Model save
Browse files
README.md
CHANGED
|
@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -46,29 +46,33 @@ The following hyperparameters were used during training:
|
|
| 46 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
-
- num_epochs:
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch | Step
|
| 54 |
-
|
| 55 |
-
| 5.9062 | 0.2806 | 500
|
| 56 |
-
| 4.8598 | 0.5612 | 1000
|
| 57 |
-
| 4.3025 | 0.8418 | 1500
|
| 58 |
-
| 3.9635 | 1.1223 | 2000
|
| 59 |
-
| 3.7769 | 1.4029 | 2500
|
| 60 |
-
| 3.6738 | 1.6835 | 3000
|
| 61 |
-
| 3.5744 | 1.9641 | 3500
|
| 62 |
-
| 3.456 | 2.2447 | 4000
|
| 63 |
-
| 3.3972 | 2.5253 | 4500
|
| 64 |
-
| 3.3654 | 2.8058 | 5000
|
| 65 |
-
| 3.247 | 3.0864 | 5500
|
| 66 |
-
| 3.2403 | 3.3670 | 6000
|
| 67 |
-
| 3.2167 | 3.6476 | 6500
|
| 68 |
-
| 3.1903 | 3.9282 | 7000
|
| 69 |
-
| 3.1212 | 4.2088 | 7500
|
| 70 |
-
| 3.0816 | 4.4893 | 8000
|
| 71 |
-
| 3.0917 | 4.7699 | 8500
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 3.1790
|
| 21 |
+
- Accuracy: 0.4217
|
| 22 |
+
- Perplexity: 24.0231
|
| 23 |
+
- Bleu: 0.1309
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 46 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 6
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Accuracy | Bleu | Validation Loss | Perplexity |
|
| 54 |
+
|:-------------:|:------:|:-----:|:--------:|:------:|:---------------:|:----------:|
|
| 55 |
+
| 5.9062 | 0.2806 | 500 | 0.2234 | 0.0493 | 5.7470 | 313.2463 |
|
| 56 |
+
| 4.8598 | 0.5612 | 1000 | 0.2811 | 0.0698 | 4.7428 | 114.7554 |
|
| 57 |
+
| 4.3025 | 0.8418 | 1500 | 0.3170 | 0.0834 | 4.2329 | 68.9191 |
|
| 58 |
+
| 3.9635 | 1.1223 | 2000 | 0.3454 | 0.0932 | 3.9291 | 50.8590 |
|
| 59 |
+
| 3.7769 | 1.4029 | 2500 | 0.3636 | 0.1020 | 3.7427 | 42.2098 |
|
| 60 |
+
| 3.6738 | 1.6835 | 3000 | 0.3754 | 0.1066 | 3.6225 | 37.4295 |
|
| 61 |
+
| 3.5744 | 1.9641 | 3500 | 0.3845 | 0.1118 | 3.5325 | 34.2102 |
|
| 62 |
+
| 3.456 | 2.2447 | 4000 | 0.3902 | 0.1139 | 3.4704 | 32.1497 |
|
| 63 |
+
| 3.3972 | 2.5253 | 4500 | 0.3955 | 0.1230 | 3.4190 | 30.5384 |
|
| 64 |
+
| 3.3654 | 2.8058 | 5000 | 0.4007 | 0.1230 | 3.3686 | 29.0392 |
|
| 65 |
+
| 3.247 | 3.0864 | 5500 | 0.4043 | 0.1247 | 3.3328 | 28.0168 |
|
| 66 |
+
| 3.2403 | 3.3670 | 6000 | 0.4083 | 0.1298 | 3.2985 | 27.0714 |
|
| 67 |
+
| 3.2167 | 3.6476 | 6500 | 0.4112 | 0.1288 | 3.2693 | 26.2922 |
|
| 68 |
+
| 3.1903 | 3.9282 | 7000 | 0.4134 | 0.1305 | 3.2456 | 25.6768 |
|
| 69 |
+
| 3.1212 | 4.2088 | 7500 | 0.4161 | 0.1325 | 3.2262 | 25.1831 |
|
| 70 |
+
| 3.0816 | 4.4893 | 8000 | 0.4176 | 0.1307 | 3.2128 | 24.8480 |
|
| 71 |
+
| 3.0917 | 4.7699 | 8500 | 0.4196 | 0.1339 | 3.1985 | 24.4954 |
|
| 72 |
+
| 3.0562 | 5.0505 | 9000 | 3.2049 | 0.4185 | 24.6521 | 0.1326 |
|
| 73 |
+
| 3.0683 | 5.3311 | 9500 | 3.1970 | 0.4195 | 24.4597 | 0.1307 |
|
| 74 |
+
| 3.0502 | 5.6117 | 10000 | 3.1857 | 0.4209 | 24.1847 | 0.1331 |
|
| 75 |
+
| 3.0469 | 5.8923 | 10500 | 3.1790 | 0.4217 | 24.0231 | 0.1309 |
|
| 76 |
|
| 77 |
|
| 78 |
### Framework versions
|