End of training

README.md

@@ -1,12 +1,6 @@
 ---
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
-- precision
-- recall
-- f1
-base_model: duraad/nep-spell-hft
 model-index:
 - name: nep-spell-hft
   results: []
@@ -17,13 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # nep-spell-hft
 
-This model is a fine-tuned version of [duraad/nep-spell-hft](https://huggingface.co/duraad/nep-spell-hft) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0066
-- Accuracy: 0.4528
-- Precision: 0.4606
-- Recall: 0.4528
-- F1: 0.4554
+This model was trained from scratch on the None dataset.
 
 ## Model description
 
@@ -49,16 +37,7 @@ 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_steps: 500
-- num_epochs: 2
-
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.0112        | 0.63  | 8000  | 0.0071          | 0.4159   | 0.4228    | 0.4159 | 0.4182 |
-| 0.0106        | 1.27  | 16000 | 0.0068          | 0.4401   | 0.4477    | 0.4401 | 0.4426 |
-| 0.0094        | 1.9   | 24000 | 0.0066          | 0.4528   | 0.4606    | 0.4528 | 0.4554 |
-
+- num_epochs: 1
 
 ### Framework versions
 

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c55e3399602b93c4ba608798a65f62e367a8d7bc1a83bdefd9ed7b7a6a55170
+oid sha256:d8c42a25c0ab7329e7bf9d22e672fd00c9d713c87830dea4cb5fadc71443e821
 size 4219