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: 0.2473
-- Cer: 14.4430
+- eval_loss: 0.2518
+- eval_cer: 16.5091
+- eval_runtime: 1356.705
+- eval_samples_per_second: 3.685
+- eval_steps_per_second: 0.461
+- step: 0
 
 ## Model description
 
@@ -50,16 +54,6 @@ The following hyperparameters were used during training:
 - training_steps: 4000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Cer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.3544        | 0.8   | 1000 | 0.3489          | 26.3543 |
-| 0.248         | 1.6   | 2000 | 0.2792          | 19.9000 |
-| 0.1376        | 2.4   | 3000 | 0.2565          | 16.0652 |
-| 0.0896        | 3.2   | 4000 | 0.2473          | 14.4430 |
-
-
 ### Framework versions
 
 - Transformers 4.39.0.dev0

runs/Mar08_15-03-07_edf86bff0885/events.out.tfevents.1709927268.edf86bff0885.2330.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b90cb173628a81ebff3d7c01ab7527edb8c5ddca62153195ddffd87048e46fd
+size 341