End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.9609375,
|
| 4 |
+
"eval_loss": 0.12107539176940918,
|
| 5 |
+
"eval_runtime": 11.6544,
|
| 6 |
+
"eval_samples_per_second": 10.983,
|
| 7 |
+
"eval_steps_per_second": 0.343,
|
| 8 |
+
"total_flos": 5.0805641487089664e+17,
|
| 9 |
+
"train_loss": 0.10081802383065223,
|
| 10 |
+
"train_runtime": 2771.0512,
|
| 11 |
+
"train_samples_per_second": 7.376,
|
| 12 |
+
"train_steps_per_second": 0.058
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.9609375,
|
| 4 |
+
"eval_loss": 0.12107539176940918,
|
| 5 |
+
"eval_runtime": 11.6544,
|
| 6 |
+
"eval_samples_per_second": 10.983,
|
| 7 |
+
"eval_steps_per_second": 0.343
|
| 8 |
+
}
|
runs/Apr20_09-50-37_94f669bc21b5/events.out.tfevents.1681987059.94f669bc21b5.459.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f664e408a2ce9a0f05ed49ce5ec90e2f04b19cd8e7f99e3194401725ec1686b7
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"total_flos": 5.0805641487089664e+17,
|
| 4 |
+
"train_loss": 0.10081802383065223,
|
| 5 |
+
"train_runtime": 2771.0512,
|
| 6 |
+
"train_samples_per_second": 7.376,
|
| 7 |
+
"train_steps_per_second": 0.058
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,481 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9609375,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-60",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"global_step": 160,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.8515625,
|
| 13 |
+
"eval_loss": 0.4862026572227478,
|
| 14 |
+
"eval_runtime": 11.5152,
|
| 15 |
+
"eval_samples_per_second": 11.116,
|
| 16 |
+
"eval_steps_per_second": 0.347,
|
| 17 |
+
"step": 4
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_accuracy": 0.8828125,
|
| 22 |
+
"eval_loss": 0.41026031970977783,
|
| 23 |
+
"eval_runtime": 10.9773,
|
| 24 |
+
"eval_samples_per_second": 11.66,
|
| 25 |
+
"eval_steps_per_second": 0.364,
|
| 26 |
+
"step": 8
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.5,
|
| 30 |
+
"learning_rate": 3.125e-05,
|
| 31 |
+
"loss": 0.4518,
|
| 32 |
+
"step": 10
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.0,
|
| 36 |
+
"eval_accuracy": 0.8984375,
|
| 37 |
+
"eval_loss": 0.3210464119911194,
|
| 38 |
+
"eval_runtime": 11.059,
|
| 39 |
+
"eval_samples_per_second": 11.574,
|
| 40 |
+
"eval_steps_per_second": 0.362,
|
| 41 |
+
"step": 12
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 4.0,
|
| 45 |
+
"eval_accuracy": 0.9375,
|
| 46 |
+
"eval_loss": 0.2052571028470993,
|
| 47 |
+
"eval_runtime": 11.5695,
|
| 48 |
+
"eval_samples_per_second": 11.064,
|
| 49 |
+
"eval_steps_per_second": 0.346,
|
| 50 |
+
"step": 16
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 5.0,
|
| 54 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 55 |
+
"loss": 0.2909,
|
| 56 |
+
"step": 20
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 5.0,
|
| 60 |
+
"eval_accuracy": 0.9453125,
|
| 61 |
+
"eval_loss": 0.16745075583457947,
|
| 62 |
+
"eval_runtime": 11.0604,
|
| 63 |
+
"eval_samples_per_second": 11.573,
|
| 64 |
+
"eval_steps_per_second": 0.362,
|
| 65 |
+
"step": 20
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 6.0,
|
| 69 |
+
"eval_accuracy": 0.953125,
|
| 70 |
+
"eval_loss": 0.14394168555736542,
|
| 71 |
+
