File size: 3,856 Bytes
d0836b0 07aa41a d0836b0 07aa41a d0836b0 1bd31f2 d0836b0 1bd31f2 d0836b0 8728efa 2d2ff6c 9767285 2646de1 0f62944 acb207e c3e6485 b698e96 26f2191 07aa41a d0836b0 07aa41a d0836b0 |
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 |
{
"best_metric": 1.4184046983718872,
"best_model_checkpoint": "./outputs/checkpoint-1100",
"epoch": 1.4666666666666668,
"eval_steps": 100,
"global_step": 1100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 1.4578,
"step": 100
},
{
"epoch": 0.13,
"eval_loss": 1.567879319190979,
"eval_runtime": 93.4626,
"eval_samples_per_second": 15.525,
"eval_steps_per_second": 1.947,
"step": 100
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 1.2977,
"step": 200
},
{
"epoch": 0.27,
"eval_loss": 1.5340639352798462,
"eval_runtime": 93.3831,
"eval_samples_per_second": 15.538,
"eval_steps_per_second": 1.949,
"step": 200
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 1.2762,
"step": 300
},
{
"epoch": 0.4,
"eval_loss": 1.5129507780075073,
"eval_runtime": 93.3176,
"eval_samples_per_second": 15.549,
"eval_steps_per_second": 1.95,
"step": 300
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 1.2673,
"step": 400
},
{
"epoch": 0.53,
"eval_loss": 1.4979034662246704,
"eval_runtime": 93.4276,
"eval_samples_per_second": 15.531,
"eval_steps_per_second": 1.948,
"step": 400
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 1.2497,
"step": 500
},
{
"epoch": 0.67,
"eval_loss": 1.4787811040878296,
"eval_runtime": 93.1297,
"eval_samples_per_second": 15.58,
"eval_steps_per_second": 1.954,
"step": 500
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 1.2326,
"step": 600
},
{
"epoch": 0.8,
"eval_loss": 1.4662799835205078,
"eval_runtime": 93.3055,
"eval_samples_per_second": 15.551,
"eval_steps_per_second": 1.951,
"step": 600
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 1.2216,
"step": 700
},
{
"epoch": 0.93,
"eval_loss": 1.455640435218811,
"eval_runtime": 93.4836,
"eval_samples_per_second": 15.521,
"eval_steps_per_second": 1.947,
"step": 700
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 1.2091,
"step": 800
},
{
"epoch": 1.07,
"eval_loss": 1.446093201637268,
"eval_runtime": 93.3855,
"eval_samples_per_second": 15.538,
"eval_steps_per_second": 1.949,
"step": 800
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 1.1928,
"step": 900
},
{
"epoch": 1.2,
"eval_loss": 1.4368518590927124,
"eval_runtime": 93.1897,
"eval_samples_per_second": 15.57,
"eval_steps_per_second": 1.953,
"step": 900
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 1.1859,
"step": 1000
},
{
"epoch": 1.33,
"eval_loss": 1.4286835193634033,
"eval_runtime": 93.2996,
"eval_samples_per_second": 15.552,
"eval_steps_per_second": 1.951,
"step": 1000
},
{
"epoch": 1.47,
"learning_rate": 0.0002,
"loss": 1.1844,
"step": 1100
},
{
"epoch": 1.47,
"eval_loss": 1.4184046983718872,
"eval_runtime": 93.2489,
"eval_samples_per_second": 15.56,
"eval_steps_per_second": 1.952,
"step": 1100
}
],
"logging_steps": 100,
"max_steps": 2250,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 6.43012944795648e+16,
"trial_name": null,
"trial_params": null
}
|