File size: 5,071 Bytes
e0b7f9e |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 6250,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.9648939348670451,
"eval_f1": 0.8973252804141502,
"eval_loss": 0.189955934882164,
"eval_precision": 0.8587943848059455,
"eval_recall": 0.9394760614272809,
"eval_runtime": 2.5262,
"eval_samples_per_second": 395.851,
"eval_steps_per_second": 24.939,
"step": 625
},
{
"epoch": 1.6,
"grad_norm": 5.951064109802246,
"learning_rate": 1.6800000000000002e-05,
"loss": 0.0567,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.97169106662683,
"eval_f1": 0.9429726088908846,
"eval_loss": 0.1852019727230072,
"eval_precision": 0.9375,
"eval_recall": 0.948509485094851,
"eval_runtime": 2.561,
"eval_samples_per_second": 390.465,
"eval_steps_per_second": 24.599,
"step": 1250
},
{
"epoch": 3.0,
"eval_accuracy": 0.9731102479832686,
"eval_f1": 0.9533213644524237,
"eval_loss": 0.17272309958934784,
"eval_precision": 0.9473684210526315,
"eval_recall": 0.959349593495935,
"eval_runtime": 3.904,
"eval_samples_per_second": 256.151,
"eval_steps_per_second": 16.137,
"step": 1875
},
{
"epoch": 3.2,
"grad_norm": 0.4564518630504608,
"learning_rate": 1.3600000000000002e-05,
"loss": 0.0338,
"step": 2000
},
{
"epoch": 4.0,
"eval_accuracy": 0.9777412608305945,
"eval_f1": 0.9547288211564321,
"eval_loss": 0.15044009685516357,
"eval_precision": 0.947508896797153,
"eval_recall": 0.962059620596206,
"eval_runtime": 2.4284,
"eval_samples_per_second": 411.796,
"eval_steps_per_second": 25.943,
"step": 2500
},
{
"epoch": 4.8,
"grad_norm": 0.006230680737644434,
"learning_rate": 1.04e-05,
"loss": 0.0318,
"step": 3000
},
{
"epoch": 5.0,
"eval_accuracy": 0.9756498356737376,
"eval_f1": 0.9563259792886086,
"eval_loss": 0.17377431690692902,
"eval_precision": 0.9533213644524237,
"eval_recall": 0.959349593495935,
"eval_runtime": 2.4667,
"eval_samples_per_second": 405.403,
"eval_steps_per_second": 25.54,
"step": 3125
},
{
"epoch": 6.0,
"eval_accuracy": 0.9788616671646251,
"eval_f1": 0.9630297565374211,
"eval_loss": 0.1647682785987854,
"eval_precision": 0.9612961296129613,
"eval_recall": 0.964769647696477,
"eval_runtime": 3.1374,
"eval_samples_per_second": 318.737,
"eval_steps_per_second": 20.08,
"step": 3750
},
{
"epoch": 6.4,
"grad_norm": 0.0044134571217000484,
"learning_rate": 7.2000000000000005e-06,
"loss": 0.02,
"step": 4000
},
{
"epoch": 7.0,
"eval_accuracy": 0.9770690170301762,
"eval_f1": 0.9643340857787811,
"eval_loss": 0.17450480163097382,
"eval_precision": 0.9638989169675091,
"eval_recall": 0.964769647696477,
"eval_runtime": 2.53,
"eval_samples_per_second": 395.256,
"eval_steps_per_second": 24.901,
"step": 4375
},
{
"epoch": 8.0,
"grad_norm": 0.0022473218850791454,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0063,
"step": 5000
},
{
"epoch": 8.0,
"eval_accuracy": 0.9793845234538393,
"eval_f1": 0.9652370203160271,
"eval_loss": 0.16244609653949738,
"eval_precision": 0.9648014440433214,
"eval_recall": 0.9656729900632339,
"eval_runtime": 2.5135,
"eval_samples_per_second": 397.859,
"eval_steps_per_second": 25.065,
"step": 5000
},
{
"epoch": 9.0,
"eval_accuracy": 0.98125186734389,
"eval_f1": 0.9643340857787811,
"eval_loss": 0.16350433230400085,
"eval_precision": 0.9638989169675091,
"eval_recall": 0.964769647696477,
"eval_runtime": 2.4878,
"eval_samples_per_second": 401.967,
"eval_steps_per_second": 25.324,
"step": 5625
},
{
"epoch": 9.6,
"grad_norm": 0.0036331522278487682,
"learning_rate": 8.000000000000001e-07,
"loss": 0.0036,
"step": 6000
},
{
"epoch": 10.0,
"eval_accuracy": 0.9799820734986555,
"eval_f1": 0.9643662607126748,
"eval_loss": 0.16758297383785248,
"eval_precision": 0.9630630630630631,
"eval_recall": 0.9656729900632339,
"eval_runtime": 2.4417,
"eval_samples_per_second": 409.55,
"eval_steps_per_second": 25.802,
"step": 6250
}
],
"logging_steps": 1000,
"max_steps": 6250,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1559350717084512.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|