irfanamal
/

distilbert_multiple_choice

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3839
-- Accuracy: 0.35
 ## Model description
@@ -37,30 +37,67 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 30
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 12   | 1.5968          | 0.45     |
-| No log        | 2.0   | 24   | 1.6002          | 0.4      |
-| No log        | 3.0   | 36   | 1.5491          | 0.5      |
-| No log        | 4.0   | 48   | 1.4812          | 0.5      |
-| No log        | 5.0   | 60   | 1.4929          | 0.55     |
-| No log        | 6.0   | 72   | 1.4072          | 0.6      |
-| No log        | 7.0   | 84   | 1.3880          | 0.5      |
-| No log        | 8.0   | 96   | 1.4828          | 0.5      |
-| No log        | 9.0   | 108  | 1.5161          | 0.6      |
-| No log        | 10.0  | 120  | 1.3911          | 0.4      |
-| No log        | 11.0  | 132  | 1.4533          | 0.35     |
-| No log        | 12.0  | 144  | 1.3839          | 0.35     |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.4354
+- Accuracy: 0.45
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 5e-06
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 50
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.6063        | 1.0   | 12   | 1.6079          | 0.4      |
+| 1.6038        | 2.0   | 24   | 1.6066          | 0.4      |
+| 1.6027        | 3.0   | 36   | 1.6045          | 0.35     |
+| 1.5909        | 4.0   | 48   | 1.6023          | 0.35     |
+| 1.5994        | 5.0   | 60   | 1.6000          | 0.35     |
+| 1.5947        | 6.0   | 72   | 1.5967          | 0.4      |
+| 1.5896        | 7.0   | 84   | 1.5932          | 0.4      |
+| 1.5862        | 8.0   | 96   | 1.5893          | 0.4      |
+| 1.5743        | 9.0   | 108  | 1.5846          | 0.35     |
+| 1.5579        | 10.0  | 120  | 1.5791          | 0.3      |
+| 1.558         | 11.0  | 132  | 1.5720          | 0.4      |
+| 1.5166        | 12.0  | 144  | 1.5640          | 0.35     |
+| 1.5053        | 13.0  | 156  | 1.5566          | 0.45     |
+| 1.4926        | 14.0  | 168  | 1.5483          | 0.45     |
+| 1.4577        | 15.0  | 180  | 1.5420          | 0.35     |
+| 1.4501        | 16.0  | 192  | 1.5342          | 0.35     |
+| 1.4348        | 17.0  | 204  | 1.5291          | 0.35     |
+| 1.3919        | 18.0  | 216  | 1.5234          | 0.35     |
+| 1.3671        | 19.0  | 228  | 1.5184          | 0.35     |
+| 1.3579        | 20.0  | 240  | 1.5130          | 0.4      |
+| 1.3319        | 21.0  | 252  | 1.5057          | 0.3      |
+| 1.3035        | 22.0  | 264  | 1.5005          | 0.35     |
+| 1.2822        | 23.0  | 276  | 1.4957          | 0.35     |
+| 1.2843        | 24.0  | 288  | 1.4913          | 0.4      |
+| 1.2554        | 25.0  | 300  | 1.4843          | 0.4      |
+| 1.2392        | 26.0  | 312  | 1.4783          | 0.4      |
+| 1.1955        | 27.0  | 324  | 1.4736          | 0.4      |
+| 1.1923        | 28.0  | 336  | 1.4714          | 0.4      |
+| 1.1681        | 29.0  | 348  | 1.4712          | 0.4      |
+| 1.1196        | 30.0  | 360  | 1.4671          | 0.4      |
+| 1.1386        | 31.0  | 372  | 1.4667          | 0.45     |
+| 1.1523        | 32.0  | 384  | 1.4619          | 0.4      |
+| 1.108         | 33.0  | 396  | 1.4591          | 0.45     |
+| 1.0866        | 34.0  | 408  | 1.4560          | 0.4      |
+| 1.1072        | 35.0  | 420  | 1.4525          | 0.4      |
+| 1.0432        | 36.0  | 432  | 1.4535          | 0.45     |
+| 1.0792        | 37.0  | 444  | 1.4467          | 0.45     |
+| 1.047         | 38.0  | 456  | 1.4447          | 0.45     |
+| 1.0416        | 39.0  | 468  | 1.4459          | 0.45     |
+| 1.0377        | 40.0  | 480  | 1.4470          | 0.45     |
+| 1.0075        | 41.0  | 492  | 1.4427          | 0.45     |
+| 1.0202        | 42.0  | 504  | 1.4410          | 0.45     |
+| 1.0331        | 43.0  | 516  | 1.4390          | 0.45     |
+| 1.0288        | 44.0  | 528  | 1.4361          | 0.45     |
+| 0.9867        | 45.0  | 540  | 1.4363          | 0.45     |
+| 0.9985        | 46.0  | 552  | 1.4370          | 0.45     |
+| 0.9887        | 47.0  | 564  | 1.4377          | 0.45     |
+| 1.0523        | 48.0  | 576  | 1.4365          | 0.45     |
+| 0.9999        | 49.0  | 588  | 1.4354          | 0.45     |
 ### Framework versions