Model save

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9223
+- Loss: 0.8927
 - Wer: 26.6667
 
 ## Model description
@@ -43,15 +43,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 1000
+- training_steps: 700
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0           | 500.0  | 500  | 0.8967          | 26.6667 |
-| 0.0           | 1000.0 | 1000 | 0.9223          | 26.6667 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0           | 350.0 | 350  | 0.8709          | 26.6667 |
+| 0.0           | 700.0 | 700  | 0.8927          | 26.6667 |
 
 
 ### Framework versions

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1000.0,
-    "total_flos": 4.08241963008e+18,
-    "train_loss": 0.005452081066950086,
-    "train_runtime": 1064.1917,
-    "train_samples_per_second": 15.035,
-    "train_steps_per_second": 0.94
+    "epoch": 700.0,
+    "total_flos": 2.857693741056e+18,
+    "train_loss": 0.007796804091854678,
+    "train_runtime": 887.094,
+    "train_samples_per_second": 12.625,
+    "train_steps_per_second": 0.789
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54fe2ae2b5384071299d78bb39535f7e4d6e49f6498c0ac0e2287cc401977d1b
+oid sha256:0fc56b8ea5c94b7e97debb4ceb50cbef2b98c91dd962e802835d9183f2e0028c
 size 3055544304

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1000.0,
-    "total_flos": 4.08241963008e+18,
-    "train_loss": 0.005452081066950086,
-    "train_runtime": 1064.1917,
-    "train_samples_per_second": 15.035,
-    "train_steps_per_second": 0.94
+    "epoch": 700.0,
+    "total_flos": 2.857693741056e+18,
+    "train_loss": 0.007796804091854678,
+    "train_runtime": 887.094,
+    "train_samples_per_second": 12.625,
+    "train_steps_per_second": 0.789
 }