | 1850 | 0.0307 |
91
+ | 0.0161 | 2.8815 | 1900 | 0.0303 |
92
+ | 0.0235 | 2.9573 | 1950 | 0.0302 |
93
+ | 0.01 | 3.0332 | 2000 | 0.0301 |
94
+ | 0.0073 | 3.1090 | 2050 | 0.0325 |
95
+ | 0.0099 | 3.1848 | 2100 | 0.0337 |
96
+ | 0.0085 | 3.2607 | 2150 | 0.0337 |
97
+ | 0.0076 | 3.3365 | 2200 | 0.0354 |
98
+ | 0.0077 | 3.4123 | 2250 | 0.0341 |
99
+ | 0.0107 | 3.4882 | 2300 | 0.0338 |
100
+ | 0.006 | 3.5640 | 2350 | 0.0338 |
101
+ | 0.0127 | 3.6398 | 2400 | 0.0336 |
102
+ | 0.0099 | 3.7156 | 2450 | 0.0338 |
103
+ | 0.014 | 3.7915 | 2500 | 0.0337 |
104
+ | 0.0129 | 3.8673 | 2550 | 0.0339 |
105
+ | 0.0118 | 3.9431 | 2600 | 0.0350 |
106
+ | 0.0073 | 4.0190 | 2650 | 0.0346 |
107
+ | 0.0048 | 4.0948 | 2700 | 0.0357 |
108
+ | 0.0059 | 4.1706 | 2750 | 0.0373 |
109
+ | 0.0053 | 4.2464 | 2800 | 0.0373 |
110
+ | 0.0045 | 4.3223 | 2850 | 0.0381 |
111
+ | 0.0054 | 4.3981 | 2900 | 0.0388 |
112
+ | 0.0085 | 4.4739 | 2950 | 0.0385 |
113
+ | 0.0066 | 4.5498 | 3000 | 0.0384 |
114
+ | 0.0051 | 4.6256 | 3050 | 0.0386 |
115
+ | 0.0052 | 4.7014 | 3100 | 0.0388 |
116
+ | 0.0065 | 4.7773 | 3150 | 0.0389 |
117
+ | 0.0036 | 4.8531 | 3200 | 0.0391 |
118
+ | 0.0039 | 4.9289 | 3250 | 0.0391 |
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 sha256:92d7e6bcfb3032c1ee5cb95ea55dfa2d7c9991f4da01957b6c3b68b5059dd6cd
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c82e6cd1f3192019e28babe2a1eddb91c972b49eacae4fb9f3de35ae94c3c3
3
  size 80013120