Eurosmart commited on
Commit
bad7725
verified
1 Parent(s): 9139869

Model save

Browse files
README.md CHANGED
@@ -15,12 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.9805
19
- - eval_runtime: 24.4486
20
- - eval_samples_per_second: 63.971
21
- - eval_steps_per_second: 4.008
22
- - epoch: 2.0
23
- - step: 1314
24
 
25
  ## Model description
26
 
@@ -47,6 +42,62 @@ The following hyperparameters were used during training:
47
  - lr_scheduler_type: linear
48
  - num_epochs: 50
49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  ### Framework versions
51
 
52
  - Transformers 4.39.3
 
15
 
16
  This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 4.1822
 
 
 
 
 
19
 
20
  ## Model description
21
 
 
42
  - lr_scheduler_type: linear
43
  - num_epochs: 50
44
 
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 1.5553 | 1.0 | 657 | 1.0374 |
50
+ | 1.0747 | 2.0 | 1314 | 0.9805 |
51
+ | 0.8656 | 3.0 | 1971 | 1.0557 |
52
+ | 0.5949 | 4.0 | 2628 | 1.1109 |
53
+ | 0.4757 | 5.0 | 3285 | 1.1982 |
54
+ | 0.3937 | 6.0 | 3942 | 1.3565 |
55
+ | 0.2476 | 7.0 | 4599 | 1.4817 |
56
+ | 0.2064 | 8.0 | 5256 | 1.5591 |
57
+ | 0.191 | 9.0 | 5913 | 2.0118 |
58
+ | 0.1382 | 10.0 | 6570 | 2.1637 |
59
+ | 0.1161 | 11.0 | 7227 | 2.1896 |
60
+ | 0.1066 | 12.0 | 7884 | 2.3879 |
61
+ | 0.1017 | 13.0 | 8541 | 2.6023 |
62
+ | 0.0901 | 14.0 | 9198 | 2.8120 |
63
+ | 0.0859 | 15.0 | 9855 | 2.8291 |
64
+ | 0.0666 | 16.0 | 10512 | 2.8947 |
65
+ | 0.0598 | 17.0 | 11169 | 3.1198 |
66
+ | 0.0459 | 18.0 | 11826 | 3.0020 |
67
+ | 0.0533 | 19.0 | 12483 | 3.1257 |
68
+ | 0.0546 | 20.0 | 13140 | 3.1757 |
69
+ | 0.0487 | 21.0 | 13797 | 3.4253 |
70
+ | 0.0424 | 22.0 | 14454 | 3.2998 |
71
+ | 0.0465 | 23.0 | 15111 | 3.4184 |
72
+ | 0.0298 | 24.0 | 15768 | 3.6026 |
73
+ | 0.038 | 25.0 | 16425 | 3.7422 |
74
+ | 0.032 | 26.0 | 17082 | 3.6208 |
75
+ | 0.0247 | 27.0 | 17739 | 3.6113 |
76
+ | 0.0283 | 28.0 | 18396 | 3.8404 |
77
+ | 0.0237 | 29.0 | 19053 | 3.6326 |
78
+ | 0.017 | 30.0 | 19710 | 3.8710 |
79
+ | 0.0195 | 31.0 | 20367 | 3.8173 |
80
+ | 0.0205 | 32.0 | 21024 | 3.7101 |
81
+ | 0.0187 | 33.0 | 21681 | 3.8000 |
82
+ | 0.0236 | 34.0 | 22338 | 3.7253 |
83
+ | 0.0251 | 35.0 | 22995 | 3.7891 |
84
+ | 0.0399 | 36.0 | 23652 | 3.8655 |
85
+ | 0.0355 | 37.0 | 24309 | 3.7444 |
86
+ | 0.0214 | 38.0 | 24966 | 3.9477 |
87
+ | 0.0132 | 39.0 | 25623 | 4.1278 |
88
+ | 0.019 | 40.0 | 26280 | 4.1814 |
89
+ | 0.0227 | 41.0 | 26937 | 3.9744 |
90
+ | 0.0161 | 42.0 | 27594 | 4.1047 |
91
+ | 0.0165 | 43.0 | 28251 | 4.2342 |
92
+ | 0.0162 | 44.0 | 28908 | 4.1003 |
93
+ | 0.013 | 45.0 | 29565 | 4.2922 |
94
+ | 0.0158 | 46.0 | 30222 | 4.1349 |
95
+ | 0.0118 | 47.0 | 30879 | 4.1534 |
96
+ | 0.0155 | 48.0 | 31536 | 4.1656 |
97
+ | 0.0167 | 49.0 | 32193 | 4.1763 |
98
+ | 0.0205 | 50.0 | 32850 | 4.1822 |
99
+
100
+
101
  ### Framework versions
102
 
103
  - Transformers 4.39.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f15817471f31f193df4c78565851b21962202e3463829cefd12f84ee5d8c622
3
  size 526438888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba39fafbba6789185624e6dc6a259dcc41cd2f00a9f1e1b5c3fdf48df957f1a4
3
  size 526438888
runs/Jun03_05-25-09_0b85b752ef0c/events.out.tfevents.1717392310.0b85b752ef0c.25.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b6c2f96d57751c36434ae98ff9c1205ce09503af65036f97d42dc47fe5d5a43
3
- size 32081
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ebef75875d338b42f21938733cc98f92c616b6782f26dd2e5fb0afa17ad542f
3
+ size 32717