Hugging Face's logo

Aysha630
/
whisper-large-v3-MH-fine-tuned

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Aysha630 commited on
Commit
417a533
•
1 Parent(s): 0c5e08c

End of training

Browse files
Files changed (5) hide show
  1. README.md +63 -12
  2. adapter_model.safetensors +1 -1
  3. runs/May17_16-28-51_9d38c77a2c49/events.out.tfevents.1715963445.9d38c77a2c49.1534.0 +3 -0
  4. runs/May17_16-34-56_9d38c77a2c49/events.out.tfevents.1715963697.9d38c77a2c49.1534.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,12 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - eval_loss: 0.6723
20
- - eval_runtime: 24.726
21
- - eval_samples_per_second: 1.092
22
- - eval_steps_per_second: 0.162
23
- - epoch: 48.0
24
- - step: 48
25
 
26
  ## Model description
27
 
@@ -42,18 +37,74 @@ More information needed
42
  The following hyperparameters were used during training:
43
  - learning_rate: 0.001
44
  - train_batch_size: 10
45
- - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 50
50
- - num_epochs: 80
51
  - mixed_precision_training: Native AMP
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  ### Framework versions
54
 
55
  - PEFT 0.11.2.dev0
56
- - Transformers 4.39.3
57
- - Pytorch 2.1.2
58
- - Datasets 2.18.0
59
- - Tokenizers 0.15.2
 
16
 
17
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6849
 
 
 
 
 
20
 
21
  ## Model description
22
 
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.001
39
  - train_batch_size: 10
40
+ - eval_batch_size: 4
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 50
45
+ - num_epochs: 50
46
  - mixed_precision_training: Native AMP
47
 
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 1.0 | 1 | 1.0192 |
53
+ | No log | 2.0 | 2 | 1.0085 |
54
+ | No log | 3.0 | 3 | 0.9859 |
55
+ | No log | 4.0 | 4 | 0.9554 |
56
+ | No log | 5.0 | 5 | 0.9172 |
57
+ | No log | 6.0 | 6 | 0.8728 |
58
+ | No log | 7.0 | 7 | 0.8330 |
59
+ | No log | 8.0 | 8 | 0.7908 |
60
+ | No log | 9.0 | 9 | 0.7546 |
61
+ | No log | 10.0 | 10 | 0.7167 |
62
+ | No log | 11.0 | 11 | 0.6891 |
63
+ | No log | 12.0 | 12 | 0.6698 |
64
+ | No log | 13.0 | 13 | 0.6546 |
65
+ | No log | 14.0 | 14 | 0.6372 |
66
+ | No log | 15.0 | 15 | 0.6247 |
67
+ | No log | 16.0 | 16 | 0.6198 |
68
+ | No log | 17.0 | 17 | 0.6209 |
69
+ | No log | 18.0 | 18 | 0.6249 |
70
+ | No log | 19.0 | 19 | 0.6316 |
71
+ | No log | 20.0 | 20 | 0.6368 |
72
+ | No log | 21.0 | 21 | 0.6398 |
73
+ | No log | 22.0 | 22 | 0.6463 |
74
+ | No log | 23.0 | 23 | 0.6555 |
75
+ | No log | 24.0 | 24 | 0.6680 |
76
+ | 0.4535 | 25.0 | 25 | 0.6789 |
77
+ | 0.4535 | 26.0 | 26 | 0.6905 |
78
+ | 0.4535 | 27.0 | 27 | 0.7006 |
79
+ | 0.4535 | 28.0 | 28 | 0.7102 |
80
+ | 0.4535 | 29.0 | 29 | 0.7208 |
81
+ | 0.4535 | 30.0 | 30 | 0.7363 |
82
+ | 0.4535 | 31.0 | 31 | 0.7512 |
83
+ | 0.4535 | 32.0 | 32 | 0.7582 |
84
+ | 0.4535 | 33.0 | 33 | 0.7685 |
85
+ | 0.4535 | 34.0 | 34 | 0.7794 |
86
+ | 0.4535 | 35.0 | 35 | 0.7849 |
87
+ | 0.4535 | 36.0 | 36 | 0.7896 |
88
+ | 0.4535 | 37.0 | 37 | 0.7917 |
89
+ | 0.4535 | 38.0 | 38 | 0.8132 |
90
+ | 0.4535 | 39.0 | 39 | 0.7889 |
91
+ | 0.4535 | 40.0 | 40 | 0.7614 |
92
+ | 0.4535 | 41.0 | 41 | 0.7371 |
93
+ | 0.4535 | 42.0 | 42 | 0.7206 |
94
+ | 0.4535 | 43.0 | 43 | 0.7066 |
95
+ | 0.4535 | 44.0 | 44 | 0.7024 |
96
+ | 0.4535 | 45.0 | 45 | 0.7128 |
97
+ | 0.4535 | 46.0 | 46 | 0.7242 |
98
+ | 0.4535 | 47.0 | 47 | 0.7137 |
99
+ | 0.4535 | 48.0 | 48 | 0.7004 |
100
+ | 0.4535 | 49.0 | 49 | 0.6883 |
101
+ | 0.0261 | 50.0 | 50 | 0.6849 |
102
+
103
+
104
  ### Framework versions
105
 
106
  - PEFT 0.11.2.dev0
107
+ - Transformers 4.40.2
108
+ - Pytorch 2.2.1+cu121
109
+ - Datasets 2.19.1
110
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc9cd753315241fcd85e8aace8a41dba0ccff4439c66d0c86d320d34df19a38c
3
  size 62969640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0476bd87a645dd4a1c4b28e9908cd0ebda1fada36ea7dc94dc7a7a51773c5c5
3
  size 62969640
runs/May17_16-28-51_9d38c77a2c49/events.out.tfevents.1715963445.9d38c77a2c49.1534.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19c02901e726974e8a3d2f68fd5c22a527c611317ab93f6b3ebfcfe38b1c286
3
+ size 6879
runs/May17_16-34-56_9d38c77a2c49/events.out.tfevents.1715963697.9d38c77a2c49.1534.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6e14b57b9edc31fdf3d9556c2b87175abfd1c43f087d649d3d06829877c5a8
3
+ size 20143
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c949b3062a355d3221303c499157ee9dd4a2e1ea9026195dd18b78b7de12c094
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fbb0f4c57d5daf63506c6fdbd65d23b84a80771b0874037dc2e7fd5afe1eaf1
3
  size 5176