akrishnan commited on
Commit
3843f83
1 Parent(s): 8cc719e

End of training

Browse files
Files changed (2) hide show
  1. README.md +94 -48
  2. model.safetensors +1 -1
README.md CHANGED
@@ -13,13 +13,13 @@ model-index:
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/krishnan-aravind/huggingface/runs/2ay2lri6)
17
  # malayalam_combined_
18
 
19
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4789
22
- - Wer: 0.4611
23
 
24
  ## Model description
25
 
@@ -52,51 +52,97 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:------:|:-----:|:---------------:|:------:|
57
- | 0.8401 | 0.2031 | 500 | 0.8498 | 0.7068 |
58
- | 0.7367 | 0.4063 | 1000 | 0.7280 | 0.6183 |
59
- | 0.6974 | 0.6094 | 1500 | 0.7055 | 0.6113 |
60
- | 0.6493 | 0.8125 | 2000 | 0.6765 | 0.5989 |
61
- | 0.5905 | 1.0156 | 2500 | 0.6521 | 0.5937 |
62
- | 0.606 | 1.2188 | 3000 | 0.6192 | 0.5639 |
63
- | 0.5601 | 1.4219 | 3500 | 0.6242 | 0.5526 |
64
- | 0.5868 | 1.6250 | 4000 | 0.6118 | 0.5559 |
65
- | 0.5792 | 1.8282 | 4500 | 0.5879 | 0.5523 |
66
- | 0.554 | 2.0313 | 5000 | 0.5775 | 0.5501 |
67
- | 0.505 | 2.2344 | 5500 | 0.5640 | 0.5466 |
68
- | 0.5055 | 2.4375 | 6000 | 0.5668 | 0.5298 |
69
- | 0.5228 | 2.6407 | 6500 | 0.5410 | 0.5178 |
70
- | 0.5186 | 2.8438 | 7000 | 0.5785 | 0.5540 |
71
- | 0.4811 | 3.0469 | 7500 | 0.5446 | 0.5408 |
72
- | 0.4794 | 3.2501 | 8000 | 0.5333 | 0.5102 |
73
- | 0.4952 | 3.4532 | 8500 | 0.5205 | 0.5135 |
74
- | 0.4761 | 3.6563 | 9000 | 0.5218 | 0.5092 |
75
- | 0.5079 | 3.8594 | 9500 | 0.5192 | 0.5166 |
76
- | 0.4407 | 4.0626 | 10000 | 0.5207 | 0.5054 |
77
- | 0.4711 | 4.2657 | 10500 | 0.5215 | 0.5086 |
78
- | 0.4396 | 4.4688 | 11000 | 0.5289 | 0.5145 |
79
- | 0.4667 | 4.6719 | 11500 | 0.5144 | 0.5015 |
80
- | 0.4518 | 4.8751 | 12000 | 0.5222 | 0.5112 |
81
- | 0.4211 | 5.0782 | 12500 | 0.5094 | 0.4897 |
82
- | 0.43 | 5.2813 | 13000 | 0.5242 | 0.5011 |
83
- | 0.4218 | 5.4845 | 13500 | 0.5132 | 0.4905 |
84
- | 0.4279 | 5.6876 | 14000 | 0.5153 | 0.4883 |
85
- | 0.4341 | 5.8907 | 14500 | 0.5321 | 0.4899 |
86
- | 0.409 | 6.0938 | 15000 | 0.5079 | 0.4884 |
87
- | 0.4111 | 6.2970 | 15500 | 0.5067 | 0.4844 |
88
- | 0.3781 | 6.5001 | 16000 | 0.5091 | 0.4643 |
89
- | 0.4274 | 6.7032 | 16500 | 0.4842 | 0.4831 |
90
- | 0.4009 | 6.9064 | 17000 | 0.4791 | 0.4738 |
91
- | 0.3895 | 7.1095 | 17500 | 0.4786 | 0.4691 |
92
- | 0.3788 | 7.3126 | 18000 | 0.4845 | 0.4691 |
93
- | 0.3909 | 7.5157 | 18500 | 0.4869 | 0.4612 |
94
- | 0.3795 | 7.7189 | 19000 | 0.4729 | 0.4606 |
95
- | 0.3874 | 7.9220 | 19500 | 0.4667 | 0.4655 |
96
- | 0.3472 | 8.1251 | 20000 | 0.4718 | 0.4720 |
97
- | 0.3634 | 8.3283 | 20500 | 0.4767 | 0.4616 |
98
- | 0.3545 | 8.5314 | 21000 | 0.4821 | 0.4640 |
99
- | 0.37 | 8.7345 | 21500 | 0.4789 | 0.4611 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100
 