"eval_runtime": 11.4729,
|
| 72 |
+
"eval_samples_per_second": 11.157,
|
| 73 |
+
"eval_steps_per_second": 0.349,
|
| 74 |
+
"step": 24
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 7.0,
|
| 78 |
+
"eval_accuracy": 0.9296875,
|
| 79 |
+
"eval_loss": 0.1447799652814865,
|
| 80 |
+
"eval_runtime": 10.9705,
|
| 81 |
+
"eval_samples_per_second": 11.668,
|
| 82 |
+
"eval_steps_per_second": 0.365,
|
| 83 |
+
"step": 28
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 7.5,
|
| 87 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 88 |
+
"loss": 0.1492,
|
| 89 |
+
"step": 30
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 8.0,
|
| 93 |
+
"eval_accuracy": 0.953125,
|
| 94 |
+
"eval_loss": 0.1797824651002884,
|
| 95 |
+
"eval_runtime": 11.56,
|
| 96 |
+
"eval_samples_per_second": 11.073,
|
| 97 |
+
"eval_steps_per_second": 0.346,
|
| 98 |
+
"step": 32
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 9.0,
|
| 102 |
+
"eval_accuracy": 0.9453125,
|
| 103 |
+
"eval_loss": 0.13595758378505707,
|
| 104 |
+
"eval_runtime": 10.9633,
|
| 105 |
+
"eval_samples_per_second": 11.675,
|
| 106 |
+
"eval_steps_per_second": 0.365,
|
| 107 |
+
"step": 36
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 10.0,
|
| 111 |
+
"learning_rate": 4.166666666666667e-05,
|
| 112 |
+
"loss": 0.1161,
|
| 113 |
+
"step": 40
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 10.0,
|
| 117 |
+
"eval_accuracy": 0.953125,
|
| 118 |
+
"eval_loss": 0.16701428592205048,
|
| 119 |
+
"eval_runtime": 11.2363,
|
| 120 |
+
"eval_samples_per_second": 11.392,
|
| 121 |
+
"eval_steps_per_second": 0.356,
|
| 122 |
+
"step": 40
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 11.0,
|
| 126 |
+
"eval_accuracy": 0.953125,
|
| 127 |
+
"eval_loss": 0.16373871266841888,
|
| 128 |
+
"eval_runtime": 11.6774,
|
| 129 |
+
"eval_samples_per_second": 10.961,
|
| 130 |
+
"eval_steps_per_second": 0.343,
|
| 131 |
+
"step": 44
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 12.0,
|
| 135 |
+
"eval_accuracy": 0.953125,
|
| 136 |
+
"eval_loss": 0.12978079915046692,
|
| 137 |
+
"eval_runtime": 11.0841,
|
| 138 |
+
"eval_samples_per_second": 11.548,
|
| 139 |
+
"eval_steps_per_second": 0.361,
|
| 140 |
+
"step": 48
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 12.5,
|
| 144 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 145 |
+
"loss": 0.1053,
|
| 146 |
+
"step": 50
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 13.0,
|
| 150 |
+
"eval_accuracy": 0.953125,
|
| 151 |
+
"eval_loss": 0.11624787002801895,
|
| 152 |
+
"eval_runtime": 11.6132,
|
| 153 |
+
"eval_samples_per_second": 11.022,
|
| 154 |
+
"eval_steps_per_second": 0.344,
|
| 155 |
+
"step": 52
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 14.0,
|
| 159 |
+
"eval_accuracy": 0.953125,
|
| 160 |
+
"eval_loss": 0.13526399433612823,
|
| 161 |
+
"eval_runtime": 11.0555,
|
| 162 |
+
"eval_samples_per_second": 11.578,
|
| 163 |
+
"eval_steps_per_second": 0.362,
|
| 164 |
+
"step": 56
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 15.0,
|
| 168 |
+
"learning_rate": 3.472222222222222e-05,
|
| 169 |
+
"loss": 0.0839,
|
| 170 |
+
"step": 60
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 15.0,
|
| 174 |
+
"eval_accuracy": 0.9609375,
|
| 175 |
