pilotj/distil-bert-tweaking

README.md

@@ -1,26 +1,21 @@
 ---
-base_model: pilotj/distilbert-base-uncased-fibe-full-finetuned
 library_name: transformers
+base_model: pilotj/distilbert-base-uncased-fibe-full-finetuned
 tags:
 - generated_from_trainer
 model-index:
-- name: distil-bert-final-version
+- name: distil-bert-tweaking
   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. -->
 
-# distil-bert-final-version
+# distil-bert-tweaking
 
 This model is a fine-tuned version of [pilotj/distilbert-base-uncased-fibe-full-finetuned](https://huggingface.co/pilotj/distilbert-base-uncased-fibe-full-finetuned) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4621
-- eval_runtime: 244.5245
-- eval_samples_per_second: 106.946
-- eval_steps_per_second: 0.838
-- epoch: 0.4331
-- step: 9000
+- Loss: 0.4871
 
 ## Model description
 
@@ -46,7 +41,23 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.5
-- num_epochs: 1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3542        | 0.1905 | 500  | 0.4708          |
+| 0.418         | 0.3810 | 1000 | 0.4670          |
+| 0.4303        | 0.5714 | 1500 | 0.4833          |
+| 0.4404        | 0.7619 | 2000 | 0.5177          |
+| 0.4589        | 0.9524 | 2500 | 0.5050          |
+| 0.3911        | 1.1429 | 3000 | 0.5887          |
+| 0.3654        | 1.3333 | 3500 | 0.5227          |
+| 0.3415        | 1.5238 | 4000 | 0.5158          |
+| 0.3284        | 1.7143 | 4500 | 0.5228          |
+| 0.3178        | 1.9048 | 5000 | 0.4871          |
+
 
 ### Framework versions