Hugging Face's logo

s-sysia
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
s-sysia commited on
Commit
564d0d4
·
verified ·
1 Parent(s): 9a8d8bd

End of training

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: calculator_model_test
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # calculator_model_test
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.5538
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.001
37
+ - train_batch_size: 512
38
+ - eval_batch_size: 512
39
+ - seed: 42
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 40
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 3.4511 | 1.0 | 5 | 2.8467 |
50
+ | 2.5181 | 2.0 | 10 | 2.1116 |
51
+ | 1.9303 | 3.0 | 15 | 1.7151 |
52
+ | 1.6577 | 4.0 | 20 | 1.5789 |
53
+ | 1.5651 | 5.0 | 25 | 1.5754 |
54
+ | 1.5127 | 6.0 | 30 | 1.5309 |
55
+ | 1.4740 | 7.0 | 35 | 1.4478 |
56
+ | 1.4122 | 8.0 | 40 | 1.4028 |
57
+ | 1.3682 | 9.0 | 45 | 1.3378 |
58
+ | 1.3127 | 10.0 | 50 | 1.2629 |
59
+ | 1.2188 | 11.0 | 55 | 1.1926 |
60
+ | 1.1528 | 12.0 | 60 | 1.1110 |
61
+ | 1.0918 | 13.0 | 65 | 1.0502 |
62
+ | 1.0482 | 14.0 | 70 | 1.0344 |
63
+ | 1.0041 | 15.0 | 75 | 0.9841 |
64
+ | 0.9944 | 16.0 | 80 | 0.9972 |
65
+ | 0.9652 | 17.0 | 85 | 0.9387 |
66
+ | 0.9474 | 18.0 | 90 | 0.9364 |
67
+ | 0.9464 | 19.0 | 95 | 0.8833 |
68
+ | 0.8842 | 20.0 | 100 | 0.8297 |
69
+ | 0.8439 | 21.0 | 105 | 0.8420 |
70
+ | 0.8259 | 22.0 | 110 | 0.8106 |
71
+ | 0.8101 | 23.0 | 115 | 0.7762 |
72
+ | 0.7815 | 24.0 | 120 | 0.7527 |
73
+ | 0.7651 | 25.0 | 125 | 0.7202 |
74
+ | 0.7371 | 26.0 | 130 | 0.7016 |
75
+ | 0.7205 | 27.0 | 135 | 0.6782 |
76
+ | 0.7045 | 28.0 | 140 | 0.6595 |
77
+ | 0.6867 | 29.0 | 145 | 0.6433 |
78
+ | 0.6672 | 30.0 | 150 | 0.6401 |
79
+ | 0.6627 | 31.0 | 155 | 0.6267 |
80
+ | 0.6433 | 32.0 | 160 | 0.6054 |
81
+ | 0.6396 | 33.0 | 165 | 0.6003 |
82
+ | 0.6211 | 34.0 | 170 | 0.5905 |
83
+ | 0.6128 | 35.0 | 175 | 0.5826 |
84
+ | 0.6134 | 36.0 | 180 | 0.5728 |
85
+ | 0.6001 | 37.0 | 185 | 0.5680 |
86
+ | 0.5967 | 38.0 | 190 | 0.5584 |
87
+ | 0.5884 | 39.0 | 195 | 0.5570 |
88
+ | 0.5887 | 40.0 | 200 | 0.5538 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 5.0.0
94
+ - Pytorch 2.10.0+cpu
95
+ - Datasets 4.0.0
96
+ - Tokenizers 0.22.2