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
9438643
•
1 Parent(s): eb72c56

End of training

Browse files
Files changed (6) hide show
  1. README.md +102 -52
  2. adapter_model.safetensors +1 -1
  3. runs/May16_17-37-02_c24437a47acf/events.out.tfevents.1715881088.c24437a47acf.3776.0 +3 -0
  4. runs/May16_17-37-02_c24437a47acf/events.out.tfevents.1715881323.c24437a47acf.3776.1 +3 -0
  5. runs/May16_17-37-02_c24437a47acf/events.out.tfevents.1715881915.c24437a47acf.3776.2 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +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
- - Loss: 1.0926
20
 
21
  ## Model description
22
 
@@ -42,63 +42,113 @@ 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: 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 | 1.5700 |
53
- | No log | 2.0 | 2 | 1.5532 |
54
- | No log | 3.0 | 3 | 1.5169 |
55
- | No log | 4.0 | 4 | 1.4654 |
56
- | No log | 5.0 | 5 | 1.4050 |
57
- | No log | 6.0 | 6 | 1.3413 |
58
- | No log | 7.0 | 7 | 1.2879 |
59
- | No log | 8.0 | 8 | 1.2420 |
60
- | No log | 9.0 | 9 | 1.1945 |
61
- | No log | 10.0 | 10 | 1.1463 |
62
- | No log | 11.0 | 11 | 1.0969 |
63
- | No log | 12.0 | 12 | 1.0539 |
64
- | No log | 13.0 | 13 | 1.0243 |
65
- | No log | 14.0 | 14 | 1.0018 |
66
- | No log | 15.0 | 15 | 0.9775 |
67
- | No log | 16.0 | 16 | 0.9583 |
68
- | No log | 17.0 | 17 | 0.9521 |
69
- | No log | 18.0 | 18 | 0.9549 |
70
- | No log | 19.0 | 19 | 0.9596 |
71
- | No log | 20.0 | 20 | 0.9569 |
72
- | No log | 21.0 | 21 | 0.9512 |
73
- | No log | 22.0 | 22 | 0.9512 |
74
- | No log | 23.0 | 23 | 0.9577 |
75
- | No log | 24.0 | 24 | 0.9615 |
76
- | 1.0177 | 25.0 | 25 | 0.9770 |
77
- | 1.0177 | 26.0 | 26 | 0.9980 |
78
- | 1.0177 | 27.0 | 27 | 1.0184 |
79
- | 1.0177 | 28.0 | 28 | 1.0271 |
80
- | 1.0177 | 29.0 | 29 | 1.0317 |
81
- | 1.0177 | 30.0 | 30 | 1.0514 |
82
- | 1.0177 | 31.0 | 31 | 1.0524 |
83
- | 1.0177 | 32.0 | 32 | 1.0568 |
84
- | 1.0177 | 33.0 | 33 | 1.0673 |
85
- | 1.0177 | 34.0 | 34 | 1.0699 |
86
- | 1.0177 | 35.0 | 35 | 1.0774 |
87
- | 1.0177 | 36.0 | 36 | 1.0873 |
88
- | 1.0177 | 37.0 | 37 | 1.0838 |
89
- | 1.0177 | 38.0 | 38 | 1.0742 |
90
- | 1.0177 | 39.0 | 39 | 1.0757 |
91
- | 1.0177 | 40.0 | 40 | 1.0692 |
92
- | 1.0177 | 41.0 | 41 | 1.0705 |
93
- | 1.0177 | 42.0 | 42 | 1.0738 |
94
- | 1.0177 | 43.0 | 43 | 1.0765 |
95
- | 1.0177 | 44.0 | 44 | 1.0762 |
96
- | 1.0177 | 45.0 | 45 | 1.0806 |
97
- | 1.0177 | 46.0 | 46 | 1.0755 |
98
- | 1.0177 | 47.0 | 47 | 1.0789 |
99
- | 1.0177 | 48.0 | 48 | 1.0783 |
100
- | 1.0177 | 49.0 | 49 | 1.0856 |
101
- | 0.2796 | 50.0 | 50 | 1.0926 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
102
 
