Hugging Face's logo

Virus-Proton
/
Bn_GEDC

Transformers
Safetensors
mbart
text2text-generation
Generated from Trainer
Model card Files
xet
Community
Virus-Proton commited on
Commit
402011d
·
verified ·
1 Parent(s): 6ed9a6c

Virus-Proton/Bn_GEDC

Browse files
Files changed (2) hide show
  1. README.md +85 -59
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1584
22
- - Wer: 0.285
23
- - Bleu: 0.525
24
 
25
  ## Model description
26
 
@@ -44,65 +44,91 @@ The following hyperparameters were used during training:
44
  - eval_batch_size: 16
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
- - lr_scheduler_type: reduce_lr_on_plateau
48
- - num_epochs: 10
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer | Bleu |
53
- |:-------------:|:-----:|:-----:|:---------------:|:-----:|:-----:|
54
- | 1.514 | 0.016 | 500 | 0.0705 | 0.132 | 0.705 |
55
- | 0.1289 | 0.032 | 1000 | 0.0761 | 0.129 | 0.712 |
56
- | 0.102 | 0.048 | 1500 | 0.0756 | 0.128 | 0.709 |
57
- | 0.0909 | 0.064 | 2000 | 0.0768 | 0.132 | 0.702 |
58
- | 0.074 | 0.08 | 2500 | 0.0808 | 0.13 | 0.706 |
59
- | 0.0685 | 0.096 | 3000 | 0.0821 | 0.132 | 0.692 |
60
- | 0.0609 | 0.112 | 3500 | 0.0858 | 0.134 | 0.695 |
61
- | 0.1022 | 0.128 | 4000 | 0.1186 | 0.293 | 0.535 |
62
- | 0.0532 | 0.144 | 4500 | 0.1323 | 0.288 | 0.538 |
63
- | 0.0498 | 0.16 | 5000 | 0.1254 | 0.276 | 0.549 |
64
- | 0.0477 | 0.176 | 5500 | 0.1310 | 0.27 | 0.554 |
65
- | 0.0459 | 0.192 | 6000 | 0.1391 | 0.267 | 0.559 |
66
- | 0.0447 | 0.208 | 6500 | 0.1300 | 0.278 | 0.545 |
67
- | 0.0418 | 0.224 | 7000 | 0.1243 | 0.263 | 0.571 |
68
- | 0.0403 | 0.24 | 7500 | 0.1288 | 0.275 | 0.549 |
69
- | 0.038 | 0.256 | 8000 | 0.1315 | 0.278 | 0.547 |
70
- | 0.0382 | 0.272 | 8500 | 0.1345 | 0.276 | 0.545 |
71
- | 0.0372 | 0.288 | 9000 | 0.1381 | 0.29 | 0.528 |
72
- | 0.0345 | 0.304 | 9500 | 0.1348 | 0.3 | 0.521 |
73
- | 0.0361 | 0.32 | 10000 | 0.1342 | 0.274 | 0.548 |
