End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9787037037037037,
|
| 4 |
+
"eval_loss": 0.06794986128807068,
|
| 5 |
+
"eval_runtime": 12.873,
|
| 6 |
+
"eval_samples_per_second": 167.793,
|
| 7 |
+
"eval_steps_per_second": 5.282,
|
| 8 |
+
"total_flos": 1.4499253204608614e+18,
|
| 9 |
+
"train_loss": 0.3743210191789426,
|
| 10 |
+
"train_runtime": 869.999,
|
| 11 |
+
"train_samples_per_second": 67.035,
|
| 12 |
+
"train_steps_per_second": 0.524
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9787037037037037,
|
| 4 |
+
"eval_loss": 0.06794986128807068,
|
| 5 |
+
"eval_runtime": 12.873,
|
| 6 |
+
"eval_samples_per_second": 167.793,
|
| 7 |
+
"eval_steps_per_second": 5.282
|
| 8 |
+
}
|
runs/Sep23_21-31-14_ca2c564dd3e0/events.out.tfevents.1727127964.ca2c564dd3e0.330.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b68d36cc095776406d3b89f05f6f2248405b051aa865277dff19ebc331895da
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.4499253204608614e+18,
|
| 4 |
+
"train_loss": 0.3743210191789426,
|
| 5 |
+
"train_runtime": 869.999,
|
| 6 |
+
"train_samples_per_second": 67.035,
|
| 7 |
+
"train_steps_per_second": 0.524
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,384 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9787037037037037,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-456",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 456,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06578947368421052,
|
| 13 |
+
"grad_norm": 6.047317981719971,
|
| 14 |
+
"learning_rate": 1.0869565217391305e-05,
|
| 15 |
+
"loss": 2.3059,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.13157894736842105,
|
| 20 |
+
"grad_norm": 5.119813442230225,
|
| 21 |
+
"learning_rate": 2.173913043478261e-05,
|
| 22 |
+
"loss": 2.0868,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.19736842105263158,
|
| 27 |
+
"grad_norm": 8.138529777526855,
|
| 28 |
+
"learning_rate": 3.260869565217392e-05,
|
| 29 |
+
"loss": 1.5345,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2631578947368421,
|
| 34 |
+
"grad_norm": 14.628665924072266,
|
| 35 |
+
"learning_rate": 4.347826086956522e-05,
|
| 36 |
+
"loss": 0.8696,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.32894736842105265,
|
| 41 |
+
"grad_norm": 14.560131072998047,
|
| 42 |
+
"learning_rate": 4.951219512195122e-05,
|
| 43 |
+
"loss": 0.6197,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.39473684210526316,
|
| 48 |
+
"grad_norm": 14.169949531555176,
|
| 49 |
+
"learning_rate": 4.829268292682927e-05,
|
| 50 |
+
"loss": 0.487,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4605263157894737,
|
| 55 |
+
"grad_norm": 15.145587921142578,
|
| 56 |
+
"learning_rate": 4.707317073170732e-05,
|
| 57 |
+
"loss": 0.5187,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5263157894736842,
|
| 62 |
+
"grad_norm": 14.87001895904541,
|
| 63 |
+
"learning_rate": 4.585365853658537e-05,
|
| 64 |
+
"loss": 0.4016,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5921052631578947,
|
| 69 |
+
"grad_norm": 21.998821258544922,
|
| 70 |
+
"learning_rate": 4.4634146341463416e-05,
|
| 71 |
+
"loss": 0.3696,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6578947368421053,
|
| 76 |
+
"grad_norm": 16.311429977416992,
|
| 77 |
+
"learning_rate": 4.3414634146341465e-05,
|
| 78 |
+
"loss": 0.3486,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.7236842105263158,
|
| 83 |
+
"grad_norm": 17.85744857788086,
|
| 84 |
+
"learning_rate": 4.2195121951219514e-05,
|
| 85 |
+
"loss": 0.3221,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.7894736842105263,
|
| 90 |
+
"grad_norm": 11.210858345031738,
|
| 91 |
+
"learning_rate": 4.097560975609756e-05,
|
| 92 |
+
"loss": 0.3001,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.8552631578947368,
|
| 97 |
+
"grad_norm": 14.170101165771484,
|
| 98 |
+
"learning_rate": 3.975609756097561e-05,
|
| 99 |
+
"loss": 0.2871,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.9210526315789473,
|
| 104 |
+
"grad_norm": 8.286581993103027,
