End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.34061393152302244
+      value: 0.31995277449822906
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9112
-- Wer Ortho: 0.3374
-- Wer: 0.3406
+- Loss: 0.6737
+- Wer Ortho: 0.3208
+- Wer: 0.3200
 
 ## Model description
 
@@ -54,30 +54,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - 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: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 5000
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch    | Step | Validation Loss | Wer Ortho | Wer    |
-|:-------------:|:--------:|:----:|:---------------:|:---------:|:------:|
-| 0.0006        | 17.8571  | 500  | 0.6628          | 0.3239    | 0.3247 |
-| 0.0002        | 35.7143  | 1000 | 0.7220          | 0.3263    | 0.3276 |
-| 0.0001        | 53.5714  | 1500 | 0.7574          | 0.3226    | 0.3241 |
-| 0.0001        | 71.4286  | 2000 | 0.7868          | 0.3300    | 0.3312 |
-| 0.0           | 89.2857  | 2500 | 0.8103          | 0.3319    | 0.3329 |
-| 0.0           | 107.1429 | 3000 | 0.8325          | 0.3331    | 0.3353 |
-| 0.0           | 125.0    | 3500 | 0.8530          | 0.3356    | 0.3383 |
-| 0.0           | 142.8571 | 4000 | 0.8730          | 0.3337    | 0.3371 |
-| 0.0           | 160.7143 | 4500 | 0.8927          | 0.3344    | 0.3371 |
-| 0.0           | 178.5714 | 5000 | 0.9112          | 0.3374    | 0.3406 |
+| Training Loss | Epoch   | Step | Validation Loss | Wer Ortho | Wer    |
+|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|
+| 0.0009        | 17.8571 | 500  | 0.6737          | 0.3208    | 0.3200 |
 
 
 ### Framework versions

config.json

@@ -55,7 +55,7 @@
   "scale_embedding": false,
   "torch_dtype": "float32",
   "transformers_version": "4.47.0",
-  "use_cache": false,
+  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe5bfe70a768907d4df924474831876b7e64e543d27010d6416d7264a960d901
+oid sha256:4f007f554dcbcde96dd9fda73760c3d9466e1daf2e230d0f98e259e721212932
 size 151061672

runs/Mar23_19-02-20_e8336f4a552a/events.out.tfevents.1742756541.e8336f4a552a.31.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27a7fd7ad2791c67687994ebaae41f4154987dcdd7c0101a8c1488a0474a61d
+size 11782

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf14e810b158955102a7e2fda73bc00d9f0cf3c39345450e9e4d3ca0ab6ffabb
+oid sha256:2f43341e0519b9c4ca97ff4e24d4a777e6989232efbaae8e98f762676c31ef8b
 size 5496