+
"eval_loss": 0.12107539176940918,
|
| 176 |
+
"eval_runtime": 11.0588,
|
| 177 |
+
"eval_samples_per_second": 11.574,
|
| 178 |
+
"eval_steps_per_second": 0.362,
|
| 179 |
+
"step": 60
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 16.0,
|
| 183 |
+
"eval_accuracy": 0.9609375,
|
| 184 |
+
"eval_loss": 0.11126996576786041,
|
| 185 |
+
"eval_runtime": 11.181,
|
| 186 |
+
"eval_samples_per_second": 11.448,
|
| 187 |
+
"eval_steps_per_second": 0.358,
|
| 188 |
+
"step": 64
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 17.0,
|
| 192 |
+
"eval_accuracy": 0.9609375,
|
| 193 |
+
"eval_loss": 0.11446654796600342,
|
| 194 |
+
"eval_runtime": 10.8152,
|
| 195 |
+
"eval_samples_per_second": 11.835,
|
| 196 |
+
"eval_steps_per_second": 0.37,
|
| 197 |
+
"step": 68
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 17.5,
|
| 201 |
+
"learning_rate": 3.125e-05,
|
| 202 |
+
"loss": 0.0689,
|
| 203 |
+
"step": 70
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 18.0,
|
| 207 |
+
"eval_accuracy": 0.953125,
|
| 208 |
+
"eval_loss": 0.1238832175731659,
|
| 209 |
+
"eval_runtime": 11.2676,
|
| 210 |
+
"eval_samples_per_second": 11.36,
|
| 211 |
+
"eval_steps_per_second": 0.355,
|
| 212 |
+
"step": 72
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 19.0,
|
| 216 |
+
"eval_accuracy": 0.953125,
|
| 217 |
+
"eval_loss": 0.1279521882534027,
|
| 218 |
+
"eval_runtime": 10.0825,
|
| 219 |
+
"eval_samples_per_second": 12.695,
|
| 220 |
+
"eval_steps_per_second": 0.397,
|
| 221 |
+
"step": 76
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 20.0,
|
| 225 |
+
"learning_rate": 2.777777777777778e-05,
|
| 226 |
+
"loss": 0.0581,
|
| 227 |
+
"step": 80
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 20.0,
|
| 231 |
+
"eval_accuracy": 0.953125,
|
| 232 |
+
"eval_loss": 0.15327975153923035,
|
| 233 |
+
"eval_runtime": 10.9213,
|
| 234 |
+
"eval_samples_per_second": 11.72,
|
| 235 |
+
"eval_steps_per_second": 0.366,
|
| 236 |
+
"step": 80
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 21.0,
|
| 240 |
+
"eval_accuracy": 0.9609375,
|
| 241 |
+
"eval_loss": 0.13229623436927795,
|
| 242 |
+
"eval_runtime": 11.6242,
|
| 243 |
+
"eval_samples_per_second": 11.011,
|
| 244 |
+
"eval_steps_per_second": 0.344,
|
| 245 |
+
"step": 84
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 22.0,
|
| 249 |
+
"eval_accuracy": 0.953125,
|
| 250 |
+
"eval_loss": 0.1327400803565979,
|
| 251 |
+
"eval_runtime": 11.4822,
|
| 252 |
+
"eval_samples_per_second": 11.148,
|
| 253 |
+
"eval_steps_per_second": 0.348,
|
| 254 |
+
"step": 88
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 22.5,
|
| 258 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 259 |
+
"loss": 0.0545,
|
| 260 |
+
"step": 90
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 23.0,
|
| 264 |
+
"eval_accuracy": 0.953125,
|
| 265 |
+
"eval_loss": 0.15285906195640564,
|
| 266 |
+
"eval_runtime": 11.5375,
|
| 267 |
+
"eval_samples_per_second": 11.094,
|
| 268 |
+
"eval_steps_per_second": 0.347,
|
| 269 |
+
"step": 92
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 24.0,
|
| 273 |
+
"eval_accuracy": 0.953125,
|
| 274 |
+
"eval_loss": 0.1356508731842041,
|
| 275 |
+
"eval_runtime": 11.2408,
|
| 276 |
+
"eval_samples_per_second": 11.387,
