End of training
Browse files- all_results.json +15 -0
- eval_results.json +11 -0
- runs/Mar20_09-41-34_bookbot-hf/events.out.tfevents.1679311059.bookbot-hf.27068.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +205 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.07136897146353674,
|
| 4 |
+
"eval_f1": 0.48760985270454266,
|
| 5 |
+
"eval_loss": 0.30630359053611755,
|
| 6 |
+
"eval_mAP": 0.47426149334040063,
|
| 7 |
+
"eval_roc_auc": 0.7140083968239697,
|
| 8 |
+
"eval_runtime": 199.8257,
|
| 9 |
+
"eval_samples_per_second": 89.963,
|
| 10 |
+
"eval_steps_per_second": 2.812,
|
| 11 |
+
"train_loss": 0.4376198089200687,
|
| 12 |
+
"train_runtime": 5452.4515,
|
| 13 |
+
"train_samples_per_second": 36.024,
|
| 14 |
+
"train_steps_per_second": 0.281
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.07136897146353674,
|
| 4 |
+
"eval_f1": 0.48760985270454266,
|
| 5 |
+
"eval_loss": 0.30630359053611755,
|
| 6 |
+
"eval_mAP": 0.47426149334040063,
|
| 7 |
+
"eval_roc_auc": 0.7140083968239697,
|
| 8 |
+
"eval_runtime": 199.8257,
|
| 9 |
+
"eval_samples_per_second": 89.963,
|
| 10 |
+
"eval_steps_per_second": 2.812
|
| 11 |
+
}
|
runs/Mar20_09-41-34_bookbot-hf/events.out.tfevents.1679311059.bookbot-hf.27068.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b52774c294c8bc80134541562f5ed01c8dd067762bd6ca6b86ec7465506ee64
|
| 3 |
+
size 555
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.4376198089200687,
|
| 4 |
+
"train_runtime": 5452.4515,
|
| 5 |
+
"train_samples_per_second": 36.024,
|
| 6 |
+
"train_steps_per_second": 0.281
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.996742671009772,
|
| 5 |
+
"global_step": 1530,
|
| 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 |
+
"learning_rate": 3e-05,
|
| 13 |
+
"loss": 1.5521,
|
| 14 |
+
"step": 153
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.020859987762140514,
|
| 19 |
+
"eval_f1": 0.3928758387664779,
|
| 20 |
+
"eval_loss": 0.7758789658546448,
|
| 21 |
+
"eval_mAP": 0.339376592817118,
|
| 22 |
+
"eval_roc_auc": 0.6789196770069326,
|
| 23 |
+
"eval_runtime": 199.2822,
|
| 24 |
+
"eval_samples_per_second": 90.209,
|
| 25 |
+
"eval_steps_per_second": 2.82,
|
| 26 |
+
"step": 153
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 31 |
+
"loss": 0.7088,
|
| 32 |
+
"step": 306
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.03487789953829894,
|
| 37 |
+
"eval_f1": 0.44802049737602123,
|
| 38 |
+
"eval_loss": 0.518318772315979,
|
| 39 |
+
"eval_mAP": 0.40469907094541646,
|
| 40 |
+
"eval_roc_auc": 0.7161709917220414,
|
| 41 |
+
"eval_runtime": 199.2709,
|
| 42 |
+
"eval_samples_per_second": 90.214,
|
| 43 |
+
"eval_steps_per_second": 2.82,
|
| 44 |
+
"step": 306
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 49 |
+
"loss": 0.484,
|
| 50 |
+
"step": 459
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"eval_accuracy": 0.04472381376202926,
|
| 55 |
+
"eval_f1": 0.4673244026068067,
|
| 56 |
+
"eval_loss": 0.4342249929904938,
|
| 57 |
+
"eval_mAP": 0.43476738028039985,
|
| 58 |
+
"eval_roc_auc": 0.7240716119428349,
|
| 59 |
+
"eval_runtime": 199.3141,
|
| 60 |
+
"eval_samples_per_second": 90.194,
|
| 61 |
+
"eval_steps_per_second": 2.82,
|
| 62 |
+
"step": 459
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 67 |
+
"loss": 0.369,
|
| 68 |
+
"step": 612
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.0,
|
| 72 |
+
"eval_accuracy": 0.05039773043333148,
|
| 73 |
+
"eval_f1": 0.4777058032688526,
|
| 74 |
+
"eval_loss": 0.38471919298171997,
|
| 75 |
+
"eval_mAP": 0.4462659411425718,
|
| 76 |
+
"eval_roc_auc": 0.7332463051626695,
|
| 77 |
+
"eval_runtime": 199.7831,
|
| 78 |
+
"eval_samples_per_second": 89.983,
|
| 79 |
+
"eval_steps_per_second": 2.813,
|
| 80 |
+
"step": 612
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 85 |
+
"loss": 0.2943,
|
| 86 |
+
"step": 765
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.0,
|
