Hugging Face's logo

ms8080
/
calculator_model_test_2

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
ms8080 commited on
Commit
9c30a3e
·
verified ·
1 Parent(s): 031eeaa

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_2
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_2
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: 0.0796
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
+ | 3.0122 | 1.0 | 6 | 2.2341 |
50
+ | 2.0139 | 2.0 | 12 | 1.7303 |
51
+ | 1.5716 | 3.0 | 18 | 1.3182 |
52
+ | 1.2075 | 4.0 | 24 | 1.0462 |
53
+ | 0.9857 | 5.0 | 30 | 0.9041 |
54
+ | 0.8531 | 6.0 | 36 | 0.8073 |
55
+ | 0.7766 | 7.0 | 42 | 0.7281 |
56
+ | 0.6967 | 8.0 | 48 | 0.6472 |
57
+ | 0.6500 | 9.0 | 54 | 0.6128 |
58
+ | 0.6093 | 10.0 | 60 | 0.5931 |
59
+ | 0.5940 | 11.0 | 66 | 0.5832 |
60
+ | 0.5649 | 12.0 | 72 | 0.5204 |
61
+ | 0.5204 | 13.0 | 78 | 0.4749 |
62
+ | 0.4860 | 14.0 | 84 | 0.4492 |
63
+ | 0.4544 | 15.0 | 90 | 0.4304 |
64
+ | 0.4405 | 16.0 | 96 | 0.4120 |
65
+ | 0.4213 | 17.0 | 102 | 0.4185 |
66
+ | 0.4109 | 18.0 | 108 | 0.3708 |
67
+ | 0.3905 | 19.0 | 114 | 0.3601 |
68
+ | 0.3704 | 20.0 | 120 | 0.3407 |
69
+ | 0.3448 | 21.0 | 126 | 0.3095 |
70
+ | 0.3217 | 22.0 | 132 | 0.2805 |
71
+ | 0.3015 | 23.0 | 138 | 0.2602 |
72
+ | 0.2891 | 24.0 | 144 | 0.2410 |
73
+ | 0.2659 | 25.0 | 150 | 0.2206 |
74
+ | 0.2457 | 26.0 | 156 | 0.1997 |
75
+ | 0.2334 | 27.0 | 162 | 0.1874 |
76
+ | 0.2244 | 28.0 | 168 | 0.1780 |
77
+ | 0.2119 | 29.0 | 174 | 0.1686 |
78
+ | 0.1992 | 30.0 | 180 | 0.1615 |
79
+ | 0.1853 | 31.0 | 186 | 0.1473 |
80
+ | 0.1748 | 32.0 | 192 | 0.1302 |
81
+ | 0.1571 | 33.0 | 198 | 0.1183 |
82
+ | 0.1565 | 34.0 | 204 | 0.1065 |
83
+ | 0.1435 | 35.0 | 210 | 0.0978 |
84
+ | 0.1310 | 36.0 | 216 | 0.0947 |
85
+ | 0.1251 | 37.0 | 222 | 0.0867 |
86
+ | 0.1276 | 38.0 | 228 | 0.0843 |
87
+ | 0.1116 | 39.0 | 234 | 0.0806 |
88
+ | 0.1153 | 40.0 | 240 | 0.0796 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 5.0.0
94
+ - Pytorch 2.10.0+cu128
95
+ - Datasets 4.0.0
96
+ - Tokenizers 0.22.2