File size: 3,666 Bytes
9101a22 |
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 |
{
"best_metric": 1.814998745918274,
"best_model_checkpoint": "/home/ubuntu/workplace/NER_simi/output/LLM_05_13/checkpoint-1000",
"epoch": 0.5675368898978433,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 3.147441434337073e-05,
"loss": 2.3247,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 3.705117131325856e-05,
"loss": 1.9413,
"step": 100
},
{
"epoch": 0.09,
"learning_rate": 4.031336501627827e-05,
"loss": 1.8845,
"step": 150
},
{
"epoch": 0.11,
"learning_rate": 4.262792828314637e-05,
"loss": 1.8492,
"step": 200
},
{
"epoch": 0.11,
"eval_loss": 1.9344485998153687,
"eval_runtime": 336.1736,
"eval_samples_per_second": 95.918,
"eval_steps_per_second": 0.75,
"step": 200
},
{
"epoch": 0.14,
"learning_rate": 4.442324303011218e-05,
"loss": 1.8316,
"step": 250
},
{
"epoch": 0.17,
"learning_rate": 4.589012198616609e-05,
"loss": 1.8137,
"step": 300
},
{
"epoch": 0.2,
"learning_rate": 4.713035047190436e-05,
"loss": 1.7988,
"step": 350
},
{
"epoch": 0.23,
"learning_rate": 4.82046852530342e-05,
"loss": 1.7873,
"step": 400
},
{
"epoch": 0.23,
"eval_loss": 1.8653844594955444,
"eval_runtime": 336.5787,
"eval_samples_per_second": 95.802,
"eval_steps_per_second": 0.749,
"step": 400
},
{
"epoch": 0.26,
"learning_rate": 4.915231568918581e-05,
"loss": 1.7599,
"step": 450
},
{
"epoch": 0.28,
"learning_rate": 5e-05,
"loss": 1.7658,
"step": 500
},
{
"epoch": 0.31,
"learning_rate": 5e-05,
"loss": 1.7534,
"step": 550
},
{
"epoch": 0.34,
"learning_rate": 5e-05,
"loss": 1.7399,
"step": 600
},
{
"epoch": 0.34,
"eval_loss": 1.8613653182983398,
"eval_runtime": 336.3899,
"eval_samples_per_second": 95.856,
"eval_steps_per_second": 0.749,
"step": 600
},
{
"epoch": 0.37,
"learning_rate": 5e-05,
"loss": 1.7327,
"step": 650
},
{
"epoch": 0.4,
"learning_rate": 5e-05,
"loss": 1.7445,
"step": 700
},
{
"epoch": 0.43,
"learning_rate": 5e-05,
"loss": 1.7255,
"step": 750
},
{
"epoch": 0.45,
"learning_rate": 5e-05,
"loss": 1.7249,
"step": 800
},
{
"epoch": 0.45,
"eval_loss": 1.8731602430343628,
"eval_runtime": 336.4325,
"eval_samples_per_second": 95.844,
"eval_steps_per_second": 0.749,
"step": 800
},
{
"epoch": 0.48,
"learning_rate": 5e-05,
"loss": 1.7257,
"step": 850
},
{
"epoch": 0.51,
"learning_rate": 5e-05,
"loss": 1.7176,
"step": 900
},
{
"epoch": 0.54,
"learning_rate": 5e-05,
"loss": 1.708,
"step": 950
},
{
"epoch": 0.57,
"learning_rate": 5e-05,
"loss": 1.7116,
"step": 1000
},
{
"epoch": 0.57,
"eval_loss": 1.814998745918274,
"eval_runtime": 336.1286,
"eval_samples_per_second": 95.931,
"eval_steps_per_second": 0.75,
"step": 1000
}
],
"max_steps": 1762,
"num_train_epochs": 1,
"total_flos": 196298259038208.0,
"trial_name": null,
"trial_params": null
}
|