Commit
•
ce106b2
1
Parent(s):
0f5fcf1
End of training
Browse files- all_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +266 -56
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 2.3031444978081792e+18,
|
| 4 |
+
"train_loss": 0.5514378428459168,
|
| 5 |
+
"train_runtime": 353.1964,
|
| 6 |
+
"train_samples_per_second": 84.146,
|
| 7 |
+
"train_steps_per_second": 0.17
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 2.3031444978081792e+18,
|
| 4 |
+
"train_loss": 0.5514378428459168,
|
| 5 |
+
"train_runtime": 353.1964,
|
| 6 |
+
"train_samples_per_second": 84.146,
|
| 7 |
+
"train_steps_per_second": 0.17
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,91 +1,301 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "vit-base-aihub_model-v2/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 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.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_precision": 0.
|
| 16 |
-
"eval_recall": 0.
|
| 17 |
-
"eval_runtime":
|
| 18 |
-
"eval_samples_per_second":
|
| 19 |
-
"eval_steps_per_second": 0.
|
| 20 |
"step": 3
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 2.0,
|
| 24 |
-
"eval_accuracy": 0.
|
| 25 |
-
"eval_f1": 0.
|
| 26 |
-
"eval_loss": 1.
|
| 27 |
-
"eval_precision": 0.
|
| 28 |
-
"eval_recall": 0.
|
| 29 |
-
"eval_runtime": 5.
|
| 30 |
-
"eval_samples_per_second":
|
| 31 |
-
"eval_steps_per_second": 0.
|
| 32 |
"step": 6
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 3.0,
|
| 36 |
-
"eval_accuracy": 0.
|
| 37 |
-
"eval_f1": 0.
|
| 38 |
-
"eval_loss":
|
| 39 |
-
"eval_precision": 0.
|
| 40 |
-
"eval_recall": 0.
|
| 41 |
-
"eval_runtime": 5.
|
| 42 |
-
"eval_samples_per_second": 32.
|
| 43 |
-
"eval_steps_per_second": 0.
|
| 44 |
"step": 9
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 3.33,
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 1.
|
| 50 |
"step": 10
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 4.0,
|
| 54 |
-
"eval_accuracy": 0.
|
| 55 |
-
"eval_f1": 0.
|
| 56 |
-
"eval_loss":
|
| 57 |
-
"eval_precision": 0.
|
| 58 |
-
"eval_recall": 0.
|
| 59 |
-
"eval_runtime":
|
| 60 |
-
"eval_samples_per_second":
|
| 61 |
-
"eval_steps_per_second": 0.
|
| 62 |
"step": 12
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 5.0,
|
| 66 |
-
"eval_accuracy": 0.
|
| 67 |
-
"eval_f1": 0.
|
| 68 |
-
"eval_loss":
|
| 69 |
-
"eval_precision": 0.
|
| 70 |
-
"eval_recall": 0.
|
| 71 |
-
"eval_runtime": 5.
|
| 72 |
-
"eval_samples_per_second":
|
| 73 |
-
"eval_steps_per_second": 0.
