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 [fahadqazi/testts1234](https://huggingface.co/fahadqazi/testts1234) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -34,50 +34,39 @@ More information needed
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate:
|
| 38 |
- train_batch_size: 64
|
| 39 |
-
- eval_batch_size:
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 42 |
-
- lr_scheduler_type:
|
| 43 |
-
-
|
| 44 |
-
- training_steps: 30000
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch
|
| 50 |
-
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.3568 | 80.7692 | 21000 | 0.3192 |
|
| 72 |
-
| 0.3558 | 84.6154 | 22000 | 0.3194 |
|
| 73 |
-
| 0.3553 | 88.4615 | 23000 | 0.3188 |
|
| 74 |
-
| 0.356 | 92.3077 | 24000 | 0.3184 |
|
| 75 |
-
| 0.3562 | 96.1538 | 25000 | 0.3184 |
|
| 76 |
-
| 0.3552 | 100.0 | 26000 | 0.3181 |
|
| 77 |
-
| 0.3521 | 103.8462 | 27000 | 0.3175 |
|
| 78 |
-
| 0.3542 | 107.6923 | 28000 | 0.3181 |
|
| 79 |
-
| 0.3569 | 111.5385 | 29000 | 0.3178 |
|
| 80 |
-
| 0.3539 | 115.3846 | 30000 | 0.3178 |
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [fahadqazi/testts1234](https://huggingface.co/fahadqazi/testts1234) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.3086
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
- train_batch_size: 64
|
| 39 |
+
- eval_batch_size: 64
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 42 |
+
- lr_scheduler_type: constant
|
| 43 |
+
- training_steps: 1000
|
|
|
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 50 |
+
| 0.3542 | 0.3401 | 50 | 0.3087 |
|
| 51 |
+
| 0.3558 | 0.6803 | 100 | 0.3088 |
|
| 52 |
+
| 0.3571 | 1.0204 | 150 | 0.3085 |
|
| 53 |
+
| 0.3578 | 1.3605 | 200 | 0.3090 |
|
| 54 |
+
| 0.3608 | 1.7007 | 250 | 0.3091 |
|
| 55 |
+
| 0.3508 | 2.0408 | 300 | 0.3090 |
|
| 56 |
+
| 0.3551 | 2.3810 | 350 | 0.3088 |
|
| 57 |
+
| 0.3553 | 2.7211 | 400 | 0.3096 |
|
| 58 |
+
| 0.3572 | 3.0612 | 450 | 0.3090 |
|
| 59 |
+
| 0.3517 | 3.4014 | 500 | 0.3096 |
|
| 60 |
+
| 0.3633 | 3.7415 | 550 | 0.3094 |
|
| 61 |
+
| 0.3612 | 4.0816 | 600 | 0.3093 |
|
| 62 |
+
| 0.3655 | 4.4218 | 650 | 0.3091 |
|
| 63 |
+
| 0.3619 | 4.7619 | 700 | 0.3090 |
|
| 64 |
+
| 0.3601 | 5.1020 | 750 | 0.3090 |
|
| 65 |
+
| 0.3557 | 5.4422 | 800 | 0.3092 |
|
| 66 |
+
| 0.3533 | 5.7823 | 850 | 0.3094 |
|
| 67 |
+
| 0.3531 | 6.1224 | 900 | 0.3091 |
|
| 68 |
+
| 0.3597 | 6.4626 | 950 | 0.3100 |
|
| 69 |
+
| 0.3559 | 6.8027 | 1000 | 0.3086 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|