End of training
Browse files- README.md +6 -33
- pytorch_model.bin +1 -1
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 [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss:
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -36,46 +36,19 @@ More information needed
|
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0001
|
| 38 |
- train_batch_size: 24
|
| 39 |
-
- eval_batch_size:
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
-
| No log | 1.0 | 5 | 2.
|
| 50 |
-
| No log | 2.0 | 10 | 2.
|
| 51 |
-
| No log | 3.0 | 15 | 1.
|
| 52 |
-
| No log | 4.0 | 20 | 1.2522 |
|
| 53 |
-
| No log | 5.0 | 25 | 0.6961 |
|
| 54 |
-
| No log | 6.0 | 30 | 0.2864 |
|
| 55 |
-
| No log | 7.0 | 35 | 0.1121 |
|
| 56 |
-
| No log | 8.0 | 40 | 0.0688 |
|
| 57 |
-
| No log | 9.0 | 45 | 0.0579 |
|
| 58 |
-
| No log | 10.0 | 50 | 0.0459 |
|
| 59 |
-
| No log | 11.0 | 55 | 0.0411 |
|
| 60 |
-
| No log | 12.0 | 60 | 0.0382 |
|
| 61 |
-
| No log | 13.0 | 65 | 0.0345 |
|
| 62 |
-
| No log | 14.0 | 70 | 0.0289 |
|
| 63 |
-
| No log | 15.0 | 75 | 0.0228 |
|
| 64 |
-
| No log | 16.0 | 80 | 0.0175 |
|
| 65 |
-
| No log | 17.0 | 85 | 0.0134 |
|
| 66 |
-
| No log | 18.0 | 90 | 0.0130 |
|
| 67 |
-
| No log | 19.0 | 95 | 0.0130 |
|
| 68 |
-
| No log | 20.0 | 100 | 0.0104 |
|
| 69 |
-
| No log | 21.0 | 105 | 0.0096 |
|
| 70 |
-
| No log | 22.0 | 110 | 0.0084 |
|
| 71 |
-
| No log | 23.0 | 115 | 0.0075 |
|
| 72 |
-
| No log | 24.0 | 120 | 0.0065 |
|
| 73 |
-
| No log | 25.0 | 125 | 0.0067 |
|
| 74 |
-
| No log | 26.0 | 130 | 0.0068 |
|
| 75 |
-
| No log | 27.0 | 135 | 0.0069 |
|
| 76 |
-
| No log | 28.0 | 140 | 0.0066 |
|
| 77 |
-
| No log | 29.0 | 145 | 0.0066 |
|
| 78 |
-
| No log | 30.0 | 150 | 0.0064 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.8117
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0001
|
| 38 |
- train_batch_size: 24
|
| 39 |
+
- eval_batch_size: 24
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 3.0
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| No log | 1.0 | 5 | 2.8891 |
|
| 50 |
+
| No log | 2.0 | 10 | 2.1063 |
|
| 51 |
+
| No log | 3.0 | 15 | 1.8117 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442691445
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:527a65cc77aba1f84a6d4cd70f4c40a4c005c10e2acf77be4dd3b9d5067a07ba
|
| 3 |
size 442691445
|