|
| 105 |
+
"learning_rate": 3.853658536585366e-05,
|
| 106 |
+
"loss": 0.2954,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.9868421052631579,
|
| 111 |
+
"grad_norm": 8.435368537902832,
|
| 112 |
+
"learning_rate": 3.731707317073171e-05,
|
| 113 |
+
"loss": 0.2774,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.0,
|
| 118 |
+
"eval_accuracy": 0.9578703703703704,
|
| 119 |
+
"eval_loss": 0.12819555401802063,
|
| 120 |
+
"eval_runtime": 12.8415,
|
| 121 |
+
"eval_samples_per_second": 168.205,
|
| 122 |
+
"eval_steps_per_second": 5.295,
|
| 123 |
+
"step": 152
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0526315789473684,
|
| 127 |
+
"grad_norm": 11.784485816955566,
|
| 128 |
+
"learning_rate": 3.609756097560976e-05,
|
| 129 |
+
"loss": 0.2328,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.118421052631579,
|
| 134 |
+
"grad_norm": 13.228792190551758,
|
| 135 |
+
"learning_rate": 3.48780487804878e-05,
|
| 136 |
+
"loss": 0.2462,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1842105263157894,
|
| 141 |
+
"grad_norm": 10.550958633422852,
|
| 142 |
+
"learning_rate": 3.365853658536586e-05,
|
| 143 |
+
"loss": 0.2399,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.25,
|
| 148 |
+
"grad_norm": 5.997585296630859,
|
| 149 |
+
"learning_rate": 3.2439024390243906e-05,
|
| 150 |
+
"loss": 0.2252,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.3157894736842106,
|
| 155 |
+
"grad_norm": 8.08625602722168,
|
| 156 |
+
"learning_rate": 3.1219512195121955e-05,
|
| 157 |
+
"loss": 0.2357,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.381578947368421,
|
| 162 |
+
"grad_norm": 17.572458267211914,
|
| 163 |
+
"learning_rate": 3e-05,
|
| 164 |
+
"loss": 0.2258,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.4473684210526316,
|
| 169 |
+
"grad_norm": 12.296513557434082,
|
| 170 |
+
"learning_rate": 2.8780487804878046e-05,
|
| 171 |
+
"loss": 0.2645,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.513157894736842,
|
| 176 |
+
"grad_norm": 8.180034637451172,
|
| 177 |
+
"learning_rate": 2.7560975609756102e-05,
|
| 178 |
+
"loss": 0.2159,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.5789473684210527,
|
| 183 |
+
"grad_norm": 12.796661376953125,
|
| 184 |
+
"learning_rate": 2.6341463414634148e-05,
|
| 185 |
+
"loss": 0.2375,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.6447368421052633,
|
| 190 |
+
"grad_norm": 10.516425132751465,
|
| 191 |
+
"learning_rate": 2.5121951219512197e-05,
|
| 192 |
+
"loss": 0.2049,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.7105263157894737,
|
| 197 |
+
"grad_norm": 6.393877983093262,
|
| 198 |
+
"learning_rate": 2.3902439024390243e-05,
|
| 199 |
+
"loss": 0.211,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.776315789473684,
|
| 204 |
+
"grad_norm": 9.698746681213379,
|
| 205 |
+
"learning_rate": 2.2682926829268295e-05,
|
| 206 |
+
"loss": 0.2134,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.8421052631578947,
|
| 211 |
+
"grad_norm": 6.169530391693115,
|
| 212 |
+
"learning_rate": 2.146341463414634e-05,
|
| 213 |
+
"loss": 0.1787,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.9078947368421053,
|
| 218 |
+
"grad_norm": 9.887014389038086,
|
| 219 |
+
"learning_rate": 2.0243902439024393e-05,
|
| 220 |
+
"loss": 0.1795,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.973684210526316,
|
| 225 |
+
"grad_norm": 7.333874225616455,
|
| 226 |
+
"learning_rate": 1.902439024390244e-05,
|
| 227 |
+
"loss": 0.2199,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.0,
|
| 232 |
+
"eval_accuracy": 0.975462962962963,
|
| 233 |
+
"eval_loss": 0.07434366643428802,
|
| 234 |
+
"eval_runtime": 12.8241,
|
| 235 |
+
"eval_samples_per_second": 168.433,
|
| 236 |
+
"eval_steps_per_second": 5.303,
|
| 237 |
+
"step": 304
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.039473684210526,
|
| 241 |
+
"grad_norm": 14.901606559753418,
|
| 242 |
+
"learning_rate": 1.7804878048780488e-05,
|
| 243 |
+
"loss": 0.1771,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.1052631578947367,
