File size: 3,776 Bytes
0fc4f39 |
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 |
{
"best_metric": 0.3133811950683594,
"best_model_checkpoint": "./kumpun-output/checkpoint-200",
"epoch": 1.0582010582010581,
"eval_steps": 200,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"grad_norm": 5.246432304382324,
"learning_rate": 7.000000000000001e-05,
"loss": 4.0922,
"step": 10
},
{
"epoch": 0.11,
"grad_norm": 3.076571226119995,
"learning_rate": 0.00017,
"loss": 3.5074,
"step": 20
},
{
"epoch": 0.16,
"grad_norm": 11.657795906066895,
"learning_rate": 0.00026000000000000003,
"loss": 2.2509,
"step": 30
},
{
"epoch": 0.21,
"grad_norm": 3.2525696754455566,
"learning_rate": 0.00034,
"loss": 0.8157,
"step": 40
},
{
"epoch": 0.26,
"grad_norm": 2.755035400390625,
"learning_rate": 0.00044,
"loss": 0.5126,
"step": 50
},
{
"epoch": 0.32,
"grad_norm": 2.1165263652801514,
"learning_rate": 0.00054,
"loss": 0.4988,
"step": 60
},
{
"epoch": 0.37,
"grad_norm": 0.805057168006897,
"learning_rate": 0.00064,
"loss": 0.2959,
"step": 70
},
{
"epoch": 0.42,
"grad_norm": 0.8083710074424744,
"learning_rate": 0.00074,
"loss": 0.2779,
"step": 80
},
{
"epoch": 0.48,
"grad_norm": 0.7004362344741821,
"learning_rate": 0.00084,
"loss": 0.244,
"step": 90
},
{
"epoch": 0.53,
"grad_norm": 1.5553646087646484,
"learning_rate": 0.00094,
"loss": 0.3729,
"step": 100
},
{
"epoch": 0.58,
"grad_norm": 0.8424310684204102,
"learning_rate": 0.0009914346895074947,
"loss": 0.3408,
"step": 110
},
{
"epoch": 0.63,
"grad_norm": 6.2793192863464355,
"learning_rate": 0.0009700214132762313,
"loss": 0.3011,
"step": 120
},
{
"epoch": 0.69,
"grad_norm": 0.8749362826347351,
"learning_rate": 0.0009486081370449678,
"loss": 0.249,
"step": 130
},
{
"epoch": 0.74,
"grad_norm": 0.6772909760475159,
"learning_rate": 0.0009271948608137045,
"loss": 0.2258,
"step": 140
},
{
"epoch": 0.79,
"grad_norm": 1.4329707622528076,
"learning_rate": 0.0009057815845824411,
"loss": 0.2977,
"step": 150
},
{
"epoch": 0.85,
"grad_norm": 1.501881718635559,
"learning_rate": 0.0008843683083511778,
"loss": 0.2276,
"step": 160
},
{
"epoch": 0.9,
"grad_norm": 1.2264193296432495,
"learning_rate": 0.0008629550321199144,
"loss": 0.2724,
"step": 170
},
{
"epoch": 0.95,
"grad_norm": 0.8799680471420288,
"learning_rate": 0.0008415417558886511,
"loss": 0.2358,
"step": 180
},
{
"epoch": 1.01,
"grad_norm": 23.913034439086914,
"learning_rate": 0.0008201284796573875,
"loss": 0.4151,
"step": 190
},
{
"epoch": 1.06,
"grad_norm": 2.3118550777435303,
"learning_rate": 0.0007987152034261242,
"loss": 0.4287,
"step": 200
},
{
"epoch": 1.06,
"eval_loss": 0.3133811950683594,
"eval_runtime": 0.6704,
"eval_samples_per_second": 14.916,
"eval_steps_per_second": 2.983,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 567,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 200,
"total_flos": 1229703996899328.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|