End of training
Browse files
README.md
CHANGED
|
@@ -16,12 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 137.251
|
| 21 |
-
- eval_samples_per_second: 43.643
|
| 22 |
-
- eval_steps_per_second: 2.732
|
| 23 |
-
- epoch: 0.03
|
| 24 |
-
- step: 75
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -51,6 +46,22 @@ The following hyperparameters were used during training:
|
|
| 51 |
- lr_scheduler_warmup_steps: 1
|
| 52 |
- training_steps: 250
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- PEFT 0.8.2
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1808
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 46 |
- lr_scheduler_warmup_steps: 1
|
| 47 |
- training_steps: 250
|
| 48 |
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 6.3144 | 0.01 | 25 | 1.5334 |
|
| 54 |
+
| 1.2668 | 0.02 | 50 | 0.6688 |
|
| 55 |
+
| 1.021 | 0.03 | 75 | 0.3675 |
|
| 56 |
+
| 0.5247 | 0.03 | 100 | 0.3007 |
|
| 57 |
+
| 0.6415 | 0.04 | 125 | 0.2400 |
|
| 58 |
+
| 0.3774 | 0.05 | 150 | 0.2170 |
|
| 59 |
+
| 0.5336 | 0.06 | 175 | 0.1966 |
|
| 60 |
+
| 0.3201 | 0.07 | 200 | 0.1882 |
|
| 61 |
+
| 0.5068 | 0.08 | 225 | 0.1824 |
|
| 62 |
+
| 0.3218 | 0.08 | 250 | 0.1808 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
- PEFT 0.8.2
|