Training in progress, epoch 0
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Apr26_13-18-59_1c59b5307e97/events.out.tfevents.1714137552.1c59b5307e97.453.4 +3 -0
- runs/Apr26_13-20-29_1c59b5307e97/events.out.tfevents.1714137639.1c59b5307e97.453.5 +3 -0
- train_results.json +8 -0
- trainer_state.json +274 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.777777777777779,
|
| 3 |
+
"total_flos": 1.102133137023959e+18,
|
| 4 |
+
"train_loss": 0.670017595724626,
|
| 5 |
+
"train_runtime": 696.1068,
|
| 6 |
+
"train_samples_per_second": 82.746,
|
| 7 |
+
"train_steps_per_second": 0.316
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 86691704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa55a9d449693c1d3e5edc08dab244a8ca8f92a03edf6ad75d9c2d493f0dba1e
|
| 3 |
size 86691704
|
runs/Apr26_13-18-59_1c59b5307e97/events.out.tfevents.1714137552.1c59b5307e97.453.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:235fb1b256b47d4246864a1c4a16b00266db008c5e635d13fa1063a6a8492301
|
| 3 |
+
size 4928
|
runs/Apr26_13-20-29_1c59b5307e97/events.out.tfevents.1714137639.1c59b5307e97.453.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bceb18a68c65a9d24cdbe82213638d8a09f3fc0da223914265c0752aeab2fe60
|
| 3 |
+
size 5659
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.777777777777779,
|
| 3 |
+
"total_flos": 1.102133137023959e+18,
|
| 4 |
+
"train_loss": 0.670017595724626,
|
| 5 |
+
"train_runtime": 696.1068,
|
| 6 |
+
"train_samples_per_second": 82.746,
|
| 7 |
+
"train_steps_per_second": 0.316
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8625,
|
| 3 |
+
"best_model_checkpoint": "vit-msn-small-finetuned-alzheimers/checkpoint-220",
|
| 4 |
+
"epoch": 9.777777777777779,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 220,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.4444444444444444,
|
| 13 |
+
"grad_norm": 4.161161422729492,
|
| 14 |
+
"learning_rate": 2.272727272727273e-05,
|
| 15 |
+
"loss": 1.0688,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8888888888888888,
|
| 20 |
+
"grad_norm": 19.670530319213867,
|
| 21 |
+
"learning_rate": 4.545454545454546e-05,
|
| 22 |
+
"loss": 0.9297,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.9777777777777777,
|
| 27 |
+
"eval_accuracy": 0.615625,
|
| 28 |
+
"eval_loss": 0.8769256472587585,
|
| 29 |
+
"eval_runtime": 3.9355,
|
| 30 |
+
"eval_samples_per_second": 162.623,
|
| 31 |
+
"eval_steps_per_second": 2.541,
|
| 32 |
+
"step": 22
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.3333333333333333,
|
| 36 |
+
"grad_norm": 7.473578929901123,
|
| 37 |
+
"learning_rate": 4.797979797979798e-05,
|
| 38 |
+
"loss": 0.8854,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.7777777777777777,
|
| 43 |
+
"grad_norm": 7.05064058303833,
|
| 44 |
+
"learning_rate": 4.545454545454546e-05,
|
| 45 |
+
"loss": 0.8601,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0,
|
| 50 |
+
"eval_accuracy": 0.634375,
|
| 51 |
+
"eval_loss": 0.7798857688903809,
|
| 52 |
+
"eval_runtime": 3.5552,
|
| 53 |
+
"eval_samples_per_second": 180.019,
|
| 54 |
+
"eval_steps_per_second": 2.813,
|
| 55 |
+
"step": 45
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.2222222222222223,
|
| 59 |
+
"grad_norm": 12.152384757995605,
|
| 60 |
+
"learning_rate": 4.292929292929293e-05,
|
| 61 |
+
"loss": 0.8571,
|
| 62 |
+
"step": 50
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.6666666666666665,
|
| 66 |