|
| 74 |
"step": 15
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
}
|
| 85 |
],
|
| 86 |
-
"max_steps":
|
| 87 |
-
"num_train_epochs":
|
| 88 |
-
"total_flos":
|
| 89 |
"trial_name": null,
|
| 90 |
"trial_params": null
|
| 91 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9759036144578314,
|
| 3 |
+
"best_model_checkpoint": "vit-base-aihub_model-v2/checkpoint-21",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 60,
|
| 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": 0.8373493975903614,
|
| 13 |
+
"eval_f1": 0.8021719960125756,
|
| 14 |
+
"eval_loss": 1.275346279144287,
|
| 15 |
+
"eval_precision": 0.8562555276264954,
|
| 16 |
+
"eval_recall": 0.7993336310123969,
|
| 17 |
+
"eval_runtime": 5.1244,
|
| 18 |
+
"eval_samples_per_second": 32.394,
|
| 19 |
+
"eval_steps_per_second": 0.39,
|
| 20 |
"step": 3
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 2.0,
|
| 24 |
+
"eval_accuracy": 0.8674698795180723,
|
| 25 |
+
"eval_f1": 0.8332850826867517,
|
| 26 |
+
"eval_loss": 1.12519371509552,
|
| 27 |
+
"eval_precision": 0.8895164063267512,
|
| 28 |
+
"eval_recall": 0.8299773699894692,
|
| 29 |
+
"eval_runtime": 5.8768,
|
| 30 |
+
"eval_samples_per_second": 28.246,
|
| 31 |
+
"eval_steps_per_second": 0.34,
|
| 32 |
"step": 6
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 3.0,
|
| 36 |
+
"eval_accuracy": 0.8975903614457831,
|
| 37 |
+
"eval_f1": 0.8759773182856855,
|
| 38 |
+
"eval_loss": 0.9427085518836975,
|
| 39 |
+
"eval_precision": 0.9184748178650618,
|
| 40 |
+
"eval_recall": 0.8695583787053841,
|
| 41 |
+
"eval_runtime": 5.0377,
|
| 42 |
+
"eval_samples_per_second": 32.952,
|
| 43 |
+
"eval_steps_per_second": 0.397,
|
| 44 |
"step": 9
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 3.33,
|
| 48 |
+
"learning_rate": 4.62962962962963e-05,
|
| 49 |
+
"loss": 1.1721,
|
| 50 |
"step": 10
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 4.0,
|
| 54 |
+
"eval_accuracy": 0.9397590361445783,
|
| 55 |
+
"eval_f1": 0.9245832269900981,
|
| 56 |
+
"eval_loss": 0.7995439171791077,
|
| 57 |
+
"eval_precision": 0.9474358974358973,
|
| 58 |
+
"eval_recall": 0.9195160314579552,
|
| 59 |
+
"eval_runtime": 4.7832,
|
| 60 |
+
"eval_samples_per_second": 34.705,
|
| 61 |
+
"eval_steps_per_second": 0.418,
|
| 62 |
"step": 12
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 5.0,
|
| 66 |
+
"eval_accuracy": 0.9698795180722891,
|
| 67 |
+
"eval_f1": 0.9642226698488042,
|
| 68 |
+
"eval_loss": 0.6819571256637573,
|
| 69 |
+
"eval_precision": 0.9703703703703704,
|
| 70 |
+
"eval_recall": 0.9612704174228676,
|
| 71 |
+
"eval_runtime": 5.722,
|
| 72 |
+
"eval_samples_per_second": 29.011,
|
| 73 |
+
"eval_steps_per_second": 0.35,
|
| 74 |
"step": 15
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 6.0,
|
| 78 |
+
"eval_accuracy": 0.963855421686747,
|
| 79 |
+
"eval_f1": 0.9587309087309088,
|
| 80 |
+
"eval_loss": 0.5926513671875,
|
| 81 |
+
"eval_precision": 0.9603174603174603,
|
| 82 |
+
"eval_recall": 0.9583428398582664,
|
| 83 |
+
"eval_runtime": 4.9473,
|
| 84 |
+
"eval_samples_per_second": 33.554,
|
| 85 |
+
"eval_steps_per_second": 0.404,
|
| 86 |
+
"step": 18
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 6.67,
|
| 90 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 91 |
+
"loss": 0.7084,
|
| 92 |
+
"step": 20
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_accuracy": 0.9759036144578314,
|
| 97 |
+
"eval_f1": 0.9725477910462431,
|
| 98 |
+
"eval_loss": 0.5238566398620605,
|
| 99 |
+
"eval_precision": 0.9724551764025448,
|
| 100 |
