Yova commited on
Commit
b9520a2
·
1 Parent(s): 7688887

End of training

Browse files
Files changed (2) hide show
  1. README.md +55 -6
  2. model.safetensors +1 -1
README.md CHANGED
@@ -13,8 +13,8 @@ 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: 1.2427
17
- - Exact Match: 0.31
18
 
19
  ## Model description
20
 
@@ -40,14 +40,63 @@ The following hyperparameters were used during training:
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: inverse_sqrt
42
  - lr_scheduler_warmup_steps: 4000
43
- - training_steps: 400
44
  - label_smoothing_factor: 0.1
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss | Exact Match |
49
- |:-------------:|:------:|:----:|:---------------:|:-----------:|
50
- | 2.9226 | 133.33 | 400 | 1.2427 | 0.31 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
 
53
  ### 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: 0.9254
17
+ - Exact Match: 0.702
18
 
19
  ## Model description
20
 
 
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: inverse_sqrt
42
  - lr_scheduler_warmup_steps: 4000
43
+ - training_steps: 20000
44
  - label_smoothing_factor: 0.1
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss | Exact Match |
49
+ |:-------------:|:-----:|:-----:|:---------------:|:-----------:|
50
+ | 2.8524 | 16.0 | 400 | 1.7375 | 0.059 |
51
+ | 1.422 | 32.0 | 800 | 1.6708 | 0.11 |
52
+ | 1.0862 | 48.0 | 1200 | 1.7149 | 0.094 |
53
+ | 0.9374 | 64.0 | 1600 | 1.6508 | 0.159 |
54
+ | 0.8704 | 80.0 | 2000 | 1.6920 | 0.112 |
55
+ | 0.8356 | 96.0 | 2400 | 1.5605 | 0.16 |
56
+ | 0.8157 | 112.0 | 2800 | 1.5249 | 0.188 |
57
+ | 0.8029 | 128.0 | 3200 | 1.3993 | 0.25 |
58
+ | 0.7917 | 144.0 | 3600 | 1.2768 | 0.312 |
59
+ | 0.7821 | 160.0 | 4000 | 1.2213 | 0.397 |
60
+ | 0.7719 | 176.0 | 4400 | 1.1216 | 0.432 |
61
+ | 0.7635 | 192.0 | 4800 | 1.1076 | 0.458 |
62
+ | 0.7584 | 208.0 | 5200 | 1.0275 | 0.567 |
63
+ | 0.7556 | 224.0 | 5600 | 1.0464 | 0.552 |
64
+ | 0.7525 | 240.0 | 6000 | 1.0442 | 0.56 |
65
+ | 0.7496 | 256.0 | 6400 | 1.0108 | 0.581 |
66
+ | 0.7487 | 272.0 | 6800 | 0.9721 | 0.61 |
67
+ | 0.7467 | 288.0 | 7200 | 1.0326 | 0.567 |
68
+ | 0.7466 | 304.0 | 7600 | 0.9900 | 0.572 |
69
+ | 0.7449 | 320.0 | 8000 | 1.0150 | 0.604 |
70
+ | 0.7445 | 336.0 | 8400 | 0.9755 | 0.603 |
71
+ | 0.7433 | 352.0 | 8800 | 0.9705 | 0.645 |
72
+ | 0.7432 | 368.0 | 9200 | 0.9567 | 0.663 |
73
+ | 0.7432 | 384.0 | 9600 | 0.9733 | 0.68 |
74
+ | 0.7425 | 400.0 | 10000 | 0.9262 | 0.67 |
75
+ | 0.7417 | 416.0 | 10400 | 0.9216 | 0.673 |
76
+ | 0.7409 | 432.0 | 10800 | 0.9411 | 0.681 |
77
+ | 0.7404 | 448.0 | 11200 | 0.9312 | 0.674 |
78
+ | 0.7405 | 464.0 | 11600 | 0.9777 | 0.585 |
79
+ | 0.7406 | 480.0 | 12000 | 0.9191 | 0.683 |
80
+ | 0.7395 | 496.0 | 12400 | 0.9216 | 0.643 |
81
+ | 0.7396 | 512.0 | 12800 | 0.9764 | 0.645 |
82
+ | 0.7394 | 528.0 | 13200 | 0.9361 | 0.644 |
83
+ | 0.7392 | 544.0 | 13600 | 0.9210 | 0.67 |
84
+ | 0.739 | 560.0 | 14000 | 0.9387 | 0.688 |
85
+ | 0.7389 | 576.0 | 14400 | 0.9385 | 0.67 |
86
+ | 0.7383 | 592.0 | 14800 | 0.9500 | 0.655 |
87
+ | 0.7386 | 608.0 | 15200 | 0.9405 | 0.67 |
88
+ | 0.7383 | 624.0 | 15600 | 0.9335 | 0.691 |
89
+ | 0.738 | 640.0 | 16000 | 0.9079 | 0.708 |
90
+ | 0.7379 | 656.0 | 16400 | 0.9027 | 0.714 |
91
+ | 0.7376 | 672.0 | 16800 | 0.8969 | 0.703 |
92
+ | 0.7372 | 688.0 | 17200 | 0.9169 | 0.685 |
93
+ | 0.7375 | 704.0 | 17600 | 0.8895 | 0.738 |
94
+ | 0.7376 | 720.0 | 18000 | 0.8951 | 0.734 |
95
+ | 0.7371 | 736.0 | 18400 | 0.9408 | 0.673 |
96
+ | 0.737 | 752.0 | 18800 | 0.9270 | 0.693 |
97
+ | 0.7371 | 768.0 | 19200 | 0.9063 | 0.71 |
98
+ | 0.7369 | 784.0 | 19600 | 0.9253 | 0.678 |
99
+ | 0.7367 | 800.0 | 20000 | 0.9254 | 0.702 |
100
 
101
 
102
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e66cc2174d507c6a5dc883e8aeee659c633faf1d69734b8106bae1a78ec5d8f4
3
  size 29459544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763dd525357111d73e2b383446aacb647910821428e47e7ba8b517d9aa5fa114
3
  size 29459544