|
| 248 |
+
"grad_norm": 15.063396453857422,
|
| 249 |
+
"learning_rate": 1.6585365853658537e-05,
|
| 250 |
+
"loss": 0.1884,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.1710526315789473,
|
| 255 |
+
"grad_norm": 11.021356582641602,
|
| 256 |
+
"learning_rate": 1.5365853658536586e-05,
|
| 257 |
+
"loss": 0.1874,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.236842105263158,
|
| 262 |
+
"grad_norm": 12.141759872436523,
|
| 263 |
+
"learning_rate": 1.4146341463414633e-05,
|
| 264 |
+
"loss": 0.1737,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.3026315789473686,
|
| 269 |
+
"grad_norm": 8.017112731933594,
|
| 270 |
+
"learning_rate": 1.2926829268292684e-05,
|
| 271 |
+
"loss": 0.1793,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.3684210526315788,
|
| 276 |
+
"grad_norm": 8.373170852661133,
|
| 277 |
+
"learning_rate": 1.1707317073170733e-05,
|
| 278 |
+
"loss": 0.1863,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.4342105263157894,
|
| 283 |
+
"grad_norm": 9.354153633117676,
|
| 284 |
+
"learning_rate": 1.048780487804878e-05,
|
| 285 |
+
"loss": 0.1579,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.5,
|
| 290 |
+
"grad_norm": 8.749258041381836,
|
| 291 |
+
"learning_rate": 9.26829268292683e-06,
|
| 292 |
+
"loss": 0.1672,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.5657894736842106,
|
| 297 |
+
"grad_norm": 8.372227668762207,
|
| 298 |
+
"learning_rate": 8.048780487804879e-06,
|
| 299 |
+
"loss": 0.1624,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.6315789473684212,
|
| 304 |
+
"grad_norm": 11.717450141906738,
|
| 305 |
+
"learning_rate": 6.829268292682928e-06,
|
| 306 |
+
"loss": 0.1826,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.6973684210526314,
|
| 311 |
+
"grad_norm": 6.175394535064697,
|
| 312 |
+
"learning_rate": 5.609756097560976e-06,
|
| 313 |
+
"loss": 0.192,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.763157894736842,
|
| 318 |
+
"grad_norm": 9.798537254333496,
|
| 319 |
+
"learning_rate": 4.390243902439024e-06,
|
| 320 |
+
"loss": 0.158,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.8289473684210527,
|
| 325 |
+
"grad_norm": 7.753054141998291,
|
| 326 |
+
"learning_rate": 3.1707317073170736e-06,
|
| 327 |
+
"loss": 0.1463,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.8947368421052633,
|
| 332 |
+
"grad_norm": 9.600172996520996,
|
| 333 |
+
"learning_rate": 1.951219512195122e-06,
|
| 334 |
+
"loss": 0.1926,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.9605263157894735,
|
| 339 |
+
"grad_norm": 7.151966094970703,
|
| 340 |
+
"learning_rate": 7.317073170731708e-07,
|
| 341 |
+
"loss": 0.1356,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.0,
|
| 346 |
+
"eval_accuracy": 0.9787037037037037,
|
| 347 |
+
"eval_loss": 0.06794986128807068,
|
| 348 |
+
"eval_runtime": 13.1952,
|
| 349 |
+
"eval_samples_per_second": 163.695,
|
| 350 |
+
"eval_steps_per_second": 5.153,
|
| 351 |
+
"step": 456
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.0,
|
| 355 |
+
"step": 456,
|
| 356 |
+
"total_flos": 1.4499253204608614e+18,
|
| 357 |
+
"train_loss": 0.3743210191789426,
|
| 358 |
+
"train_runtime": 869.999,
|
| 359 |
+
"train_samples_per_second": 67.035,
|
| 360 |
+
"train_steps_per_second": 0.524
|
| 361 |
+
}
|
| 362 |
+
],
|
| 363 |
+
"logging_steps": 10,
|
| 364 |
+
"max_steps": 456,
|
| 365 |
+
"num_input_tokens_seen": 0,
|
| 366 |
+
"num_train_epochs": 3,
|
| 367 |
+
"save_steps": 500,
|
| 368 |
+
"stateful_callbacks": {
|
| 369 |
+
"TrainerControl": {
|
| 370 |
+
"args": {
|
| 371 |
+
"should_epoch_stop": false,
|
| 372 |
+
"should_evaluate": false,
|
| 373 |
+
"should_log": false,
|
| 374 |
+
"should_save": true,
|
| 375 |
+
"should_training_stop": true
|
| 376 |
+
},
|
| 377 |
+
"attributes": {}
|
| 378 |
+
}
|
| 379 |
+
},
|
| 380 |
+
"total_flos": 1.4499253204608614e+18,
|
| 381 |
+
"train_batch_size": 32,
|
| 382 |
+
"trial_name": null,
|
| 383 |
+
"trial_params": null
|
| 384 |
+
}
|