File size: 5,138 Bytes
3ddb29c |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 14.936708860759493,
"eval_steps": 100,
"global_step": 1770,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.84,
"eval_loss": 4.394069194793701,
"eval_runtime": 118.8089,
"eval_samples_per_second": 14.99,
"eval_steps_per_second": 1.877,
"eval_wer": 1.0,
"step": 100
},
{
"epoch": 1.69,
"eval_loss": 3.200528383255005,
"eval_runtime": 116.974,
"eval_samples_per_second": 15.226,
"eval_steps_per_second": 1.906,
"eval_wer": 1.0,
"step": 200
},
{
"epoch": 2.53,
"eval_loss": 2.7843868732452393,
"eval_runtime": 118.9835,
"eval_samples_per_second": 14.968,
"eval_steps_per_second": 1.874,
"eval_wer": 1.0144723900519883,
"step": 300
},
{
"epoch": 3.38,
"eval_loss": 0.8691409230232239,
"eval_runtime": 118.7268,
"eval_samples_per_second": 15.001,
"eval_steps_per_second": 1.878,
"eval_wer": 1.000281017282563,
"step": 400
},
{
"epoch": 4.22,
"learning_rate": 0.0002988,
"loss": 4.317,
"step": 500
},
{
"epoch": 4.22,
"eval_loss": 0.684583306312561,
"eval_runtime": 119.9053,
"eval_samples_per_second": 14.853,
"eval_steps_per_second": 1.86,
"eval_wer": 0.8393986230153154,
"step": 500
},
{
"epoch": 5.06,
"eval_loss": 0.6270079612731934,
"eval_runtime": 120.1998,
"eval_samples_per_second": 14.817,
"eval_steps_per_second": 1.855,
"eval_wer": 0.7789799072642968,
"step": 600
},
{
"epoch": 5.91,
"eval_loss": 0.593498945236206,
"eval_runtime": 120.001,
"eval_samples_per_second": 14.842,
"eval_steps_per_second": 1.858,
"eval_wer": 0.7802444850358297,
"step": 700
},
{
"epoch": 6.75,
"eval_loss": 0.570054829120636,
"eval_runtime": 120.3712,
"eval_samples_per_second": 14.796,
"eval_steps_per_second": 1.853,
"eval_wer": 0.7812280455247997,
"step": 800
},
{
"epoch": 7.59,
"eval_loss": 0.564914345741272,
"eval_runtime": 122.0077,
"eval_samples_per_second": 14.597,
"eval_steps_per_second": 1.828,
"eval_wer": 0.7890965294365604,
"step": 900
},
{
"epoch": 8.44,
"learning_rate": 0.00018236220472440942,
"loss": 0.3656,
"step": 1000
},
{
"epoch": 8.44,
"eval_loss": 0.6092184782028198,
"eval_runtime": 120.3224,
"eval_samples_per_second": 14.802,
"eval_steps_per_second": 1.853,
"eval_wer": 0.8177602922579739,
"step": 1000
},
{
"epoch": 9.28,
"eval_loss": 0.6092739701271057,
"eval_runtime": 120.225,
"eval_samples_per_second": 14.814,
"eval_steps_per_second": 1.855,
"eval_wer": 0.7720949838415062,
"step": 1100
},
{
"epoch": 10.13,
"eval_loss": 0.6154232621192932,
"eval_runtime": 120.1186,
"eval_samples_per_second": 14.827,
"eval_steps_per_second": 1.856,
"eval_wer": 0.7286778136855416,
"step": 1200
},
{
"epoch": 10.97,
"eval_loss": 0.6283690333366394,
"eval_runtime": 122.0867,
"eval_samples_per_second": 14.588,
"eval_steps_per_second": 1.827,
"eval_wer": 0.7407615568357454,
"step": 1300
},
{
"epoch": 11.81,
"eval_loss": 0.6343453526496887,
"eval_runtime": 120.4977,
"eval_samples_per_second": 14.78,
"eval_steps_per_second": 1.851,
"eval_wer": 0.7143459322748349,
"step": 1400
},
{
"epoch": 12.66,
"learning_rate": 6.425196850393701e-05,
"loss": 0.1681,
"step": 1500
},
{
"epoch": 12.66,
"eval_loss": 0.6523498296737671,
"eval_runtime": 119.5948,
"eval_samples_per_second": 14.892,
"eval_steps_per_second": 1.865,
"eval_wer": 0.7362652803147394,
"step": 1500
},
{
"epoch": 13.5,
"eval_loss": 0.6542894244194031,
"eval_runtime": 120.5721,
"eval_samples_per_second": 14.771,
"eval_steps_per_second": 1.85,
"eval_wer": 0.7139244063509906,
"step": 1600
},
{
"epoch": 14.35,
"eval_loss": 0.6598775386810303,
"eval_runtime": 124.634,
"eval_samples_per_second": 14.29,
"eval_steps_per_second": 1.789,
"eval_wer": 0.7094281298299846,
"step": 1700
},
{
"epoch": 14.94,
"step": 1770,
"total_flos": 7.546311277696558e+18,
"train_loss": 1.3876537419981876,
"train_runtime": 7307.918,
"train_samples_per_second": 7.775,
"train_steps_per_second": 0.242
}
],
"logging_steps": 500,
"max_steps": 1770,
"num_input_tokens_seen": 0,
"num_train_epochs": 15,
"save_steps": 400,
"total_flos": 7.546311277696558e+18,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|