File size: 4,611 Bytes
3c44035 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.04289544235925,
"eval_steps": 500,
"global_step": 6000,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.6702412868632708,
"grad_norm": 1.8121609687805176,
"learning_rate": 4.400558387583305e-05,
"loss": 0.6264,
"step": 500
},
{
"epoch": 1.0,
"eval_accuracy": 0.5072075128555298,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.1548,
"eval_samples_per_second": 325.839,
"eval_steps_per_second": 20.426,
"step": 746
},
{
"epoch": 1.3404825737265416,
"grad_norm": 1.8386740684509277,
"learning_rate": 4.0844263195097915e-05,
"loss": 0.7039,
"step": 1000
},
{
"epoch": 2.0,
"eval_accuracy": 0.49882668256759644,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.1028,
"eval_samples_per_second": 327.702,
"eval_steps_per_second": 20.543,
"step": 1492
},
{
"epoch": 2.0107238605898123,
"grad_norm": 1.775593876838684,
"learning_rate": 3.768294251436278e-05,
"loss": 0.7008,
"step": 1500
},
{
"epoch": 2.680965147453083,
"grad_norm": 1.6979082822799683,
"learning_rate": 3.452162183362765e-05,
"loss": 0.7034,
"step": 2000
},
{
"epoch": 3.0,
"eval_accuracy": 0.5015085339546204,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.1903,
"eval_samples_per_second": 324.583,
"eval_steps_per_second": 20.348,
"step": 2238
},
{
"epoch": 3.351206434316354,
"grad_norm": 1.7350631952285767,
"learning_rate": 3.136030115289252e-05,
"loss": 0.7017,
"step": 2500
},
{
"epoch": 4.0,
"eval_accuracy": 0.5065370202064514,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.2185,
"eval_samples_per_second": 323.589,
"eval_steps_per_second": 20.285,
"step": 2984
},
{
"epoch": 4.021447721179625,
"grad_norm": 1.841038465499878,
"learning_rate": 2.8198980472157382e-05,
"loss": 0.7019,
"step": 3000
},
{
"epoch": 4.6916890080428955,
"grad_norm": 1.6272307634353638,
"learning_rate": 2.5037659791422253e-05,
"loss": 0.6994,
"step": 3500
},
{
"epoch": 5.0,
"eval_accuracy": 0.5095541477203369,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.0976,
"eval_samples_per_second": 327.89,
"eval_steps_per_second": 20.555,
"step": 3730
},
{
"epoch": 5.361930294906166,
"grad_norm": 1.7355244159698486,
"learning_rate": 2.1876339110687117e-05,
"loss": 0.7006,
"step": 4000
},
{
"epoch": 6.0,
"eval_accuracy": 0.49446865916252136,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.0977,
"eval_samples_per_second": 327.885,
"eval_steps_per_second": 20.555,
"step": 4476
},
{
"epoch": 6.032171581769437,
"grad_norm": 1.6792231798171997,
"learning_rate": 1.8715018429951985e-05,
"loss": 0.7005,
"step": 4500
},
{
"epoch": 6.702412868632708,
"grad_norm": 1.7535431385040283,
"learning_rate": 1.5553697749216852e-05,
"loss": 0.701,
"step": 5000
},
{
"epoch": 7.0,
"eval_accuracy": 0.4941334128379822,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.0431,
"eval_samples_per_second": 329.865,
"eval_steps_per_second": 20.679,
"step": 5222
},
{
"epoch": 7.372654155495979,
"grad_norm": 1.7443852424621582,
"learning_rate": 1.239237706848172e-05,
"loss": 0.7015,
"step": 5500
},
{
"epoch": 8.0,
"eval_accuracy": 0.5122359991073608,
"eval_loss": 0.6931472420692444,
"eval_runtime": 9.0713,
"eval_samples_per_second": 328.839,
"eval_steps_per_second": 20.614,
"step": 5968
},
{
"epoch": 8.04289544235925,
"grad_norm": 1.6793931722640991,
"learning_rate": 9.231056387746587e-06,
"loss": 0.7003,
"step": 6000
}
],
"logging_steps": 500,
"max_steps": 7460,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1.563011071614504e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": {
"learning_rate": 4.716690455656818e-05,
"per_device_train_batch_size": 16
}
}
|