Hugging Face's logo

chchen
/
MentaLLaMA-chat-7B-PsyCourse-fold9

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
fa3b0cc
·
verified ·
1 Parent(s): 19ef803

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-fold9
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-fold9
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: 0.0456
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
+ | 0.8389 | 0.0768 | 50 | 0.6107 |
55
+ | 0.1391 | 0.1535 | 100 | 0.1064 |
56
+ | 0.0757 | 0.2303 | 150 | 0.0694 |
57
+ | 0.0639 | 0.3070 | 200 | 0.0581 |
58
+ | 0.0739 | 0.3838 | 250 | 0.0467 |
59
+ | 0.0558 | 0.4606 | 300 | 0.0439 |
60
+ | 0.0394 | 0.5373 | 350 | 0.0425 |
61
+ | 0.0477 | 0.6141 | 400 | 0.0419 |
62
+ | 0.047 | 0.6908 | 450 | 0.0432 |
63
+ | 0.0416 | 0.7676 | 500 | 0.0376 |
64
+ | 0.0637 | 0.8444 | 550 | 0.0395 |
65
+ | 0.0377 | 0.9211 | 600 | 0.0357 |
66
+ | 0.0315 | 0.9979 | 650 | 0.0361 |
67
+ | 0.0332 | 1.0746 | 700 | 0.0360 |
68
+ | 0.0322 | 1.1514 | 750 | 0.0352 |
69
+ | 0.0321 | 1.2282 | 800 | 0.0333 |
70
+ | 0.0299 | 1.3049 | 850 | 0.0323 |
71
+ | 0.0286 | 1.3817 | 900 | 0.0340 |
72
+ | 0.0266 | 1.4585 | 950 | 0.0332 |
73
+ | 0.0296 | 1.5352 | 1000 | 0.0320 |
74
+ | 0.022 | 1.6120 | 1050 | 0.0307 |
75
+ | 0.0292 | 1.6887 | 1100 | 0.0312 |
76
+ | 0.0269 | 1.7655 | 1150 | 0.0330 |
77
+ | 0.0204 | 1.8423 | 1200 | 0.0306 |
78
+ | 0.0306 | 1.9190 | 1250 | 0.0309 |
79
+ | 0.0364 | 1.9958 | 1300 | 0.0314 |
80
+ | 0.0194 | 2.0725 | 1350 | 0.0319 |
81
+ | 0.0148 | 2.1493 | 1400 | 0.0318 |
82
+ | 0.0161 | 2.2261 | 1450 | 0.0305 |
83
+ | 0.0293 | 2.3028 | 1500 | 0.0323 |
84
+ | 0.0203 | 2.3796 | 1550 | 0.0329 |
85
+ | 0.0235 | 2.4563 | 1600 | 0.0327 |
86
+ | 0.0234 | 2.5331 | 1650 | 0.0311 |
87
+ | 0.0227 | 2.6099 | 1700 | 0.0307 |
88
+ | 0.0147 | 2.6866 | 1750 | 0.0313 |
89
+ | 0.0202 | 2.7634 | 1800 | 0.0322 |
90
+ | 0.0203 | 2.8401 | 1850 | 0.0313 |
91
+ | 0.0199 | 2.9169 | 1900 | 0.0310 |
92
+ | 0.0152 | 2.9937 | 1950 | 0.0315 |
93
+ | 0.0065 | 3.0704 | 2000 | 0.0347 |
94
+ | 0.0155 | 3.1472 | 2050 | 0.0345 |
95
+ | 0.0087 | 3.2239 | 2100 | 0.0367 |
96
+ | 0.0107 | 3.3007 | 2150 | 0.0353 |
97
+ | 0.0113 | 3.3775 | 2200 | 0.0377 |
98
+ | 0.0115 | 3.4542 | 2250 | 0.0358 |
99
+ | 0.0087 | 3.5310 | 2300 | 0.0377 |
100
+ | 0.0099 | 3.6078 | 2350 | 0.0374 |
101
+ | 0.0075 | 3.6845 | 2400 | 0.0381 |
102
+ | 0.0064 | 3.7613 | 2450 | 0.0384 |
103
+ | 0.0111 | 3.8380 | 2500 | 0.0382 |
104
+ | 0.0154 | 3.9148 | 2550 | 0.0380 |
105
+ | 0.0087 | 3.9916 | 2600 | 0.0379 |
106
+ | 0.0042 | 4.0683 | 2650 | 0.0392 |
107
+ | 0.0029 | 4.1451 | 2700 | 0.0411 |
108
+ | 0.0044 | 4.2218 | 2750 | 0.0422 |
109
+ | 0.0035 | 4.2986 | 2800 | 0.0430 |
110
+ | 0.0031 | 4.3754 | 2850 | 0.0441 |
111
+ | 0.004 | 4.4521 | 2900 | 0.0445 |
112
+ | 0.0035 | 4.5289 | 2950 | 0.0446 |
113
+ | 0.0021 | 4.6056 | 3000 | 0.0454 |
114
+ | 0.0041 | 4.6824 | 3050 | 0.0459 |
115
+ | 0.006 | 4.7592 | 3100 | 0.0456 |
116
+ | 0.0043 | 4.8359 | 3150 | 0.0455 |
117
+ | 0.0031 | 4.9127 | 3200 | 0.0456 |
118
+ | 0.0073 | 4.9894 | 3250 | 0.0456 |
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:ace0f58b9dee4661ec566974c2f8f79490ee3b18919abf5aa02605d03c50172c
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace91e68801cf5ac52c8ee4f6f3d2e06d20deaefb231f52ec040fce180d75020
3
  size 80013120