makhataei commited on
Commit
860ff8e
verified
1 Parent(s): 1a5c5d2

End of training

Browse files
README.md CHANGED
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 1.25e-08
38
  - train_batch_size: 14
39
  - eval_batch_size: 14
40
  - seed: 42
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
49
  | 5.5993 | 1.0 | 9 | 5.3355 |
50
  | 5.6986 | 2.0 | 18 | 5.3355 |
51
  | 5.6845 | 3.0 | 27 | 5.3355 |
52
- | 5.6477 | 4.0 | 36 | 5.3355 |
53
  | 5.7219 | 5.0 | 45 | 5.3355 |
54
- | 5.6463 | 6.0 | 54 | 5.3355 |
55
- | 5.5946 | 7.0 | 63 | 5.3355 |
56
  | 5.577 | 8.0 | 72 | 5.3355 |
57
  | 5.5841 | 9.0 | 81 | 5.3355 |
58
  | 5.5863 | 10.0 | 90 | 5.3355 |
@@ -60,14 +60,14 @@ The following hyperparameters were used during training:
60
  | 5.6131 | 12.0 | 108 | 5.3355 |
61
  | 5.6692 | 13.0 | 117 | 5.3355 |
62
  | 5.7031 | 14.0 | 126 | 5.3355 |
63
- | 5.6996 | 15.0 | 135 | 5.3355 |
64
  | 5.6724 | 16.0 | 144 | 5.3355 |
65
- | 5.738 | 17.0 | 153 | 5.3355 |
66
  | 5.6687 | 18.0 | 162 | 5.3355 |
67
  | 5.7009 | 19.0 | 171 | 5.3355 |
68
  | 5.6232 | 20.0 | 180 | 5.3355 |
69
  | 5.6514 | 21.0 | 189 | 5.3355 |
70
- | 5.6815 | 22.0 | 198 | 5.3355 |
71
  | 5.6305 | 23.0 | 207 | 5.3355 |
72
  | 5.7509 | 24.0 | 216 | 5.3355 |
73
  | 5.6747 | 25.0 | 225 | 5.3355 |
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
76
  | 5.673 | 28.0 | 252 | 5.3355 |
77
  | 5.6222 | 29.0 | 261 | 5.3355 |
78
  | 5.6194 | 30.0 | 270 | 5.3355 |
79
- | 5.6945 | 31.0 | 279 | 5.3355 |
80
  | 5.6899 | 32.0 | 288 | 5.3355 |
81
- | 5.6166 | 33.0 | 297 | 5.3355 |
82
  | 5.6643 | 34.0 | 306 | 5.3355 |
83
  | 5.7039 | 35.0 | 315 | 5.3355 |
84
  | 5.6704 | 36.0 | 324 | 5.3355 |
@@ -97,7 +97,7 @@ The following hyperparameters were used during training:
97
  | 5.6381 | 49.0 | 441 | 5.3355 |
98
  | 5.7056 | 50.0 | 450 | 5.3355 |
99
  | 5.6693 | 51.0 | 459 | 5.3355 |
100
- | 5.6051 | 52.0 | 468 | 5.3355 |
101
  | 5.6551 | 53.0 | 477 | 5.3355 |
102
  | 5.5851 | 54.0 | 486 | 5.3355 |
103
  | 5.6209 | 55.0 | 495 | 5.3355 |
@@ -136,11 +136,11 @@ The following hyperparameters were used during training:
136
  | 5.704 | 88.0 | 792 | 5.3355 |
137
  | 5.6389 | 89.0 | 801 | 5.3355 |
138
  | 5.6339 | 90.0 | 810 | 5.3355 |
139
- | 5.6446 | 91.0 | 819 | 5.3355 |
140
  | 5.6303 | 92.0 | 828 | 5.3355 |
141
  | 5.6814 | 93.0 | 837 | 5.3355 |
142
  | 5.6435 | 94.0 | 846 | 5.3355 |
143
- | 5.6821 | 95.0 | 855 | 5.3355 |
144
  | 5.6318 | 96.0 | 864 | 5.3355 |
145
  | 5.6404 | 97.0 | 873 | 5.3355 |
146
  | 5.6277 | 98.0 | 882 | 5.3355 |
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 6.25e-09
38
  - train_batch_size: 14
39
  - eval_batch_size: 14
40
  - seed: 42
 
