update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,15 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
-
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
-
|
| 21 |
-
- eval_runtime: 4.1041
|
| 22 |
-
- eval_samples_per_second: 43.372
|
| 23 |
-
- eval_steps_per_second: 2.924
|
| 24 |
-
- epoch: 5.0
|
| 25 |
-
- step: 500
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -47,12 +42,28 @@ The following hyperparameters were used during training:
|
|
| 47 |
- seed: 42
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
-
- num_epochs:
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
-
- Transformers 4.12.
|
| 56 |
- Pytorch 1.9.0+cu111
|
| 57 |
-
- Datasets 1.
|
| 58 |
- Tokenizers 0.10.3
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.6131
|
| 18 |
+
- Rouge2 Precision: 0.3
|
| 19 |
+
- Rouge2 Recall: 0.2152
|
| 20 |
+
- Rouge2 Fmeasure: 0.2379
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 10
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
| 52 |
+
| 2.1335 | 1.0 | 563 | 1.7632 | 0.2716 | 0.1936 | 0.2135 |
|
| 53 |
+
| 1.9373 | 2.0 | 1126 | 1.7037 | 0.2839 | 0.2068 | 0.2265 |
|
| 54 |
+
| 1.8827 | 3.0 | 1689 | 1.6723 | 0.2901 | 0.2118 | 0.2316 |
|
| 55 |
+
| 1.8257 | 4.0 | 2252 | 1.6503 | 0.2938 | 0.2115 | 0.2332 |
|
| 56 |
+
| 1.8152 | 5.0 | 2815 | 1.6386 | 0.2962 | 0.2139 | 0.2357 |
|
| 57 |
+
| 1.7939 | 6.0 | 3378 | 1.6284 | 0.2976 | 0.212 | 0.2354 |
|
| 58 |
+
| 1.7845 | 7.0 | 3941 | 1.6211 | 0.2991 | 0.2155 | 0.2383 |
|
| 59 |
+
| 1.7468 | 8.0 | 4504 | 1.6167 | 0.2994 | 0.217 | 0.239 |
|
| 60 |
+
| 1.7464 | 9.0 | 5067 | 1.6137 | 0.3007 | 0.2154 | 0.2382 |
|
| 61 |
+
| 1.744 | 10.0 | 5630 | 1.6131 | 0.3 | 0.2152 | 0.2379 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
### Framework versions
|
| 65 |
|
| 66 |
+
- Transformers 4.12.3
|
| 67 |
- Pytorch 1.9.0+cu111
|
| 68 |
+
- Datasets 1.15.1
|
| 69 |
- Tokenizers 0.10.3
|