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 [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -41,21 +41,40 @@ The following hyperparameters were used during training:
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_steps: 10
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
-
| Training Loss | Epoch | Step
|
| 49 |
-
|
| 50 |
-
| 0.
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.2142
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_steps: 10
|
| 44 |
+
- num_epochs: 3
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 0.6235 | 0.11 | 500 | 0.5410 |
|
| 51 |
+
| 0.4635 | 0.21 | 1000 | 0.4417 |
|
| 52 |
+
| 0.4507 | 0.32 | 1500 | 0.3773 |
|
| 53 |
+
| 0.4462 | 0.43 | 2000 | 0.3337 |
|
| 54 |
+
| 0.3643 | 0.54 | 2500 | 0.3198 |
|
| 55 |
+
| 0.3213 | 0.64 | 3000 | 0.2976 |
|
| 56 |
+
| 0.3098 | 0.75 | 3500 | 0.2889 |
|
| 57 |
+
| 0.3236 | 0.86 | 4000 | 0.2682 |
|
| 58 |
+
| 0.3267 | 0.96 | 4500 | 0.2589 |
|
| 59 |
+
| 0.2307 | 1.07 | 5000 | 0.2618 |
|
| 60 |
+
| 0.2242 | 1.18 | 5500 | 0.2537 |
|
| 61 |
+
| 0.2231 | 1.28 | 6000 | 0.2519 |
|
| 62 |
+
| 0.2095 | 1.39 | 6500 | 0.2453 |
|
| 63 |
+
| 0.2247 | 1.5 | 7000 | 0.2386 |
|
| 64 |
+
| 0.2149 | 1.61 | 7500 | 0.2376 |
|
| 65 |
+
| 0.1928 | 1.71 | 8000 | 0.2354 |
|
| 66 |
+
| 0.2517 | 1.82 | 8500 | 0.2277 |
|
| 67 |
+
| 0.212 | 1.93 | 9000 | 0.2253 |
|
| 68 |
+
| 0.176 | 2.03 | 9500 | 0.2255 |
|
| 69 |
+
| 0.1613 | 2.14 | 10000 | 0.2263 |
|
| 70 |
+
| 0.1639 | 2.25 | 10500 | 0.2239 |
|
| 71 |
+
| 0.1575 | 2.35 | 11000 | 0.2206 |
|
| 72 |
+
| 0.1497 | 2.46 | 11500 | 0.2193 |
|
| 73 |
+
| 0.1645 | 2.57 | 12000 | 0.2165 |
|
| 74 |
+
| 0.18 | 2.68 | 12500 | 0.2158 |
|
| 75 |
+
| 0.1328 | 2.78 | 13000 | 0.2171 |
|
| 76 |
+
| 0.1525 | 2.89 | 13500 | 0.2150 |
|
| 77 |
+
| 0.154 | 3.0 | 14000 | 0.2142 |
|
| 78 |
|
| 79 |
|
| 80 |
### Framework versions
|