Commit ·
ea82e08
1
Parent(s): bd7db4a
update model card README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss:
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -39,23 +39,41 @@ The following hyperparameters were used during training:
|
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- lr_scheduler_warmup_steps: 100
|
| 42 |
-
- num_epochs:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
-
|
|
| 49 |
-
| 2.
|
| 50 |
-
|
|
| 51 |
-
| 1.
|
| 52 |
-
| 1.
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.5681
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- lr_scheduler_warmup_steps: 100
|
| 42 |
+
- num_epochs: 10
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 2.533 | 0.34 | 200 | 2.4607 |
|
| 49 |
+
| 2.1012 | 0.68 | 400 | 1.9922 |
|
| 50 |
+
| 1.6059 | 1.02 | 600 | 1.7986 |
|
| 51 |
+
| 1.4557 | 1.36 | 800 | 1.6130 |
|
| 52 |
+
| 1.4268 | 1.7 | 1000 | 1.4073 |
|
| 53 |
+
| 0.8588 | 2.04 | 1200 | 1.2657 |
|
| 54 |
+
| 0.8191 | 2.38 | 1400 | 1.1214 |
|
| 55 |
+
| 0.81 | 2.72 | 1600 | 1.0418 |
|
| 56 |
+
| 0.5546 | 3.06 | 1800 | 0.9735 |
|
| 57 |
+
| 0.4905 | 3.4 | 2000 | 0.9006 |
|
| 58 |
+
| 0.5209 | 3.74 | 2200 | 0.8762 |
|
| 59 |
+
| 0.3127 | 4.08 | 2400 | 0.8457 |
|
| 60 |
+
| 0.3145 | 4.42 | 2600 | 0.7886 |
|
| 61 |
+
| 0.3265 | 4.76 | 2800 | 0.7853 |
|
| 62 |
+
| 0.2215 | 5.1 | 3000 | 0.7309 |
|
| 63 |
+
| 0.2351 | 5.44 | 3200 | 0.7082 |
|
| 64 |
+
| 0.2332 | 5.78 | 3400 | 0.6770 |
|
| 65 |
+
| 0.1793 | 6.12 | 3600 | 0.6856 |
|
| 66 |
+
| 0.1617 | 6.46 | 3800 | 0.6470 |
|
| 67 |
+
| 0.1468 | 6.8 | 4000 | 0.6700 |
|
| 68 |
+
| 0.1293 | 7.14 | 4200 | 0.6460 |
|
| 69 |
+
| 0.1257 | 7.48 | 4400 | 0.6415 |
|
| 70 |
+
| 0.0975 | 7.82 | 4600 | 0.6454 |
|
| 71 |
+
| 0.0835 | 8.16 | 4800 | 0.6111 |
|
| 72 |
+
| 0.0856 | 8.5 | 5000 | 0.6124 |
|
| 73 |
+
| 0.0887 | 8.84 | 5200 | 0.5956 |
|
| 74 |
+
| 0.069 | 9.18 | 5400 | 0.5877 |
|
| 75 |
+
| 0.0625 | 9.52 | 5600 | 0.5798 |
|
| 76 |
+
| 0.0599 | 9.86 | 5800 | 0.5681 |
|
| 77 |
|
| 78 |
|
| 79 |
### Framework versions
|