End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3341
-- Accuracy: 0.9066
+- Loss: 1.0061
+- Accuracy: 0.7605
 
 ## Model description
 
@@ -38,21 +38,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 256
+- eval_batch_size: 256
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
-- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.3319        | 1.0   | 8584  | 0.2900          | 0.8934   |
-| 0.2389        | 2.0   | 17168 | 0.2888          | 0.9007   |
-| 0.1374        | 3.0   | 25752 | 0.3341          | 0.9066   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3323        | 1.0   | 2146 | 0.2873          | 0.8940   |
+| 0.2398        | 2.0   | 4292 | 0.2693          | 0.9048   |
+| 0.1543        | 3.0   | 6438 | 0.3082          | 0.9062   |
 
 
 ### Framework versions

runs/Jan24_18-40-19_gl1526.arc-ts.umich.edu/events.out.tfevents.1706145419.gl1526.arc-ts.umich.edu.1086638.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e5e4971c82f5c5de3445e3ae185b205441704f6222d44beb030eda8077543a
+size 1380