nazemi commited on
Commit
2372a66
·
1 Parent(s): 76334cc

End of training

Browse files
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 [t5-large](https://huggingface.co/t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.9452
19
 
20
  ## Model description
21
 
@@ -46,16 +46,16 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 14.6117 | 1.0 | 13 | 12.1354 |
50
- | 4.7373 | 2.0 | 26 | 5.1054 |
51
- | 1.7596 | 3.0 | 39 | 3.2154 |
52
- | 1.3121 | 4.0 | 52 | 2.1497 |
53
- | 1.1923 | 5.0 | 65 | 1.6547 |
54
- | 0.3427 | 6.0 | 78 | 1.2120 |
55
- | 0.3447 | 7.0 | 91 | 1.1350 |
56
- | 1.8694 | 8.0 | 104 | 0.9754 |
57
- | 0.7097 | 9.0 | 117 | 0.9623 |
58
- | 1.4038 | 10.0 | 130 | 0.9452 |
59
 
60
 
61
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0984
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 9.4766 | 1.0 | 23 | 8.7001 |
50
+ | 2.2197 | 2.0 | 46 | 2.2284 |
51
+ | 1.508 | 3.0 | 69 | 1.1642 |
52
+ | 0.9361 | 4.0 | 92 | 0.5838 |
53
+ | 0.5719 | 5.0 | 115 | 0.3348 |
54
+ | 0.3519 | 6.0 | 138 | 0.2189 |
55
+ | 0.1204 | 7.0 | 161 | 0.1504 |
56
+ | 0.278 | 8.0 | 184 | 0.1213 |
57
+ | 0.1673 | 9.0 | 207 | 0.1035 |
58
+ | 0.1508 | 10.0 | 230 | 0.0984 |
59
 
60
 
61
  ### Framework versions
runs/Jun11_14-13-16_MacBook-Pro.local/events.out.tfevents.1718086397.MacBook-Pro.local.5064.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5844258916dee4fa2a8ccba6e92f50f0b4473fcd9ac28c206997b422be76fbf3
3
+ size 56665
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc6eefef83db66e3695b7a94b9c3b8570f9a4cbdbf350c0e4bac08b5e98cbed
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2150beaf32b5d4447dd1436d07a5998c1a3b7db8e347170b4436698a5f88cbb
3
  size 5112