katsuchi/bert-dair-ai-emotion-testing

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.1414
-- F1: 0.9337
+- Loss: 0.0969
+- F1: 0.9388
 
 ## Model description
 
@@ -45,13 +45,15 @@ The following hyperparameters were used during training:
 - 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: 500
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | F1     |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|
-| 0.2988        | 1.0   | 20841 | 0.1414          | 0.9337 |
+| 0.2591        | 1.0   | 20841 | 0.1267          | 0.9389 |
+| 0.1394        | 2.0   | 41682 | 0.1041          | 0.9383 |
+| 0.0932        | 3.0   | 62523 | 0.0969          | 0.9388 |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1a61d08a2752ac039eda26198b947c50fba33c6a557bbccfab6233e0a7bd2b
+oid sha256:160faf08b93ce6d385bfb423188fd697a1c252931bdb01e07b3991ab6aa91f35
 size 2384720