Hugging Face's logo

gayanin
/
bart-noised-with-all-dist

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
gayanin commited on
Commit
e2707de
•
1 Parent(s): 756b100

End of training

Browse files
Files changed (2) hide show
  1. README.md +30 -142
  2. model.safetensors +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.5676
19
 
20
  ## Model description
21
 
@@ -41,153 +41,41 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 10
44
- - num_epochs: 5
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
- | 0.8623 | 0.04 | 500 | 0.7548 |
52
- | 0.8068 | 0.07 | 1000 | 0.7303 |
53
- | 0.737 | 0.11 | 1500 | 0.6990 |
54
- | 0.7218 | 0.14 | 2000 | 0.6914 |
55
- | 0.6651 | 0.18 | 2500 | 0.6626 |
56
- | 0.7029 | 0.21 | 3000 | 0.6471 |
57
- | 0.7005 | 0.25 | 3500 | 0.6587 |
58
- | 0.5888 | 0.29 | 4000 | 0.6436 |
59
- | 0.7348 | 0.32 | 4500 | 0.6318 |
60
- | 0.6163 | 0.36 | 5000 | 0.6303 |
61
- | 0.6713 | 0.39 | 5500 | 0.6231 |
62
- | 0.6785 | 0.43 | 6000 | 0.6144 |
63
- | 0.5977 | 0.46 | 6500 | 0.6138 |
64
- | 0.6054 | 0.5 | 7000 | 0.6260 |
65
- | 0.6999 | 0.54 | 7500 | 0.6011 |
66
- | 0.609 | 0.57 | 8000 | 0.6104 |
67
- | 0.6847 | 0.61 | 8500 | 0.5991 |
68
- | 0.6034 | 0.64 | 9000 | 0.6010 |
69
- | 0.633 | 0.68 | 9500 | 0.5930 |
70
- | 0.5587 | 0.71 | 10000 | 0.5913 |
71
- | 0.5923 | 0.75 | 10500 | 0.5906 |
72
- | 0.6014 | 0.79 | 11000 | 0.5943 |
73
- | 0.5995 | 0.82 | 11500 | 0.5798 |
74
- | 0.5985 | 0.86 | 12000 | 0.5874 |
75
- | 0.5695 | 0.89 | 12500 | 0.5791 |
76
- | 0.5503 | 0.93 | 13000 | 0.5723 |
77
- | 0.4953 | 0.96 | 13500 | 0.5799 |
78
- | 0.56 | 1.0 | 14000 | 0.5806 |
79
- | 0.5176 | 1.03 | 14500 | 0.5809 |
80
- | 0.5437 | 1.07 | 15000 | 0.5758 |
81
- | 0.4667 | 1.11 | 15500 | 0.5769 |
82
- | 0.5583 | 1.14 | 16000 | 0.5729 |
83
- | 0.5239 | 1.18 | 16500 | 0.5826 |
84
- | 0.5363 | 1.21 | 17000 | 0.5719 |
85
- | 0.4974 | 1.25 | 17500 | 0.5768 |
86
- | 0.5269 | 1.28 | 18000 | 0.5756 |
87
- | 0.4757 | 1.32 | 18500 | 0.5690 |
88
- | 0.5561 | 1.36 | 19000 | 0.5736 |
89
- | 0.5894 | 1.39 | 19500 | 0.5712 |
90
- | 0.4579 | 1.43 | 20000 | 0.5740 |
91
- | 0.5121 | 1.46 | 20500 | 0.5721 |
92
- | 0.4792 | 1.5 | 21000 | 0.5679 |
93
- | 0.4931 | 1.53 | 21500 | 0.5648 |
94
- | 0.5022 | 1.57 | 22000 | 0.5655 |
95
- | 0.4695 | 1.61 | 22500 | 0.5662 |
96
- | 0.4898 | 1.64 | 23000 | 0.5589 |
97
- | 0.4569 | 1.68 | 23500 | 0.5617 |
98
- | 0.4615 | 1.71 | 24000 | 0.5645 |
99
- | 0.5262 | 1.75 | 24500 | 0.5568 |
100
- | 0.5437 | 1.78 | 25000 | 0.5586 |
101
- | 0.4631 | 1.82 | 25500 | 0.5570 |
102
- | 0.4292 | 1.86 | 26000 | 0.5561 |
103
- | 0.5198 | 1.89 | 26500 | 0.5518 |
104
- | 0.5068 | 1.93 | 27000 | 0.5574 |
105
- | 0.4675 | 1.96 | 27500 | 0.5523 |
106
- | 0.4849 | 2.0 | 28000 | 0.5534 |
107
- | 0.4484 | 2.03 | 28500 | 0.5542 |
108
- | 0.4749 | 2.07 | 29000 | 0.5600 |
109
- | 0.3938 | 2.11 | 29500 | 0.5651 |
110
- | 0.4612 | 2.14 | 30000 | 0.5626 |
111
- | 0.4312 | 2.18 | 30500 | 0.5603 |
112
- | 0.4445 | 2.21 | 31000 | 0.5618 |
113
- | 0.3791 | 2.25 | 31500 | 0.5641 |
114
- | 0.3479 | 2.28 | 32000 | 0.5663 |
115
