End of training
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss:
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -34,26 +34,54 @@ More information needed
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate: 2e-
|
| 38 |
- train_batch_size: 1
|
| 39 |
- eval_batch_size: 1
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
|
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
-
| No log | 1.0 | 65 |
|
| 50 |
-
| No log | 2.0 | 130 |
|
| 51 |
-
| No log | 3.0 | 195 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.38.2
|
| 57 |
-
- Pytorch 2.2.
|
| 58 |
- Datasets 2.18.0
|
| 59 |
- Tokenizers 0.15.2
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: nan
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 2e-07
|
| 38 |
- train_batch_size: 1
|
| 39 |
- eval_batch_size: 1
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 30
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| No log | 1.0 | 65 | nan |
|
| 51 |
+
| No log | 2.0 | 130 | nan |
|
| 52 |
+
| No log | 3.0 | 195 | nan |
|
| 53 |
+
| No log | 4.0 | 260 | nan |
|
| 54 |
+
| No log | 5.0 | 325 | nan |
|
| 55 |
+
| No log | 6.0 | 390 | nan |
|
| 56 |
+
| No log | 7.0 | 455 | nan |
|
| 57 |
+
| 22.0508 | 8.0 | 520 | nan |
|
| 58 |
+
| 22.0508 | 9.0 | 585 | nan |
|
| 59 |
+
| 22.0508 | 10.0 | 650 | nan |
|
| 60 |
+
| 22.0508 | 11.0 | 715 | nan |
|
| 61 |
+
| 22.0508 | 12.0 | 780 | nan |
|
| 62 |
+
| 22.0508 | 13.0 | 845 | nan |
|
| 63 |
+
| 22.0508 | 14.0 | 910 | nan |
|
| 64 |
+
| 22.0508 | 15.0 | 975 | nan |
|
| 65 |
+
| 0.0 | 16.0 | 1040 | nan |
|
| 66 |
+
| 0.0 | 17.0 | 1105 | nan |
|
| 67 |
+
| 0.0 | 18.0 | 1170 | nan |
|
| 68 |
+
| 0.0 | 19.0 | 1235 | nan |
|
| 69 |
+
| 0.0 | 20.0 | 1300 | nan |
|
| 70 |
+
| 0.0 | 21.0 | 1365 | nan |
|
| 71 |
+
| 0.0 | 22.0 | 1430 | nan |
|
| 72 |
+
| 0.0 | 23.0 | 1495 | nan |
|
| 73 |
+
| 0.0 | 24.0 | 1560 | nan |
|
| 74 |
+
| 0.0 | 25.0 | 1625 | nan |
|
| 75 |
+
| 0.0 | 26.0 | 1690 | nan |
|
| 76 |
+
| 0.0 | 27.0 | 1755 | nan |
|
| 77 |
+
| 0.0 | 28.0 | 1820 | nan |
|
| 78 |
+
| 0.0 | 29.0 | 1885 | nan |
|
| 79 |
+
| 0.0 | 30.0 | 1950 | nan |
|
| 80 |
|
| 81 |
|
| 82 |
### Framework versions
|
| 83 |
|
| 84 |
- Transformers 4.38.2
|
| 85 |
+
- Pytorch 2.2.2+cu121
|
| 86 |
- Datasets 2.18.0
|
| 87 |
- Tokenizers 0.15.2
|