103
 
104
  ### Framework versions
 
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: 1.1026
20
 
21
  ## Model description
22
 
 
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 | 1.6433 |
53
+ | No log | 2.0 | 2 | 1.6256 |
54
+ | No log | 3.0 | 3 | 1.5850 |
55
+ | No log | 4.0 | 4 | 1.5268 |
56
+ | No log | 5.0 | 5 | 1.4583 |
57
+ | No log | 6.0 | 6 | 1.3911 |
58
+ | No log | 7.0 | 7 | 1.3293 |
59
+ | No log | 8.0 | 8 | 1.2727 |
60
+ | No log | 9.0 | 9 | 1.2201 |
61
+ | No log | 10.0 | 10 | 1.1695 |
62
+ | No log | 11.0 | 11 | 1.1209 |
63
+ | No log | 12.0 | 12 | 1.0779 |
64
+ | No log | 13.0 | 13 | 1.0471 |
65
+ | No log | 14.0 | 14 | 1.0264 |
66
+ | No log | 15.0 | 15 | 1.0034 |
67
+ | No log | 16.0 | 16 | 0.9841 |
68
+ | No log | 17.0 | 17 | 0.9749 |
69
+ | No log | 18.0 | 18 | 0.9693 |
70
+ | No log | 19.0 | 19 | 0.9609 |
71
+ | No log | 20.0 | 20 | 0.9441 |
72
+ | No log | 21.0 | 21 | 0.9278 |
73
+ | No log | 22.0 | 22 | 0.9189 |
74
+ | No log | 23.0 | 23 | 0.9244 |
75
+ | No log | 24.0 | 24 | 0.9232 |
76
+ | 0.9846 | 25.0 | 25 | 0.9187 |
77
+ | 0.9846 | 26.0 | 26 | 0.9295 |
78
+ | 0.9846 | 27.0 | 27 | 0.9583 |
79
+ | 0.9846 | 28.0 | 28 | 0.9774 |
80
+ | 0.9846 | 29.0 | 29 | 0.9789 |
81
+ | 0.9846 | 30.0 | 30 | 0.9960 |
82
+ | 0.9846 | 31.0 | 31 | 1.0306 |
83
+ | 0.9846 | 32.0 | 32 | 1.0483 |
84
+ | 0.9846 | 33.0 | 33 | 1.0384 |
85
+ | 0.9846 | 34.0 | 34 | 1.0458 |
86
+ | 0.9846 | 35.0 | 35 | 1.0651 |
87
+ | 0.9846 | 36.0 | 36 | 1.0418 |
88
+ | 0.9846 | 37.0 | 37 | 1.0329 |
89
+ | 0.9846 | 38.0 | 38 | 1.0425 |
90
+ | 0.9846 | 39.0 | 39 | 1.0538 |
91
+ | 0.9846 | 40.0 | 40 | 1.0397 |
92
+ | 0.9846 | 41.0 | 41 | 1.0374 |
93
+ | 0.9846 | 42.0 | 42 | 1.0477 |
94
+ | 0.9846 | 43.0 | 43 | 1.0589 |
95
+ | 0.9846 | 44.0 | 44 | 1.0609 |
96
+ | 0.9846 | 45.0 | 45 | 1.0615 |
97
+ | 0.9846 | 46.0 | 46 | 1.0700 |
98
+ | 0.9846 | 47.0 | 47 | 1.0893 |
99
+ | 0.9846 | 48.0 | 48 | 1.0948 |
100
+ | 0.9846 | 49.0 | 49 | 1.0906 |
101
+ | 0.2714 | 50.0 | 50 | 1.1002 |
102
+ | 0.2714 | 51.0 | 51 | 1.1112 |
103
+ | 0.2714 | 52.0 | 52 | 1.1162 |
104
+ | 0.2714 | 53.0 | 53 | 1.1117 |
105
+ | 0.2714 | 54.0 | 54 | 1.1243 |
106
+ | 0.2714 | 55.0 | 55 | 1.1166 |
107
+ | 0.2714 | 56.0 | 56 | 1.1230 |
108
+ | 0.2714 | 57.0 | 57 | 1.1156 |
109
+ | 0.2714 | 58.0 | 58 | 1.1162 |
110
+ | 0.2714 | 59.0 | 59 | 1.1310 |
111
+ | 0.2714 | 60.0 | 60 | 1.0921 |
112
+ | 0.2714 | 61.0 | 61 | 1.1188 |
113
+ | 0.2714 | 62.0 | 62 | 1.0336 |
114
+ | 0.2714 | 63.0 | 63 | 0.9937 |
115
+ | 0.2714 | 64.0 | 64 | 1.0263 |
116
