Hugging Face's logo

kmok1
/
cs_mT5_0.01_100_v0.2

Text2Text Generation
Transformers
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Community
kmok1 commited on
Commit
575682f
•
1 Parent(s): 3bb9435

End of training

Browse files
Files changed (3) hide show
  1. README.md +160 -0
  2. generation_config.json +6 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: cs_mT5_0.01_100_v0.2
10
+ results: []
11
+ ---
12
+
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
+ # cs_mT5_0.01_100_v0.2
17
+
18
+ This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 7.1529
21
+ - Bleu: 1.1802
22
+ - Gen Len: 19.0
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.01
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 100
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
53
+ | 7.8225 | 1.0 | 6 | 7.8823 | 0.1442 | 19.0 |
54
+ | 6.4593 | 2.0 | 12 | 6.2595 | 0.0 | 19.0 |
55
+ | 5.7362 | 3.0 | 18 | 5.8728 | 0.5829 | 19.0 |
56
+ | 5.1022 | 4.0 | 24 | 6.0663 | 0.5829 | 19.0 |
57
+ | 5.1499 | 5.0 | 30 | 6.1787 | 0.5829 | 19.0 |
58
+ | 4.4478 | 6.0 | 36 | 6.1807 | 0.2295 | 19.0 |
59
+ | 4.6633 | 7.0 | 42 | 5.8996 | 0.5829 | 19.0 |
60
+ | 4.6893 | 8.0 | 48 | 6.0757 | 0.0 | 19.0 |
61
+ | 5.3314 | 9.0 | 54 | 5.8488 | 0.5829 | 19.0 |
62
+ | 4.9772 | 10.0 | 60 | 5.8862 | 0.5829 | 19.0 |
63
+ | 4.6109 | 11.0 | 66 | 6.0246 | 0.6041 | 19.0 |
64
+ | 4.133 | 12.0 | 72 | 5.9013 | 0.5829 | 19.0 |
65
+ | 4.9029 | 13.0 | 78 | 6.0611 | 0.6006 | 19.0 |
66
+ | 3.9306 | 14.0 | 84 | 5.8331 | 0.5938 | 19.0 |
67
+ | 4.2939 | 15.0 | 90 | 6.0608 | 0.202 | 19.0 |
68
+ | 3.7392 | 16.0 | 96 | 5.9132 | 0.4958 | 19.0 |
69
+ | 4.0965 | 17.0 | 102 | 6.0289 | 0.6011 | 19.0 |
70
+ | 4.8056 | 18.0 | 108 | 5.8952 | 0.6233 | 19.0 |
71
+ | 4.9226 | 19.0 | 114 | 6.1260 | 0.2865 | 19.0 |
72
+ | 3.463 | 20.0 | 120 | 6.0577 | 0.5829 | 19.0 |
73
+ | 3.6935 | 21.0 | 126 | 5.9865 | 0.6482 | 19.0 |
74
+ | 4.8423 | 22.0 | 132 | 6.1672 | 0.5938 | 19.0 |
75
+ | 4.1419 | 23.0 | 138 | 5.9532 | 0.0 | 19.0 |
76
+ | 4.114 | 24.0 | 144 | 5.9337 | 0.1363 | 19.0 |
77
+ | 3.687 | 25.0 | 150 | 5.9786 | 0.0 | 19.0 |
78
+ | 4.4531 | 26.0 | 156 | 6.2074 | 0.1645 | 8.0 |
79
+ | 3.7463 | 27.0 | 162 | 6.1692 | 0.0 | 19.0 |
80
