kimsiun
/

ec_classfication

Text Classification

Transformers

PyTorch

distilbert

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

kimsiun commited on Apr 28, 2023

Commit

ab9b88a

1 Parent(s): 256dfd1

update model card README.md

Browse files

Files changed (1) hide show

README.md +19 -19

README.md CHANGED Viewed

@@ -16,8 +16,8 @@ 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: 0.7927
-- F1: 0.7727
 ## Model description
@@ -37,8 +37,8 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-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
@@ -48,21 +48,21 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 61   | 0.6210          | 0.4068 |
-| No log        | 2.0   | 122  | 0.4597          | 0.8261 |
-| No log        | 3.0   | 183  | 0.4635          | 0.7917 |
-| No log        | 4.0   | 244  | 0.5446          | 0.7342 |
-| No log        | 5.0   | 305  | 0.5366          | 0.8000 |
-| No log        | 6.0   | 366  | 0.6233          | 0.7789 |
-| No log        | 7.0   | 427  | 0.6171          | 0.7955 |
-| No log        | 8.0   | 488  | 0.6582          | 0.7955 |
-| 0.2985        | 9.0   | 549  | 0.7222          | 0.7816 |
-| 0.2985        | 10.0  | 610  | 0.7377          | 0.7865 |
-| 0.2985        | 11.0  | 671  | 0.7467          | 0.7727 |
-| 0.2985        | 12.0  | 732  | 0.7914          | 0.7826 |
-| 0.2985        | 13.0  | 793  | 0.7886          | 0.7727 |
-| 0.2985        | 14.0  | 854  | 0.7914          | 0.7727 |
-| 0.2985        | 15.0  | 915  | 0.7927          | 0.7727 |
 ### 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: 0.6543
+- F1: 0.7609
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 1.0   | 31   | 0.6418          | 0.4262 |
+| No log        | 2.0   | 62   | 0.4992          | 0.7342 |
+| No log        | 3.0   | 93   | 0.4732          | 0.7879 |
+| No log        | 4.0   | 124  | 0.4817          | 0.7089 |
+| No log        | 5.0   | 155  | 0.4872          | 0.7742 |
+| No log        | 6.0   | 186  | 0.5026          | 0.7872 |
+| No log        | 7.0   | 217  | 0.5202          | 0.7778 |
+| No log        | 8.0   | 248  | 0.5280          | 0.7711 |
+| No log        | 9.0   | 279  | 0.5629          | 0.75   |
+| No log        | 10.0  | 310  | 0.6319          | 0.7872 |
+| No log        | 11.0  | 341  | 0.6363          | 0.7872 |
+| No log        | 12.0  | 372  | 0.6850          | 0.7708 |
+| No log        | 13.0  | 403  | 0.6702          | 0.7872 |
+| No log        | 14.0  | 434  | 0.6495          | 0.7692 |
+| No log        | 15.0  | 465  | 0.6543          | 0.7609 |
 ### Framework versions