74
- | 0.0334 | 0.336 | 10500 | 0.1322 | 0.285 | 0.532 |
75
- | 0.0332 | 0.352 | 11000 | 0.1346 | 0.299 | 0.525 |
76
- | 0.0327 | 0.368 | 11500 | 0.1355 | 0.317 | 0.507 |
77
- | 0.0323 | 0.384 | 12000 | 0.1368 | 0.293 | 0.525 |
78
- | 0.0317 | 0.4 | 12500 | 0.1437 | 0.287 | 0.529 |
79
- | 0.03 | 0.416 | 13000 | 0.1419 | 0.322 | 0.499 |
80
- | 0.0299 | 0.432 | 13500 | 0.1427 | 0.315 | 0.503 |
81
- | 0.0289 | 0.448 | 14000 | 0.1461 | 0.291 | 0.525 |
82
- | 0.0292 | 0.464 | 14500 | 0.1512 | 0.297 | 0.516 |
83
- | 0.029 | 0.48 | 15000 | 0.1518 | 0.308 | 0.506 |
84
- | 0.0277 | 0.496 | 15500 | 0.1533 | 0.3 | 0.514 |
85
- | 0.0285 | 0.512 | 16000 | 0.1550 | 0.28 | 0.532 |
86
- | 0.0271 | 0.528 | 16500 | 0.1484 | 0.29 | 0.525 |
87
- | 0.0272 | 0.544 | 17000 | 0.1490 | 0.293 | 0.522 |
88
- | 0.0267 | 0.56 | 17500 | 0.1535 | 0.284 | 0.527 |
89
- | 0.0271 | 0.576 | 18000 | 0.1547 | 0.278 | 0.532 |
90
- | 0.0256 | 0.592 | 18500 | 0.1553 | 0.3 | 0.513 |
91
- | 0.024 | 0.608 | 19000 | 0.1559 | 0.29 | 0.523 |
92
- | 0.0236 | 0.624 | 19500 | 0.1553 | 0.289 | 0.523 |
93
- | 0.0233 | 0.64 | 20000 | 0.1552 | 0.289 | 0.525 |
94
- | 0.022 | 0.656 | 20500 | 0.1565 | 0.288 | 0.525 |
95
- | 0.0222 | 0.672 | 21000 | 0.1568 | 0.288 | 0.522 |
96
- | 0.022 | 0.688 | 21500 | 0.1564 | 0.286 | 0.525 |
97
- | 0.0215 | 0.704 | 22000 | 0.1575 | 0.285 | 0.527 |
98
- | 0.0216 | 0.72 | 22500 | 0.1569 | 0.289 | 0.523 |
99
- | 0.0213 | 0.736 | 23000 | 0.1580 | 0.288 | 0.522 |
100
- | 0.0218 | 0.752 | 23500 | 0.1581 | 0.286 | 0.525 |
101
- | 0.0208 | 0.768 | 24000 | 0.1584 | 0.286 | 0.524 |
102
- | 0.0212 | 0.784 | 24500 | 0.1581 | 0.287 | 0.523 |
103
- | 0.0203 | 0.8 | 25000 | 0.1583 | 0.285 | 0.525 |
104
- | 0.0205 | 0.816 | 25500 | 0.1584 | 0.286 | 0.524 |
105
- | 0.0204 | 0.832 | 26000 | 0.1584 | 0.285 | 0.525 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
 
