Hugging Face's logo

chchen
/
MentaLLaMA-chat-7B-PsyCourse-fold4

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
 Community
chchen commited on
Commit
d62f844
·
verified ·
1 Parent(s): 84c9591

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-fold4
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-fold4
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: 0.0436
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
+ | 0.796 | 0.0763 | 50 | 0.6145 |
55
+ | 0.1534 | 0.1527 | 100 | 0.1050 |
56
+ | 0.0619 | 0.2290 | 150 | 0.0629 |
57
+ | 0.0535 | 0.3053 | 200 | 0.0550 |
58
+ | 0.0576 | 0.3816 | 250 | 0.0468 |
59
+ | 0.0501 | 0.4580 | 300 | 0.0469 |
60
+ | 0.0456 | 0.5343 | 350 | 0.0423 |
61
+ | 0.0487 | 0.6106 | 400 | 0.0392 |
62
+ | 0.0543 | 0.6870 | 450 | 0.0389 |
63
+ | 0.0298 | 0.7633 | 500 | 0.0349 |
64
+ | 0.0378 | 0.8396 | 550 | 0.0347 |
65
+ | 0.0387 | 0.9159 | 600 | 0.0329 |
66
+ | 0.0275 | 0.9923 | 650 | 0.0352 |
67
+ | 0.0348 | 1.0686 | 700 | 0.0339 |
68
+ | 0.0346 | 1.1449 | 750 | 0.0338 |
69
+ | 0.0321 | 1.2213 | 800 | 0.0337 |
70
+ | 0.0288 | 1.2976 | 850 | 0.0333 |
71
+ | 0.028 | 1.3739 | 900 | 0.0359 |
72
+ | 0.0277 | 1.4502 | 950 | 0.0330 |
73
+ | 0.0202 | 1.5266 | 1000 | 0.0334 |
74
+ | 0.0291 | 1.6029 | 1050 | 0.0343 |
75
+ | 0.0402 | 1.6792 | 1100 | 0.0321 |
76
+ | 0.0268 | 1.7556 | 1150 | 0.0328 |
77
+ | 0.0411 | 1.8319 | 1200 | 0.0320 |
78
+ | 0.0262 | 1.9082 | 1250 | 0.0289 |
79
+ | 0.0318 | 1.9845 | 1300 | 0.0292 |
80
+ | 0.0159 | 2.0609 | 1350 | 0.0306 |
81
+ | 0.019 | 2.1372 | 1400 | 0.0313 |
82
+ | 0.022 | 2.2135 | 1450 | 0.0314 |
83
+ | 0.0133 | 2.2899 | 1500 | 0.0329 |
84
+ | 0.0134 | 2.3662 | 1550 | 0.0317 |
85
+ | 0.0185 | 2.4425 | 1600 | 0.0299 |
86
+ | 0.0229 | 2.5188 | 1650 | 0.0308 |
87
+ | 0.0224 | 2.5952 | 1700 | 0.0307 |
88
+ | 0.0159 | 2.6715 | 1750 | 0.0309 |
89
+ | 0.0185 | 2.7478 | 1800 | 0.0314 |
90
+ | 0.0203 | 2.8242 | 1850 | 0.0304 |
91
+ | 0.0159 | 2.9005 | 1900 | 0.0317 |
92
+ | 0.0229 | 2.9768 | 1950 | 0.0304 |
93
+ | 0.0087 | 3.0531 | 2000 | 0.0329 |
94
+ | 0.0073 | 3.1295 | 2050 | 0.0336 |
95
+ | 0.0068 | 3.2058 | 2100 | 0.0346 |
96
+ | 0.0099 | 3.2821 | 2150 | 0.0367 |
97
+ | 0.0124 | 3.3585 | 2200 | 0.0352 |
98
+ | 0.0087 | 3.4348 | 2250 | 0.0360 |
99
+ | 0.0131 | 3.5111 | 2300 | 0.0354 |
100
+ | 0.0143 | 3.5874 | 2350 | 0.0362 |
101
+ | 0.0066 | 3.6638 | 2400 | 0.0361 |
102
+ | 0.0093 | 3.7401 | 2450 | 0.0372 |
103
+ | 0.0074 | 3.8164 | 2500 | 0.0362 |
104
+ | 0.0081 | 3.8928 | 2550 | 0.0366 |
105
+ | 0.0088 | 3.9691 | 2600 | 0.0370 |
106
+ | 0.0052 | 4.0454 | 2650 | 0.0377 |
107
+ | 0.0053 | 4.1217 | 2700 | 0.0390 |
108
+ | 0.0025 | 4.1981 | 2750 | 0.0402 |
109
+ | 0.0027 | 4.2744 | 2800 | 0.0414 |
110
+ | 0.0076 | 4.3507 | 2850 | 0.0418 |
111
+ | 0.0022 | 4.4271 | 2900 | 0.0428 |
112
+ | 0.0036 | 4.5034 | 2950 | 0.0434 |
113
+ | 0.003 | 4.5797 | 3000 | 0.0432 |
114
+ | 0.002 | 4.6560 | 3050 | 0.0434 |
115
+ | 0.0078 | 4.7324 | 3100 | 0.0435 |
116
+ | 0.0033 | 4.8087 | 3150 | 0.0436 |
117
+ | 0.0055 | 4.8850 | 3200 | 0.0436 |
118
+ | 0.006 | 4.9614 | 3250 | 0.0436 |
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 sha256:4891fd02a75b70ea5bb535dfbea65a97fbf43e29af0c05bac2ac8ac115624a02
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d57b15afcc5a550c276005d530139d18ca83dc704673ac7ba0fab613935ce93
3
  size 80013120