Hugging Face's logo

jeroenherczeg
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
jeroenherczeg commited on
Commit
ce2e36a
•
1 Parent(s): b62a3ae

jeroenherczeg/shawgpt-ft

Browse files
Files changed (4) hide show
  1. README.md +12 -95
  2. runs/Apr05_09-52-57_EVAOS-1/events.out.tfevents.1712303577.EVAOS-1.444372.0 +3 -0
  3. runs/Apr05_09-54-12_EVAOS-1/events.out.tfevents.1712303653.EVAOS-1.453618.0 +3 -0
  4. training_args.bin +2 -2
README.md CHANGED
@@ -44,111 +44,28 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
- - num_epochs: 100
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 4.6493 | 0.92 | 3 | 4.2320 |
54
- | 4.6282 | 1.85 | 6 | 4.2320 |
55
- | 4.645 | 2.77 | 9 | 4.2320 |
56
- | 3.4787 | 4.0 | 13 | 4.2320 |
57
- | 4.6562 | 4.92 | 16 | 4.2320 |
58
- | 4.6364 | 5.85 | 19 | 4.2320 |
59
- | 4.6498 | 6.77 | 22 | 4.2320 |
60
- | 3.457 | 8.0 | 26 | 4.2320 |
61
- | 4.6149 | 8.92 | 29 | 4.2320 |
62
- | 4.6338 | 9.85 | 32 | 4.2320 |
63
- | 4.6256 | 10.77 | 35 | 4.2320 |
64
- | 3.4795 | 12.0 | 39 | 4.2320 |
65
- | 4.6287 | 12.92 | 42 | 4.2320 |
66
- | 4.6345 | 13.85 | 45 | 4.2320 |
67
- | 4.6308 | 14.77 | 48 | 4.2320 |
68
- | 3.4811 | 16.0 | 52 | 4.2320 |
69
- | 4.6598 | 16.92 | 55 | 4.2320 |
70
- | 4.6658 | 17.85 | 58 | 4.2320 |
71
- | 4.6393 | 18.77 | 61 | 4.2320 |
72
- | 3.4755 | 20.0 | 65 | 4.2320 |
73
- | 4.6234 | 20.92 | 68 | 4.2320 |
74
- | 4.6511 | 21.85 | 71 | 4.2320 |
75
- | 4.6326 | 22.77 | 74 | 4.2320 |
76
- | 3.4732 | 24.0 | 78 | 4.2320 |
77
- | 4.6331 | 24.92 | 81 | 4.2320 |
78
- | 4.6402 | 25.85 | 84 | 4.2320 |
79
- | 4.6498 | 26.77 | 87 | 4.2320 |
80
- | 3.4715 | 28.0 | 91 | 4.2320 |
81
- | 4.665 | 28.92 | 94 | 4.2320 |
82
- | 4.6558 | 29.85 | 97 | 4.2320 |
83
- | 4.6404 | 30.77 | 100 | 4.2320 |
84
- | 3.4852 | 32.0 | 104 | 4.2320 |
85
- | 4.6258 | 32.92 | 107 | 4.2320 |
86
- | 4.6543 | 33.85 | 110 | 4.2320 |
87
- | 4.6502 | 34.77 | 113 | 4.2320 |
88
- | 3.4824 | 36.0 | 117 | 4.2320 |
89
- | 4.6669 | 36.92 | 120 | 4.2320 |
90
- | 4.6597 | 37.85 | 123 | 4.2320 |
91
- | 4.6377 | 38.77 | 126 | 4.2320 |
92
- | 3.4882 | 40.0 | 130 | 4.2320 |
93
- | 4.6538 | 40.92 | 133 | 4.2320 |
94
- | 4.6345 | 41.85 | 136 | 4.2320 |
95
- | 4.6379 | 42.77 | 139 | 4.2320 |
96
- | 3.4759 | 44.0 | 143 | 4.2320 |
97
- | 4.6265 | 44.92 | 146 | 4.2320 |
98
- | 4.6388 | 45.85 | 149 | 4.2320 |
99
- | 4.627 | 46.77 | 152 | 4.2320 |
100
- | 3.4803 | 48.0 | 156 | 4.2320 |
101
- | 4.6648 | 48.92 | 159 | 4.2320 |
102
- | 4.6395 | 49.85 | 162 | 4.2320 |
103
- | 4.6139 | 50.77 | 165 | 4.2320 |
104
- | 3.4922 | 52.0 | 169 | 4.2320 |
105
- | 4.637 | 52.92 | 172 | 4.2320 |
106
- | 4.6463 | 53.85 | 175 | 4.2320 |
107
- | 4.6362 | 54.77 | 178 | 4.2320 |
108
- | 3.487 | 56.0 | 182 | 4.2320 |
109
- | 4.6366 | 56.92 | 185 | 4.2320 |
110
- | 4.6218 | 57.85 | 188 | 4.2320 |
111
- | 4.6565 | 58.77 | 191 | 4.2320 |
112
- | 3.5069 | 60.0 | 195 | 4.2320 |
113
- | 4.6391 | 60.92 | 198 | 4.2320 |
114
- | 4.6256 | 61.85 | 201 | 4.2320 |
115
- | 4.6583 | 62.77 | 204 | 4.2320 |
116
- | 3.4692 | 64.0 | 208 | 4.2320 |
117
- | 4.6473 | 64.92 | 211 | 4.2320 |
118
- | 4.6427 | 65.85 | 214 | 4.2320 |
119
- | 4.6547 | 66.77 | 217 | 4.2320 |
120
- | 3.4708 | 68.0 | 221 | 4.2320 |
121
- | 4.6536 | 68.92 | 224 | 4.2320 |
122
- | 4.6429 | 69.85 | 227 | 4.2320 |
123
- | 4.634 | 70.77 | 230 | 4.2320 |
124
- | 3.4907 | 72.0 | 234 | 4.2320 |
125
- | 4.6467 | 72.92 | 237 | 4.2320 |
126
- | 4.6311 | 73.85 | 240 | 4.2320 |
127
- | 4.6493 | 74.77 | 243 | 4.2320 |
128
- | 3.4631 | 76.0 | 247 | 4.2320 |
129
- | 4.6688 | 76.92 | 250 | 4.2320 |
130
- | 4.6465 | 77.85 | 253 | 4.2320 |
131
- | 4.6302 | 78.77 | 256 | 4.2320 |
132
- | 3.4796 | 80.0 | 260 | 4.2320 |
133
- | 4.6425 | 80.92 | 263 | 4.2320 |
134
- | 4.6324 | 81.85 | 266 | 4.2320 |
135
- | 4.6696 | 82.77 | 269 | 4.2320 |
136
- | 3.4871 | 84.0 | 273 | 4.2320 |
137
- | 4.6406 | 84.92 | 276 | 4.2320 |
138
- | 4.618 | 85.85 | 279 | 4.2320 |
139
- | 4.6478 | 86.77 | 282 | 4.2320 |
140
- | 3.4833 | 88.0 | 286 | 4.2320 |
141
- | 4.6455 | 88.92 | 289 | 4.2320 |
142
- | 4.6476 | 89.85 | 292 | 4.2320 |
143
- | 4.6218 | 90.77 | 295 | 4.2320 |
144
- | 3.4687 | 92.0 | 299 | 4.2320 |
145
- | 4.283 | 92.31 | 300 | 4.2320 |
146
 