+
"eval_recall": 0.9728618961196093,
|
| 101 |
+
"eval_runtime": 4.8707,
|
| 102 |
+
"eval_samples_per_second": 34.081,
|
| 103 |
+
"eval_steps_per_second": 0.411,
|
| 104 |
+
"step": 21
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.0,
|
| 108 |
+
"eval_accuracy": 0.9698795180722891,
|
| 109 |
+
"eval_f1": 0.9664890836717462,
|
| 110 |
+
"eval_loss": 0.47428616881370544,
|
| 111 |
+
"eval_precision": 0.9665027954501638,
|
| 112 |
+
"eval_recall": 0.9671147696828277,
|
| 113 |
+
"eval_runtime": 5.4877,
|
| 114 |
+
"eval_samples_per_second": 30.249,
|
| 115 |
+
"eval_steps_per_second": 0.364,
|
| 116 |
+
"step": 24
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.0,
|
| 120 |
+
"eval_accuracy": 0.9578313253012049,
|
| 121 |
+
"eval_f1": 0.9543541588175232,
|
| 122 |
+
"eval_loss": 0.4436134994029999,
|
| 123 |
+
"eval_precision": 0.9557885097358781,
|
| 124 |
+
"eval_recall": 0.9556205168092645,
|
| 125 |
+
"eval_runtime": 5.8287,
|
| 126 |
+
"eval_samples_per_second": 28.48,
|
| 127 |
+
"eval_steps_per_second": 0.343,
|
| 128 |
+
"step": 27
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 10.0,
|
| 132 |
+
"learning_rate": 2.777777777777778e-05,
|
| 133 |
+
"loss": 0.4668,
|
| 134 |
+
"step": 30
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"eval_accuracy": 0.963855421686747,
|
| 139 |
+
"eval_f1": 0.9604284776111401,
|
| 140 |
+
"eval_loss": 0.4069555699825287,
|
| 141 |
+
"eval_precision": 0.9609609235289817,
|
| 142 |
+
"eval_recall": 0.9613676432460462,
|
| 143 |
+
"eval_runtime": 5.1247,
|
| 144 |
+
"eval_samples_per_second": 32.392,
|
| 145 |
+
"eval_steps_per_second": 0.39,
|
| 146 |
+
"step": 30
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 11.0,
|
| 150 |
+
"eval_accuracy": 0.9698795180722891,
|
| 151 |
+
"eval_f1": 0.9664890836717462,
|
| 152 |
+
"eval_loss": 0.3817099928855896,
|
| 153 |
+
"eval_precision": 0.9665027954501638,
|
| 154 |
+
"eval_recall": 0.9671147696828277,
|
| 155 |
+
"eval_runtime": 5.2147,
|
| 156 |
+
"eval_samples_per_second": 31.833,
|
| 157 |
+
"eval_steps_per_second": 0.384,
|
| 158 |
+
"step": 33
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 12.0,
|
| 162 |
+
"eval_accuracy": 0.9698795180722891,
|
| 163 |
+
"eval_f1": 0.9664890836717462,
|
| 164 |
+
"eval_loss": 0.36248189210891724,
|
| 165 |
+
"eval_precision": 0.9665027954501638,
|
| 166 |
+
"eval_recall": 0.9671147696828277,
|
| 167 |
+
"eval_runtime": 5.5147,
|
| 168 |
+
"eval_samples_per_second": 30.101,
|
| 169 |
+
"eval_steps_per_second": 0.363,
|
| 170 |
+
"step": 36
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 13.0,
|
| 174 |
+
"eval_accuracy": 0.9578313253012049,
|
| 175 |
+
"eval_f1": 0.9543541588175232,
|
| 176 |
+
"eval_loss": 0.35361266136169434,
|
| 177 |
+
"eval_precision": 0.9557885097358781,
|
| 178 |
+
"eval_recall": 0.9556205168092645,
|
| 179 |
+
"eval_runtime": 5.2314,
|
| 180 |
+
"eval_samples_per_second": 31.731,
|
| 181 |
+
"eval_steps_per_second": 0.382,
|
| 182 |
+
"step": 39
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.33,
|
| 186 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 187 |
+
"loss": 0.3611,
|
| 188 |
+
"step": 40
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 14.0,
|
| 192 |
+
"eval_accuracy": 0.9578313253012049,
|
| 193 |
+
"eval_f1": 0.9543541588175232,
|
| 194 |
+
"eval_loss": 0.338364839553833,
|
| 195 |
+
"eval_precision": 0.9557885097358781,
|
| 196 |
+
"eval_recall": 0.9556205168092645,
|
| 197 |
+
"eval_runtime": 4.9478,
|
| 198 |
+
"eval_samples_per_second": 33.551,
|
| 199 |
