File size: 5,016 Bytes
48c94e1 |
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": 1.0888582468032837,
"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": 1.1506,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 2.7750000000000004e-08,
"loss": 1.1326,
"step": 1000
},
{
"epoch": 0.04,
"eval_accuracy": 0.3331337325349301,
"eval_loss": 1.1057127714157104,
"eval_runtime": 61.3538,
"eval_samples_per_second": 81.657,
"eval_steps_per_second": 10.219,
"step": 1000
},
{
"epoch": 0.08,
"learning_rate": 5.5527777777777784e-08,
"loss": 1.1238,
"step": 2000
},
{
"epoch": 0.08,
"eval_accuracy": 0.33812375249501,
"eval_loss": 1.1044437885284424,
"eval_runtime": 61.256,
"eval_samples_per_second": 81.788,
"eval_steps_per_second": 10.236,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 8.327777777777778e-08,
"loss": 1.1251,
"step": 3000
},
{
"epoch": 0.12,
"eval_accuracy": 0.3407185628742515,
"eval_loss": 1.1043975353240967,
"eval_runtime": 61.2433,
"eval_samples_per_second": 81.805,
"eval_steps_per_second": 10.238,
"step": 3000
},
{
"epoch": 0.16,
"learning_rate": 1.1105555555555557e-07,
"loss": 1.1205,
"step": 4000
},
{
"epoch": 0.16,
"eval_accuracy": 0.3387225548902196,
"eval_loss": 1.100860357284546,
"eval_runtime": 61.4457,
"eval_samples_per_second": 81.535,
"eval_steps_per_second": 10.204,
"step": 4000
},
{
"epoch": 0.2,
"learning_rate": 1.3880555555555558e-07,
"loss": 1.1192,
"step": 5000
},
{
"epoch": 0.2,
"eval_accuracy": 0.34151696606786425,
"eval_loss": 1.1005476713180542,
"eval_runtime": 61.2568,
"eval_samples_per_second": 81.787,
"eval_steps_per_second": 10.236,
"step": 5000
},
{
"epoch": 0.24,
"learning_rate": 1.6658333333333335e-07,
"loss": 1.1145,
"step": 6000
},
{
"epoch": 0.24,
"eval_accuracy": 0.3508982035928144,
"eval_loss": 1.0979759693145752,
"eval_runtime": 61.2221,
"eval_samples_per_second": 81.833,
"eval_steps_per_second": 10.241,
"step": 6000
},
{
"epoch": 0.29,
"learning_rate": 1.9433333333333334e-07,
"loss": 1.1164,
"step": 7000
},
{
"epoch": 0.29,
"eval_accuracy": 0.35508982035928144,
"eval_loss": 1.0955135822296143,
"eval_runtime": 61.255,
"eval_samples_per_second": 81.789,
"eval_steps_per_second": 10.236,
"step": 7000
},
{
"epoch": 0.33,
"learning_rate": 2.2211111111111114e-07,
"loss": 1.1091,
"step": 8000
},
{
"epoch": 0.33,
"eval_accuracy": 0.36147704590818364,
"eval_loss": 1.0946425199508667,
"eval_runtime": 61.3011,
"eval_samples_per_second": 81.728,
"eval_steps_per_second": 10.228,
"step": 8000
},
{
"epoch": 0.37,
"learning_rate": 2.4986111111111113e-07,
"loss": 1.107,
"step": 9000
},
{
"epoch": 0.37,
"eval_accuracy": 0.3471057884231537,
"eval_loss": 1.10226309299469,
"eval_runtime": 61.3193,
"eval_samples_per_second": 81.703,
"eval_steps_per_second": 10.225,
"step": 9000
},
{
"epoch": 0.41,
"learning_rate": 2.776388888888889e-07,
"loss": 1.1055,
"step": 10000
},
{
"epoch": 0.41,
"eval_accuracy": 0.3774451097804391,
"eval_loss": 1.0922847986221313,
"eval_runtime": 61.1866,
"eval_samples_per_second": 81.881,
"eval_steps_per_second": 10.247,
"step": 10000
},
{
"epoch": 0.45,
"learning_rate": 3.0541666666666667e-07,
"loss": 1.1028,
"step": 11000
},
{
"epoch": 0.45,
"eval_accuracy": 0.37425149700598803,
"eval_loss": 1.0914534330368042,
"eval_runtime": 61.341,
"eval_samples_per_second": 81.675,
"eval_steps_per_second": 10.222,
"step": 11000
},
{
"epoch": 0.49,
"learning_rate": 3.3319444444444444e-07,
"loss": 1.1024,
"step": 12000
},
{
"epoch": 0.49,
"eval_accuracy": 0.3872255489021956,
"eval_loss": 1.0888582468032837,
"eval_runtime": 61.4245,
"eval_samples_per_second": 81.564,
"eval_steps_per_second": 10.208,
"step": 12000
}
],
"logging_steps": 1000,
"max_steps": 10000000,
"num_train_epochs": 408,
"save_steps": 1000,
"total_flos": 2.5084261564416e+16,
"trial_name": null,
"trial_params": null
}
|