File size: 5,385 Bytes
71429a6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 99.87956643918105,
"eval_steps": 3110,
"global_step": 31100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 9.987956643918105,
"grad_norm": 0.008763309568166733,
"learning_rate": 9.002572347266882e-06,
"loss": 2.156,
"step": 3110
},
{
"epoch": 9.987956643918105,
"eval_accuracy": 0.04915439834529748,
"eval_loss": 2.9957287311553955,
"eval_runtime": 36.4037,
"eval_samples_per_second": 225.774,
"eval_steps_per_second": 11.29,
"step": 3110
},
{
"epoch": 19.97591328783621,
"grad_norm": 1.9511775970458984,
"learning_rate": 8.002572347266881e-06,
"loss": 2.1411,
"step": 6220
},
{
"epoch": 19.97591328783621,
"eval_accuracy": 0.05371699720160603,
"eval_loss": 3.0536019802093506,
"eval_runtime": 36.6549,
"eval_samples_per_second": 224.227,
"eval_steps_per_second": 11.213,
"step": 6220
},
{
"epoch": 29.963869931754317,
"grad_norm": 2.7666614055633545,
"learning_rate": 7.002572347266882e-06,
"loss": 1.9888,
"step": 9330
},
{
"epoch": 29.963869931754317,
"eval_accuracy": 0.05665733868678266,
"eval_loss": 3.3323957920074463,
"eval_runtime": 36.5927,
"eval_samples_per_second": 224.607,
"eval_steps_per_second": 11.232,
"step": 9330
},
{
"epoch": 39.95182657567242,
"grad_norm": 3.709224224090576,
"learning_rate": 6.002572347266882e-06,
"loss": 1.8759,
"step": 12440
},
{
"epoch": 39.95182657567242,
"eval_accuracy": 0.05706290302956564,
"eval_loss": 3.6092300415039062,
"eval_runtime": 36.6501,
"eval_samples_per_second": 224.256,
"eval_steps_per_second": 11.214,
"step": 12440
},
{
"epoch": 49.939783219590524,
"grad_norm": 3.455683708190918,
"learning_rate": 5.002893890675241e-06,
"loss": 1.8129,
"step": 15550
},
{
"epoch": 49.939783219590524,
"eval_accuracy": 0.05752524638033824,
"eval_loss": 3.809110641479492,
"eval_runtime": 36.6247,
"eval_samples_per_second": 224.411,
"eval_steps_per_second": 11.222,
"step": 15550
},
{
"epoch": 59.927739863508634,
"grad_norm": 3.957350254058838,
"learning_rate": 4.003536977491962e-06,
"loss": 1.7708,
"step": 18660
},
{
"epoch": 59.927739863508634,
"eval_accuracy": 0.05777264062943586,
"eval_loss": 3.9897844791412354,
"eval_runtime": 36.4616,
"eval_samples_per_second": 225.415,
"eval_steps_per_second": 11.272,
"step": 18660
},
{
"epoch": 69.91569650742673,
"grad_norm": 4.713634014129639,
"learning_rate": 3.003858520900322e-06,
"loss": 1.7413,
"step": 21770
},
{
"epoch": 69.91569650742673,
"eval_accuracy": 0.057914588149409904,
"eval_loss": 4.2735114097595215,
"eval_runtime": 36.4969,
"eval_samples_per_second": 225.197,
"eval_steps_per_second": 11.261,
"step": 21770
},
{
"epoch": 79.90365315134484,
"grad_norm": 3.9962944984436035,
"learning_rate": 2.0045016077170422e-06,
"loss": 1.7172,
"step": 24880
},
{
"epoch": 79.90365315134484,
"eval_accuracy": 0.0580362574522448,
"eval_loss": 4.343382835388184,
"eval_runtime": 36.6256,
"eval_samples_per_second": 224.406,
"eval_steps_per_second": 11.222,
"step": 24880
},
{
"epoch": 89.89160979526295,
"grad_norm": 2.9578592777252197,
"learning_rate": 1.0048231511254019e-06,
"loss": 1.7056,
"step": 27990
},
{
"epoch": 89.89160979526295,
"eval_accuracy": 0.058063295075097,
"eval_loss": 4.511988162994385,
"eval_runtime": 36.4648,
"eval_samples_per_second": 225.395,
"eval_steps_per_second": 11.271,
"step": 27990
},
{
"epoch": 99.87956643918105,
"grad_norm": 3.108112335205078,
"learning_rate": 5.466237942122187e-09,
"loss": 1.7018,
"step": 31100
},
{
"epoch": 99.87956643918105,
"eval_accuracy": 0.05819442754593016,
"eval_loss": 4.51352071762085,
"eval_runtime": 36.5052,
"eval_samples_per_second": 225.146,
"eval_steps_per_second": 11.259,
"step": 31100
},
{
"epoch": 99.87956643918105,
"step": 31100,
"total_flos": 1.4711495868588088e+18,
"train_loss": 1.861133707420619,
"train_runtime": 58944.542,
"train_samples_per_second": 105.616,
"train_steps_per_second": 0.528
}
],
"logging_steps": 3110,
"max_steps": 31100,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"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": 1.4711495868588088e+18,
"train_batch_size": 25,
"trial_name": null,
"trial_params": null
}
|