Hugging Face's logo

chchen
/
Ministral-8B-Instruct-2410-PsyCourse-fold6

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
chchen commited on
Commit
2c8a0e1
·
verified ·
1 Parent(s): e3d4bf3

Model save

Browse files
Files changed (2) hide show
  1. README.md +126 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: mistralai/Ministral-8B-Instruct-2410
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Ministral-8B-Instruct-2410-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
+ # Ministral-8B-Instruct-2410-PsyCourse-fold6
17
+
18
+ This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0473
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
+ | 0.2584 | 0.0770 | 50 | 0.2416 |
55
+ | 0.0852 | 0.1539 | 100 | 0.0695 |
56
+ | 0.0619 | 0.2309 | 150 | 0.0585 |
57
+ | 0.0573 | 0.3078 | 200 | 0.0544 |
58
+ | 0.0447 | 0.3848 | 250 | 0.0429 |
59
+ | 0.0395 | 0.4617 | 300 | 0.0470 |
60
+ | 0.0436 | 0.5387 | 350 | 0.0453 |
61
+ | 0.0482 | 0.6156 | 400 | 0.0444 |
62
+ | 0.0291 | 0.6926 | 450 | 0.0388 |
63
+ | 0.0291 | 0.7695 | 500 | 0.0380 |
64
+ | 0.0421 | 0.8465 | 550 | 0.0345 |
65
+ | 0.0363 | 0.9234 | 600 | 0.0357 |
66
+ | 0.0313 | 1.0004 | 650 | 0.0356 |
67
+ | 0.0354 | 1.0773 | 700 | 0.0369 |
68
+ | 0.0264 | 1.1543 | 750 | 0.0354 |
69
+ | 0.028 | 1.2312 | 800 | 0.0342 |
70
+ | 0.029 | 1.3082 | 850 | 0.0342 |
71
+ | 0.0209 | 1.3851 | 900 | 0.0329 |
72
+ | 0.036 | 1.4621 | 950 | 0.0340 |
73
+ | 0.0319 | 1.5391 | 1000 | 0.0342 |
74
+ | 0.0316 | 1.6160 | 1050 | 0.0328 |
75
+ | 0.0331 | 1.6930 | 1100 | 0.0366 |
76
+ | 0.0221 | 1.7699 | 1150 | 0.0336 |
77
+ | 0.0215 | 1.8469 | 1200 | 0.0373 |
78
+ | 0.028 | 1.9238 | 1250 | 0.0327 |
79
+ | 0.0216 | 2.0008 | 1300 | 0.0314 |
80
+ | 0.0173 | 2.0777 | 1350 | 0.0313 |
81
+ | 0.0224 | 2.1547 | 1400 | 0.0340 |
82
+ | 0.0096 | 2.2316 | 1450 | 0.0382 |
83
+ | 0.0191 | 2.3086 | 1500 | 0.0345 |
84
+ | 0.0153 | 2.3855 | 1550 | 0.0382 |
85
+ | 0.0133 | 2.4625 | 1600 | 0.0371 |
86
+ | 0.0176 | 2.5394 | 1650 | 0.0336 |
87
+ | 0.0207 | 2.6164 | 1700 | 0.0343 |
88
+ | 0.0232 | 2.6933 | 1750 | 0.0332 |
89
+ | 0.018 | 2.7703 | 1800 | 0.0336 |
90
+ | 0.0196 | 2.8472 | 1850 | 0.0327 |
91
+ | 0.0168 | 2.9242 | 1900 | 0.0337 |
92
+ | 0.0226 | 3.0012 | 1950 | 0.0350 |
93
+ | 0.0087 | 3.0781 | 2000 | 0.0381 |
94
+ | 0.0109 | 3.1551 | 2050 | 0.0420 |
95
+ | 0.0093 | 3.2320 | 2100 | 0.0398 |
96
+ | 0.0063 | 3.3090 | 2150 | 0.0419 |
97
+ | 0.0131 | 3.3859 | 2200 | 0.0391 |
98
+ | 0.0076 | 3.4629 | 2250 | 0.0381 |
99
+ | 0.0102 | 3.5398 | 2300 | 0.0391 |
100
+ | 0.0056 | 3.6168 | 2350 | 0.0426 |
101
+ | 0.011 | 3.6937 | 2400 | 0.0372 |
102
+ | 0.0062 | 3.7707 | 2450 | 0.0394 |
103
+ | 0.0071 | 3.8476 | 2500 | 0.0414 |
104
+ | 0.009 | 3.9246 | 2550 | 0.0411 |
105
+ | 0.009 | 4.0015 | 2600 | 0.0390 |
106
+ | 0.002 | 4.0785 | 2650 | 0.0410 |
107
+ | 0.0072 | 4.1554 | 2700 | 0.0437 |
108
+ | 0.0018 | 4.2324 | 2750 | 0.0441 |
109
+ | 0.0022 | 4.3093 | 2800 | 0.0459 |
110
+ | 0.0023 | 4.3863 | 2850 | 0.0472 |
111
+ | 0.0042 | 4.4633 | 2900 | 0.0476 |
112
+ | 0.0013 | 4.5402 | 2950 | 0.0468 |
113
+ | 0.004 | 4.6172 | 3000 | 0.0470 |
114
+ | 0.0035 | 4.6941 | 3050 | 0.0472 |
115
+ | 0.0029 | 4.7711 | 3100 | 0.0473 |
116
+ | 0.0026 | 4.8480 | 3150 | 0.0471 |
117
+ | 0.0042 | 4.9250 | 3200 | 0.0473 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - PEFT 0.12.0
123
+ - Transformers 4.46.1
124
+ - Pytorch 2.5.1+cu124
125
+ - Datasets 3.1.0
126
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74f56bf5b755092fa31c56878733a86fea2532f7b0005b64f78eeca725900ad9
3
  size 87360584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965f2afa78c11976a1d48928e863972a50888a2801eb20d3df328578787c9fd7
3
  size 87360584