noflm
Training in progress, step 10000
d083be0
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1111.0001,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 11.0,
"learning_rate": 4.85e-06,
"loss": 0.716,
"step": 100
},
{
"epoch": 22.0,
"learning_rate": 9.85e-06,
"loss": 0.0615,
"step": 200
},
{
"epoch": 33.0,
"learning_rate": 1e-05,
"loss": 0.0043,
"step": 300
},
{
"epoch": 44.0,
"learning_rate": 1e-05,
"loss": 0.002,
"step": 400
},
{
"epoch": 55.0,
"learning_rate": 1e-05,
"loss": 0.0008,
"step": 500
},
{
"epoch": 66.0,
"learning_rate": 1e-05,
"loss": 0.0006,
"step": 600
},
{
"epoch": 77.0,
"learning_rate": 1e-05,
"loss": 0.0004,
"step": 700
},
{
"epoch": 88.0,
"learning_rate": 1e-05,
"loss": 0.0003,
"step": 800
},
{
"epoch": 99.0,
"learning_rate": 1e-05,
"loss": 0.0003,
"step": 900
},
{
"epoch": 111.0,
"learning_rate": 1e-05,
"loss": 0.0002,
"step": 1000
},
{
"epoch": 111.0,
"eval_loss": 0.21552081406116486,
"eval_runtime": 10.773,
"eval_samples_per_second": 1.671,
"eval_steps_per_second": 0.093,
"eval_wer": 9.75609756097561,
"step": 1000
},
{
"epoch": 122.0,
"learning_rate": 1e-05,
"loss": 0.0002,
"step": 1100
},
{
"epoch": 133.0,
"learning_rate": 1e-05,
"loss": 0.0002,
"step": 1200
},
{
"epoch": 144.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 1300
},
{
"epoch": 155.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 1400
},
{
"epoch": 166.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 1500
},
{
"epoch": 177.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 1600
},
{
"epoch": 188.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 1700
},
{
"epoch": 199.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 1800
},
{
"epoch": 211.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 1900
},
{
"epoch": 222.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 2000
},
{
"epoch": 222.0,
"eval_loss": 0.2447899729013443,
"eval_runtime": 14.1456,
"eval_samples_per_second": 1.272,
"eval_steps_per_second": 0.071,
"eval_wer": 12.195121951219512,
"step": 2000
},
{
"epoch": 233.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 2100
},
{
"epoch": 244.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 2200
},
{
"epoch": 255.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 2300
},
{
"epoch": 266.0,
"learning_rate": 1e-05,
"loss": 0.0001,
"step": 2400
},
{
"epoch": 277.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 2500
},
{
"epoch": 288.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 2600
},
{
"epoch": 299.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 2700
},
{
"epoch": 311.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 2800
},
{
"epoch": 322.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 2900
},
{
"epoch": 333.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3000
},
{
"epoch": 333.0,
"eval_loss": 0.2674005329608917,
"eval_runtime": 8.0249,
"eval_samples_per_second": 2.243,
"eval_steps_per_second": 0.125,
"eval_wer": 13.414634146341465,
"step": 3000
},
{
"epoch": 344.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3100
},
{
"epoch": 355.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3200
},
{
"epoch": 366.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3300
},
{
"epoch": 377.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3400
},
{
"epoch": 388.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3500
},
{
"epoch": 399.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3600
},
{
"epoch": 411.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3700
},
{
"epoch": 422.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3800
},
{
"epoch": 433.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 3900
},
{
"epoch": 444.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4000
},
{
"epoch": 444.0,
"eval_loss": 0.29429247975349426,
"eval_runtime": 7.7984,
"eval_samples_per_second": 2.308,
"eval_steps_per_second": 0.128,
"eval_wer": 15.853658536585366,
"step": 4000
},
{
"epoch": 455.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4100
},
{
"epoch": 466.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4200
},
{
"epoch": 477.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4300
},
{
"epoch": 488.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4400
},
{
"epoch": 499.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4500
},
{
"epoch": 511.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4600
},
{
"epoch": 522.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4700
},
{
"epoch": 533.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4800
},
{
"epoch": 544.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 4900
},
{
"epoch": 555.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5000
},
{
"epoch": 555.0,
"eval_loss": 0.31815305352211,
"eval_runtime": 7.3177,
"eval_samples_per_second": 2.46,
"eval_steps_per_second": 0.137,
"eval_wer": 17.073170731707318,
"step": 5000
},
{