147
 
148
  ### Framework versions
149
 
150
  - PEFT 0.10.0
151
- - Transformers 4.39.3
152
  - Pytorch 2.1.0+cu121
153
  - Datasets 2.18.0
154
  - Tokenizers 0.15.2
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 10
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 4.6433 | 0.92 | 3 | 4.2320 |
54
+ | 4.6544 | 1.85 | 6 | 4.2320 |
55
+ | 4.6459 | 2.77 | 9 | 4.2320 |
56
+ | 3.4822 | 4.0 | 13 | 4.2320 |
57
+ | 4.6298 | 4.92 | 16 | 4.2320 |
58
+ | 4.6605 | 5.85 | 19 | 4.2320 |
59
+ | 4.6392 | 6.77 | 22 | 4.2320 |
60
+ | 3.4844 | 8.0 | 26 | 4.2320 |
61
+ | 4.6305 | 8.92 | 29 | 4.2320 |
62
+ | 3.3623 | 9.23 | 30 | 4.2320 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
66
 
67
  - PEFT 0.10.0
68
+ - Transformers 4.36.2
69
  - Pytorch 2.1.0+cu121
70
  - Datasets 2.18.0
71
  - Tokenizers 0.15.2
runs/Apr05_09-52-57_EVAOS-1/events.out.tfevents.1712303577.EVAOS-1.444372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a785b3f0272cba8ce6b5ddc8de528a8840b28b6e4eae2b25f380d7f7346fd3
3
+ size 4951
runs/Apr05_09-54-12_EVAOS-1/events.out.tfevents.1712303653.EVAOS-1.453618.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfad24e4b8812678f5b8c24460d88e2688e173a50c0e852f23c7787747ac1f68
3
+ size 9499
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb10d117c569682b5de44954c8a5568fc4ba993cbfb57fc4205d28d0c4d34136
3
- size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf858ca08d1bff2109ddf6414ee2668f05186c26549b1860bb60e3182bddc1b
3
+ size 4664