File size: 4,273 Bytes
9e882be |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"global_step": 417130,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999988013329178e-05,
"loss": 5.0345,
"step": 1
},
{
"epoch": 1.0,
"learning_rate": 4.5e-05,
"loss": 3.5452,
"step": 41713
},
{
"epoch": 1.0,
"eval_accuracy": 0.4118760802529946,
"eval_loss": 3.3738181591033936,
"eval_runtime": 157.5504,
"eval_samples_per_second": 129.368,
"eval_steps_per_second": 16.173,
"step": 41713
},
{
"epoch": 2.0,
"learning_rate": 4e-05,
"loss": 3.4132,
"step": 83426
},
{
"epoch": 2.0,
"eval_accuracy": 0.4179529258872079,
"eval_loss": 3.326674461364746,
"eval_runtime": 156.5806,
"eval_samples_per_second": 130.169,
"eval_steps_per_second": 16.273,
"step": 83426
},
{
"epoch": 3.0,
"learning_rate": 3.5e-05,
"loss": 3.3573,
"step": 125139
},
{
"epoch": 3.0,
"eval_accuracy": 0.4213834655713664,
"eval_loss": 3.3009300231933594,
"eval_runtime": 156.2147,
"eval_samples_per_second": 130.474,
"eval_steps_per_second": 16.311,
"step": 125139
},
{
"epoch": 4.0,
"learning_rate": 3e-05,
"loss": 3.3196,
"step": 166852
},
{
"epoch": 4.0,
"eval_accuracy": 0.42338731797471446,
"eval_loss": 3.2852749824523926,
"eval_runtime": 157.4446,
"eval_samples_per_second": 129.455,
"eval_steps_per_second": 16.183,
"step": 166852
},
{
"epoch": 5.0,
"learning_rate": 2.5e-05,
"loss": 3.2912,
"step": 208565
},
{
"epoch": 5.0,
"eval_accuracy": 0.42540662325952266,
"eval_loss": 3.2730937004089355,
"eval_runtime": 155.9547,
"eval_samples_per_second": 130.692,
"eval_steps_per_second": 16.338,
"step": 208565
},
{
"epoch": 6.0,
"learning_rate": 2e-05,
"loss": 3.2688,
"step": 250278
},
{
"epoch": 6.0,
"eval_accuracy": 0.42657331580976576,
"eval_loss": 3.265730857849121,
"eval_runtime": 157.36,
"eval_samples_per_second": 129.525,
"eval_steps_per_second": 16.192,
"step": 250278
},
{
"epoch": 7.0,
"learning_rate": 1.5e-05,
"loss": 3.2506,
"step": 291991
},
{
"epoch": 7.0,
"eval_accuracy": 0.4276302929016416,
"eval_loss": 3.25875186920166,
"eval_runtime": 157.1763,
"eval_samples_per_second": 129.676,
"eval_steps_per_second": 16.211,
"step": 291991
},
{
"epoch": 8.0,
"learning_rate": 1e-05,
"loss": 3.2358,
"step": 333704
},
{
"epoch": 8.0,
"eval_accuracy": 0.4284013916865043,
"eval_loss": 3.2545275688171387,
"eval_runtime": 155.6431,
"eval_samples_per_second": 130.953,
"eval_steps_per_second": 16.371,
"step": 333704
},
{
"epoch": 9.0,
"learning_rate": 5e-06,
"loss": 3.2237,
"step": 375417
},
{
"epoch": 9.0,
"eval_accuracy": 0.4288819762999157,
"eval_loss": 3.2520158290863037,
"eval_runtime": 156.3518,
"eval_samples_per_second": 130.36,
"eval_steps_per_second": 16.297,
"step": 375417
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 3.2144,
"step": 417130
},
{
"epoch": 10.0,
"eval_accuracy": 0.42910256618275966,
"eval_loss": 3.251399040222168,
"eval_runtime": 154.5215,
"eval_samples_per_second": 131.904,
"eval_steps_per_second": 16.49,
"step": 417130
},
{
"epoch": 10.0,
"step": 417130,
"total_flos": 6.5394993954816e+17,
"train_loss": 3.311987802313766,
"train_runtime": 196254.5716,
"train_samples_per_second": 51.01,
"train_steps_per_second": 2.125
}
],
"max_steps": 417130,
"num_train_epochs": 10,
"total_flos": 6.5394993954816e+17,
"trial_name": null,
"trial_params": null
}
|