| 90 |
+
"eval_accuracy": 0.057184179785281196,
|
| 91 |
+
"eval_f1": 0.48378530618813875,
|
| 92 |
+
"eval_loss": 0.35873091220855713,
|
| 93 |
+
"eval_mAP": 0.4555505029466916,
|
| 94 |
+
"eval_roc_auc": 0.728419646417412,
|
| 95 |
+
"eval_runtime": 199.5573,
|
| 96 |
+
"eval_samples_per_second": 90.084,
|
| 97 |
+
"eval_steps_per_second": 2.816,
|
| 98 |
+
"step": 765
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.0,
|
| 102 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 103 |
+
"loss": 0.2446,
|
| 104 |
+
"step": 918
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"eval_accuracy": 0.06079991099738555,
|
| 109 |
+
"eval_f1": 0.48746197105190375,
|
| 110 |
+
"eval_loss": 0.34149762988090515,
|
| 111 |
+
"eval_mAP": 0.4627587003938359,
|
| 112 |
+
"eval_roc_auc": 0.7296145264183724,
|
| 113 |
+
"eval_runtime": 199.5498,
|
| 114 |
+
"eval_samples_per_second": 90.088,
|
| 115 |
+
"eval_steps_per_second": 2.816,
|
| 116 |
+
"step": 918
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.0,
|
| 120 |
+
"learning_rate": 9.999999999999999e-06,
|
| 121 |
+
"loss": 0.2099,
|
| 122 |
+
"step": 1071
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"eval_accuracy": 0.06480502864771652,
|
| 127 |
+
"eval_f1": 0.48957753814467153,
|
| 128 |
+
"eval_loss": 0.3272540867328644,
|
| 129 |
+
"eval_mAP": 0.46815321516964326,
|
| 130 |
+
"eval_roc_auc": 0.7245854561214261,
|
| 131 |
+
"eval_runtime": 199.6486,
|
| 132 |
+
"eval_samples_per_second": 90.043,
|
| 133 |
+
"eval_steps_per_second": 2.815,
|
| 134 |
+
"step": 1071
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.0,
|
| 138 |
+
"learning_rate": 6.666666666666667e-06,
|
| 139 |
+
"loss": 0.186,
|
| 140 |
+
"step": 1224
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 8.0,
|
| 144 |
+
"eval_accuracy": 0.06892139956611225,
|
| 145 |
+
"eval_f1": 0.4888448554234551,
|
| 146 |
+
"eval_loss": 0.31404560804367065,
|
| 147 |
+
"eval_mAP": 0.47110233159119475,
|
| 148 |
+
"eval_roc_auc": 0.7170914721421969,
|
| 149 |
+
"eval_runtime": 199.7258,
|
| 150 |
+
"eval_samples_per_second": 90.008,
|
| 151 |
+
"eval_steps_per_second": 2.814,
|
| 152 |
+
"step": 1224
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 9.0,
|
| 156 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 157 |
+
"loss": 0.1693,
|
| 158 |
+
"step": 1377
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 9.0,
|
| 162 |
+
"eval_accuracy": 0.07031206541692162,
|
| 163 |
+
"eval_f1": 0.48868811698382614,
|
| 164 |
+
"eval_loss": 0.3100704848766327,
|
| 165 |
+
"eval_mAP": 0.4740859292456036,
|
| 166 |
+
"eval_roc_auc": 0.7156721287285349,
|
| 167 |
+
"eval_runtime": 199.6676,
|
| 168 |
+
"eval_samples_per_second": 90.035,
|
| 169 |
+
"eval_steps_per_second": 2.815,
|
| 170 |
+
"step": 1377
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 10.0,
|
| 174 |
+
"learning_rate": 0.0,
|
| 175 |
+
"loss": 0.1582,
|
| 176 |
+
"step": 1530
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.0,
|
| 180 |
+
"eval_accuracy": 0.07136897146353674,
|
| 181 |
+
"eval_f1": 0.48760985270454266,
|
| 182 |
+
"eval_loss": 0.30630359053611755,
|
| 183 |
+
"eval_mAP": 0.47426149334040063,
|
| 184 |
+
"eval_roc_auc": 0.7140083968239697,
|
| 185 |
+
"eval_runtime": 199.7463,
|
| 186 |
+
"eval_samples_per_second": 89.999,
|
| 187 |
+
"eval_steps_per_second": 2.814,
|
| 188 |
+
"step": 1530
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 10.0,
|
| 192 |
+
"step": 1530,
|
| 193 |
+
"total_flos": 6.805036258155823e+18,
|
| 194 |
+
"train_loss": 0.4376198089200687,
|
| 195 |
+
"train_runtime": 5452.4515,
|
| 196 |
+
"train_samples_per_second": 36.024,
|
| 197 |
+
"train_steps_per_second": 0.281
|
| 198 |
+
}
|
| 199 |
+
],
|
| 200 |
+
"max_steps": 1530,
|
| 201 |
+
"num_train_epochs": 10,
|
| 202 |
+
"total_flos": 6.805036258155823e+18,
|
| 203 |
+
"trial_name": null,
|
| 204 |
+
"trial_params": null
|
| 205 |
+
}
|