+ | 0.2714 | 65.0 | 65 | 1.0224 |
117
+ | 0.2714 | 66.0 | 66 | 1.0067 |
118
+ | 0.2714 | 67.0 | 67 | 1.0112 |
119
+ | 0.2714 | 68.0 | 68 | 1.0143 |
120
+ | 0.2714 | 69.0 | 69 | 1.0155 |
121
+ | 0.2714 | 70.0 | 70 | 1.0211 |
122
+ | 0.2714 | 71.0 | 71 | 1.0260 |
123
+ | 0.2714 | 72.0 | 72 | 1.0292 |
124
+ | 0.2714 | 73.0 | 73 | 1.0363 |
125
+ | 0.2714 | 74.0 | 74 | 1.0443 |
126
+ | 0.2554 | 75.0 | 75 | 1.0529 |
127
+ | 0.2554 | 76.0 | 76 | 1.0624 |
128
+ | 0.2554 | 77.0 | 77 | 1.0681 |
129
+ | 0.2554 | 78.0 | 78 | 1.0688 |
130
+ | 0.2554 | 79.0 | 79 | 1.0684 |
131
+ | 0.2554 | 80.0 | 80 | 1.0690 |
132
+ | 0.2554 | 81.0 | 81 | 1.0702 |
133
+ | 0.2554 | 82.0 | 82 | 1.0719 |
134
+ | 0.2554 | 83.0 | 83 | 1.0748 |
135
+ | 0.2554 | 84.0 | 84 | 1.0789 |
136
+ | 0.2554 | 85.0 | 85 | 1.0826 |
137
+ | 0.2554 | 86.0 | 86 | 1.0848 |
138
+ | 0.2554 | 87.0 | 87 | 1.0865 |
139
+ | 0.2554 | 88.0 | 88 | 1.0876 |
140
+ | 0.2554 | 89.0 | 89 | 1.0887 |
141
+ | 0.2554 | 90.0 | 90 | 1.0898 |
142
+ | 0.2554 | 91.0 | 91 | 1.0915 |
143
+ | 0.2554 | 92.0 | 92 | 1.0934 |
144
+ | 0.2554 | 93.0 | 93 | 1.0956 |
145
+ | 0.2554 | 94.0 | 94 | 1.0978 |
146
+ | 0.2554 | 95.0 | 95 | 1.0997 |
147
+ | 0.2554 | 96.0 | 96 | 1.1010 |
148
+ | 0.2554 | 97.0 | 97 | 1.1018 |
149
+ | 0.2554 | 98.0 | 98 | 1.1023 |
150
+ | 0.2554 | 99.0 | 99 | 1.1025 |
151
+ | 0.2451 | 100.0 | 100 | 1.1026 |
152
 
153
 
154
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f83b79fca0572f68ffb2eff70342e3aba4c083ae84fc97a4c28448298249d5c
3
  size 62969640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041753f53855b71731cc7d382952171482a4e237b66354d3e79ca64d5cad8d3e
3
  size 62969640
runs/May16_17-37-02_c24437a47acf/events.out.tfevents.1715881088.c24437a47acf.3776.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a699b7b9c0a82678846b936f02cc00629544b4670b0e6173b1d71e798ad38d7
3
+ size 6084
runs/May16_17-37-02_c24437a47acf/events.out.tfevents.1715881323.c24437a47acf.3776.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4450bd44af2e0df97cee5e5e7379c88c70fcbfe8e6b6606c3f229374981be8e1
3
+ size 6084
runs/May16_17-37-02_c24437a47acf/events.out.tfevents.1715881915.c24437a47acf.3776.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1184cdc1f8261beebfd08b2118b2b2e0a98e00be5b91f944b9cc77df79728a1e
3
+ size 33860
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f271a78586cc707a0ed5b2a42f9f949dd3a4907192e88bcf3cc33636b8292659
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e96bed6921354c4b49880d92ecba4785884371649b530adadd002702138d03a
3
  size 5176