End of training

README.md

@@ -20,8 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the jsfamily/test-small-komodel dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4073
-- Cer: 14.5602
+- eval_loss: 0.7197
+- eval_cer: 13.8258
+- eval_runtime: 73.4069
+- eval_samples_per_second: 2.738
+- eval_steps_per_second: 0.354
+- step: 0
 
 ## Model description
 
@@ -50,13 +54,6 @@ The following hyperparameters were used during training:
 - num_epochs: 3.0
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Cer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0063        | 1.98  | 200  | 0.4073          | 14.5602 |
-
-
 ### Framework versions
 
 - Transformers 4.39.0.dev0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3901a6163881ca0a62e2638279c6a72d70c41b053f3929b7f488ff0ea5b95415
+oid sha256:1824cdf25ca0a2ad9c4d96426071718afb59615aeb443861ccbd450e9a65f630
 size 966995080

runs/May09_10-54-51_dockervm2/events.out.tfevents.1715219765.dockervm2.15799.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b521132b7cdd00c5650c4c25dedd71c7a26113fd13b418273984f78fda00b2
+size 341

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e64e0b5ac55dadfc5777b352e8b1c3613bbd90295dca9a1b032a8b507e6db27
+oid sha256:c587b35479c150726bab4e4a64ff8efc0a702c2de8eed6751479129a3052cb45
 size 5112