107
 
108
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0461
22
+ - Wer: 0.07
23
+ - Bleu: 0.847
24
 
25
  ## Model description
26
 
 
44
  - eval_batch_size: 16
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine_with_restarts
48
+ - num_epochs: 2
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Bleu | Validation Loss | Wer |
53
+ |:-------------:|:------:|:------:|:-----:|:---------------:|:-----:|
54
+ | 0.461 | 0.0245 | 2000 | 0.604 | 0.0894 | 0.185 |
55
+ | 0.0683 | 0.0490 | 4000 | 0.683 | 0.0677 | 0.144 |
56
+ | 0.052 | 0.0735 | 6000 | 0.71 | 0.0621 | 0.134 |
57
+ | 0.0427 | 0.0980 | 8000 | 0.732 | 0.0572 | 0.121 |
58
+ | 0.0373 | 0.1225 | 10000 | 0.749 | 0.0531 | 0.113 |
59
+ | 0.0335 | 0.1470 | 12000 | 0.759 | 0.0514 | 0.108 |
60
+ | 0.0397 | 0.1715 | 14000 | 0.77 | 0.0506 | 0.103 |
61
+ | 0.029 | 0.1960 | 16000 | 0.772 | 0.0508 | 0.103 |
62
+ | 0.0277 | 0.2205 | 18000 | 0.779 | 0.0496 | 0.099 |
63
+ | 0.0284 | 0.2450 | 20000 | 0.785 | 0.0468 | 0.096 |
64
+ | 0.0249 | 0.2695 | 22000 | 0.785 | 0.0479 | 0.097 |
65
+ | 0.0239 | 0.2940 | 24000 | 0.787 | 0.0481 | 0.095 |
66
+ | 0.0229 | 0.3185 | 26000 | 0.791 | 0.0473 | 0.094 |
67
+ | 0.0223 | 0.3430 | 28000 | 0.795 | 0.0461 | 0.092 |
68
+ | 0.0216 | 0.3674 | 30000 | 0.798 | 0.0471 | 0.091 |
69
+ | 0.0209 | 0.3919 | 32000 | 0.798 | 0.0467 | 0.091 |
70
+ | 0.0203 | 0.4164 | 34000 | 0.802 | 0.0464 | 0.089 |
71
+ | 0.0202 | 0.4409 | 36000 | 0.806 | 0.0454 | 0.087 |
72
+ | 0.0194 | 0.4654 | 38000 | 0.806 | 0.0462 | 0.087 |
73
+ | 0.0187 | 0.4899 | 40000 | 0.806 | 0.0471 | 0.087 |
74
+ | 0.0184 | 0.5144 | 42000 | 0.809 | 0.0462 | 0.086 |
75
+ | 0.0179 | 0.5389 | 44000 | 0.811 | 0.0444 | 0.085 |
76
+ | 0.0176 | 0.5634 | 46000 | 0.812 | 0.0460 | 0.085 |
77
+ | 0.0174 | 0.5879 | 48000 | 0.811 | 0.0469 | 0.086 |
78
+ | 0.0171 | 0.6124 | 50000 | 0.813 | 0.0465 | 0.084 |
79
+ | 0.0166 | 0.6369 | 52000 | 0.816 | 0.0446 | 0.083 |
80
+ | 0.016 | 0.6614 | 54000 | 0.816 | 0.0461 | 0.083 |
81
+ | 0.0162 | 0.6859 | 56000 | 0.818 | 0.0451 | 0.082 |
82
+ | 0.0158 | 0.7104 | 58000 | 0.819 | 0.0449 | 0.082 |
83
+ | 0.0156 | 0.7349 | 60000 | 0.818 | 0.0454 | 0.082 |
84
+ | 0.0157 | 0.7594 | 62000 | 0.82 | 0.0455 | 0.082 |
85
+ | 0.015 | 0.7839 | 64000 | 0.822 | 0.0455 | 0.081 |
86
+ | 0.0148 | 0.8084 | 66000 | 0.822 | 0.0461 | 0.081 |
87
+ | 0.0146 | 0.8329 | 68000 | 0.823 | 0.0460 | 0.08 |
88
+ | 0.0145 | 0.8574 | 70000 | 0.824 | 0.0446 | 0.08 |
89
+ | 0.0144 | 0.8819 | 72000 | 0.824 | 0.0450 | 0.079 |
90
+ | 0.0141 | 0.9064 | 74000 | 0.822 | 0.0477 | 0.081 |
91
+ | 0.0139 | 0.9309 | 76000 | 0.826 | 0.0446 | 0.079 |
92
