Hugging Face's logo

bbunijieun
/
seq2seq_huggingface_mix_results

Transformers
Safetensors
transformer
Generated from Trainer
Inference Endpoints
Model card Files Community
bbunijieun commited on
Commit
d8f3f34
·
verified ·
1 Parent(s): e0fee29

Initial model training

Browse files
Files changed (2) hide show
  1. README.md +22 -64
  2. model.safetensors +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 7.0175
17
 
18
  ## Model description
19
 
@@ -41,75 +41,33 @@ 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: 500
44
- - num_epochs: 3
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
- | 10.5072 | 0.0480 | 10 | 10.4491 |
52
- | 10.3574 | 0.0959 | 20 | 10.1991 |
53
- | 10.0831 | 0.1439 | 30 | 9.8790 |
54
- | 9.7946 | 0.1918 | 40 | 9.5780 |
55
- | 9.5118 | 0.2398 | 50 | 9.3344 |
56
- | 9.3333 | 0.2878 | 60 | 9.1722 |
57
- | 9.1888 | 0.3357 | 70 | 9.0610 |
58
- | 9.0913 | 0.3837 | 80 | 8.9742 |
59
- | 9.0007 | 0.4317 | 90 | 8.9005 |
60
- | 8.9134 | 0.4796 | 100 | 8.8328 |
61
- | 8.8583 | 0.5276 | 110 | 8.7615 |
62
- | 8.7722 | 0.5755 | 120 | 8.6873 |
63
- | 8.7092 | 0.6235 | 130 | 8.6137 |
64
- | 8.6223 | 0.6715 | 140 | 8.5340 |
65
- | 8.5312 | 0.7194 | 150 | 8.4538 |
66
- | 8.4582 | 0.7674 | 160 | 8.3681 |
67
- | 8.3748 | 0.8153 | 170 | 8.2801 |
68
- | 8.2637 | 0.8633 | 180 | 8.1936 |
69
- | 8.1704 | 0.9113 | 190 | 8.1001 |
70
- | 8.0697 | 0.9592 | 200 | 8.0079 |
71
- | 7.9792 | 1.0072 | 210 | 7.9126 |
72
- | 7.9 | 1.0552 | 220 | 7.8175 |
73
- | 7.8134 | 1.1031 | 230 | 7.7236 |
74
- | 7.7153 | 1.1511 | 240 | 7.6328 |
75
- | 7.6087 | 1.1990 | 250 | 7.5477 |
76
- | 7.5328 | 1.2470 | 260 | 7.4634 |
77
- | 7.4347 | 1.2950 | 270 | 7.3862 |
78
- | 7.3531 | 1.3429 | 280 | 7.3179 |
79
- | 7.3059 | 1.3909 | 290 | 7.2513 |
80
- | 7.2403 | 1.4388 | 300 | 7.1955 |
81
- | 7.2128 | 1.4868 | 310 | 7.1506 |
82
- | 7.1508 | 1.5348 | 320 | 7.1105 |
83
- | 7.1104 | 1.5827 | 330 | 7.0835 |
84
- | 7.067 | 1.6307 | 340 | 7.0655 |
85
- | 7.0594 | 1.6787 | 350 | 7.0558 |
86
- | 7.0591 | 1.7266 | 360 | 7.0411 |
87
- | 7.0129 | 1.7746 | 370 | 7.0381 |
88
- | 7.0107 | 1.8225 | 380 | 7.0344 |
89
- | 7.0549 | 1.8705 | 390 | 7.0268 |
90
- | 7.0358 | 1.9185 | 400 | 7.0249 |
91
- | 7.0395 | 1.9664 | 410 | 7.0242 |
92
- | 7.0105 | 2.0144 | 420 | 7.0215 |
93
- | 7.0113 | 2.0624 | 430 | 7.0259 |
94
- | 6.9985 | 2.1103 | 440 | 7.0213 |
95
- | 7.0218 | 2.1583 | 450 | 7.0218 |
96
- | 6.9735 | 2.2062 | 460 | 7.0275 |
97
- | 7.0132 | 2.2542 | 470 | 7.0254 |
98
- | 7.0241 | 2.3022 | 480 | 7.0219 |
99
- | 7.0127 | 2.3501 | 490 | 7.0238 |
100
- | 6.9644 | 2.3981 | 500 | 7.0249 |
101
- | 7.0103 | 2.4460 | 510 | 7.0259 |
102
- | 7.006 | 2.4940 | 520 | 7.0266 |
103
- | 6.9882 | 2.5420 | 530 | 7.0235 |
104
- | 7.0016 | 2.5899 | 540 | 7.0235 |
105
- | 7.002 | 2.6379 | 550 | 7.0217 |
106
- | 6.9782 | 2.6859 | 560 | 7.0196 |
107
- | 6.9833 | 2.7338 | 570 | 7.0198 |
108
- | 6.9967 | 2.7818 | 580 | 7.0202 |
109
- | 6.9644 | 2.8297 | 590 | 7.0196 |
110
- | 6.9825 | 2.8777 | 600 | 7.0199 |
111
- | 7.0097 | 2.9257 | 610 | 7.0178 |
112
- | 6.9909 | 2.9736 | 620 | 7.0175 |
113
 
114
 
115
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 7.9457
17
 
18
  ## Model description
19
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 1
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
+ | 10.7021 | 0.0480 | 10 | 10.6458 |
52
+ | 10.5611 | 0.0959 | 20 | 10.4143 |
53
+ | 10.2935 | 0.1439 | 30 | 10.0786 |
54
+ | 9.9673 | 0.1918 | 40 | 9.7462 |
55
+ | 9.6468 | 0.2398 | 50 | 9.4724 |
56
+ | 9.4303 | 0.2878 | 60 | 9.2583 |
57
+ | 9.2452 | 0.3357 | 70 | 9.1136 |
58
+ | 9.1357 | 0.3837 | 80 | 9.0100 |
59
+ | 9.0307 | 0.4317 | 90 | 8.9296 |
60
+ | 8.9363 | 0.4796 | 100 | 8.8591 |
61
+ | 8.8781 | 0.5276 | 110 | 8.7821 |
62
+ | 8.7907 | 0.5755 | 120 | 8.7088 |
63
+ | 8.7214 | 0.6235 | 130 | 8.6329 |
64
+ | 8.6375 | 0.6715 | 140 | 8.5511 |
65
+ | 8.5439 | 0.7194 | 150 | 8.4701 |
66
+ | 8.4715 | 0.7674 | 160 | 8.3835 |
67
+ | 8.389 | 0.8153 | 170 | 8.2962 |
68
+ | 8.2787 | 0.8633 | 180 | 8.2072 |
69
+ | 8.1826 | 0.9113 | 190 | 8.1146 |
70
+ | 8.0848 | 0.9592 | 200 | 8.0225 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c4d450c24368b42271e65a1f934af6e1fb78361eb03ead224038471e180c732
3
  size 310717424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bbf477e86932cb8f6a5d9e8fc32017cd44e35d8a891033d4cd65fa1cc1cdcb6
3
  size 310717424