- | 0.3915 | 2.32 | 32500 | 0.5587 |
116
- | 0.4059 | 2.36 | 33000 | 0.5609 |
117
- | 0.3878 | 2.39 | 33500 | 0.5560 |
118
- | 0.4037 | 2.43 | 34000 | 0.5594 |
119
- | 0.3777 | 2.46 | 34500 | 0.5598 |
120
- | 0.3951 | 2.5 | 35000 | 0.5614 |
121
- | 0.4559 | 2.53 | 35500 | 0.5555 |
122
- | 0.4278 | 2.57 | 36000 | 0.5561 |
123
- | 0.4257 | 2.61 | 36500 | 0.5563 |
124
- | 0.3591 | 2.64 | 37000 | 0.5574 |
125
- | 0.4384 | 2.68 | 37500 | 0.5509 |
126
- | 0.4111 | 2.71 | 38000 | 0.5536 |
127
- | 0.4737 | 2.75 | 38500 | 0.5541 |
128
- | 0.3908 | 2.78 | 39000 | 0.5490 |
129
- | 0.4793 | 2.82 | 39500 | 0.5518 |
130
- | 0.396 | 2.85 | 40000 | 0.5533 |
131
- | 0.4084 | 2.89 | 40500 | 0.5538 |
132
- | 0.3882 | 2.93 | 41000 | 0.5467 |
133
- | 0.3706 | 2.96 | 41500 | 0.5521 |
134
- | 0.3878 | 3.0 | 42000 | 0.5474 |
135
- | 0.3912 | 3.03 | 42500 | 0.5681 |
136
- | 0.3462 | 3.07 | 43000 | 0.5584 |
137
- | 0.3472 | 3.1 | 43500 | 0.5635 |
138
- | 0.3646 | 3.14 | 44000 | 0.5596 |
139
- | 0.3612 | 3.18 | 44500 | 0.5647 |
140
- | 0.3543 | 3.21 | 45000 | 0.5650 |
141
- | 0.2984 | 3.25 | 45500 | 0.5639 |
142
- | 0.3568 | 3.28 | 46000 | 0.5631 |
143
- | 0.3502 | 3.32 | 46500 | 0.5613 |
144
- | 0.3667 | 3.35 | 47000 | 0.5662 |
145
- | 0.3191 | 3.39 | 47500 | 0.5624 |
146
- | 0.3204 | 3.43 | 48000 | 0.5657 |
147
- | 0.3194 | 3.46 | 48500 | 0.5649 |
148
- | 0.2981 | 3.5 | 49000 | 0.5662 |
149
- | 0.375 | 3.53 | 49500 | 0.5606 |
150
- | 0.3578 | 3.57 | 50000 | 0.5609 |
151
- | 0.3479 | 3.6 | 50500 | 0.5573 |
152
- | 0.3521 | 3.64 | 51000 | 0.5637 |
153
- | 0.3181 | 3.68 | 51500 | 0.5569 |
154
- | 0.3442 | 3.71 | 52000 | 0.5613 |
155
- | 0.3702 | 3.75 | 52500 | 0.5594 |
156
- | 0.3746 | 3.78 | 53000 | 0.5600 |
157
- | 0.3558 | 3.82 | 53500 | 0.5564 |
158
- | 0.3115 | 3.85 | 54000 | 0.5599 |
159
- | 0.3981 | 3.89 | 54500 | 0.5577 |
160
- | 0.3288 | 3.93 | 55000 | 0.5592 |
161
- | 0.3343 | 3.96 | 55500 | 0.5570 |
162
- | 0.3343 | 4.0 | 56000 | 0.5579 |
163
- | 0.296 | 4.03 | 56500 | 0.5695 |
164
- | 0.2929 | 4.07 | 57000 | 0.5696 |
165
- | 0.2685 | 4.1 | 57500 | 0.5731 |
166
- | 0.3035 | 4.14 | 58000 | 0.5739 |
167
- | 0.2659 | 4.18 | 58500 | 0.5714 |
168
- | 0.3264 | 4.21 | 59000 | 0.5701 |
169
- | 0.2972 | 4.25 | 59500 | 0.5691 |
170
- | 0.268 | 4.28 | 60000 | 0.5708 |
171
- | 0.2955 | 4.32 | 60500 | 0.5703 |
172
- | 0.2835 | 4.35 | 61000 | 0.5708 |
173
- | 0.3155 | 4.39 | 61500 | 0.5700 |
174
- | 0.2889 | 4.43 | 62000 | 0.5703 |
175
- | 0.3049 | 4.46 | 62500 | 0.5699 |
176
- | 0.3365 | 4.5 | 63000 | 0.5678 |
177
- | 0.292 | 4.53 | 63500 | 0.5682 |
178
- | 0.2916 | 4.57 | 64000 | 0.5676 |
179
- | 0.2964 | 4.6 | 64500 | 0.5705 |
180
- | 0.3321 | 4.64 | 65000 | 0.5671 |
181
- | 0.2957 | 4.67 | 65500 | 0.5698 |
182
- | 0.283 | 4.71 | 66000 | 0.5682 |
183
- | 0.3122 | 4.75 | 66500 | 0.5669 |
184
- | 0.2494 | 4.78 | 67000 | 0.5670 |
185
- | 0.2907 | 4.82 | 67500 | 0.5683 |
186
- | 0.3373 | 4.85 | 68000 | 0.5671 |
187
- | 0.2861 | 4.89 | 68500 | 0.5676 |
188
- | 0.3375 | 4.92 | 69000 | 0.5682 |
189
- | 0.28 | 4.96 | 69500 | 0.5676 |
190
- | 0.328 | 5.0 | 70000 | 0.5676 |
191
 