+
"eval_steps_per_second": 0.404,
|
| 200 |
+
"step": 42
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 15.0,
|
| 204 |
+
"eval_accuracy": 0.9698795180722891,
|
| 205 |
+
"eval_f1": 0.9664890836717462,
|
| 206 |
+
"eval_loss": 0.32493022084236145,
|
| 207 |
+
"eval_precision": 0.9665027954501638,
|
| 208 |
+
"eval_recall": 0.9671147696828277,
|
| 209 |
+
"eval_runtime": 5.2287,
|
| 210 |
+
"eval_samples_per_second": 31.748,
|
| 211 |
+
"eval_steps_per_second": 0.383,
|
| 212 |
+
"step": 45
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 16.0,
|
| 216 |
+
"eval_accuracy": 0.9698795180722891,
|
| 217 |
+
"eval_f1": 0.9664890836717462,
|
| 218 |
+
"eval_loss": 0.3163941204547882,
|
| 219 |
+
"eval_precision": 0.9665027954501638,
|
| 220 |
+
"eval_recall": 0.9671147696828277,
|
| 221 |
+
"eval_runtime": 5.5155,
|
| 222 |
+
"eval_samples_per_second": 30.097,
|
| 223 |
+
"eval_steps_per_second": 0.363,
|
| 224 |
+
"step": 48
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.67,
|
| 228 |
+
"learning_rate": 9.259259259259259e-06,
|
| 229 |
+
"loss": 0.3063,
|
| 230 |
+
"step": 50
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 17.0,
|
| 234 |
+
"eval_accuracy": 0.963855421686747,
|
| 235 |
+
"eval_f1": 0.9604284776111401,
|
| 236 |
+
"eval_loss": 0.3141733705997467,
|
| 237 |
+
"eval_precision": 0.9609609235289817,
|
| 238 |
+
"eval_recall": 0.9613676432460462,
|
| 239 |
+
"eval_runtime": 5.4681,
|
| 240 |
+
"eval_samples_per_second": 30.358,
|
| 241 |
+
"eval_steps_per_second": 0.366,
|
| 242 |
+
"step": 51
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 18.0,
|
| 246 |
+
"eval_accuracy": 0.963855421686747,
|
| 247 |
+
"eval_f1": 0.9604284776111401,
|
| 248 |
+
"eval_loss": 0.3122059106826782,
|
| 249 |
+
"eval_precision": 0.9609609235289817,
|
| 250 |
+
"eval_recall": 0.9613676432460462,
|
| 251 |
+
"eval_runtime": 4.8313,
|
| 252 |
+
"eval_samples_per_second": 34.36,
|
| 253 |
+
"eval_steps_per_second": 0.414,
|
| 254 |
+
"step": 54
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 19.0,
|
| 258 |
+
"eval_accuracy": 0.963855421686747,
|
| 259 |
+
"eval_f1": 0.9604284776111401,
|
| 260 |
+
"eval_loss": 0.30928835272789,
|
| 261 |
+
"eval_precision": 0.9609609235289817,
|
| 262 |
+
"eval_recall": 0.9613676432460462,
|
| 263 |
+
"eval_runtime": 5.3566,
|
| 264 |
+
"eval_samples_per_second": 30.99,
|
| 265 |
+
"eval_steps_per_second": 0.373,
|
| 266 |
+
"step": 57
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 20.0,
|
| 270 |
+
"learning_rate": 0.0,
|
| 271 |
+
"loss": 0.294,
|
| 272 |
+
"step": 60
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 20.0,
|
| 276 |
+
"eval_accuracy": 0.963855421686747,
|
| 277 |
+
"eval_f1": 0.9604284776111401,
|
| 278 |
+
"eval_loss": 0.3075591027736664,
|
| 279 |
+
"eval_precision": 0.9609609235289817,
|
| 280 |
+
"eval_recall": 0.9613676432460462,
|
| 281 |
+
"eval_runtime": 5.6855,
|
| 282 |
+
"eval_samples_per_second": 29.197,
|
| 283 |
+
"eval_steps_per_second": 0.352,
|
| 284 |
+
"step": 60
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 20.0,
|
| 288 |
+
"step": 60,
|
| 289 |
+
"total_flos": 2.3031444978081792e+18,
|
| 290 |
+
"train_loss": 0.5514378428459168,
|
| 291 |
+
"train_runtime": 353.1964,
|
| 292 |
+
"train_samples_per_second": 84.146,
|
| 293 |
+
"train_steps_per_second": 0.17
|
| 294 |
}
|
| 295 |
],
|
| 296 |
+
"max_steps": 60,
|
| 297 |
+
"num_train_epochs": 20,
|
| 298 |
+
"total_flos": 2.3031444978081792e+18,
|
| 299 |
"trial_name": null,
|
| 300 |
"trial_params": null
|
| 301 |
}
|