File size: 3,681 Bytes
c831e1d |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 11.148272017837236,
"eval_steps": 500,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.56,
"grad_norm": 4.136017322540283,
"learning_rate": 4.75e-05,
"loss": 1.4862,
"step": 500
},
{
"epoch": 1.11,
"grad_norm": 3.5059304237365723,
"learning_rate": 4.5e-05,
"loss": 1.2182,
"step": 1000
},
{
"epoch": 1.67,
"grad_norm": 3.1735312938690186,
"learning_rate": 4.25e-05,
"loss": 1.0549,
"step": 1500
},
{
"epoch": 2.23,
"grad_norm": 3.1064469814300537,
"learning_rate": 4e-05,
"loss": 0.9527,
"step": 2000
},
{
"epoch": 2.79,
"grad_norm": 2.8415098190307617,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.8717,
"step": 2500
},
{
"epoch": 3.34,
"grad_norm": 2.4496607780456543,
"learning_rate": 3.5e-05,
"loss": 0.783,
"step": 3000
},
{
"epoch": 3.9,
"grad_norm": 2.9042794704437256,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.7372,
"step": 3500
},
{
"epoch": 4.46,
"grad_norm": 2.628190517425537,
"learning_rate": 3e-05,
"loss": 0.6509,
"step": 4000
},
{
"epoch": 5.02,
"grad_norm": 2.9309325218200684,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.6398,
"step": 4500
},
{
"epoch": 5.57,
"grad_norm": 2.357445240020752,
"learning_rate": 2.5e-05,
"loss": 0.56,
"step": 5000
},
{
"epoch": 6.13,
"grad_norm": 2.1420226097106934,
"learning_rate": 2.25e-05,
"loss": 0.5543,
"step": 5500
},
{
"epoch": 6.69,
"grad_norm": 2.6394078731536865,
"learning_rate": 2e-05,
"loss": 0.5104,
"step": 6000
},
{
"epoch": 7.25,
"grad_norm": 2.395305633544922,
"learning_rate": 1.75e-05,
"loss": 0.4832,
"step": 6500
},
{
"epoch": 7.8,
"grad_norm": 2.048461675643921,
"learning_rate": 1.5e-05,
"loss": 0.4705,
"step": 7000
},
{
"epoch": 8.36,
"grad_norm": 2.379493236541748,
"learning_rate": 1.25e-05,
"loss": 0.442,
"step": 7500
},
{
"epoch": 8.92,
"grad_norm": 2.170802116394043,
"learning_rate": 1e-05,
"loss": 0.4264,
"step": 8000
},
{
"epoch": 9.48,
"grad_norm": 2.277756690979004,
"learning_rate": 7.5e-06,
"loss": 0.405,
"step": 8500
},
{
"epoch": 10.03,
"grad_norm": 2.3412973880767822,
"learning_rate": 5e-06,
"loss": 0.4069,
"step": 9000
},
{
"epoch": 10.59,
"grad_norm": 2.220499038696289,
"learning_rate": 2.5e-06,
"loss": 0.3937,
"step": 9500
},
{
"epoch": 11.15,
"grad_norm": 2.1124320030212402,
"learning_rate": 0.0,
"loss": 0.3872,
"step": 10000
},
{
"epoch": 11.15,
"step": 10000,
"total_flos": 5225840640000000.0,
"train_loss": 0.6717062408447265,
"train_runtime": 2130.1373,
"train_samples_per_second": 4.695,
"train_steps_per_second": 4.695
}
],
"logging_steps": 500,
"max_steps": 10000,
"num_input_tokens_seen": 0,
"num_train_epochs": 12,
"save_steps": 1000,
"total_flos": 5225840640000000.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|