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
0c5e08c
•
1 Parent(s): eab68f5

End of training

Browse files
Files changed (5) hide show
  1. README.md +8 -109
  2. adapter_model.safetensors +1 -1
  3. runs/May17_14-16-51_cd9fc56ae957/events.out.tfevents.1715955429.cd9fc56ae957.34.0 +3 -0
  4. runs/May17_14-22-11_cd9fc56ae957/events.out.tfevents.1715955743.cd9fc56ae957.34.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,12 @@ 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
- - Loss: 1.1050
 
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -42,118 +47,12 @@ The following hyperparameters were used during training:
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: 100
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 | 1.6559 |
53
- | No log | 2.0 | 2 | 1.6397 |
54
- | No log | 3.0 | 3 | 1.6015 |
55
- | No log | 4.0 | 4 | 1.5469 |
56
- | No log | 5.0 | 5 | 1.4813 |
57
- | No log | 6.0 | 6 | 1.4143 |
58
- | No log | 7.0 | 7 | 1.3524 |
59
- | No log | 8.0 | 8 | 1.2961 |
60
- | No log | 9.0 | 9 | 1.2443 |
61
- | No log | 10.0 | 10 | 1.1941 |
62
- | No log | 11.0 | 11 | 1.1438 |
63
- | No log | 12.0 | 12 | 1.0963 |
64
- | No log | 13.0 | 13 | 1.0597 |
65
- | No log | 14.0 | 14 | 1.0356 |
66
- | No log | 15.0 | 15 | 1.0152 |
67
- | No log | 16.0 | 16 | 0.9937 |
68
- | No log | 17.0 | 17 | 0.9774 |
69
- | No log | 18.0 | 18 | 0.9688 |
70
- | No log | 19.0 | 19 | 0.9666 |
71
- | No log | 20.0 | 20 | 0.9624 |
72
- | No log | 21.0 | 21 | 0.9540 |
73
- | No log | 22.0 | 22 | 0.9510 |
74
- | No log | 23.0 | 23 | 0.9600 |
75
- | No log | 24.0 | 24 | 0.9656 |
76
- | 1.0039 | 25.0 | 25 | 0.9712 |
77
- | 1.0039 | 26.0 | 26 | 0.9890 |
78
- | 1.0039 | 27.0 | 27 | 1.0123 |
79
- | 1.0039 | 28.0 | 28 | 1.0186 |
80
- | 1.0039 | 29.0 | 29 | 1.0223 |
81
- | 1.0039 | 30.0 | 30 | 1.0406 |
82
- | 1.0039 | 31.0 | 31 | 1.0501 |
83
- | 1.0039 | 32.0 | 32 | 1.0564 |
84
- | 1.0039 | 33.0 | 33 | 1.0711 |
85
- | 1.0039 | 34.0 | 34 | 1.0799 |
86
- | 1.0039 | 35.0 | 35 | 1.0843 |
87
- | 1.0039 | 36.0 | 36 | 1.0861 |
88
- | 1.0039 | 37.0 | 37 | 1.0943 |
89
- | 1.0039 | 38.0 | 38 | 1.1023 |
90
- | 1.0039 | 39.0 | 39 | 1.1005 |
91
- | 1.0039 | 40.0 | 40 | 1.1138 |
92
- | 1.0039 | 41.0 | 41 | 1.0908 |
93
- | 1.0039 | 42.0 | 42 | 1.1106 |
94
- | 1.0039 | 43.0 | 43 | 1.1051 |
95
- | 1.0039 | 44.0 | 44 | 1.1027 |
96
- | 1.0039 | 45.0 | 45 | 1.1110 |
97
- | 1.0039 | 46.0 | 46 | 1.1231 |
98
- | 1.0039 | 47.0 | 47 | 1.1304 |
99
- | 1.0039 | 48.0 | 48 | 1.1325 |
100
- | 1.0039 | 49.0 | 49 | 1.1372 |
101
- | 0.2875 | 50.0 | 50 | 1.1450 |
102
- | 0.2875 | 51.0 | 51 | 1.1635 |
103
- | 0.2875 | 52.0 | 52 | 1.1798 |
104
- | 0.2875 | 53.0 | 53 | 1.1333 |
105
- | 0.2875 | 54.0 | 54 | 1.1759 |
106
- | 0.2875 | 55.0 | 55 | 1.2435 |
107
- | 0.2875 | 56.0 | 56 | 1.1802 |
108
- | 0.2875 | 57.0 | 57 | 1.0951 |
