End of training

README.md

@@ -2,12 +2,12 @@
 language:
 - ko
 license: apache-2.0
+base_model: openai/whisper-base
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
 datasets:
 - hyojin99/EBRC
-base_model: openai/whisper-base
 model-index:
 - name: ft_model
   results: []
@@ -20,8 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the EBRC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1886
-- Cer: 10.6428
+- eval_loss: 0.1907
+- eval_cer: 10.7153
+- eval_runtime: 1285.9622
+- eval_samples_per_second: 3.888
+- eval_steps_per_second: 0.486
+- step: 0
 
 ## Model description
 
@@ -50,18 +54,6 @@ The following hyperparameters were used during training:
 - training_steps: 6000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Cer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.3649        | 0.4   | 1000 | 0.3399          | 18.5291 |
-| 0.2559        | 0.8   | 2000 | 0.2578          | 14.4563 |
-| 0.1746        | 1.2   | 3000 | 0.2247          | 13.3580 |
-| 0.1639        | 1.6   | 4000 | 0.2017          | 11.5004 |
-| 0.1251        | 2.0   | 5000 | 0.1909          | 10.8103 |
-| 0.1051        | 2.4   | 6000 | 0.1886          | 10.6428 |
-
-
 ### Framework versions
 
 - Transformers 4.39.0.dev0

runs/Mar12_22-35-36_0764078b8668/events.out.tfevents.1710307806.0764078b8668.2736.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa01be76a0a91737bcb9b3c10ba8eb00d667157f3206a5c1e9f7e0386f59465
+size 341