File size: 3,659 Bytes
d5ae0f6 |
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 |
{
"best_metric": 0.16926079988479614,
"best_model_checkpoint": "./checkpoint-2000",
"epoch": 28.97666068222621,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.45,
"learning_rate": 1.0202e-05,
"loss": 6.1347,
"step": 100
},
{
"epoch": 2.89,
"learning_rate": 2.0102e-05,
"loss": 3.041,
"step": 200
},
{
"epoch": 4.34,
"learning_rate": 3.0002000000000002e-05,
"loss": 1.8943,
"step": 300
},
{
"epoch": 5.79,
"learning_rate": 3.9902e-05,
"loss": 1.473,
"step": 400
},
{
"epoch": 7.24,
"learning_rate": 4.9802e-05,
"loss": 1.255,
"step": 500
},
{
"epoch": 7.24,
"eval_cer": 0.07577137076378351,
"eval_loss": 0.29775065183639526,
"eval_runtime": 14.4182,
"eval_samples_per_second": 23.234,
"eval_steps_per_second": 0.416,
"eval_wer": 0.42935206869633097,
"step": 500
},
{
"epoch": 8.69,
"learning_rate": 5e-05,
"loss": 1.1289,
"step": 600
},
{
"epoch": 10.14,
"learning_rate": 5e-05,
"loss": 1.0964,
"step": 700
},
{
"epoch": 11.59,
"learning_rate": 5e-05,
"loss": 1.0491,
"step": 800
},
{
"epoch": 13.04,
"learning_rate": 5e-05,
"loss": 1.0342,
"step": 900
},
{
"epoch": 14.49,
"learning_rate": 5e-05,
"loss": 1.0058,
"step": 1000
},
{
"epoch": 14.49,
"eval_cer": 0.04825493171471927,
"eval_loss": 0.18830506503582,
"eval_runtime": 13.5348,
"eval_samples_per_second": 24.751,
"eval_steps_per_second": 0.443,
"eval_wer": 0.28376268540202965,
"step": 1000
},
{
"epoch": 15.93,
"learning_rate": 5e-05,
"loss": 0.9735,
"step": 1100
},
{
"epoch": 17.39,
"learning_rate": 5e-05,
"loss": 0.9772,
"step": 1200
},
{
"epoch": 18.83,
"learning_rate": 5e-05,
"loss": 0.9625,
"step": 1300
},
{
"epoch": 20.29,
"learning_rate": 5e-05,
"loss": 0.9492,
"step": 1400
},
{
"epoch": 21.73,
"learning_rate": 5e-05,
"loss": 0.9371,
"step": 1500
},
{
"epoch": 21.73,
"eval_cer": 0.045725847243297923,
"eval_loss": 0.1812673956155777,
"eval_runtime": 13.3792,
"eval_samples_per_second": 25.039,
"eval_steps_per_second": 0.448,
"eval_wer": 0.26268540202966434,
"step": 1500
},
{
"epoch": 23.19,
"learning_rate": 5e-05,
"loss": 0.9325,
"step": 1600
},
{
"epoch": 24.63,
"learning_rate": 5e-05,
"loss": 0.9169,
"step": 1700
},
{
"epoch": 26.09,
"learning_rate": 5e-05,
"loss": 0.9168,
"step": 1800
},
{
"epoch": 27.53,
"learning_rate": 5e-05,
"loss": 0.9111,
"step": 1900
},
{
"epoch": 28.98,
"learning_rate": 5e-05,
"loss": 0.8999,
"step": 2000
},
{
"epoch": 28.98,
"eval_cer": 0.042943854324734444,
"eval_loss": 0.16926079988479614,
"eval_runtime": 13.6397,
"eval_samples_per_second": 24.561,
"eval_steps_per_second": 0.44,
"eval_wer": 0.2373145979703357,
"step": 2000
}
],
"max_steps": 5000,
"num_train_epochs": 73,
"total_flos": 1.8112953812816295e+20,
"trial_name": null,
"trial_params": null
}
|