101
 
102
  ### Framework versions
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/krishnan-aravind/huggingface/runs/7l3na48x)
17
  # malayalam_combined_
18
 
19
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5025
22
+ - Wer: 0.4256
23
 
24
  ## Model description
25
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
57
+ | 0.8238 | 0.2031 | 500 | 0.8281 | 0.6745 |
58
+ | 0.7415 | 0.4063 | 1000 | 0.7477 | 0.6446 |
59
+ | 0.6913 | 0.6094 | 1500 | 0.6962 | 0.6072 |
60
+ | 0.6401 | 0.8125 | 2000 | 0.6981 | 0.5929 |
61
+ | 0.5864 | 1.0156 | 2500 | 0.6809 | 0.5712 |
62
+ | 0.5843 | 1.2188 | 3000 | 0.6125 | 0.5691 |
63
+ | 0.5547 | 1.4219 | 3500 | 0.6110 | 0.5616 |
64
+ | 0.5657 | 1.6250 | 4000 | 0.5882 | 0.5464 |
65
+ | 0.5809 | 1.8282 | 4500 | 0.5776 | 0.5481 |
66
+ | 0.5464 | 2.0313 | 5000 | 0.5689 | 0.5278 |
67
+ | 0.4974 | 2.2344 | 5500 | 0.5926 | 0.5428 |
68
+ | 0.5012 | 2.4375 | 6000 | 0.5622 | 0.5384 |
69
+ | 0.5162 | 2.6407 | 6500 | 0.5697 | 0.5179 |
70
+ | 0.5006 | 2.8438 | 7000 | 0.5357 | 0.5375 |
71
+ | 0.4661 | 3.0469 | 7500 | 0.5255 | 0.5255 |
72
+ | 0.4658 | 3.2501 | 8000 | 0.5182 | 0.5002 |
73
+ | 0.4716 | 3.4532 | 8500 | 0.5176 | 0.5044 |
74
+ | 0.4658 | 3.6563 | 9000 | 0.5139 | 0.5061 |
75
+ | 0.5031 | 3.8594 | 9500 | 0.5114 | 0.5068 |
76
+ | 0.4482 | 4.0626 | 10000 | 0.5331 | 0.5101 |
77
+ | 0.4678 | 4.2657 | 10500 | 0.5165 | 0.5126 |
78
+ | 0.4353 | 4.4688 | 11000 | 0.5292 | 0.5112 |
79
+ | 0.4711 | 4.6719 | 11500 | 0.5178 | 0.4979 |
80
+ | 0.4574 | 4.8751 | 12000 | 0.5215 | 0.5100 |
81
+ | 0.4246 | 5.0782 | 12500 | 0.5190 | 0.4938 |
82
+ | 0.4164 | 5.2813 | 13000 | 0.5504 | 0.4898 |
83
+ | 0.4181 | 5.4845 | 13500 | 0.5045 | 0.4979 |
84
+ | 0.4279 | 5.6876 | 14000 | 0.5118 | 0.4932 |
85
+ | 0.4244 | 5.8907 | 14500 | 0.4970 | 0.4842 |
86
+ | 0.4038 | 6.0938 | 15000 | 0.5013 | 0.4776 |
87
+ | 0.4179 | 6.2970 | 15500 | 0.5061 | 0.4762 |
88
+ | 0.3812 | 6.5001 | 16000 | 0.4987 | 0.4689 |
89
+ | 0.4217 | 6.7032 | 16500 | 0.4986 | 0.4807 |
90
+ | 0.3989 | 6.9064 | 17000 | 0.4905 | 0.4709 |
91
+ | 0.3741 | 7.1095 | 17500 | 0.4842 | 0.4700 |
92
+ | 0.3743 | 7.3126 | 18000 | 0.4869 | 0.4734 |
93
+ | 0.3785 | 7.5157 | 18500 | 0.4692 | 0.4690 |
94
+ | 0.3759 | 7.7189 | 19000 | 0.4691 | 0.4646 |
95
+ | 0.3809 | 7.9220 | 19500 | 0.4736 | 0.4720 |
96
+ | 0.3499 | 8.1251 | 20000 | 0.4787 | 0.4691 |
97
+ | 0.3523 | 8.3283 | 20500 | 0.4689 | 0.4680 |
98
+ | 0.3551 | 8.5314 | 21000 | 0.4792 | 0.4567 |
99
+ | 0.3672 | 8.7345 | 21500 | 0.4760 | 0.4652 |
100
+ | 0.3554 | 8.9376 | 22000 | 0.4649 | 0.4648 |
101
+ | 0.3182 | 9.1408 | 22500 | 0.4853 | 0.4565 |
