End of training

README.md

@@ -7,19 +7,19 @@ metrics:
 tags:
 - generated_from_trainer
 model-index:
-- name: bert-dair-ai-emotion
+- name: bert-dair-ai-emotion-testing
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# bert-dair-ai-emotion
+# bert-dair-ai-emotion-testing
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1483
-- F1: 0.9320
+- Loss: 0.1414
+- F1: 0.9337
 
 ## Model description
 
@@ -42,20 +42,16 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 256
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 3
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | F1     |
-|:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.3127        | 0.9996 | 1302 | 0.2391          | 0.9128 |
-| 0.2249        | 1.9996 | 2604 | 0.1632          | 0.9301 |
-| 0.204         | 2.9996 | 3906 | 0.1483          | 0.9320 |
+| Training Loss | Epoch | Step  | Validation Loss | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.2988        | 1.0   | 20841 | 0.1414          | 0.9337 |
 
 
 ### Framework versions