"epoch": 566.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5100
},
{
"epoch": 577.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5200
},
{
"epoch": 588.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5300
},
{
"epoch": 599.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5400
},
{
"epoch": 611.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5500
},
{
"epoch": 622.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5600
},
{
"epoch": 633.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5700
},
{
"epoch": 644.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5800
},
{
"epoch": 655.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 5900
},
{
"epoch": 666.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6000
},
{
"epoch": 666.0,
"eval_loss": 0.35010817646980286,
"eval_runtime": 7.7729,
"eval_samples_per_second": 2.316,
"eval_steps_per_second": 0.129,
"eval_wer": 18.902439024390244,
"step": 6000
},
{
"epoch": 677.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6100
},
{
"epoch": 688.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6200
},
{
"epoch": 699.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6300
},
{
"epoch": 711.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6400
},
{
"epoch": 722.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6500
},
{
"epoch": 733.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6600
},
{
"epoch": 744.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6700
},
{
"epoch": 755.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6800
},
{
"epoch": 766.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 6900
},
{
"epoch": 777.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7000
},
{
"epoch": 777.0,
"eval_loss": 0.37315306067466736,
"eval_runtime": 8.5166,
"eval_samples_per_second": 2.114,
"eval_steps_per_second": 0.117,
"eval_wer": 16.463414634146343,
"step": 7000
},
{
"epoch": 788.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7100
},
{
"epoch": 799.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7200
},
{
"epoch": 811.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7300
},
{
"epoch": 822.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7400
},
{
"epoch": 833.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7500
},
{
"epoch": 844.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7600
},
{
"epoch": 855.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7700
},
{
"epoch": 866.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7800
},
{
"epoch": 877.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 7900
},
{
"epoch": 888.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8000
},
{
"epoch": 888.0,
"eval_loss": 0.4024837911128998,
"eval_runtime": 8.2162,
"eval_samples_per_second": 2.191,
"eval_steps_per_second": 0.122,
"eval_wer": 17.073170731707318,
"step": 8000
},
{
"epoch": 899.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8100
},
{
"epoch": 911.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8200
},
{
"epoch": 922.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8300
},
{
"epoch": 933.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8400
},
{
"epoch": 944.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8500
},
{
"epoch": 955.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8600
},
{
"epoch": 966.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8700
},
{
"epoch": 977.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8800
},
{
"epoch": 988.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 8900
},
{
"epoch": 999.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9000
},
{
"epoch": 999.0,
"eval_loss": 0.4178398847579956,
"eval_runtime": 8.2617,
"eval_samples_per_second": 2.179,
"eval_steps_per_second": 0.121,
"eval_wer": 20.121951219512198,
"step": 9000
},
{
"epoch": 1011.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9100
},
{
"epoch": 1022.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9200
},
{
"epoch": 1033.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9300
},
{
"epoch": 1044.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9400
},
{
"epoch": 1055.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9500
},
{
"epoch": 1066.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9600
},
{
"epoch": 1077.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9700
},
{
"epoch": 1088.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9800
},
{
"epoch": 1099.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 9900
},
{
"epoch": 1111.0,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 10000
},
{
"epoch": 1111.0,
"eval_loss": 0.43846404552459717,
"eval_runtime": 7.9746,
"eval_samples_per_second": 2.257,
"eval_steps_per_second": 0.125,
"eval_wer": 17.073170731707318,
"step": 10000
}
],
"max_steps": 10000,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.960224747945984e+19,
"trial_name": null,
"trial_params": null
}