File size: 4,247 Bytes
3c780f8 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 28.06997084548105,
"global_step": 4800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.34,
"learning_rate": 0.00023999999999999998,
"loss": 4.1009,
"step": 400
},
{
"epoch": 2.34,
"eval_loss": 2.947835922241211,
"eval_runtime": 361.2993,
"eval_samples_per_second": 6.944,
"eval_wer": 1.0,
"step": 400
},
{
"epoch": 4.68,
"learning_rate": 0.0002805615550755939,
"loss": 2.0411,
"step": 800
},
{
"epoch": 4.68,
"eval_loss": 0.5171445608139038,
"eval_runtime": 364.5526,
"eval_samples_per_second": 6.882,
"eval_wer": 0.7113982218374346,
"step": 800
},
{
"epoch": 7.02,
"learning_rate": 0.0002546436285097192,
"loss": 0.4401,
"step": 1200
},
{
"epoch": 7.02,
"eval_loss": 0.3676733076572418,
"eval_runtime": 366.7629,
"eval_samples_per_second": 6.841,
"eval_wer": 0.5746395391428857,
"step": 1200
},
{
"epoch": 9.36,
"learning_rate": 0.00022872570194384448,
"loss": 0.2829,
"step": 1600
},
{
"epoch": 9.36,
"eval_loss": 0.3323122262954712,
"eval_runtime": 371.0751,
"eval_samples_per_second": 6.761,
"eval_wer": 0.5098065332489761,
"step": 1600
},
{
"epoch": 11.69,
"learning_rate": 0.00020280777537796973,
"loss": 0.2019,
"step": 2000
},
{
"epoch": 11.69,
"eval_loss": 0.3595321476459503,
"eval_runtime": 359.0792,
"eval_samples_per_second": 6.987,
"eval_wer": 0.483899970030968,
"step": 2000
},
{
"epoch": 14.03,
"learning_rate": 0.00017688984881209503,
"loss": 0.1641,
"step": 2400
},
{
"epoch": 14.03,
"eval_loss": 0.38239890336990356,
"eval_runtime": 369.6977,
"eval_samples_per_second": 6.787,
"eval_wer": 0.4745096733375512,
"step": 2400
},
{
"epoch": 16.37,
"learning_rate": 0.00015097192224622027,
"loss": 0.1311,
"step": 2800
},
{
"epoch": 16.37,
"eval_loss": 0.3804999887943268,
"eval_runtime": 365.1667,
"eval_samples_per_second": 6.871,
"eval_wer": 0.46205587559521827,
"step": 2800
},
{
"epoch": 18.71,
"learning_rate": 0.00012505399568034557,
"loss": 0.1157,
"step": 3200
},
{
"epoch": 18.71,
"eval_loss": 0.39201927185058594,
"eval_runtime": 362.8973,
"eval_samples_per_second": 6.914,
"eval_wer": 0.4496686757017748,
"step": 3200
},
{
"epoch": 21.05,
"learning_rate": 9.913606911447084e-05,
"loss": 0.0989,
"step": 3600
},
{
"epoch": 21.05,
"eval_loss": 0.41990572214126587,
"eval_runtime": 358.4193,
"eval_samples_per_second": 7.0,
"eval_wer": 0.45106723052845393,
"step": 3600
},
{
"epoch": 23.39,
"learning_rate": 7.32181425485961e-05,
"loss": 0.0895,
"step": 4000
},
{
"epoch": 23.39,
"eval_loss": 0.409751832485199,
"eval_runtime": 369.3102,
"eval_samples_per_second": 6.794,
"eval_wer": 0.4471046585195298,
"step": 4000
},
{
"epoch": 25.73,
"learning_rate": 4.7300215982721384e-05,
"loss": 0.081,
"step": 4400
},
{
"epoch": 25.73,
"eval_loss": 0.41373974084854126,
"eval_runtime": 371.7326,
"eval_samples_per_second": 6.749,
"eval_wer": 0.4345176650794179,
"step": 4400
},
{
"epoch": 28.07,
"learning_rate": 2.1382289416846652e-05,
"loss": 0.0761,
"step": 4800
},
{
"epoch": 28.07,
"eval_loss": 0.4309007227420807,
"eval_runtime": 384.4679,
"eval_samples_per_second": 6.526,
"eval_wer": 0.4348506543238653,
"step": 4800
}
],
"max_steps": 5130,
"num_train_epochs": 30,
"total_flos": 3.173501973340016e+19,
"trial_name": null,
"trial_params": null
}
|