Hugging Face's logo

nerottt
/
lc_random_repeat

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
nerottt commited on
Commit
6bca7b9
·
verified ·
1 Parent(s): ead5152

End of training

Browse files
Files changed (1) hide show
  1. README.md +110 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-v0.1
9
+ model-index:
10
+ - name: lc_random_repeat
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # lc_random_repeat
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.6186
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.4379 | 1.0 | 179 | 1.4131 |
53
+ | 1.4264 | 2.0 | 358 | 1.3916 |
54
+ | 1.3008 | 3.0 | 537 | 1.3836 |
55
+ | 1.3527 | 4.0 | 716 | 1.3795 |
56
+ | 1.3232 | 5.0 | 895 | 1.3847 |
57
+ | 1.123 | 6.0 | 1074 | 1.3991 |
58
+ | 1.2001 | 7.0 | 1253 | 1.3956 |
59
+ | 1.2633 | 8.0 | 1432 | 1.4122 |
60
+ | 1.246 | 9.0 | 1611 | 1.4136 |
61
+ | 1.1377 | 10.0 | 1790 | 1.4250 |
62
+ | 1.1705 | 11.0 | 1969 | 1.4381 |
63
+ | 1.1582 | 12.0 | 2148 | 1.4502 |
64
+ | 1.1204 | 13.0 | 2327 | 1.4652 |
65
+ | 1.164 | 14.0 | 2506 | 1.4837 |
66
+ | 1.1277 | 15.0 | 2685 | 1.4842 |
67
+ | 1.0011 | 16.0 | 2864 | 1.5123 |
68
+ | 1.018 | 17.0 | 3043 | 1.5116 |
69
+ | 1.0135 | 18.0 | 3222 | 1.5332 |
70
+ | 1.0115 | 19.0 | 3401 | 1.5386 |
71
+ | 0.9707 | 20.0 | 3580 | 1.5623 |
72
+ | 1.105 | 21.0 | 3759 | 1.5591 |
73
+ | 1.0399 | 22.0 | 3938 | 1.5469 |
74
+ | 1.0203 | 23.0 | 4117 | 1.5725 |
75
+ | 1.0629 | 24.0 | 4296 | 1.5643 |
76
+ | 0.9934 | 25.0 | 4475 | 1.5698 |
77
+ | 0.9231 | 26.0 | 4654 | 1.5924 |
78
+ | 0.9423 | 27.0 | 4833 | 1.5916 |
79
+ | 1.0153 | 28.0 | 5012 | 1.5976 |
80
+ | 0.9623 | 29.0 | 5191 | 1.6060 |
81
+ | 0.796 | 30.0 | 5370 | 1.6051 |
82
+ | 0.9592 | 31.0 | 5549 | 1.6067 |
83
+ | 0.9507 | 32.0 | 5728 | 1.6060 |
84
+ | 0.7748 | 33.0 | 5907 | 1.6183 |
85
+ | 1.0306 | 34.0 | 6086 | 1.6126 |
86
+ | 0.8095 | 35.0 | 6265 | 1.6120 |
87
+ | 0.8423 | 36.0 | 6444 | 1.6163 |
88
+ | 0.8873 | 37.0 | 6623 | 1.6162 |
89
+ | 0.9068 | 38.0 | 6802 | 1.6177 |
90
+ | 0.9126 | 39.0 | 6981 | 1.6182 |
91
+ | 0.948 | 40.0 | 7160 | 1.6169 |
92
+ | 0.8804 | 41.0 | 7339 | 1.6188 |
93
+ | 0.8854 | 42.0 | 7518 | 1.6185 |
94
+ | 0.8272 | 43.0 | 7697 | 1.6170 |
95
+ | 0.9812 | 44.0 | 7876 | 1.6179 |
96
+ | 0.8171 | 45.0 | 8055 | 1.6183 |
97
+ | 0.8417 | 46.0 | 8234 | 1.6177 |
98
+ | 0.9621 | 47.0 | 8413 | 1.6188 |
99
+ | 0.9239 | 48.0 | 8592 | 1.6179 |
100
+ | 0.9687 | 49.0 | 8771 | 1.6189 |
101
+ | 0.8301 | 50.0 | 8950 | 1.6186 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - PEFT 0.11.1
107
+ - Transformers 4.41.2
108
+ - Pytorch 2.1.0+cu118
109
+ - Datasets 2.19.2
110
+ - Tokenizers 0.19.1