Training complete

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1111
-- Precision: 0.8031
-- Recall: 0.7991
-- F1: 0.8011
-- Accuracy: 0.9748
+- Loss: 0.0676
+- Precision: 0.8088
+- Recall: 0.8196
+- F1: 0.8142
+- Accuracy: 0.9796
 
 ## Model description
 
@@ -44,32 +44,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 5
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 0.9970 | 252  | 0.0965          | 0.7524    | 0.7852 | 0.7684 | 0.9711   |
-| 0.1751        | 1.9980 | 505  | 0.0858          | 0.7924    | 0.7861 | 0.7892 | 0.9747   |
-| 0.1751        | 2.9990 | 758  | 0.0870          | 0.7932    | 0.7944 | 0.7938 | 0.9746   |
-| 0.0409        | 4.0    | 1011 | 0.0970          | 0.8050    | 0.8026 | 0.8038 | 0.9749   |
-| 0.0409        | 4.9852 | 1260 | 0.1111          | 0.8031    | 0.7991 | 0.8011 | 0.9748   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 231  | 0.0876          | 0.7650    | 0.7897 | 0.7771 | 0.9734   |
+| No log        | 2.0   | 462  | 0.0676          | 0.8088    | 0.8196 | 0.8142 | 0.9796   |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
-- Pytorch 2.4.0+cu121
+- Pytorch 2.4.1+cu121
 - Datasets 2.21.0
 - Tokenizers 0.19.1

runs/Sep05_12-03-33_83295d15965e/events.out.tfevents.1725537813.83295d15965e.5325.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77ce49944d3c6fb55094d16109bdb61a00e7f336c2980d02c4d123053a02684
-size 6170
+oid sha256:3ffb8c34ee62453d9dc3b26ff9bb1fb2979c64f41a63f017301349d1cdf866cf
+size 6996