Hugging Face's logo

chchen
/
MentaLLaMA-chat-7B-PsyCourse-fold6

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
chchen commited on
Commit
4957fc1
·
verified ·
1 Parent(s): 3fbacf3

Model save

Browse files
Files changed (2) hide show
  1. README.md +128 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold6
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-fold6
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: 0.0430
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
+ | 0.8292 | 0.0751 | 50 | 0.6473 |
55
+ | 0.1595 | 0.1502 | 100 | 0.1169 |
56
+ | 0.0933 | 0.2254 | 150 | 0.0727 |
57
+ | 0.0512 | 0.3005 | 200 | 0.0581 |
58
+ | 0.0619 | 0.3756 | 250 | 0.0474 |
59
+ | 0.0395 | 0.4507 | 300 | 0.0460 |
60
+ | 0.0476 | 0.5258 | 350 | 0.0454 |
61
+ | 0.0444 | 0.6009 | 400 | 0.0407 |
62
+ | 0.0543 | 0.6761 | 450 | 0.0425 |
63
+ | 0.0454 | 0.7512 | 500 | 0.0372 |
64
+ | 0.0562 | 0.8263 | 550 | 0.0377 |
65
+ | 0.0336 | 0.9014 | 600 | 0.0361 |
66
+ | 0.0494 | 0.9765 | 650 | 0.0368 |
67
+ | 0.0354 | 1.0516 | 700 | 0.0386 |
68
+ | 0.029 | 1.1268 | 750 | 0.0376 |
69
+ | 0.0301 | 1.2019 | 800 | 0.0352 |
70
+ | 0.0321 | 1.2770 | 850 | 0.0341 |
71
+ | 0.0271 | 1.3521 | 900 | 0.0343 |
72
+ | 0.0351 | 1.4272 | 950 | 0.0330 |
73
+ | 0.0244 | 1.5023 | 1000 | 0.0330 |
74
+ | 0.0277 | 1.5775 | 1050 | 0.0341 |
75
+ | 0.0231 | 1.6526 | 1100 | 0.0340 |
76
+ | 0.0261 | 1.7277 | 1150 | 0.0327 |
77
+ | 0.0297 | 1.8028 | 1200 | 0.0348 |
78
+ | 0.027 | 1.8779 | 1250 | 0.0334 |
79
+ | 0.0417 | 1.9531 | 1300 | 0.0348 |
80
+ | 0.0173 | 2.0282 | 1350 | 0.0328 |
81
+ | 0.0207 | 2.1033 | 1400 | 0.0323 |
82
+ | 0.0223 | 2.1784 | 1450 | 0.0325 |
83
+ | 0.0107 | 2.2535 | 1500 | 0.0359 |
84
+ | 0.0182 | 2.3286 | 1550 | 0.0332 |
85
+ | 0.0187 | 2.4038 | 1600 | 0.0323 |
86
+ | 0.018 | 2.4789 | 1650 | 0.0327 |
87
+ | 0.0205 | 2.5540 | 1700 | 0.0350 |
88
+ | 0.0182 | 2.6291 | 1750 | 0.0323 |
89
+ | 0.0202 | 2.7042 | 1800 | 0.0325 |
90
+ | 0.0218 | 2.7793 | 1850 | 0.0323 |
91
+ | 0.0179 | 2.8545 | 1900 | 0.0319 |
92
+ | 0.0213 | 2.9296 | 1950 | 0.0330 |
93
+ | 0.0104 | 3.0047 | 2000 | 0.0328 |
94
+ | 0.0097 | 3.0798 | 2050 | 0.0359 |
95
+ | 0.0103 | 3.1549 | 2100 | 0.0363 |
96
+ | 0.0131 | 3.2300 | 2150 | 0.0359 |
97
+ | 0.0149 | 3.3052 | 2200 | 0.0362 |
98
+ | 0.0083 | 3.3803 | 2250 | 0.0365 |
99
+ | 0.0115 | 3.4554 | 2300 | 0.0359 |
100
+ | 0.0111 | 3.5305 | 2350 | 0.0387 |
101
+ | 0.0094 | 3.6056 | 2400 | 0.0376 |
102
+ | 0.0051 | 3.6808 | 2450 | 0.0376 |
103
+ | 0.0053 | 3.7559 | 2500 | 0.0375 |
104
+ | 0.0078 | 3.8310 | 2550 | 0.0377 |
105
+ | 0.0105 | 3.9061 | 2600 | 0.0372 |
106
+ | 0.0105 | 3.9812 | 2650 | 0.0371 |
107
+ | 0.0064 | 4.0563 | 2700 | 0.0382 |
108
+ | 0.0048 | 4.1315 | 2750 | 0.0398 |
109
+ | 0.0065 | 4.2066 | 2800 | 0.0407 |
110
+ | 0.0031 | 4.2817 | 2850 | 0.0417 |
111
+ | 0.0028 | 4.3568 | 2900 | 0.0420 |
112
+ | 0.0043 | 4.4319 | 2950 | 0.0421 |
113
+ | 0.0048 | 4.5070 | 3000 | 0.0424 |
114
+ | 0.0038 | 4.5822 | 3050 | 0.0428 |
115
+ | 0.0041 | 4.6573 | 3100 | 0.0430 |
116
+ | 0.0066 | 4.7324 | 3150 | 0.0431 |
117
+ | 0.003 | 4.8075 | 3200 | 0.0430 |
118
+ | 0.0031 | 4.8826 | 3250 | 0.0429 |
119
+ | 0.0046 | 4.9577 | 3300 | 0.0430 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - PEFT 0.12.0
125
+ - Transformers 4.46.1
126
+ - Pytorch 2.5.1+cu124
127
+ - Datasets 3.1.0
128
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a92551080b6f40146ff7d962f0102bb831603ebfbc63f84e5d97ff445bf8afd9
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1018f40acbf1a6ff08e04068cc97d7ee4b2d9bf650232e01408a1d2da0aef1
3
  size 80013120