102
+ | 0.3412 | 9.3439 | 23000 | 0.4958 | 0.4616 |
103
+ | 0.3494 | 9.5470 | 23500 | 0.4971 | 0.4527 |
104
+ | 0.3426 | 9.7502 | 24000 | 0.4959 | 0.4554 |
105
+ | 0.3365 | 9.9533 | 24500 | 0.4659 | 0.4582 |
106
+ | 0.3179 | 10.1564 | 25000 | 0.4807 | 0.4445 |
107
+ | 0.3361 | 10.3595 | 25500 | 0.4700 | 0.4535 |
108
+ | 0.3234 | 10.5627 | 26000 | 0.4562 | 0.4542 |
109
+ | 0.3296 | 10.7658 | 26500 | 0.4682 | 0.4452 |
110
+ | 0.3148 | 10.9689 | 27000 | 0.4716 | 0.4521 |
111
+ | 0.3112 | 11.1720 | 27500 | 0.4537 | 0.4473 |
112
+ | 0.3246 | 11.3752 | 28000 | 0.4594 | 0.4444 |
113
+ | 0.3062 | 11.5783 | 28500 | 0.4544 | 0.4445 |
114
+ | 0.2979 | 11.7814 | 29000 | 0.4531 | 0.4516 |
115
+ | 0.3108 | 11.9846 | 29500 | 0.4514 | 0.4428 |
116
+ | 0.2876 | 12.1877 | 30000 | 0.4598 | 0.4402 |
117
+ | 0.2911 | 12.3908 | 30500 | 0.4554 | 0.4426 |
118
+ | 0.2963 | 12.5939 | 31000 | 0.4641 | 0.4483 |
119
+ | 0.296 | 12.7971 | 31500 | 0.4575 | 0.4394 |
120
+ | 0.2777 | 13.0002 | 32000 | 0.4586 | 0.4444 |
121
+ | 0.2782 | 13.2033 | 32500 | 0.4498 | 0.4461 |
122
+ | 0.2695 | 13.4065 | 33000 | 0.4696 | 0.4450 |
123
+ | 0.286 | 13.6096 | 33500 | 0.4630 | 0.4383 |
124
+ | 0.279 | 13.8127 | 34000 | 0.4618 | 0.4401 |
125
+ | 0.2584 | 14.0158 | 34500 | 0.4526 | 0.4356 |
126
+ | 0.267 | 14.2190 | 35000 | 0.4726 | 0.4297 |
127
+ | 0.2667 | 14.4221 | 35500 | 0.4572 | 0.4308 |
128
+ | 0.2592 | 14.6252 | 36000 | 0.4795 | 0.4325 |
129
+ | 0.2592 | 14.8284 | 36500 | 0.4528 | 0.4303 |
130
+ | 0.2644 | 15.0315 | 37000 | 0.4604 | 0.4306 |
131
+ | 0.2312 | 15.2346 | 37500 | 0.4632 | 0.4367 |
132
+ | 0.2408 | 15.4377 | 38000 | 0.4670 | 0.4324 |
133
+ | 0.2489 | 15.6409 | 38500 | 0.4580 | 0.4253 |
134
+ | 0.2652 | 15.8440 | 39000 | 0.4581 | 0.4375 |
135
+ | 0.2367 | 16.0471 | 39500 | 0.4770 | 0.4213 |
136
+ | 0.2366 | 16.2503 | 40000 | 0.4751 | 0.4243 |
137
+ | 0.2267 | 16.4534 | 40500 | 0.4622 | 0.4282 |
138
+ | 0.2461 | 16.6565 | 41000 | 0.4671 | 0.4249 |
139
+ | 0.2326 | 16.8596 | 41500 | 0.4736 | 0.4293 |
140
+ | 0.2121 | 17.0628 | 42000 | 0.4905 | 0.4300 |
141
+ | 0.222 | 17.2659 | 42500 | 0.4782 | 0.4261 |
142
+ | 0.2202 | 17.4690 | 43000 | 0.4670 | 0.4250 |
143
+ | 0.2141 | 17.6722 | 43500 | 0.4688 | 0.4259 |
144
+ | 0.2231 | 17.8753 | 44000 | 0.4718 | 0.4254 |
145
+ | 0.2144 | 18.0784 | 44500 | 0.5025 | 0.4256 |
146
 
147
 
148
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25719821d03e2cb54ad653826df83d215029865b9a22b5b39a34e77849208c9c
3
  size 2423199960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc815b3814b98749a38d292b2501f00adc18477bb37def4c80a8ac115ed2eff
3
  size 2423199960