edwinlaw commited on
Commit
7025143
1 Parent(s): f1512d2

End of training

Browse files
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 3.7189
21
- - Bleu: 1.3095
22
- - Gen Len: 12.8089
23
 
24
  ## Model description
25
 
@@ -44,63 +44,23 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 50
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
54
- | No log | 1.0 | 62 | 4.0260 | 0.5212 | 12.1748 |
55
- | No log | 2.0 | 124 | 3.9917 | 0.5398 | 12.2033 |
56
- | No log | 3.0 | 186 | 3.9573 | 0.923 | 12.0894 |
57
- | No log | 4.0 | 248 | 3.9330 | 0.9257 | 12.252 |
58
- | No log | 5.0 | 310 | 3.9073 | 0.9197 | 12.2154 |
59
- | No log | 6.0 | 372 | 3.8840 | 0.9586 | 12.2561 |
60
- | No log | 7.0 | 434 | 3.8681 | 0.9702 | 12.3374 |
61
- | No log | 8.0 | 496 | 3.8540 | 0.9676 | 12.3415 |
62
- | 3.0832 | 9.0 | 558 | 3.8380 | 0.9564 | 12.4268 |
63
- | 3.0832 | 10.0 | 620 | 3.8276 | 0.963 | 12.5081 |
64
- | 3.0832 | 11.0 | 682 | 3.8159 | 0.9326 | 12.5528 |
65
- | 3.0832 | 12.0 | 744 | 3.8086 | 0.9326 | 12.5772 |
66
- | 3.0832 | 13.0 | 806 | 3.8007 | 0.9668 | 12.5813 |
67
- | 3.0832 | 14.0 | 868 | 3.7919 | 0.922 | 12.7073 |
68
- | 3.0832 | 15.0 | 930 | 3.7833 | 0.9319 | 12.626 |
69
- | 3.0832 | 16.0 | 992 | 3.7754 | 1.0907 | 12.7033 |
70
- | 2.6953 | 17.0 | 1054 | 3.7698 | 1.0914 | 12.7317 |
71
- | 2.6953 | 18.0 | 1116 | 3.7657 | 1.1198 | 12.7642 |
72
- | 2.6953 | 19.0 | 1178 | 3.7597 | 1.2304 | 12.6707 |
73
- | 2.6953 | 20.0 | 1240 | 3.7555 | 1.2345 | 12.7683 |
74
- | 2.6953 | 21.0 | 1302 | 3.7519 | 1.2465 | 12.7439 |
75
- | 2.6953 | 22.0 | 1364 | 3.7506 | 1.2322 | 12.7764 |
76
- | 2.6953 | 23.0 | 1426 | 3.7480 | 1.2558 | 12.7642 |
77
- | 2.6953 | 24.0 | 1488 | 3.7453 | 1.2465 | 12.7317 |
78
- | 2.4546 | 25.0 | 1550 | 3.7415 | 1.2614 | 12.7073 |
79
- | 2.4546 | 26.0 | 1612 | 3.7377 | 1.2339 | 12.7073 |
80
- | 2.4546 | 27.0 | 1674 | 3.7346 | 1.2664 | 12.7195 |
81
- | 2.4546 | 28.0 | 1736 | 3.7315 | 1.2664 | 12.7195 |
82
- | 2.4546 | 29.0 | 1798 | 3.7310 | 1.3041 | 12.7033 |
83
- | 2.4546 | 30.0 | 1860 | 3.7293 | 1.2715 | 12.687 |
84
- | 2.4546 | 31.0 | 1922 | 3.7266 | 1.2941 | 12.6748 |
85
- | 2.4546 | 32.0 | 1984 | 3.7266 | 1.2988 | 12.7398 |
86
- | 2.2894 | 33.0 | 2046 | 3.7260 | 1.3227 | 12.7439 |
87
- | 2.2894 | 34.0 | 2108 | 3.7243 | 1.3227 | 12.752 |
88
- | 2.2894 | 35.0 | 2170 | 3.7240 | 1.3227 | 12.752 |
89
- | 2.2894 | 36.0 | 2232 | 3.7230 | 1.3338 | 12.7276 |
90
- | 2.2894 | 37.0 | 2294 | 3.7242 | 1.3338 | 12.7724 |
91
- | 2.2894 | 38.0 | 2356 | 3.7224 | 1.3338 | 12.7764 |
92
- | 2.2894 | 39.0 | 2418 | 3.7210 | 1.3338 | 12.7642 |
93
- | 2.2894 | 40.0 | 2480 | 3.7214 | 1.351 | 12.7642 |
94
- | 2.1784 | 41.0 | 2542 | 3.7215 | 1.3283 | 12.7967 |
95
- | 2.1784 | 42.0 | 2604 | 3.7208 | 1.3173 | 12.7642 |
96
- | 2.1784 | 43.0 | 2666 | 3.7208 | 1.3519 | 12.7114 |
97
- | 2.1784 | 44.0 | 2728 | 3.7200 | 1.3519 | 12.7114 |
98
- | 2.1784 | 45.0 | 2790 | 3.7198 | 1.3173 | 12.7886 |
99
- | 2.1784 | 46.0 | 2852 | 3.7199 | 1.3519 | 12.752 |
100
- | 2.1784 | 47.0 | 2914 | 3.7192 | 1.3576 | 12.7642 |
101
- | 2.1784 | 48.0 | 2976 | 3.7191 | 1.3282 | 12.7967 |
102
- | 2.1365 | 49.0 | 3038 | 3.7189 | 1.3282 | 12.8089 |
103
- | 2.1365 | 50.0 | 3100 | 3.7189 | 1.3095 | 12.8089 |
104
 
105
 
106
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-zh](https://huggingface.co/Helsinki-NLP/opus-mt-en-zh) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.7154
21
+ - Bleu: 1.4102
22
+ - Gen Len: 12.6992
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
54
+ | No log | 1.0 | 62 | 3.7154 | 1.3724 | 12.7073 |
55
+ | No log | 2.0 | 124 | 3.7185 | 1.3718 | 12.7398 |
56
+ | No log | 3.0 | 186 | 3.7168 | 1.4342 | 12.6504 |
57
+ | No log | 4.0 | 248 | 3.7168 | 1.4109 | 12.7805 |
58
+ | No log | 5.0 | 310 | 3.7161 | 1.4265 | 12.7073 |
59
+ | No log | 6.0 | 372 | 3.7150 | 1.4013 | 12.7114 |
60
+ | No log | 7.0 | 434 | 3.7151 | 1.4102 | 12.7073 |
61
+ | No log | 8.0 | 496 | 3.7152 | 1.3981 | 12.7439 |
62
+ | 2.0086 | 9.0 | 558 | 3.7152 | 1.4327 | 12.6951 |
63
+ | 2.0086 | 10.0 | 620 | 3.7154 | 1.4102 | 12.6992 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e65f68df8a8dc988c18fd5c635c255c3ade22e18bf4fc4e08b473a04d969f1b
3
  size 309965092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25773988fb8ae43ea73577b2b9b06525a6db7dba3588087f68c877620cef4999
3
  size 309965092
runs/Mar31_03-49-15_9106895eed54/events.out.tfevents.1711856964.9106895eed54.1341.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e917648036d9e15614403ba20776c48e19f1353d6262ccf7f697239978ce42b2
3
- size 8798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ec6fcb70ce1a6faf8b52afda5298e58a7f505f17f714adce7e36ebbd058eed
3
+ size 9892