End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: calculator_model_test_with_steps
|
| 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_with_steps
|
| 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: 0.0741
|
| 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 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 3.0444 | 1.0 | 6 | 2.2982 |
|
| 49 |
+
| 2.0319 | 2.0 | 12 | 1.7372 |
|
| 50 |
+
| 1.5871 | 3.0 | 18 | 1.3782 |
|
| 51 |
+
| 1.2735 | 4.0 | 24 | 1.1017 |
|
| 52 |
+
| 1.0332 | 5.0 | 30 | 0.9506 |
|
| 53 |
+
| 0.9051 | 6.0 | 36 | 0.8307 |
|
| 54 |
+
| 0.7868 | 7.0 | 42 | 0.7057 |
|
| 55 |
+
| 0.7026 | 8.0 | 48 | 0.6872 |
|
| 56 |
+
| 0.6729 | 9.0 | 54 | 0.6115 |
|
| 57 |
+
| 0.6270 | 10.0 | 60 | 0.6062 |
|
| 58 |
+
| 0.5786 | 11.0 | 66 | 0.5212 |
|
| 59 |
+
| 0.5293 | 12.0 | 72 | 0.4763 |
|
| 60 |
+
| 0.4852 | 13.0 | 78 | 0.4490 |
|
| 61 |
+
| 0.4583 | 14.0 | 84 | 0.4149 |
|
| 62 |
+
| 0.4152 | 15.0 | 90 | 0.3562 |
|
| 63 |
+
| 0.3767 | 16.0 | 96 | 0.3472 |
|
| 64 |
+
| 0.3715 | 17.0 | 102 | 0.3505 |
|
| 65 |
+
| 0.3611 | 18.0 | 108 | 0.3096 |
|
| 66 |
+
| 0.3194 | 19.0 | 114 | 0.2867 |
|
| 67 |
+
| 0.3072 | 20.0 | 120 | 0.2500 |
|
| 68 |
+
| 0.2794 | 21.0 | 126 | 0.2270 |
|
| 69 |
+
| 0.2550 | 22.0 | 132 | 0.2257 |
|
| 70 |
+
| 0.2486 | 23.0 | 138 | 0.2034 |
|
| 71 |
+
| 0.2315 | 24.0 | 144 | 0.1956 |
|
| 72 |
+
| 0.2167 | 25.0 | 150 | 0.1968 |
|
| 73 |
+
| 0.2169 | 26.0 | 156 | 0.1761 |
|
| 74 |
+
| 0.1939 | 27.0 | 162 | 0.1711 |
|
| 75 |
+
| 0.1856 | 28.0 | 168 | 0.1356 |
|
| 76 |
+
| 0.1744 | 29.0 | 174 | 0.1312 |
|
| 77 |
+
| 0.1595 | 30.0 | 180 | 0.1211 |
|
| 78 |
+
| 0.1495 | 31.0 | 186 | 0.1110 |
|
| 79 |
+
| 0.1418 | 32.0 | 192 | 0.0995 |
|
| 80 |
+
| 0.1329 | 33.0 | 198 | 0.0956 |
|
| 81 |
+
| 0.1260 | 34.0 | 204 | 0.0909 |
|
| 82 |
+
| 0.1162 | 35.0 | 210 | 0.0844 |
|
| 83 |
+
| 0.1135 | 36.0 | 216 | 0.0794 |
|
| 84 |
+
| 0.1060 | 37.0 | 222 | 0.0777 |
|
| 85 |
+
| 0.1105 | 38.0 | 228 | 0.0762 |
|
| 86 |
+
| 0.1032 | 39.0 | 234 | 0.0746 |
|
| 87 |
+
| 0.1033 | 40.0 | 240 | 0.0741 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 5.0.0
|
| 93 |
+
- Pytorch 2.10.0+cpu
|
| 94 |
+
- Datasets 4.0.0
|
| 95 |
+
- Tokenizers 0.22.2
|