seven-wind-c
/

MC_proteome_literature_classification_balanced

Multiple Choice

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

seven-wind-c commited on Aug 11, 2023

Commit

e83d719

•

1 Parent(s): df0300e

update model card README.md

Files changed (1) hide show

README.md +8 -18

README.md CHANGED Viewed

@@ -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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6012
-- Accuracy: 0.4382
 ## Model description
@@ -43,27 +43,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 15
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 263  | 2.4798          | 0.2809   |
-| 2.4407        | 2.0   | 526  | 2.3829          | 0.3146   |
-| 2.4407        | 3.0   | 789  | 2.3702          | 0.3146   |
-| 2.2844        | 4.0   | 1052 | 2.2006          | 0.3034   |
-| 2.2844        | 5.0   | 1315 | 2.0415          | 0.3933   |
-| 2.2551        | 6.0   | 1578 | 2.1146          | 0.3708   |
-| 2.2551        | 7.0   | 1841 | 2.4420          | 0.4045   |
-| 1.7206        | 8.0   | 2104 | 2.4813          | 0.4045   |
-| 1.7206        | 9.0   | 2367 | 2.1333          | 0.4494   |
-| 1.2881        | 10.0  | 2630 | 2.8120          | 0.4382   |
-| 1.2881        | 11.0  | 2893 | 2.7040          | 0.4607   |
-| 0.9473        | 12.0  | 3156 | 3.1826          | 0.4382   |
-| 0.9473        | 13.0  | 3419 | 3.1203          | 0.4157   |
-| 0.5293        | 14.0  | 3682 | 3.4692          | 0.4270   |
-| 0.5293        | 15.0  | 3945 | 3.6012          | 0.4382   |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.9679
+- Accuracy: 0.4494
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 263  | 2.0873          | 0.3483   |
+| 1.9438        | 2.0   | 526  | 1.9461          | 0.4157   |
+| 1.9438        | 3.0   | 789  | 1.9642          | 0.4382   |
+| 1.5822        | 4.0   | 1052 | 3.0854          | 0.4270   |
+| 1.5822        | 5.0   | 1315 | 2.9679          | 0.4494   |
 ### Framework versions