File size: 5,035 Bytes
7799ead |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
{
"best_metric": 1.0910215377807617,
"best_model_checkpoint": "/kaggle/output/checkpoint-12000",
"epoch": 0.48891786179921776,
"eval_steps": 1000,
"global_step": 12000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.7777777777777777e-11,
"loss": 1.05,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 2.7750000000000004e-08,
"loss": 1.1403,
"step": 1000
},
{
"epoch": 0.04,
"eval_accuracy": 0.33712574850299404,
"eval_loss": 1.1030837297439575,
"eval_runtime": 29.7882,
"eval_samples_per_second": 168.187,
"eval_steps_per_second": 21.049,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 5.5527777777777784e-08,
"loss": 1.1194,
"step": 2000
},
{
"epoch": 0.08,
"eval_accuracy": 0.34331337325349304,
"eval_loss": 1.1002165079116821,
"eval_runtime": 29.8685,
"eval_samples_per_second": 167.735,
"eval_steps_per_second": 20.992,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 8.327777777777778e-08,
"loss": 1.1194,
"step": 3000
},
{
"epoch": 0.12,
"eval_accuracy": 0.3471057884231537,
"eval_loss": 1.101266622543335,
"eval_runtime": 29.709,
"eval_samples_per_second": 168.636,
"eval_steps_per_second": 21.105,
"step": 3000
},
{
"epoch": 0.16,
"learning_rate": 1.1105555555555557e-07,
"loss": 1.1166,
"step": 4000
},
{
"epoch": 0.16,
"eval_accuracy": 0.34311377245508984,
"eval_loss": 1.0984796285629272,
"eval_runtime": 29.9401,
"eval_samples_per_second": 167.334,
"eval_steps_per_second": 20.942,
"step": 4000
},
{
"epoch": 0.2,
"learning_rate": 1.3883333333333335e-07,
"loss": 1.1137,
"step": 5000
},
{
"epoch": 0.2,
"eval_accuracy": 0.3403193612774451,
"eval_loss": 1.0974279642105103,
"eval_runtime": 29.8185,
"eval_samples_per_second": 168.016,
"eval_steps_per_second": 21.027,
"step": 5000
},
{
"epoch": 0.24,
"learning_rate": 1.6658333333333335e-07,
"loss": 1.1109,
"step": 6000
},
{
"epoch": 0.24,
"eval_accuracy": 0.3592814371257485,
"eval_loss": 1.0984892845153809,
"eval_runtime": 29.893,
"eval_samples_per_second": 167.598,
"eval_steps_per_second": 20.975,
"step": 6000
},
{
"epoch": 0.29,
"learning_rate": 1.9436111111111112e-07,
"loss": 1.1122,
"step": 7000
},
{
"epoch": 0.29,
"eval_accuracy": 0.36327345309381237,
"eval_loss": 1.0960686206817627,
"eval_runtime": 29.8315,
"eval_samples_per_second": 167.943,
"eval_steps_per_second": 21.018,
"step": 7000
},
{
"epoch": 0.33,
"learning_rate": 2.2213888888888891e-07,
"loss": 1.1091,
"step": 8000
},
{
"epoch": 0.33,
"eval_accuracy": 0.35728542914171657,
"eval_loss": 1.0958523750305176,
"eval_runtime": 29.9494,
"eval_samples_per_second": 167.282,
"eval_steps_per_second": 20.935,
"step": 8000
},
{
"epoch": 0.37,
"learning_rate": 2.4988888888888893e-07,
"loss": 1.1077,
"step": 9000
},
{
"epoch": 0.37,
"eval_accuracy": 0.35528942115768464,
"eval_loss": 1.1003851890563965,
"eval_runtime": 29.9762,
"eval_samples_per_second": 167.133,
"eval_steps_per_second": 20.917,
"step": 9000
},
{
"epoch": 0.41,
"learning_rate": 2.776666666666667e-07,
"loss": 1.1091,
"step": 10000
},
{
"epoch": 0.41,
"eval_accuracy": 0.3790419161676647,
"eval_loss": 1.0951762199401855,
"eval_runtime": 29.8593,
"eval_samples_per_second": 167.787,
"eval_steps_per_second": 20.998,
"step": 10000
},
{
"epoch": 0.45,
"learning_rate": 3.0541666666666667e-07,
"loss": 1.1047,
"step": 11000
},
{
"epoch": 0.45,
"eval_accuracy": 0.3780439121756487,
"eval_loss": 1.0928910970687866,
"eval_runtime": 29.8768,
"eval_samples_per_second": 167.689,
"eval_steps_per_second": 20.986,
"step": 11000
},
{
"epoch": 0.49,
"learning_rate": 3.3319444444444444e-07,
"loss": 1.1053,
"step": 12000
},
{
"epoch": 0.49,
"eval_accuracy": 0.38323353293413176,
"eval_loss": 1.0910215377807617,
"eval_runtime": 29.8703,
"eval_samples_per_second": 167.725,
"eval_steps_per_second": 20.991,
"step": 12000
}
],
"logging_steps": 1000,
"max_steps": 10000000,
"num_train_epochs": 408,
"save_steps": 1000,
"total_flos": 1.2542470520832e+16,
"trial_name": null,
"trial_params": null
}
|