File size: 4,729 Bytes
7547e01 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.6,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"grad_norm": 0.19458943605422974,
"learning_rate": 4.9910902453260824e-05,
"loss": 0.8099,
"num_input_tokens_seen": 114944,
"step": 5
},
{
"epoch": 0.16,
"grad_norm": 0.23063905537128448,
"learning_rate": 4.964424488287009e-05,
"loss": 0.958,
"num_input_tokens_seen": 227728,
"step": 10
},
{
"epoch": 0.24,
"grad_norm": 0.22587424516677856,
"learning_rate": 4.920192797165511e-05,
"loss": 0.715,
"num_input_tokens_seen": 326640,
"step": 15
},
{
"epoch": 0.32,
"grad_norm": 0.17264235019683838,
"learning_rate": 4.858710446774951e-05,
"loss": 0.7585,
"num_input_tokens_seen": 437280,
"step": 20
},
{
"epoch": 0.4,
"grad_norm": 0.19875957071781158,
"learning_rate": 4.780415671242334e-05,
"loss": 0.7342,
"num_input_tokens_seen": 530192,
"step": 25
},
{
"epoch": 0.48,
"grad_norm": 0.36600446701049805,
"learning_rate": 4.685866540361456e-05,
"loss": 0.6904,
"num_input_tokens_seen": 634960,
"step": 30
},
{
"epoch": 0.56,
"grad_norm": 0.20120520889759064,
"learning_rate": 4.5757369817809415e-05,
"loss": 0.8254,
"num_input_tokens_seen": 740704,
"step": 35
},
{
"epoch": 0.64,
"grad_norm": 0.22245633602142334,
"learning_rate": 4.45081197738023e-05,
"loss": 0.7551,
"num_input_tokens_seen": 841600,
"step": 40
},
{
"epoch": 0.72,
"grad_norm": 0.27814680337905884,
"learning_rate": 4.3119819680728e-05,
"loss": 0.7747,
"num_input_tokens_seen": 947648,
"step": 45
},
{
"epoch": 0.8,
"grad_norm": 0.27052441239356995,
"learning_rate": 4.160236506918098e-05,
"loss": 0.7027,
"num_input_tokens_seen": 1047520,
"step": 50
},
{
"epoch": 0.88,
"grad_norm": 0.38937926292419434,
"learning_rate": 3.9966572057815373e-05,
"loss": 0.7581,
"num_input_tokens_seen": 1148080,
"step": 55
},
{
"epoch": 0.96,
"grad_norm": 0.37379005551338196,
"learning_rate": 3.822410025817406e-05,
"loss": 0.7221,
"num_input_tokens_seen": 1252880,
"step": 60
},
{
"epoch": 1.04,
"grad_norm": 0.34213003516197205,
"learning_rate": 3.638736966726585e-05,
"loss": 0.8214,
"num_input_tokens_seen": 1364304,
"step": 65
},
{
"epoch": 1.12,
"grad_norm": 0.33407434821128845,
"learning_rate": 3.44694721402644e-05,
"loss": 0.6304,
"num_input_tokens_seen": 1466240,
"step": 70
},
{
"epoch": 1.2,
"grad_norm": 0.33909159898757935,
"learning_rate": 3.2484078074333954e-05,
"loss": 0.6434,
"num_input_tokens_seen": 1558752,
"step": 75
},
{
"epoch": 1.28,
"grad_norm": 0.4054814577102661,
"learning_rate": 3.0445338968721287e-05,
"loss": 0.6796,
"num_input_tokens_seen": 1668480,
"step": 80
},
{
"epoch": 1.3599999999999999,
"grad_norm": 0.2723485231399536,
"learning_rate": 2.836778655564653e-05,
"loss": 0.6651,
"num_input_tokens_seen": 1773264,
"step": 85
},
{
"epoch": 1.44,
"grad_norm": 0.3467393219470978,
"learning_rate": 2.6266229220967818e-05,
"loss": 0.7844,
"num_input_tokens_seen": 1885920,
"step": 90
},
{
"epoch": 1.52,
"grad_norm": 0.4250239431858063,
"learning_rate": 2.4155646452913296e-05,
"loss": 0.8139,
"num_input_tokens_seen": 1996656,
"step": 95
},
{
"epoch": 1.6,
"grad_norm": 0.30656036734580994,
"learning_rate": 2.2051082071228854e-05,
"loss": 0.6717,
"num_input_tokens_seen": 2102896,
"step": 100
}
],
"logging_steps": 5,
"max_steps": 186,
"num_input_tokens_seen": 2102896,
"num_train_epochs": 3,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.664954843267072e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|