File size: 3,364 Bytes
18187e5 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.41450777202072536,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"grad_norm": 4.99941873550415,
"learning_rate": 2e-05,
"loss": 9.9329,
"step": 10
},
{
"epoch": 0.04,
"grad_norm": 1.741065502166748,
"learning_rate": 4e-05,
"loss": 11.0746,
"step": 20
},
{
"epoch": 0.06,
"grad_norm": 1.4727320671081543,
"learning_rate": 6e-05,
"loss": 2.7159,
"step": 30
},
{
"epoch": 0.08,
"grad_norm": 0.1335960477590561,
"learning_rate": 8e-05,
"loss": 0.3969,
"step": 40
},
{
"epoch": 0.1,
"grad_norm": 0.0014472692273557186,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 50
},
{
"epoch": 0.12,
"grad_norm": 0.0010780546581372619,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 60
},
{
"epoch": 0.15,
"grad_norm": 1.03132963180542,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 70
},
{
"epoch": 0.17,
"grad_norm": 0.008827299810945988,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 80
},
{
"epoch": 0.19,
"grad_norm": 0.0002956670359708369,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 90
},
{
"epoch": 0.21,
"grad_norm": 0.0003419867134653032,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 100
},
{
"epoch": 0.23,
"grad_norm": 0.0003681881644297391,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 110
},
{
"epoch": 0.25,
"grad_norm": 0.0002884200366679579,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 120
},
{
"epoch": 0.27,
"grad_norm": 0.00011985149467363954,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 130
},
{
"epoch": 0.29,
"grad_norm": 0.0003195986500941217,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 140
},
{
"epoch": 0.31,
"grad_norm": 0.00010149635636480525,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 150
},
{
"epoch": 0.33,
"grad_norm": 0.00010508792183827609,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 160
},
{
"epoch": 0.35,
"grad_norm": 0.00011793687008321285,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 170
},
{
"epoch": 0.37,
"grad_norm": 8.076676749624312e-05,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 180
},
{
"epoch": 0.39,
"grad_norm": 0.0007808339432813227,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 190
},
{
"epoch": 0.41,
"grad_norm": 0.11711683869361877,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 482,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 3.335841878562816e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|