File size: 5,211 Bytes
6c3df72 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 |
{
"best_metric": 0.8714285714285714,
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\checkpoint-148",
"epoch": 3.22972972972973,
"eval_steps": 500,
"global_step": 148,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06756756756756757,
"grad_norm": 6.096624374389648,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.2942,
"step": 10
},
{
"epoch": 0.13513513513513514,
"grad_norm": 7.102034568786621,
"learning_rate": 4.81203007518797e-05,
"loss": 2.2308,
"step": 20
},
{
"epoch": 0.20270270270270271,
"grad_norm": 7.2539143562316895,
"learning_rate": 4.43609022556391e-05,
"loss": 2.1149,
"step": 30
},
{
"epoch": 0.25675675675675674,
"eval_accuracy": 0.5571428571428572,
"eval_loss": 1.8154758214950562,
"eval_runtime": 10.1069,
"eval_samples_per_second": 6.926,
"eval_steps_per_second": 0.89,
"step": 38
},
{
"epoch": 1.0135135135135136,
"grad_norm": 25.16826057434082,
"learning_rate": 4.0601503759398494e-05,
"loss": 1.97,
"step": 40
},
{
"epoch": 1.0810810810810811,
"grad_norm": 10.718199729919434,
"learning_rate": 3.6842105263157895e-05,
"loss": 1.5744,
"step": 50
},
{
"epoch": 1.1486486486486487,
"grad_norm": 10.61833381652832,
"learning_rate": 3.3082706766917295e-05,
"loss": 1.3135,
"step": 60
},
{
"epoch": 1.2162162162162162,
"grad_norm": 8.033047676086426,
"learning_rate": 2.9323308270676693e-05,
"loss": 0.8974,
"step": 70
},
{
"epoch": 1.2567567567567568,
"eval_accuracy": 0.5857142857142857,
"eval_loss": 1.1256393194198608,
"eval_runtime": 9.8133,
"eval_samples_per_second": 7.133,
"eval_steps_per_second": 0.917,
"step": 76
},
{
"epoch": 2.027027027027027,
"grad_norm": 8.3702392578125,
"learning_rate": 2.556390977443609e-05,
"loss": 0.9946,
"step": 80
},
{
"epoch": 2.0945945945945947,
"grad_norm": 9.561596870422363,
"learning_rate": 2.1804511278195487e-05,
"loss": 0.7404,
"step": 90
},
{
"epoch": 2.1621621621621623,
"grad_norm": 11.346077919006348,
"learning_rate": 1.8045112781954888e-05,
"loss": 0.6667,
"step": 100
},
{
"epoch": 2.22972972972973,
"grad_norm": 7.648571014404297,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.5226,
"step": 110
},
{
"epoch": 2.2567567567567566,
"eval_accuracy": 0.8,
"eval_loss": 0.5665245056152344,
"eval_runtime": 8.9518,
"eval_samples_per_second": 7.82,
"eval_steps_per_second": 1.005,
"step": 114
},
{
"epoch": 3.0405405405405403,
"grad_norm": 3.668431520462036,
"learning_rate": 1.0526315789473684e-05,
"loss": 0.44,
"step": 120
},
{
"epoch": 3.108108108108108,
"grad_norm": 5.99934720993042,
"learning_rate": 6.766917293233083e-06,
"loss": 0.3393,
"step": 130
},
{
"epoch": 3.175675675675676,
"grad_norm": 10.936161994934082,
"learning_rate": 3.007518796992481e-06,
"loss": 0.3423,
"step": 140
},
{
"epoch": 3.22972972972973,
"eval_accuracy": 0.8714285714285714,
"eval_loss": 0.47154754400253296,
"eval_runtime": 8.8419,
"eval_samples_per_second": 7.917,
"eval_steps_per_second": 1.018,
"step": 148
},
{
"epoch": 3.22972972972973,
"step": 148,
"total_flos": 1.460491890402263e+18,
"train_loss": 1.128270382816727,
"train_runtime": 532.0374,
"train_samples_per_second": 2.225,
"train_steps_per_second": 0.278
},
{
"epoch": 3.22972972972973,
"eval_accuracy": 0.8193548387096774,
"eval_loss": 0.4508959949016571,
"eval_runtime": 16.4959,
"eval_samples_per_second": 9.396,
"eval_steps_per_second": 1.212,
"step": 148
},
{
"epoch": 3.22972972972973,
"eval_accuracy": 0.8193548387096774,
"eval_loss": 0.4508959949016571,
"eval_runtime": 15.0463,
"eval_samples_per_second": 10.302,
"eval_steps_per_second": 1.329,
"step": 148
}
],
"logging_steps": 10,
"max_steps": 148,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.460491890402263e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|