File size: 4,267 Bytes
7804085 |
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 |
{
"best_metric": 7.829923629760742,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/2023-11-20/14-54-26/checkpoints/checkpoint-120",
"epoch": 0.96,
"eval_steps": 10,
"global_step": 120,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"learning_rate": 4.600000000000001e-05,
"loss": 10.8138,
"step": 10
},
{
"epoch": 0.08,
"eval_loss": 10.804353713989258,
"eval_runtime": 2.6966,
"eval_samples_per_second": 370.843,
"eval_steps_per_second": 46.355,
"step": 10
},
{
"epoch": 0.16,
"learning_rate": 4.2e-05,
"loss": 10.7944,
"step": 20
},
{
"epoch": 0.16,
"eval_loss": 10.780308723449707,
"eval_runtime": 2.9168,
"eval_samples_per_second": 342.842,
"eval_steps_per_second": 42.855,
"step": 20
},
{
"epoch": 0.24,
"learning_rate": 3.8e-05,
"loss": 10.7582,
"step": 30
},
{
"epoch": 0.24,
"eval_loss": 10.715201377868652,
"eval_runtime": 2.6781,
"eval_samples_per_second": 373.4,
"eval_steps_per_second": 46.675,
"step": 30
},
{
"epoch": 0.32,
"learning_rate": 3.4000000000000007e-05,
"loss": 10.5902,
"step": 40
},
{
"epoch": 0.32,
"eval_loss": 10.216275215148926,
"eval_runtime": 2.8449,
"eval_samples_per_second": 351.507,
"eval_steps_per_second": 43.938,
"step": 40
},
{
"epoch": 0.4,
"learning_rate": 3e-05,
"loss": 9.8089,
"step": 50
},
{
"epoch": 0.4,
"eval_loss": 9.195159912109375,
"eval_runtime": 2.6916,
"eval_samples_per_second": 371.531,
"eval_steps_per_second": 46.441,
"step": 50
},
{
"epoch": 0.48,
"learning_rate": 2.6000000000000002e-05,
"loss": 9.0218,
"step": 60
},
{
"epoch": 0.48,
"eval_loss": 8.602910041809082,
"eval_runtime": 2.6711,
"eval_samples_per_second": 374.379,
"eval_steps_per_second": 46.797,
"step": 60
},
{
"epoch": 0.56,
"learning_rate": 2.2000000000000003e-05,
"loss": 8.5416,
"step": 70
},
{
"epoch": 0.56,
"eval_loss": 8.279220581054688,
"eval_runtime": 2.7623,
"eval_samples_per_second": 362.019,
"eval_steps_per_second": 45.252,
"step": 70
},
{
"epoch": 0.64,
"learning_rate": 1.8e-05,
"loss": 8.3655,
"step": 80
},
{
"epoch": 0.64,
"eval_loss": 8.092720985412598,
"eval_runtime": 2.7605,
"eval_samples_per_second": 362.25,
"eval_steps_per_second": 45.281,
"step": 80
},
{
"epoch": 0.72,
"learning_rate": 1.4000000000000001e-05,
"loss": 8.2139,
"step": 90
},
{
"epoch": 0.72,
"eval_loss": 7.974403381347656,
"eval_runtime": 2.6732,
"eval_samples_per_second": 374.09,
"eval_steps_per_second": 46.761,
"step": 90
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 8.1098,
"step": 100
},
{
"epoch": 0.8,
"eval_loss": 7.899349689483643,
"eval_runtime": 2.8812,
"eval_samples_per_second": 347.075,
"eval_steps_per_second": 43.384,
"step": 100
},
{
"epoch": 0.88,
"learning_rate": 6e-06,
"loss": 8.0232,
"step": 110
},
{
"epoch": 0.88,
"eval_loss": 7.852936267852783,
"eval_runtime": 2.6664,
"eval_samples_per_second": 375.035,
"eval_steps_per_second": 46.879,
"step": 110
},
{
"epoch": 0.96,
"learning_rate": 2.0000000000000003e-06,
"loss": 8.1088,
"step": 120
},
{
"epoch": 0.96,
"eval_loss": 7.829923629760742,
"eval_runtime": 2.8976,
"eval_samples_per_second": 345.118,
"eval_steps_per_second": 43.14,
"step": 120
}
],
"logging_steps": 10,
"max_steps": 125,
"num_train_epochs": 1,
"save_steps": 10,
"total_flos": 8440665834240.0,
"trial_name": null,
"trial_params": null
}
|