+
"grad_norm": 11.653566360473633,
|
| 67 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 68 |
+
"loss": 0.7954,
|
| 69 |
+
"step": 60
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.977777777777778,
|
| 73 |
+
"eval_accuracy": 0.6828125,
|
| 74 |
+
"eval_loss": 0.7196512222290039,
|
| 75 |
+
"eval_runtime": 3.5735,
|
| 76 |
+
"eval_samples_per_second": 179.098,
|
| 77 |
+
"eval_steps_per_second": 2.798,
|
| 78 |
+
"step": 67
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.111111111111111,
|
| 82 |
+
"grad_norm": 10.308629989624023,
|
| 83 |
+
"learning_rate": 3.787878787878788e-05,
|
| 84 |
+
"loss": 0.7808,
|
| 85 |
+
"step": 70
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.5555555555555554,
|
| 89 |
+
"grad_norm": 15.87501335144043,
|
| 90 |
+
"learning_rate": 3.535353535353535e-05,
|
| 91 |
+
"loss": 0.7552,
|
| 92 |
+
"step": 80
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.0,
|
| 96 |
+
"grad_norm": 9.567431449890137,
|
| 97 |
+
"learning_rate": 3.282828282828283e-05,
|
| 98 |
+
"loss": 0.7468,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.0,
|
| 103 |
+
"eval_accuracy": 0.6734375,
|
| 104 |
+
"eval_loss": 0.7003158330917358,
|
| 105 |
+
"eval_runtime": 3.5895,
|
| 106 |
+
"eval_samples_per_second": 178.3,
|
| 107 |
+
"eval_steps_per_second": 2.786,
|
| 108 |
+
"step": 90
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.444444444444445,
|
| 112 |
+
"grad_norm": 6.920608043670654,
|
| 113 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 114 |
+
"loss": 0.683,
|
| 115 |
+
"step": 100
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 4.888888888888889,
|
| 119 |
+
"grad_norm": 8.078107833862305,
|
| 120 |
+
"learning_rate": 2.777777777777778e-05,
|
| 121 |
+
"loss": 0.6935,
|
| 122 |
+
"step": 110
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.977777777777778,
|
| 126 |
+
"eval_accuracy": 0.7546875,
|
| 127 |
+
"eval_loss": 0.6063631772994995,
|
| 128 |
+
"eval_runtime": 3.8885,
|
| 129 |
+
"eval_samples_per_second": 164.589,
|
| 130 |
+
"eval_steps_per_second": 2.572,
|
| 131 |
+
"step": 112
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 5.333333333333333,
|
| 135 |
+
"grad_norm": 11.370922088623047,
|
| 136 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 137 |
+
"loss": 0.6469,
|
| 138 |
+
"step": 120
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.777777777777778,
|
| 142 |
+
"grad_norm": 12.74963665008545,
|
| 143 |
+
"learning_rate": 2.272727272727273e-05,
|
| 144 |
+
"loss": 0.6271,
|
| 145 |
+
"step": 130
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 6.0,
|
| 149 |
+
"eval_accuracy": 0.76875,
|
| 150 |
+
"eval_loss": 0.5647965669631958,
|
| 151 |
+
"eval_runtime": 3.9273,
|
| 152 |
+
"eval_samples_per_second": 162.963,
|
| 153 |
+
"eval_steps_per_second": 2.546,
|
| 154 |
+
"step": 135
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.222222222222222,
|
| 158 |
+
"grad_norm": 11.86828327178955,
|
| 159 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 160 |
+
"loss": 0.5635,
|
| 161 |
+
"step": 140
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.666666666666667,
|
| 165 |
+
"grad_norm": 13.892380714416504,
|
| 166 |
+
"learning_rate": 1.7676767676767676e-05,
|
| 167 |
+
"loss": 0.5622,
|
| 168 |
+
"step": 150
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 6.977777777777778,
|
| 172 |
+
"eval_accuracy": 0.809375,
|
| 173 |
+