|
| 277 |
+
"eval_steps_per_second": 0.356,
|
| 278 |
+
"step": 96
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 25.0,
|
| 282 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 283 |
+
"loss": 0.046,
|
| 284 |
+
"step": 100
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 25.0,
|
| 288 |
+
"eval_accuracy": 0.953125,
|
| 289 |
+
"eval_loss": 0.13333538174629211,
|
| 290 |
+
"eval_runtime": 11.6542,
|
| 291 |
+
"eval_samples_per_second": 10.983,
|
| 292 |
+
"eval_steps_per_second": 0.343,
|
| 293 |
+
"step": 100
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 26.0,
|
| 297 |
+
"eval_accuracy": 0.953125,
|
| 298 |
+
"eval_loss": 0.14664225280284882,
|
| 299 |
+
"eval_runtime": 11.0398,
|
| 300 |
+
"eval_samples_per_second": 11.594,
|
| 301 |
+
"eval_steps_per_second": 0.362,
|
| 302 |
+
"step": 104
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 27.0,
|
| 306 |
+
"eval_accuracy": 0.953125,
|
| 307 |
+
"eval_loss": 0.13004614412784576,
|
| 308 |
+
"eval_runtime": 11.0794,
|
| 309 |
+
"eval_samples_per_second": 11.553,
|
| 310 |
+
"eval_steps_per_second": 0.361,
|
| 311 |
+
"step": 108
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 27.5,
|
| 315 |
+
"learning_rate": 1.736111111111111e-05,
|
| 316 |
+
"loss": 0.0421,
|
| 317 |
+
"step": 110
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 28.0,
|
| 321 |
+
"eval_accuracy": 0.9609375,
|
| 322 |
+
"eval_loss": 0.10774001479148865,
|
| 323 |
+
"eval_runtime": 11.5664,
|
| 324 |
+
"eval_samples_per_second": 11.067,
|
| 325 |
+
"eval_steps_per_second": 0.346,
|
| 326 |
+
"step": 112
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 29.0,
|
| 330 |
+
"eval_accuracy": 0.9609375,
|
| 331 |
+
"eval_loss": 0.09847689419984818,
|
| 332 |
+
"eval_runtime": 11.1305,
|
| 333 |
+
"eval_samples_per_second": 11.5,
|
| 334 |
+
"eval_steps_per_second": 0.359,
|
| 335 |
+
"step": 116
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 30.0,
|
| 339 |
+
"learning_rate": 1.388888888888889e-05,
|
| 340 |
+
"loss": 0.0371,
|
| 341 |
+
"step": 120
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 30.0,
|
| 345 |
+
"eval_accuracy": 0.953125,
|
| 346 |
+
"eval_loss": 0.11860589683055878,
|
| 347 |
+
"eval_runtime": 11.1207,
|
| 348 |
+
"eval_samples_per_second": 11.51,
|
| 349 |
+
"eval_steps_per_second": 0.36,
|
| 350 |
+
"step": 120
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 31.0,
|
| 354 |
+
"eval_accuracy": 0.953125,
|
| 355 |
+
"eval_loss": 0.1123187392950058,
|
| 356 |
+
"eval_runtime": 11.7828,
|
| 357 |
+
"eval_samples_per_second": 10.863,
|
| 358 |
+
"eval_steps_per_second": 0.339,
|
| 359 |
+
"step": 124
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 32.0,
|
| 363 |
+
"eval_accuracy": 0.953125,
|
| 364 |
+
"eval_loss": 0.11436556279659271,
|
| 365 |
+
"eval_runtime": 11.7664,
|
| 366 |
+
"eval_samples_per_second": 10.878,
|
| 367 |
+
"eval_steps_per_second": 0.34,
|
| 368 |
+
"step": 128
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 32.5,
|
| 372 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 373 |
+
"loss": 0.0348,
|
| 374 |
+
"step": 130
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 33.0,
|
| 378 |
+
"eval_accuracy": 0.953125,
|
| 379 |
+
"eval_loss": 0.12758083641529083,
