File size: 5,119 Bytes
72d5912 |
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": 1.9776026010513306,
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l55-l/checkpoint-5500",
"epoch": 1.013077914901455,
"eval_steps": 500,
"global_step": 5500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09209799226376865,
"grad_norm": 0.009597355499863625,
"learning_rate": 4.846503346227052e-05,
"loss": 0.7336,
"step": 500
},
{
"epoch": 0.09209799226376865,
"eval_loss": 2.0780556201934814,
"eval_runtime": 77.1404,
"eval_samples_per_second": 15.634,
"eval_steps_per_second": 1.957,
"step": 500
},
{
"epoch": 0.1841959845275373,
"grad_norm": 0.10049372166395187,
"learning_rate": 4.693006692454105e-05,
"loss": 0.6953,
"step": 1000
},
{
"epoch": 0.1841959845275373,
"eval_loss": 2.0782744884490967,
"eval_runtime": 77.8965,
"eval_samples_per_second": 15.482,
"eval_steps_per_second": 1.938,
"step": 1000
},
{
"epoch": 0.27629397679130596,
"grad_norm": 0.0041180383414030075,
"learning_rate": 4.539510038681157e-05,
"loss": 0.6953,
"step": 1500
},
{
"epoch": 0.27629397679130596,
"eval_loss": 2.077699899673462,
"eval_runtime": 78.9586,
"eval_samples_per_second": 15.274,
"eval_steps_per_second": 1.912,
"step": 1500
},
{
"epoch": 0.3683919690550746,
"grad_norm": 0.29397013783454895,
"learning_rate": 4.386013384908209e-05,
"loss": 0.6932,
"step": 2000
},
{
"epoch": 0.3683919690550746,
"eval_loss": 2.0721774101257324,
"eval_runtime": 77.349,
"eval_samples_per_second": 15.592,
"eval_steps_per_second": 1.952,
"step": 2000
},
{
"epoch": 0.46048996131884323,
"grad_norm": 0.9136261343955994,
"learning_rate": 4.232516731135262e-05,
"loss": 0.6907,
"step": 2500
},
{
"epoch": 0.46048996131884323,
"eval_loss": 2.079211711883545,
"eval_runtime": 79.3204,
"eval_samples_per_second": 15.204,
"eval_steps_per_second": 1.904,
"step": 2500
},
{
"epoch": 0.5525879535826119,
"grad_norm": 4.484213829040527,
"learning_rate": 4.079020077362314e-05,
"loss": 0.7043,
"step": 3000
},
{
"epoch": 0.5525879535826119,
"eval_loss": 2.0204577445983887,
"eval_runtime": 78.612,
"eval_samples_per_second": 15.341,
"eval_steps_per_second": 1.921,
"step": 3000
},
{
"epoch": 0.6446859458463805,
"grad_norm": 1.1021015644073486,
"learning_rate": 3.9255234235893664e-05,
"loss": 0.7078,
"step": 3500
},
{
"epoch": 0.6446859458463805,
"eval_loss": 2.1256344318389893,
"eval_runtime": 78.63,
"eval_samples_per_second": 15.338,
"eval_steps_per_second": 1.92,
"step": 3500
},
{
"epoch": 0.7367839381101492,
"grad_norm": 16.864044189453125,
"learning_rate": 3.772026769816418e-05,
"loss": 0.7034,
"step": 4000
},
{
"epoch": 0.7367839381101492,
"eval_loss": 2.0000314712524414,
"eval_runtime": 78.6543,
"eval_samples_per_second": 15.333,
"eval_steps_per_second": 1.92,
"step": 4000
},
{
"epoch": 0.8288819303739179,
"grad_norm": 20.071943283081055,
"learning_rate": 3.6185301160434705e-05,
"loss": 0.6671,
"step": 4500
},
{
"epoch": 0.8288819303739179,
"eval_loss": 2.1607539653778076,
"eval_runtime": 78.6404,
"eval_samples_per_second": 15.336,
"eval_steps_per_second": 1.92,
"step": 4500
},
{
"epoch": 0.9209799226376865,
"grad_norm": 17.817607879638672,
"learning_rate": 3.4650334622705225e-05,
"loss": 0.6899,
"step": 5000
},
{
"epoch": 0.9209799226376865,
"eval_loss": 2.093959331512451,
"eval_runtime": 78.539,
"eval_samples_per_second": 15.355,
"eval_steps_per_second": 1.923,
"step": 5000
},
{
"epoch": 1.013077914901455,
"grad_norm": 41.0746955871582,
"learning_rate": 3.311536808497575e-05,
"loss": 0.6649,
"step": 5500
},
{
"epoch": 1.013077914901455,
"eval_loss": 1.9776026010513306,
"eval_runtime": 78.5095,
"eval_samples_per_second": 15.361,
"eval_steps_per_second": 1.923,
"step": 5500
}
],
"logging_steps": 500,
"max_steps": 16287,
"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": 1979210569456890.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|