Training in progress, step 1

README.md

@@ -20,8 +20,8 @@ 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 Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8735
-- Wer: 195.8955
+- Loss: 2.8736
+- Wer: 196.0199
 
 ## Model description
 
@@ -46,15 +46,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - 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
-- training_steps: 2
+- training_steps: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer      |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.8199        | 0.1429 | 1    | 2.8735          | 195.8955 |
-| 1.4341        | 0.2857 | 2    | 2.8735          | 195.8955 |
+| 1.82          | 0.1429 | 1    | 2.8736          | 196.0199 |
 
 
 ### Framework versions

config.json

@@ -54,7 +54,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

runs/Jan20_10-32-14_sagemaker-data-scie-ml-g4dn-xlarge-b610b9b6ac0e69f553ff86c59c79/events.out.tfevents.1737369136.sagemaker-data-scie-ml-g4dn-xlarge-b610b9b6ac0e69f553ff86c59c79.24416.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b6fd64d5520522802b4cc8d20112edce6e820444a292ecdb4729e00a01d0bc
+size 7611

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:484340aa54c8792a4c2818818bc9ec40cdbffad39802d5ff2c2d60ff77598e83
+oid sha256:48c5dacce926923a478a3ebf74d95c346553b6db499efafefb00558686852bed
 size 4987