pilotj/bert-base-uncased-fibe-final

README.md

@@ -1,26 +1,26 @@
 ---
-base_model: biggy-smiley/bert-base-uncased-fibe-v2
 library_name: transformers
+base_model: pilotj/bert-base-uncased-fibe-v3
 tags:
 - generated_from_trainer
 model-index:
-- name: bert-base-uncased-fibe-v3
+- name: bert-base-uncased-fibe-final
   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-base-uncased-fibe-v3
+# bert-base-uncased-fibe-final
 
-This model is a fine-tuned version of [biggy-smiley/bert-base-uncased-fibe-v2](https://huggingface.co/biggy-smiley/bert-base-uncased-fibe-v2) on the None dataset.
+This model is a fine-tuned version of [pilotj/bert-base-uncased-fibe-v3](https://huggingface.co/pilotj/bert-base-uncased-fibe-v3) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4755
-- eval_runtime: 40.9898
-- eval_samples_per_second: 253.722
-- eval_steps_per_second: 3.977
-- epoch: 1.0311
-- step: 15500
+- eval_loss: 0.3655
+- eval_runtime: 111.3303
+- eval_samples_per_second: 234.896
+- eval_steps_per_second: 3.674
+- epoch: 1.0030
+- step: 10500
 
 ## Model description
 
@@ -40,12 +40,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
+- train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Framework versions