Model save

README.md

@@ -3,11 +3,6 @@ license: apache-2.0
 base_model: asapp/sew-d-tiny-100k-ft-ls100h
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
-- precision
-- recall
-- f1
 model-index:
 - name: sewd_classifier
   results: []
@@ -19,13 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
 # sewd_classifier
 
 This model is a fine-tuned version of [asapp/sew-d-tiny-100k-ft-ls100h](https://huggingface.co/asapp/sew-d-tiny-100k-ft-ls100h) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 4.4387
-- Accuracy: 0.0128
-- Precision: 0.0002
-- Recall: 0.0128
-- F1: 0.0003
-- Binary: 0.1156
 
 ## Model description
 
@@ -44,26 +32,17 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
+- learning_rate: 1e-05
+- train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Binary |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
-| 4.4296        | 1.0   | 876  | 4.4357          | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1156 |
-| 4.427         | 2.0   | 1752 | 4.4385          | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1156 |
-| 4.4257        | 3.0   | 2628 | 4.4387          | 0.0128   | 0.0002    | 0.0128 | 0.0003 | 0.1156 |
-
-
 ### Framework versions
 
 - Transformers 4.38.2

runs/Jun12_22-16-29_LAPTOP-1GID9RGH/events.out.tfevents.1718205390.LAPTOP-1GID9RGH.11548.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c0a6ea9393e050c0af673829f19f1d7e241e69fd69b75b1ee86dc095ad80674
-size 37351
+oid sha256:6d63469f433acb4a198fa549f7dea085612f68980d90cbbf6daf523f59932802
+size 38438