Hugging Face's logo

minhtien2405
/
pixtral-12b-transformers-v0

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
minhtien2405 commited on
Commit
ec5e7b3
·
verified ·
1 Parent(s): f0fbc65

Model save

Browse files
Files changed (2) hide show
  1. README.md +111 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: mistral-community/pixtral-12b
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: pixtral-12b-transformers-v0
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # pixtral-12b-transformers-v0
16
+
17
+ This model is a fine-tuned version of [mistral-community/pixtral-12b](https://huggingface.co/mistral-community/pixtral-12b) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0344
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 4
44
+ - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: constant
46
+ - lr_scheduler_warmup_ratio: 0.03
47
+ - num_epochs: 10
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 0.0752 | 0.1998 | 50 | 0.0506 |
54
+ | 0.035 | 0.3996 | 100 | 0.0443 |
55
+ | 0.0318 | 0.5994 | 150 | 0.0392 |
56
+ | 0.0296 | 0.7992 | 200 | 0.0329 |
57
+ | 0.0239 | 0.9990 | 250 | 0.0300 |
58
+ | 0.022 | 1.1958 | 300 | 0.0301 |
59
+ | 0.0201 | 1.3956 | 350 | 0.0343 |
60
+ | 0.0225 | 1.5954 | 400 | 0.0296 |
61
+ | 0.0197 | 1.7952 | 450 | 0.0272 |
62
+ | 0.0174 | 1.9950 | 500 | 0.0285 |
63
+ | 0.0167 | 2.1918 | 550 | 0.0266 |
64
+ | 0.0159 | 2.3916 | 600 | 0.0267 |
65
+ | 0.0141 | 2.5914 | 650 | 0.0262 |
66
+ | 0.017 | 2.7912 | 700 | 0.0270 |
67
+ | 0.0138 | 2.9910 | 750 | 0.0263 |
68
+ | 0.0126 | 3.1878 | 800 | 0.0272 |
69
+ | 0.0123 | 3.3876 | 850 | 0.0260 |
70
+ | 0.0111 | 3.5874 | 900 | 0.0249 |
71
+ | 0.011 | 3.7872 | 950 | 0.0257 |
72
+ | 0.015 | 3.9870 | 1000 | 0.0258 |
73
+ | 0.0094 | 4.1838 | 1050 | 0.0275 |
74
+ | 0.0093 | 4.3836 | 1100 | 0.0275 |
75
+ | 0.01 | 4.5834 | 1150 | 0.0272 |
76
+ | 0.0115 | 4.7832 | 1200 | 0.0269 |
77
+ | 0.012 | 4.9830 | 1250 | 0.0250 |
78
+ | 0.0079 | 5.1798 | 1300 | 0.0284 |
79
+ | 0.0081 | 5.3796 | 1350 | 0.0309 |
80
+ | 0.0096 | 5.5794 | 1400 | 0.0279 |
81
+ | 0.0094 | 5.7792 | 1450 | 0.0280 |
82
+ | 0.009 | 5.9790 | 1500 | 0.0276 |
83
+ | 0.0081 | 6.1758 | 1550 | 0.0329 |
84
+ | 0.008 | 6.3756 | 1600 | 0.0275 |
85
+ | 0.0076 | 6.5754 | 1650 | 0.0271 |
86
+ | 0.008 | 6.7752 | 1700 | 0.0292 |
87
+ | 0.0082 | 6.9750 | 1750 | 0.0270 |
88
+ | 0.005 | 7.1718 | 1800 | 0.0315 |
89
+ | 0.0069 | 7.3716 | 1850 | 0.0271 |
90
+ | 0.0063 | 7.5714 | 1900 | 0.0305 |
91
+ | 0.007 | 7.7712 | 1950 | 0.0282 |
92
+ | 0.006 | 7.9710 | 2000 | 0.0293 |
93
+ | 0.0059 | 8.1678 | 2050 | 0.0302 |
94
+ | 0.0042 | 8.3676 | 2100 | 0.0332 |
95
+ | 0.0053 | 8.5674 | 2150 | 0.0297 |
96
+ | 0.0053 | 8.7672 | 2200 | 0.0327 |
97
+ | 0.0057 | 8.9670 | 2250 | 0.0300 |
98
+ | 0.0066 | 9.1638 | 2300 | 0.0318 |
99
+ | 0.0042 | 9.3636 | 2350 | 0.0316 |
100
+ | 0.0037 | 9.5634 | 2400 | 0.0342 |
101
+ | 0.0066 | 9.7632 | 2450 | 0.0323 |
102
+ | 0.0045 | 9.9630 | 2500 | 0.0344 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - PEFT 0.14.0
108
+ - Transformers 4.48.3
109
+ - Pytorch 2.5.1+cu124
110
+ - Datasets 3.3.2
111
+ - Tokenizers 0.21.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4552f387c9d5f45800d54c3d658f37686094dc996d96fb9345a8be44755014d5
3
  size 22844832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b8172c9f9d68adf8295755c3cf8cca32032af7c5ce50ccce9de6e3f0e1c291
3
  size 22844832