Hugging Face's logo

AlekseyKorshuk
/
dalio-synthetic-io-1.3b

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
AlekseyKorshuk commited on
Commit
c32b21b
•
1 Parent(s): c7c8e2a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +119 -0
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: dalio-synthetic-io-1.3b
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
+ # dalio-synthetic-io-1.3b
16
+
17
+ This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.5957
20
+ - Accuracy: 0.0624
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: 3e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 2
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - total_train_batch_size: 16
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - num_epochs: 3.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 2.6941 | 0.05 | 1 | 2.6543 | 0.0622 |
56
+ | 2.6914 | 0.11 | 2 | 2.6543 | 0.0622 |
57
+ | 2.6003 | 0.16 | 3 | 2.6016 | 0.0627 |
58
+ | 2.5603 | 0.21 | 4 | 2.5703 | 0.0627 |
59
+ | 2.6072 | 0.26 | 5 | 2.5508 | 0.0630 |
60
+ | 2.5444 | 0.32 | 6 | 2.5469 | 0.0628 |
61
+ | 2.4467 | 0.37 | 7 | 2.5508 | 0.0629 |
62
+ | 2.5452 | 0.42 | 8 | 2.5508 | 0.0629 |
63
+ | 2.6128 | 0.47 | 9 | 2.5449 | 0.0631 |
64
+ | 2.4568 | 0.53 | 10 | 2.5391 | 0.0627 |
65
+ | 2.5098 | 0.58 | 11 | 2.5352 | 0.0628 |
66
+ | 2.6047 | 0.63 | 12 | 2.5234 | 0.0631 |
67
+ | 2.5022 | 0.68 | 13 | 2.5156 | 0.0630 |
68
+ | 2.605 | 0.74 | 14 | 2.5078 | 0.0633 |
69
+ | 2.6055 | 0.79 | 15 | 2.5020 | 0.0634 |
70
+ | 2.5061 | 0.84 | 16 | 2.4961 | 0.0632 |
71
+ | 2.4348 | 0.89 | 17 | 2.4902 | 0.0631 |
72
+ | 2.6284 | 0.95 | 18 | 2.4883 | 0.0632 |
73
+ | 2.5574 | 1.0 | 19 | 2.4863 | 0.0631 |
74
+ | 2.0814 | 1.05 | 20 | 2.4844 | 0.0633 |
75
+ | 2.0636 | 1.11 | 21 | 2.4844 | 0.0635 |
76
+ | 1.9459 | 1.16 | 22 | 2.4844 | 0.0635 |
77
+ | 2.0527 | 1.21 | 23 | 2.4883 | 0.0634 |
78
+ | 1.8881 | 1.26 | 24 | 2.4961 | 0.0635 |
79
+ | 1.8668 | 1.32 | 25 | 2.5117 | 0.0636 |
80
+ | 2.0375 | 1.37 | 26 | 2.5293 | 0.0636 |
81
+ | 1.9402 | 1.42 | 27 | 2.5449 | 0.0632 |
82
+ | 1.6086 | 1.47 | 28 | 2.5586 | 0.0633 |
83
+ | 1.8185 | 1.53 | 29 | 2.5645 | 0.0632 |
84
+ | 1.7324 | 1.58 | 30 | 2.5605 | 0.0630 |
85
+ | 1.9285 | 1.63 | 31 | 2.5527 | 0.0628 |
86
+ | 1.8031 | 1.68 | 32 | 2.5449 | 0.0631 |
87
+ | 1.7321 | 1.74 | 33 | 2.5352 | 0.0630 |
88
+ | 1.7802 | 1.79 | 34 | 2.5254 | 0.0631 |
89
+ | 2.0637 | 1.84 | 35 | 2.5156 | 0.0632 |
90
+ | 1.8159 | 1.89 | 36 | 2.5078 | 0.0633 |
91
+ | 1.7142 | 1.95 | 37 | 2.5039 | 0.0634 |
92
+ | 1.8793 | 2.0 | 38 | 2.5 | 0.0634 |
93
+ | 1.6914 | 2.05 | 39 | 2.5020 | 0.0636 |
94
+ | 1.411 | 2.11 | 40 | 2.5039 | 0.0639 |
95
+ | 1.4182 | 2.16 | 41 | 2.5098 | 0.0639 |
96
+ | 1.6223 | 2.21 | 42 | 2.5176 | 0.0638 |
97
+ | 1.623 | 2.26 | 43 | 2.5273 | 0.0634 |
98
+ | 1.5748 | 2.32 | 44 | 2.5371 | 0.0634 |
99
+ | 1.7166 | 2.37 | 45 | 2.5469 | 0.0631 |
100
+ | 1.3432 | 2.42 | 46 | 2.5566 | 0.0630 |
101
+ | 1.5325 | 2.47 | 47 | 2.5645 | 0.0631 |
102
+ | 1.5076 | 2.53 | 48 | 2.5723 | 0.0629 |
103
+ | 1.6636 | 2.58 | 49 | 2.5781 | 0.0627 |
104
+ | 1.2897 | 2.63 | 50 | 2.5840 | 0.0627 |
105
+ | 1.4559 | 2.68 | 51 | 2.5879 | 0.0627 |
106
+ | 1.3904 | 2.74 | 52 | 2.5898 | 0.0627 |
107
+ | 1.4961 | 2.79 | 53 | 2.5918 | 0.0626 |
108
+ | 1.5276 | 2.84 | 54 | 2.5938 | 0.0625 |
109
+ | 1.3479 | 2.89 | 55 | 2.5957 | 0.0625 |
110
+ | 1.4094 | 2.95 | 56 | 2.5957 | 0.0624 |
111
+ | 1.5486 | 3.0 | 57 | 2.5957 | 0.0624 |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.25.0.dev0
117
+ - Pytorch 1.12.1+cu113
118
+ - Datasets 2.3.2
119
+ - Tokenizers 0.12.1