"eval_loss": 0.48242831230163574,
|
| 174 |
+
"eval_runtime": 3.5816,
|
| 175 |
+
"eval_samples_per_second": 178.692,
|
| 176 |
+
"eval_steps_per_second": 2.792,
|
| 177 |
+
"step": 157
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.111111111111111,
|
| 181 |
+
"grad_norm": 8.864046096801758,
|
| 182 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 183 |
+
"loss": 0.525,
|
| 184 |
+
"step": 160
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 7.555555555555555,
|
| 188 |
+
"grad_norm": 8.477625846862793,
|
| 189 |
+
"learning_rate": 1.2626262626262628e-05,
|
| 190 |
+
"loss": 0.4967,
|
| 191 |
+
"step": 170
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 8.0,
|
| 195 |
+
"grad_norm": 12.289462089538574,
|
| 196 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 197 |
+
"loss": 0.4815,
|
| 198 |
+
"step": 180
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 8.0,
|
| 202 |
+
"eval_accuracy": 0.8609375,
|
| 203 |
+
"eval_loss": 0.4012059271335602,
|
| 204 |
+
"eval_runtime": 3.613,
|
| 205 |
+
"eval_samples_per_second": 177.138,
|
| 206 |
+
"eval_steps_per_second": 2.768,
|
| 207 |
+
"step": 180
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 8.444444444444445,
|
| 211 |
+
"grad_norm": 8.446834564208984,
|
| 212 |
+
"learning_rate": 7.5757575757575764e-06,
|
| 213 |
+
"loss": 0.45,
|
| 214 |
+
"step": 190
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 8.88888888888889,
|
| 218 |
+
"grad_norm": 15.683026313781738,
|
| 219 |
+
"learning_rate": 5.050505050505051e-06,
|
| 220 |
+
"loss": 0.4771,
|
| 221 |
+
"step": 200
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 8.977777777777778,
|
| 225 |
+
"eval_accuracy": 0.85625,
|
| 226 |
+
"eval_loss": 0.3798871636390686,
|
| 227 |
+
"eval_runtime": 3.5689,
|
| 228 |
+
"eval_samples_per_second": 179.325,
|
| 229 |
+
"eval_steps_per_second": 2.802,
|
| 230 |
+
"step": 202
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 9.333333333333334,
|
| 234 |
+
"grad_norm": 9.576162338256836,
|
| 235 |
+
"learning_rate": 2.5252525252525253e-06,
|
| 236 |
+
"loss": 0.4376,
|
| 237 |
+
"step": 210
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.777777777777779,
|
| 241 |
+
"grad_norm": 9.685094833374023,
|
| 242 |
+
"learning_rate": 0.0,
|
| 243 |
+
"loss": 0.4171,
|
| 244 |
+
"step": 220
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 9.777777777777779,
|
| 248 |
+
"eval_accuracy": 0.8625,
|
| 249 |
+
"eval_loss": 0.3611668050289154,
|
| 250 |
+
"eval_runtime": 3.9731,
|
| 251 |
+
"eval_samples_per_second": 161.083,
|
| 252 |
+
"eval_steps_per_second": 2.517,
|
| 253 |
+
"step": 220
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 9.777777777777779,
|
| 257 |
+
"step": 220,
|
| 258 |
+
"total_flos": 1.102133137023959e+18,
|
| 259 |
+
"train_loss": 0.670017595724626,
|
| 260 |
+
"train_runtime": 696.1068,
|
| 261 |
+
"train_samples_per_second": 82.746,
|
| 262 |
+
"train_steps_per_second": 0.316
|
| 263 |
+
}
|
| 264 |
+
],
|
| 265 |
+
"logging_steps": 10,
|
| 266 |
+
"max_steps": 220,
|
| 267 |
+
"num_input_tokens_seen": 0,
|
| 268 |
+
"num_train_epochs": 10,
|
| 269 |
+
"save_steps": 500,
|
| 270 |
+
"total_flos": 1.102133137023959e+18,
|
| 271 |
+
"train_batch_size": 64,
|
| 272 |
+
"trial_name": null,
|
| 273 |
+
"trial_params": null
|
| 274 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd4aba1bda8adf6d81402323d5e808486e4e2bd28e3454f1eddee39b33f20ac
|
| 3 |
size 5048
|