109
- | 0.2875 | 58.0 | 58 | 1.1254 |
110
- | 0.2875 | 59.0 | 59 | 1.1150 |
111
- | 0.2875 | 60.0 | 60 | 1.0558 |
112
- | 0.2875 | 61.0 | 61 | 1.0482 |
113
- | 0.2875 | 62.0 | 62 | 1.0277 |
114
- | 0.2875 | 63.0 | 63 | 1.0109 |
115
- | 0.2875 | 64.0 | 64 | 1.0255 |
116
- | 0.2875 | 65.0 | 65 | 1.0293 |
117
- | 0.2875 | 66.0 | 66 | 1.0387 |
118
- | 0.2875 | 67.0 | 67 | 1.0540 |
119
- | 0.2875 | 68.0 | 68 | 1.0771 |
120
- | 0.2875 | 69.0 | 69 | 1.0651 |
121
- | 0.2875 | 70.0 | 70 | 1.0527 |
122
- | 0.2875 | 71.0 | 71 | 1.0472 |
123
- | 0.2875 | 72.0 | 72 | 1.0476 |
124
- | 0.2875 | 73.0 | 73 | 1.0566 |
125
- | 0.2875 | 74.0 | 74 | 1.0526 |
126
- | 0.2752 | 75.0 | 75 | 1.0576 |
127
- | 0.2752 | 76.0 | 76 | 1.0647 |
128
- | 0.2752 | 77.0 | 77 | 1.0720 |
129
- | 0.2752 | 78.0 | 78 | 1.0814 |
130
- | 0.2752 | 79.0 | 79 | 1.1008 |
131
- | 0.2752 | 80.0 | 80 | 1.0758 |
132
- | 0.2752 | 81.0 | 81 | 1.0752 |
133
- | 0.2752 | 82.0 | 82 | 1.0775 |
134
- | 0.2752 | 83.0 | 83 | 1.0863 |
135
- | 0.2752 | 84.0 | 84 | 1.1308 |
136
- | 0.2752 | 85.0 | 85 | 1.0823 |
137
- | 0.2752 | 86.0 | 86 | 1.0900 |
138
- | 0.2752 | 87.0 | 87 | 1.0955 |
139
- | 0.2752 | 88.0 | 88 | 1.1000 |
140
- | 0.2752 | 89.0 | 89 | 1.1051 |
141
- | 0.2752 | 90.0 | 90 | 1.1096 |
142
- | 0.2752 | 91.0 | 91 | 1.1118 |
143
- | 0.2752 | 92.0 | 92 | 1.1115 |
144
- | 0.2752 | 93.0 | 93 | 1.1100 |
145
- | 0.2752 | 94.0 | 94 | 1.1082 |
146
- | 0.2752 | 95.0 | 95 | 1.1068 |
147
- | 0.2752 | 96.0 | 96 | 1.1059 |
148
- | 0.2752 | 97.0 | 97 | 1.1054 |
149
- | 0.2752 | 98.0 | 98 | 1.1052 |
150
- | 0.2752 | 99.0 | 99 | 1.1051 |
151
- | 0.2605 | 100.0 | 100 | 1.1050 |
152
-
153
-
154
  ### Framework versions
155
 
156
- - PEFT 0.11.1.dev0
157
  - Transformers 4.39.3
158
  - Pytorch 2.1.2
159
  - Datasets 2.18.0
 
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
 
 
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
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6329982f08454e6354f2928e5eae85740abbe164ff0a4c2f8517b9bff7becbf4
3
  size 62969640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9cd753315241fcd85e8aace8a41dba0ccff4439c66d0c86d320d34df19a38c
3
  size 62969640
runs/May17_14-16-51_cd9fc56ae957/events.out.tfevents.1715955429.cd9fc56ae957.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ddbdaacea77c9c80c0061e4f86604a09151b561eb0fb14dde72980ba842c85c
3
+ size 7616
runs/May17_14-22-11_cd9fc56ae957/events.out.tfevents.1715955743.cd9fc56ae957.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7b024d268492ac8b52ea9245e39aaa8db6076f0a8ef99d24d9b571bca7f6c5
3
+ size 18993
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bb30d67c34b1fb1a5908f1390e0fb413e3fbf13a61bfb17f899fd275b1b9e44
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c949b3062a355d3221303c499157ee9dd4a2e1ea9026195dd18b78b7de12c094
3
  size 5176