File size: 4,118 Bytes
ee4b4bb |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 30.76923076923077,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.5384615384615383,
"grad_norm": 134.7136688232422,
"learning_rate": 9.981600000000001e-06,
"loss": 5.6198,
"step": 100
},
{
"epoch": 3.076923076923077,
"grad_norm": 115.98611450195312,
"learning_rate": 9.961600000000001e-06,
"loss": 3.5959,
"step": 200
},
{
"epoch": 4.615384615384615,
"grad_norm": 114.23514556884766,
"learning_rate": 9.941600000000002e-06,
"loss": 3.3845,
"step": 300
},
{
"epoch": 6.153846153846154,
"grad_norm": 140.5648193359375,
"learning_rate": 9.921600000000002e-06,
"loss": 3.1494,
"step": 400
},
{
"epoch": 7.6923076923076925,
"grad_norm": 117.4485855102539,
"learning_rate": 9.901600000000002e-06,
"loss": 3.0773,
"step": 500
},
{
"epoch": 9.23076923076923,
"grad_norm": 389.71490478515625,
"learning_rate": 9.8816e-06,
"loss": 3.2116,
"step": 600
},
{
"epoch": 10.76923076923077,
"grad_norm": 107.11251831054688,
"learning_rate": 9.8616e-06,
"loss": 3.0471,
"step": 700
},
{
"epoch": 12.307692307692308,
"grad_norm": 85.49571228027344,
"learning_rate": 9.8416e-06,
"loss": 3.0201,
"step": 800
},
{
"epoch": 13.846153846153847,
"grad_norm": 121.62274932861328,
"learning_rate": 9.821600000000001e-06,
"loss": 2.9355,
"step": 900
},
{
"epoch": 15.384615384615385,
"grad_norm": 64.66451263427734,
"learning_rate": 9.801600000000001e-06,
"loss": 2.9637,
"step": 1000
},
{
"epoch": 16.923076923076923,
"grad_norm": 182.4657440185547,
"learning_rate": 9.781600000000001e-06,
"loss": 2.9819,
"step": 1100
},
{
"epoch": 18.46153846153846,
"grad_norm": 97.80529022216797,
"learning_rate": 9.761600000000002e-06,
"loss": 2.9486,
"step": 1200
},
{
"epoch": 20.0,
"grad_norm": 220.0562744140625,
"learning_rate": 9.741600000000002e-06,
"loss": 2.8608,
"step": 1300
},
{
"epoch": 21.53846153846154,
"grad_norm": 95.53397369384766,
"learning_rate": 9.7216e-06,
"loss": 2.8322,
"step": 1400
},
{
"epoch": 23.076923076923077,
"grad_norm": 67.54853057861328,
"learning_rate": 9.7016e-06,
"loss": 2.9429,
"step": 1500
},
{
"epoch": 24.615384615384617,
"grad_norm": 214.53131103515625,
"learning_rate": 9.6816e-06,
"loss": 2.7927,
"step": 1600
},
{
"epoch": 26.153846153846153,
"grad_norm": 293.3318786621094,
"learning_rate": 9.6616e-06,
"loss": 2.7665,
"step": 1700
},
{
"epoch": 27.692307692307693,
"grad_norm": 216.3682861328125,
"learning_rate": 9.641600000000001e-06,
"loss": 2.8309,
"step": 1800
},
{
"epoch": 29.23076923076923,
"grad_norm": 168.0605010986328,
"learning_rate": 9.621600000000001e-06,
"loss": 2.8433,
"step": 1900
},
{
"epoch": 30.76923076923077,
"grad_norm": 103.49143981933594,
"learning_rate": 9.601600000000001e-06,
"loss": 2.7606,
"step": 2000
}
],
"logging_steps": 100,
"max_steps": 50000,
"num_input_tokens_seen": 0,
"num_train_epochs": 770,
"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": 7.64486332416e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|