Model save
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -42,83 +42,83 @@ The following hyperparameters were used during training:
|
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: cosine
|
| 44 |
- lr_scheduler_warmup_steps: 2000
|
| 45 |
-
- num_epochs:
|
| 46 |
-
- label_smoothing_factor: 0.1
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:------:|:-----:|:---------------:|
|
| 52 |
-
|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 78 |
-
|
|
| 79 |
-
|
|
| 80 |
-
|
|
| 81 |
-
|
|
| 82 |
-
|
|
| 83 |
-
|
|
| 84 |
-
|
|
| 85 |
-
|
|
| 86 |
-
|
|
| 87 |
-
|
|
| 88 |
-
|
|
| 89 |
-
|
|
| 90 |
-
|
|
| 91 |
-
|
|
| 92 |
-
|
|
| 93 |
-
|
|
| 94 |
-
|
|
| 95 |
-
|
|
| 96 |
-
|
|
| 97 |
-
|
|
| 98 |
-
|
|
| 99 |
-
|
|
| 100 |
-
|
|
| 101 |
-
|
|
| 102 |
-
|
|
| 103 |
-
|
|
| 104 |
-
|
|
| 105 |
-
|
|
| 106 |
-
|
|
| 107 |
-
|
|
| 108 |
-
|
|
| 109 |
-
|
|
| 110 |
-
|
|
| 111 |
-
|
|
| 112 |
-
|
|
| 113 |
-
|
|
| 114 |
-
|
|
| 115 |
-
|
|
| 116 |
-
|
|
|
|
|
| 117 |
|
| 118 |
|
| 119 |
### Framework versions
|
| 120 |
|
| 121 |
-
- Transformers 5.
|
| 122 |
-
- Pytorch 2.
|
| 123 |
- Datasets 3.6.0
|
| 124 |
- Tokenizers 0.22.2
|
|
|
|
| 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: 0.2044
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: cosine
|
| 44 |
- lr_scheduler_warmup_steps: 2000
|
| 45 |
+
- num_epochs: 1
|
|
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:------:|:-----:|:---------------:|
|
| 51 |
+
| 0.9934 | 0.0153 | 1000 | 0.3840 |
|
| 52 |
+
| 0.9974 | 0.0306 | 2000 | 0.4156 |
|
| 53 |
+
| 1.0350 | 0.0459 | 3000 | 0.3944 |
|
| 54 |
+
| 0.9922 | 0.0612 | 4000 | 0.3625 |
|
| 55 |
+
| 1.0129 | 0.0765 | 5000 | 0.3386 |
|
| 56 |
+
| 0.8650 | 0.0918 | 6000 | 0.3348 |
|
| 57 |
+
| 0.9696 | 0.1071 | 7000 | 0.3241 |
|
| 58 |
+
| 0.9879 | 0.1224 | 8000 | 0.3174 |
|
| 59 |
+
| 0.9225 | 0.1377 | 9000 | 0.3154 |
|
| 60 |
+
| 0.8560 | 0.1530 | 10000 | 0.3139 |
|
| 61 |
+
| 0.8554 | 0.1683 | 11000 | 0.3062 |
|
| 62 |
+
| 0.9126 | 0.1836 | 12000 | 0.3000 |
|
| 63 |
+
| 0.9142 | 0.1989 | 13000 | 0.2994 |
|
| 64 |
+
| 0.8358 | 0.2142 | 14000 | 0.2943 |
|
| 65 |
+
| 0.8452 | 0.2295 | 15000 | 0.2916 |
|
| 66 |
+
| 0.8372 | 0.2449 | 16000 | 0.2822 |
|
| 67 |
+
| 0.8776 | 0.2602 | 17000 | 0.2783 |
|
| 68 |
+
| 0.8697 | 0.2755 | 18000 | 0.2809 |
|
| 69 |
+
| 0.8541 | 0.2908 | 19000 | 0.2765 |
|
| 70 |
+
| 0.8511 | 0.3061 | 20000 | 0.2728 |
