File size: 3,532 Bytes
7b27ed3 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6298815822625347,
"eval_steps": 500,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"learning_rate": 9.5e-05,
"loss": 1.6085,
"step": 500
},
{
"epoch": 0.06,
"eval_loss": 1.3112831115722656,
"eval_runtime": 3.3067,
"eval_samples_per_second": 30.241,
"eval_steps_per_second": 3.931,
"step": 500
},
{
"epoch": 0.13,
"learning_rate": 9e-05,
"loss": 1.5215,
"step": 1000
},
{
"epoch": 0.13,
"eval_loss": 1.5054197311401367,
"eval_runtime": 3.1798,
"eval_samples_per_second": 31.449,
"eval_steps_per_second": 4.088,
"step": 1000
},
{
"epoch": 0.19,
"learning_rate": 8.5e-05,
"loss": 1.4697,
"step": 1500
},
{
"epoch": 0.19,
"eval_loss": 1.32753324508667,
"eval_runtime": 3.3247,
"eval_samples_per_second": 30.078,
"eval_steps_per_second": 3.91,
"step": 1500
},
{
"epoch": 0.25,
"learning_rate": 8e-05,
"loss": 1.4948,
"step": 2000
},
{
"epoch": 0.25,
"eval_loss": 1.4151370525360107,
"eval_runtime": 3.174,
"eval_samples_per_second": 31.506,
"eval_steps_per_second": 4.096,
"step": 2000
},
{
"epoch": 0.31,
"learning_rate": 7.500000000000001e-05,
"loss": 1.4787,
"step": 2500
},
{
"epoch": 0.31,
"eval_loss": 1.1171963214874268,
"eval_runtime": 3.1742,
"eval_samples_per_second": 31.504,
"eval_steps_per_second": 4.096,
"step": 2500
},
{
"epoch": 0.38,
"learning_rate": 7e-05,
"loss": 1.4196,
"step": 3000
},
{
"epoch": 0.38,
"eval_loss": 1.495429277420044,
"eval_runtime": 3.1924,
"eval_samples_per_second": 31.325,
"eval_steps_per_second": 4.072,
"step": 3000
},
{
"epoch": 0.44,
"learning_rate": 6.500000000000001e-05,
"loss": 1.4509,
"step": 3500
},
{
"epoch": 0.44,
"eval_loss": 1.3065623044967651,
"eval_runtime": 3.1668,
"eval_samples_per_second": 31.577,
"eval_steps_per_second": 4.105,
"step": 3500
},
{
"epoch": 0.5,
"learning_rate": 6e-05,
"loss": 1.4333,
"step": 4000
},
{
"epoch": 0.5,
"eval_loss": 1.4525870084762573,
"eval_runtime": 3.1817,
"eval_samples_per_second": 31.43,
"eval_steps_per_second": 4.086,
"step": 4000
},
{
"epoch": 0.57,
"learning_rate": 5.500000000000001e-05,
"loss": 1.4404,
"step": 4500
},
{
"epoch": 0.57,
"eval_loss": 1.3187968730926514,
"eval_runtime": 3.191,
"eval_samples_per_second": 31.338,
"eval_steps_per_second": 4.074,
"step": 4500
},
{
"epoch": 0.63,
"learning_rate": 5e-05,
"loss": 1.4408,
"step": 5000
},
{
"epoch": 0.63,
"eval_loss": 1.1972750425338745,
"eval_runtime": 3.1767,
"eval_samples_per_second": 31.479,
"eval_steps_per_second": 4.092,
"step": 5000
}
],
"logging_steps": 500,
"max_steps": 10000,
"num_train_epochs": 2,
"save_steps": 5000,
"total_flos": 6.84757352448e+16,
"trial_name": null,
"trial_params": null
}
|