File size: 5,118 Bytes
634e45a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 |
{
"best_metric": 0.6430702209472656,
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-5500",
"epoch": 1.013264554163596,
"eval_steps": 500,
"global_step": 5500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09211495946941783,
"grad_norm": 3.083087682723999,
"learning_rate": 4.84647506755097e-07,
"loss": 0.2708,
"step": 500
},
{
"epoch": 0.09211495946941783,
"eval_loss": 1.0631108283996582,
"eval_runtime": 74.1964,
"eval_samples_per_second": 16.268,
"eval_steps_per_second": 2.035,
"step": 500
},
{
"epoch": 0.18422991893883567,
"grad_norm": 7.726487159729004,
"learning_rate": 4.69295013510194e-07,
"loss": 0.251,
"step": 1000
},
{
"epoch": 0.18422991893883567,
"eval_loss": 0.942773699760437,
"eval_runtime": 74.6047,
"eval_samples_per_second": 16.179,
"eval_steps_per_second": 2.024,
"step": 1000
},
{
"epoch": 0.2763448784082535,
"grad_norm": 0.02718021161854267,
"learning_rate": 4.5394252026529107e-07,
"loss": 0.235,
"step": 1500
},
{
"epoch": 0.2763448784082535,
"eval_loss": 0.8716810345649719,
"eval_runtime": 75.03,
"eval_samples_per_second": 16.087,
"eval_steps_per_second": 2.013,
"step": 1500
},
{
"epoch": 0.36845983787767134,
"grad_norm": 0.0001215290030813776,
"learning_rate": 4.385900270203881e-07,
"loss": 0.1529,
"step": 2000
},
{
"epoch": 0.36845983787767134,
"eval_loss": 0.8318113088607788,
"eval_runtime": 76.6917,
"eval_samples_per_second": 15.738,
"eval_steps_per_second": 1.969,
"step": 2000
},
{
"epoch": 0.46057479734708917,
"grad_norm": 419.545166015625,
"learning_rate": 4.232375337754851e-07,
"loss": 0.1781,
"step": 2500
},
{
"epoch": 0.46057479734708917,
"eval_loss": 0.7549223303794861,
"eval_runtime": 75.2036,
"eval_samples_per_second": 16.05,
"eval_steps_per_second": 2.008,
"step": 2500
},
{
"epoch": 0.552689756816507,
"grad_norm": 368.7484436035156,
"learning_rate": 4.0788504053058217e-07,
"loss": 0.1681,
"step": 3000
},
{
"epoch": 0.552689756816507,
"eval_loss": 0.7217888236045837,
"eval_runtime": 76.0606,
"eval_samples_per_second": 15.869,
"eval_steps_per_second": 1.985,
"step": 3000
},
{
"epoch": 0.6448047162859248,
"grad_norm": 20.03949737548828,
"learning_rate": 3.925325472856792e-07,
"loss": 0.1064,
"step": 3500
},
{
"epoch": 0.6448047162859248,
"eval_loss": 0.7048410177230835,
"eval_runtime": 76.0578,
"eval_samples_per_second": 15.87,
"eval_steps_per_second": 1.985,
"step": 3500
},
{
"epoch": 0.7369196757553427,
"grad_norm": 363.6124267578125,
"learning_rate": 3.771800540407762e-07,
"loss": 0.1357,
"step": 4000
},
{
"epoch": 0.7369196757553427,
"eval_loss": 0.6961681246757507,
"eval_runtime": 76.3574,
"eval_samples_per_second": 15.807,
"eval_steps_per_second": 1.978,
"step": 4000
},
{
"epoch": 0.8290346352247605,
"grad_norm": 494.03570556640625,
"learning_rate": 3.618275607958732e-07,
"loss": 0.1098,
"step": 4500
},
{
"epoch": 0.8290346352247605,
"eval_loss": 0.6778352856636047,
"eval_runtime": 76.4844,
"eval_samples_per_second": 15.781,
"eval_steps_per_second": 1.974,
"step": 4500
},
{
"epoch": 0.9211495946941783,
"grad_norm": 4.2969353671651334e-05,
"learning_rate": 3.464750675509703e-07,
"loss": 0.1142,
"step": 5000
},
{
"epoch": 0.9211495946941783,
"eval_loss": 0.6656659245491028,
"eval_runtime": 76.6475,
"eval_samples_per_second": 15.747,
"eval_steps_per_second": 1.97,
"step": 5000
},
{
"epoch": 1.013264554163596,
"grad_norm": 0.0010161151876673102,
"learning_rate": 3.311225743060673e-07,
"loss": 0.1113,
"step": 5500
},
{
"epoch": 1.013264554163596,
"eval_loss": 0.6430702209472656,
"eval_runtime": 76.4915,
"eval_samples_per_second": 15.78,
"eval_steps_per_second": 1.974,
"step": 5500
}
],
"logging_steps": 500,
"max_steps": 16284,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1979390448632520.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|