|
| 380 |
+
"eval_runtime": 11.1627,
|
| 381 |
+
"eval_samples_per_second": 11.467,
|
| 382 |
+
"eval_steps_per_second": 0.358,
|
| 383 |
+
"step": 132
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 34.0,
|
| 387 |
+
"eval_accuracy": 0.953125,
|
| 388 |
+
"eval_loss": 0.14878937602043152,
|
| 389 |
+
"eval_runtime": 11.0243,
|
| 390 |
+
"eval_samples_per_second": 11.611,
|
| 391 |
+
"eval_steps_per_second": 0.363,
|
| 392 |
+
"step": 136
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 35.0,
|
| 396 |
+
"learning_rate": 6.944444444444445e-06,
|
| 397 |
+
"loss": 0.0211,
|
| 398 |
+
"step": 140
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 35.0,
|
| 402 |
+
"eval_accuracy": 0.953125,
|
| 403 |
+
"eval_loss": 0.155960351228714,
|
| 404 |
+
"eval_runtime": 11.5378,
|
| 405 |
+
"eval_samples_per_second": 11.094,
|
| 406 |
+
"eval_steps_per_second": 0.347,
|
| 407 |
+
"step": 140
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 36.0,
|
| 411 |
+
"eval_accuracy": 0.953125,
|
| 412 |
+
"eval_loss": 0.1477176994085312,
|
| 413 |
+
"eval_runtime": 11.1115,
|
| 414 |
+
"eval_samples_per_second": 11.52,
|
| 415 |
+
"eval_steps_per_second": 0.36,
|
| 416 |
+
"step": 144
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 37.0,
|
| 420 |
+
"eval_accuracy": 0.953125,
|
| 421 |
+
"eval_loss": 0.1488116979598999,
|
| 422 |
+
"eval_runtime": 11.3254,
|
| 423 |
+
"eval_samples_per_second": 11.302,
|
| 424 |
+
"eval_steps_per_second": 0.353,
|
| 425 |
+
"step": 148
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 37.5,
|
| 429 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 430 |
+
"loss": 0.0274,
|
| 431 |
+
"step": 150
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 38.0,
|
| 435 |
+
"eval_accuracy": 0.953125,
|
| 436 |
+
"eval_loss": 0.14666207134723663,
|
| 437 |
+
"eval_runtime": 11.771,
|
| 438 |
+
"eval_samples_per_second": 10.874,
|
| 439 |
+
"eval_steps_per_second": 0.34,
|
| 440 |
+
"step": 152
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 39.0,
|
| 444 |
+
"eval_accuracy": 0.953125,
|
| 445 |
+
"eval_loss": 0.14005045592784882,
|
| 446 |
+
"eval_runtime": 10.9158,
|
| 447 |
+
"eval_samples_per_second": 11.726,
|
| 448 |
+
"eval_steps_per_second": 0.366,
|
| 449 |
+
"step": 156
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 40.0,
|
| 453 |
+
"learning_rate": 0.0,
|
| 454 |
+
"loss": 0.0259,
|
| 455 |
+
"step": 160
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 40.0,
|
| 459 |
+
"eval_accuracy": 0.953125,
|
| 460 |
+
"eval_loss": 0.1378861665725708,
|
| 461 |
+
"eval_runtime": 11.2497,
|
| 462 |
+
"eval_samples_per_second": 11.378,
|
| 463 |
+
"eval_steps_per_second": 0.356,
|
| 464 |
+
"step": 160
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 40.0,
|
| 468 |
+
"step": 160,
|
| 469 |
+
"total_flos": 5.0805641487089664e+17,
|
| 470 |
+
"train_loss": 0.10081802383065223,
|
| 471 |
+
"train_runtime": 2771.0512,
|
| 472 |
+
"train_samples_per_second": 7.376,
|
| 473 |
+
"train_steps_per_second": 0.058
|
| 474 |
+
}
|
| 475 |
+
],
|
| 476 |
+
"max_steps": 160,
|
| 477 |
+
"num_train_epochs": 40,
|
| 478 |
+
"total_flos": 5.0805641487089664e+17,
|
| 479 |
+
"trial_name": null,
|
| 480 |
+
"trial_params": null
|
| 481 |
+
}
|