+ | 4.1026 | 28.0 | 168 | 6.0478 | 0.0 | 19.0 |
81
+ | 3.8369 | 29.0 | 174 | 6.0615 | 0.0 | 19.0 |
82
+ | 3.7155 | 30.0 | 180 | 6.1976 | 0.6323 | 19.0 |
83
+ | 3.8799 | 31.0 | 186 | 6.2384 | 0.0 | 19.0 |
84
+ | 4.2195 | 32.0 | 192 | 6.1328 | 0.5829 | 19.0 |
85
+ | 5.1049 | 33.0 | 198 | 5.9780 | 0.5829 | 19.0 |
86
+ | 4.1496 | 34.0 | 204 | 6.0294 | 0.6233 | 19.0 |
87
+ | 3.8001 | 35.0 | 210 | 6.1042 | 0.1346 | 19.0 |
88
+ | 3.4327 | 36.0 | 216 | 5.8325 | 0.1023 | 19.0 |
89
+ | 4.1074 | 37.0 | 222 | 6.1190 | 0.611 | 19.0 |
90
+ | 3.84 | 38.0 | 228 | 6.4321 | 0.2321 | 19.0 |
91
+ | 3.7483 | 39.0 | 234 | 6.2523 | 0.2795 | 19.0 |
92
+ | 3.9157 | 40.0 | 240 | 6.2355 | 0.4213 | 19.0 |
93
+ | 3.3449 | 41.0 | 246 | 6.1757 | 0.611 | 19.0 |
94
+ | 3.5886 | 42.0 | 252 | 6.0657 | 0.5938 | 19.0 |
95
+ | 3.5048 | 43.0 | 258 | 6.0277 | 0.5829 | 19.0 |
96
+ | 3.7519 | 44.0 | 264 | 6.5569 | 0.681 | 19.0 |
97
+ | 3.7334 | 45.0 | 270 | 6.0739 | 0.5938 | 19.0 |
98
+ | 3.8206 | 46.0 | 276 | 6.0092 | 0.6401 | 19.0 |
99
+ | 3.5061 | 47.0 | 282 | 6.0719 | 0.6488 | 19.0 |
100
+ | 3.4392 | 48.0 | 288 | 6.0652 | 0.59 | 19.0 |
101
+ | 3.6158 | 49.0 | 294 | 6.0207 | 0.5829 | 19.0 |
102
+ | 3.1909 | 50.0 | 300 | 6.2023 | 0.1442 | 19.0 |
103
+ | 3.2138 | 51.0 | 306 | 6.1003 | 0.6233 | 19.0 |
104
+ | 4.0992 | 52.0 | 312 | 6.2286 | 0.5896 | 19.0 |
105
+ | 3.4983 | 53.0 | 318 | 6.2911 | 0.6006 | 19.0 |
106
+ | 3.0111 | 54.0 | 324 | 6.4124 | 0.3004 | 11.0 |
107
+ | 3.251 | 55.0 | 330 | 5.9168 | 0.7833 | 14.0 |
108
+ | 3.2281 | 56.0 | 336 | 6.0207 | 0.3379 | 19.0 |
109
+ | 3.6692 | 57.0 | 342 | 6.1399 | 0.6395 | 19.0 |
110
+ | 2.8706 | 58.0 | 348 | 6.4675 | 0.2317 | 19.0 |
111
+ | 3.7137 | 59.0 | 354 | 6.1596 | 0.0 | 19.0 |
112
+ | 3.6537 | 60.0 | 360 | 6.2131 | 0.5938 | 19.0 |
113
+ | 3.2023 | 61.0 | 366 | 6.2877 | 0.6323 | 19.0 |
114
+ | 2.3914 | 62.0 | 372 | 6.5001 | 0.6323 | 19.0 |
115
+ | 2.8612 | 63.0 | 378 | 6.5683 | 0.7084 | 19.0 |
116
+ | 3.1646 | 64.0 | 384 | 6.7003 | 0.2039 | 9.0 |
117
+ | 3.1234 | 65.0 | 390 | 6.1225 | 0.4851 | 11.0 |
118
+ | 3.0967 | 66.0 | 396 | 6.2517 | 0.5896 | 19.0 |
119
+ | 2.5832 | 67.0 | 402 | 6.3071 | 0.5896 | 19.0 |
120
+ | 3.2709 | 68.0 | 408 | 6.5033 | 0.6482 | 19.0 |