+ | 0.0137 | 0.9554 | 78000 | 0.827 | 0.0452 | 0.078 |
93
+ | 0.0136 | 0.9799 | 80000 | 0.827 | 0.0455 | 0.078 |
94
+ | 0.0128 | 1.0044 | 82000 | 0.829 | 0.0462 | 0.078 |
95
+ | 0.0104 | 1.0289 | 84000 | 0.829 | 0.0456 | 0.077 |
96
+ | 0.0105 | 1.0534 | 86000 | 0.829 | 0.0465 | 0.078 |
97
+ | 0.0103 | 1.0779 | 88000 | 0.831 | 0.0443 | 0.077 |
98
+ | 0.01 | 1.1023 | 90000 | 0.829 | 0.0456 | 0.077 |
99
+ | 0.0103 | 1.1268 | 92000 | 0.83 | 0.0466 | 0.077 |
100
+ | 0.0101 | 1.1513 | 94000 | 0.832 | 0.0462 | 0.076 |
101
+ | 0.01 | 1.1758 | 96000 | 0.832 | 0.0458 | 0.076 |
102
+ | 0.01 | 1.2003 | 98000 | 0.834 | 0.0460 | 0.075 |
103
+ | 0.0098 | 1.2248 | 100000 | 0.834 | 0.0464 | 0.076 |
104
+ | 0.0098 | 1.2493 | 102000 | 0.834 | 0.0455 | 0.075 |
105
+ | 0.0096 | 1.2738 | 104000 | 0.836 | 0.0453 | 0.075 |
106
+ | 0.0099 | 1.2983 | 106000 | 0.835 | 0.0469 | 0.075 |
107
+ | 0.0095 | 1.3228 | 108000 | 0.836 | 0.0466 | 0.075 |
108
+ | 0.0094 | 1.3473 | 110000 | 0.836 | 0.0461 | 0.075 |
109
+ | 0.0094 | 1.3718 | 112000 | 0.837 | 0.0465 | 0.074 |
110
+ | 0.0093 | 1.3963 | 114000 | 0.838 | 0.0469 | 0.074 |
111
+ | 0.0092 | 1.4208 | 116000 | 0.838 | 0.0469 | 0.074 |
112
+ | 0.0092 | 1.4453 | 118000 | 0.838 | 0.0476 | 0.074 |
113
+ | 0.0092 | 1.4698 | 120000 | 0.839 | 0.0466 | 0.074 |
114
+ | 0.0091 | 1.4943 | 122000 | 0.841 | 0.0462 | 0.072 |
115
+ | 0.0089 | 1.5188 | 124000 | 0.839 | 0.0470 | 0.074 |
116
+ | 0.0088 | 1.5433 | 126000 | 0.839 | 0.0473 | 0.073 |
117
+ | 0.0087 | 1.5678 | 128000 | 0.841 | 0.0457 | 0.073 |
118
+ | 0.0086 | 1.5923 | 130000 | 0.843 | 0.0453 | 0.072 |
119
+ | 0.0085 | 1.6168 | 132000 | 0.841 | 0.0471 | 0.073 |
120
+ | 0.0086 | 1.6413 | 134000 | 0.842 | 0.0471 | 0.072 |
121
+ | 0.0086 | 1.6658 | 136000 | 0.844 | 0.0446 | 0.072 |
122
+ | 0.0082 | 1.6903 | 138000 | 0.0458| 0.071 | 0.844 |
123
+ | 0.008 | 1.7148 | 140000 | 0.0460| 0.071 | 0.845 |
124
+ | 0.0078 | 1.7393 | 142000 | 0.0460| 0.071 | 0.846 |
125
+ | 0.008 | 1.7638 | 144000 | 0.0456| 0.07 | 0.846 |
126
+ | 0.0077 | 1.7883 | 146000 | 0.0461| 0.071 | 0.847 |
127
+ | 0.0077 | 1.8127 | 148000 | 0.0460| 0.07 | 0.847 |
128
+ | 0.0077 | 1.8372 | 150000 | 0.0464| 0.07 | 0.847 |
129
+ | 0.0076 | 1.8617 | 152000 | 0.0463| 0.07 | 0.847 |
130
+ | 0.0076 | 1.8862 | 154000 | 0.0462| 0.07 | 0.847 |
131
+ | 0.0076 | 1.9107 | 156000 | 0.0461| 0.07 | 0.847 |
132
 
133
 
134
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:addacef578873958c9fac3c364f786a8a4e572e49ded56711e918db0d448b34d
3
  size 2444578688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee6a48f1530d399b97e21f7c6abf022900a704c34edcc962a59d03887b232b4
3
  size 2444578688