192
 
193
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5751
19
 
20
  ## Model description
21
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 10
44
+ - num_epochs: 3
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.7697 | 0.11 | 500 | 0.7542 |
52
+ | 0.8211 | 0.21 | 1000 | 0.7434 |
53
+ | 0.7764 | 0.32 | 1500 | 0.6996 |
54
+ | 0.7867 | 0.43 | 2000 | 0.6640 |
55
+ | 0.6795 | 0.54 | 2500 | 0.6581 |
56
+ | 0.6778 | 0.64 | 3000 | 0.6535 |
57
+ | 0.7028 | 0.75 | 3500 | 0.6547 |
58
+ | 0.7104 | 0.86 | 4000 | 0.6318 |
59
+ | 0.7032 | 0.96 | 4500 | 0.6213 |
60
+ | 0.6062 | 1.07 | 5000 | 0.6157 |
61
+ | 0.5789 | 1.18 | 5500 | 0.6175 |
62
+ | 0.5689 | 1.28 | 6000 | 0.6118 |
63
+ | 0.5183 | 1.39 | 6500 | 0.6147 |
64
+ | 0.5834 | 1.5 | 7000 | 0.5938 |
65
+ | 0.5708 | 1.61 | 7500 | 0.5964 |
66
+ | 0.5118 | 1.71 | 8000 | 0.5924 |
67
+ | 0.5284 | 1.82 | 8500 | 0.5900 |
68
+ | 0.5192 | 1.93 | 9000 | 0.5936 |
69
+ | 0.5358 | 2.03 | 9500 | 0.5879 |
70
+ | 0.4422 | 2.14 | 10000 | 0.5948 |
71
+ | 0.4852 | 2.25 | 10500 | 0.5917 |
72
+ | 0.4383 | 2.35 | 11000 | 0.5847 |
73
+ | 0.552 | 2.46 | 11500 | 0.5824 |
74
+ | 0.4464 | 2.57 | 12000 | 0.5810 |
75
+ | 0.4089 | 2.68 | 12500 | 0.5793 |
76
+ | 0.4898 | 2.78 | 13000 | 0.5749 |
77
+ | 0.4753 | 2.89 | 13500 | 0.5794 |
78
+ | 0.4579 | 3.0 | 14000 | 0.5751 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f3850d74a3a338ffbe7a8bb4f5bc2607e304aa413d02499537d6b3a126eea88
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47fef28b188dc006949e312a9e9697570e0ee2e39d659c1442414a7e8aac22b
3
  size 557912620