121
+ | 3.2511 | 69.0 | 414 | 6.4329 | 0.6395 | 19.0 |
122
+ | 2.7053 | 70.0 | 420 | 6.5449 | 0.6323 | 19.0 |
123
+ | 3.4684 | 71.0 | 426 | 6.9512 | 0.2914 | 19.0 |
124
+ | 2.7875 | 72.0 | 432 | 6.6579 | 0.6006 | 19.0 |
125
+ | 2.5674 | 73.0 | 438 | 6.4629 | 0.6395 | 19.0 |
126
+ | 2.3457 | 74.0 | 444 | 6.6680 | 0.7084 | 19.0 |
127
+ | 2.339 | 75.0 | 450 | 6.7313 | 0.7333 | 19.0 |
128
+ | 3.4058 | 76.0 | 456 | 6.7786 | 0.3105 | 16.0 |
129
+ | 2.5678 | 77.0 | 462 | 6.6553 | 0.5896 | 19.0 |
130
+ | 2.9506 | 78.0 | 468 | 6.9532 | 0.3379 | 19.0 |
131
+ | 2.2285 | 79.0 | 474 | 7.1575 | 0.191 | 6.0 |
132
+ | 2.5635 | 80.0 | 480 | 7.1580 | 0.2837 | 15.0 |
133
+ | 1.8763 | 81.0 | 486 | 7.0203 | 0.5896 | 19.0 |
134
+ | 3.3663 | 82.0 | 492 | 6.7150 | 0.5896 | 19.0 |
135
+ | 2.1434 | 83.0 | 498 | 6.5911 | 0.5896 | 19.0 |
136
+ | 2.6678 | 84.0 | 504 | 6.7084 | 0.5829 | 19.0 |
137
+ | 3.7082 | 85.0 | 510 | 6.7475 | 0.4447 | 13.0 |
138
+ | 3.3436 | 86.0 | 516 | 6.6436 | 0.2223 | 19.0 |
139
+ | 2.3866 | 87.0 | 522 | 6.6915 | 0.5896 | 19.0 |
140
+ | 2.0647 | 88.0 | 528 | 7.0000 | 0.5896 | 19.0 |
141
+ | 2.7861 | 89.0 | 534 | 7.1116 | 0.1346 | 19.0 |
142
+ | 2.5331 | 90.0 | 540 | 7.0207 | 0.0 | 19.0 |
143
+ | 2.3609 | 91.0 | 546 | 7.0159 | 0.2837 | 12.0 |
144
+ | 2.5884 | 92.0 | 552 | 6.9928 | 0.1628 | 19.0 |
145
+ | 2.2198 | 93.0 | 558 | 7.0179 | 0.6885 | 19.0 |
146
+ | 2.4258 | 94.0 | 564 | 7.0429 | 0.5938 | 19.0 |
147
+ | 1.9681 | 95.0 | 570 | 7.0348 | 1.3808 | 19.0 |
148
+ | 2.2643 | 96.0 | 576 | 7.0513 | 1.1802 | 19.0 |
149
+ | 2.1551 | 97.0 | 582 | 7.0741 | 1.1558 | 19.0 |
150
+ | 2.1624 | 98.0 | 588 | 7.1079 | 1.1558 | 19.0 |
151
+ | 2.6342 | 99.0 | 594 | 7.1447 | 1.1558 | 19.0 |
152
+ | 1.1566 | 100.0 | 600 | 7.1529 | 1.1802 | 19.0 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.35.2
158
+ - Pytorch 1.13.1+cu117
159
+ - Datasets 2.17.0
160
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.35.2"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d96130343565a4539c14873c4ec492773cb552587510c8df85328ee7decde352
3
  size 2329638768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1c87d7f8fb71343ff856a2c393df14849cfa79925d83198b4850fe37cf6859
3
  size 2329638768