|
| 71 |
+
| 0.8440 | 0.3214 | 21000 | 0.2739 |
|
| 72 |
+
| 0.7897 | 0.3367 | 22000 | 0.2648 |
|
| 73 |
+
| 0.8196 | 0.3520 | 23000 | 0.2608 |
|
| 74 |
+
| 0.8320 | 0.3673 | 24000 | 0.2614 |
|
| 75 |
+
| 0.8043 | 0.3826 | 25000 | 0.2636 |
|
| 76 |
+
| 0.7875 | 0.3979 | 26000 | 0.2551 |
|
| 77 |
+
| 0.8257 | 0.4132 | 27000 | 0.2501 |
|
| 78 |
+
| 0.7276 | 0.4285 | 28000 | 0.2519 |
|
| 79 |
+
| 0.8196 | 0.4438 | 29000 | 0.2482 |
|
| 80 |
+
| 0.7727 | 0.4591 | 30000 | 0.2497 |
|
| 81 |
+
| 0.8316 | 0.4744 | 31000 | 0.2467 |
|
| 82 |
+
| 0.7738 | 0.4897 | 32000 | 0.2404 |
|
| 83 |
+
| 0.8146 | 0.5050 | 33000 | 0.2410 |
|
| 84 |
+
| 0.7571 | 0.5203 | 34000 | 0.2370 |
|
| 85 |
+
| 0.7921 | 0.5356 | 35000 | 0.2344 |
|
| 86 |
+
| 0.7792 | 0.5509 | 36000 | 0.2319 |
|
| 87 |
+
| 0.7014 | 0.5662 | 37000 | 0.2322 |
|
| 88 |
+
| 0.7425 | 0.5815 | 38000 | 0.2281 |
|
| 89 |
+
| 0.7644 | 0.5968 | 39000 | 0.2265 |
|
| 90 |
+
| 0.7048 | 0.6121 | 40000 | 0.2251 |
|
| 91 |
+
| 0.6970 | 0.6274 | 41000 | 0.2229 |
|
| 92 |
+
| 0.7856 | 0.6427 | 42000 | 0.2214 |
|
| 93 |
+
| 0.7114 | 0.6580 | 43000 | 0.2194 |
|
| 94 |
+
| 0.7751 | 0.6733 | 44000 | 0.2183 |
|
| 95 |
+
| 0.6482 | 0.6886 | 45000 | 0.2169 |
|
| 96 |
+
| 0.6889 | 0.7040 | 46000 | 0.2154 |
|
| 97 |
+
| 0.7554 | 0.7193 | 47000 | 0.2147 |
|
| 98 |
+
| 0.7050 | 0.7346 | 48000 | 0.2124 |
|
| 99 |
+
| 0.7927 | 0.7499 | 49000 | 0.2118 |
|
| 100 |
+
| 0.7309 | 0.7652 | 50000 | 0.2108 |
|
| 101 |
+
| 0.7264 | 0.7805 | 51000 | 0.2108 |
|
| 102 |
+
| 0.7256 | 0.7958 | 52000 | 0.2087 |
|
| 103 |
+
| 0.7605 | 0.8111 | 53000 | 0.2078 |
|
| 104 |
+
| 0.7391 | 0.8264 | 54000 | 0.2082 |
|
| 105 |
+
| 0.6781 | 0.8417 | 55000 | 0.2065 |
|
| 106 |
+
| 0.7206 | 0.8570 | 56000 | 0.2060 |
|
| 107 |
+
| 0.7342 | 0.8723 | 57000 | 0.2051 |
|
| 108 |
+
| 0.7519 | 0.8876 | 58000 | 0.2055 |
|
| 109 |
+
| 0.7258 | 0.9029 | 59000 | 0.2051 |
|
| 110 |
+
| 0.7932 | 0.9182 | 60000 | 0.2047 |
|
| 111 |
+
| 0.7391 | 0.9335 | 61000 | 0.2047 |
|
| 112 |
+
| 0.7416 | 0.9488 | 62000 | 0.2046 |
|
| 113 |
+
| 0.7249 | 0.9641 | 63000 | 0.2045 |
|
| 114 |
+
| 0.7000 | 0.9794 | 64000 | 0.2044 |
|
| 115 |
+
| 0.6958 | 0.9947 | 65000 | 0.2044 |
|
| 116 |
+
| 0.6692 | 1.0 | 65346 | 0.2044 |
|
| 117 |
|
| 118 |
|
| 119 |
### Framework versions
|
| 120 |
|
| 121 |
+
- Transformers 5.7.0
|
| 122 |
+
- Pytorch 2.8.0+cu128
|
| 123 |
- Datasets 3.6.0
|
| 124 |
- Tokenizers 0.22.2
|