49
  | 5.5993 | 1.0 | 9 | 5.3355 |
50
  | 5.6986 | 2.0 | 18 | 5.3355 |
51
  | 5.6845 | 3.0 | 27 | 5.3355 |
52
+ | 5.6475 | 4.0 | 36 | 5.3355 |
53
  | 5.7219 | 5.0 | 45 | 5.3355 |
54
+ | 5.6464 | 6.0 | 54 | 5.3355 |
55
+ | 5.5938 | 7.0 | 63 | 5.3355 |
56
  | 5.577 | 8.0 | 72 | 5.3355 |
57
  | 5.5841 | 9.0 | 81 | 5.3355 |
58
  | 5.5863 | 10.0 | 90 | 5.3355 |
 
60
  | 5.6131 | 12.0 | 108 | 5.3355 |
61
  | 5.6692 | 13.0 | 117 | 5.3355 |
62
  | 5.7031 | 14.0 | 126 | 5.3355 |
63
+ | 5.6995 | 15.0 | 135 | 5.3355 |
64
  | 5.6724 | 16.0 | 144 | 5.3355 |
65
+ | 5.7379 | 17.0 | 153 | 5.3355 |
66
  | 5.6687 | 18.0 | 162 | 5.3355 |
67
  | 5.7009 | 19.0 | 171 | 5.3355 |
68
  | 5.6232 | 20.0 | 180 | 5.3355 |
69
  | 5.6514 | 21.0 | 189 | 5.3355 |
70
+ | 5.6814 | 22.0 | 198 | 5.3355 |
71
  | 5.6305 | 23.0 | 207 | 5.3355 |
72
  | 5.7509 | 24.0 | 216 | 5.3355 |
73
  | 5.6747 | 25.0 | 225 | 5.3355 |
 
76
  | 5.673 | 28.0 | 252 | 5.3355 |
77
  | 5.6222 | 29.0 | 261 | 5.3355 |
78
  | 5.6194 | 30.0 | 270 | 5.3355 |
79
+ | 5.6944 | 31.0 | 279 | 5.3355 |
80
  | 5.6899 | 32.0 | 288 | 5.3355 |
81
+ | 5.6165 | 33.0 | 297 | 5.3355 |
82
  | 5.6643 | 34.0 | 306 | 5.3355 |
83
  | 5.7039 | 35.0 | 315 | 5.3355 |
84
  | 5.6704 | 36.0 | 324 | 5.3355 |
 
97
  | 5.6381 | 49.0 | 441 | 5.3355 |
98
  | 5.7056 | 50.0 | 450 | 5.3355 |
99
  | 5.6693 | 51.0 | 459 | 5.3355 |
100
+ | 5.6045 | 52.0 | 468 | 5.3355 |
101
  | 5.6551 | 53.0 | 477 | 5.3355 |
102
  | 5.5851 | 54.0 | 486 | 5.3355 |
103
  | 5.6209 | 55.0 | 495 | 5.3355 |
 
136
  | 5.704 | 88.0 | 792 | 5.3355 |
137
  | 5.6389 | 89.0 | 801 | 5.3355 |
138
  | 5.6339 | 90.0 | 810 | 5.3355 |
139
+ | 5.6447 | 91.0 | 819 | 5.3355 |
140
  | 5.6303 | 92.0 | 828 | 5.3355 |
141
  | 5.6814 | 93.0 | 837 | 5.3355 |
142
  | 5.6435 | 94.0 | 846 | 5.3355 |
143
+ | 5.6822 | 95.0 | 855 | 5.3355 |
144
  | 5.6318 | 96.0 | 864 | 5.3355 |
145
  | 5.6404 | 97.0 | 873 | 5.3355 |
146
  | 5.6277 | 98.0 | 882 | 5.3355 |
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eecb9996bb4fea006fe3cc7f32d8fb918cb5febde1228ae575d04caaf66ff0c
3
  size 649032520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9be6398b1ef28aeccbbf53360f659eda0f4a6b6057dc2a61fb6a2574c7b910
3
  size 649032520
runs/Mar06_16-14-10_Software-AI/events.out.tfevents.1709729051.Software-AI.118212.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74936e54db906aa7bb35b1d27d8256eaef6a40a72a0b2fecca5dae0e366302ca
3
+ size 47442
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a23059489de59322aa5235ee145edb3e49c5d4f5a9bb6df916999b0f546f00b4
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c430db8fc500a359b4a6a01bd5cb4603bb5f7867c427270c1d9ea2938339a7f
3
  size 4219