noflm
Training in progress, step 10000
b6dd850
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 35.0165,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.02,
"learning_rate": 9.960000000000001e-06,
"loss": 0.5615,
"step": 500
},
{
"epoch": 3.02,
"learning_rate": 1e-05,
"loss": 0.3273,
"step": 1000
},
{
"epoch": 3.02,
"eval_loss": 0.4225325584411621,
"eval_runtime": 1489.9228,
"eval_samples_per_second": 3.09,
"eval_steps_per_second": 0.193,
"eval_wer": 20.82533081951615,
"step": 1000
},
{
"epoch": 5.01,
"learning_rate": 1e-05,
"loss": 0.1859,
"step": 1500
},
{
"epoch": 7.0,
"learning_rate": 1e-05,
"loss": 0.0923,
"step": 2000
},
{
"epoch": 7.0,
"eval_loss": 0.46434369683265686,
"eval_runtime": 1504.5618,
"eval_samples_per_second": 3.06,
"eval_steps_per_second": 0.191,
"eval_wer": 21.22002361108664,
"step": 2000
},
{
"epoch": 8.03,
"learning_rate": 1e-05,
"loss": 0.0369,
"step": 2500
},
{
"epoch": 10.02,
"learning_rate": 1e-05,
"loss": 0.0164,
"step": 3000
},
{
"epoch": 10.02,
"eval_loss": 0.5403426885604858,
"eval_runtime": 1504.7378,
"eval_samples_per_second": 3.06,
"eval_steps_per_second": 0.191,
"eval_wer": 22.962662766725987,
"step": 3000
},
{
"epoch": 12.01,
"learning_rate": 1e-05,
"loss": 0.0089,
"step": 3500
},
{
"epoch": 14.01,
"learning_rate": 1e-05,
"loss": 0.006,
"step": 4000
},
{
"epoch": 14.01,
"eval_loss": 0.5819889307022095,
"eval_runtime": 1478.853,
"eval_samples_per_second": 3.113,
"eval_steps_per_second": 0.195,
"eval_wer": 21.086109985375224,
"step": 4000
},
{
"epoch": 16.0,
"learning_rate": 1e-05,
"loss": 0.0057,
"step": 4500
},
{
"epoch": 17.02,
"learning_rate": 1e-05,
"loss": 0.0046,
"step": 5000
},
{
"epoch": 17.02,
"eval_loss": 0.5851565003395081,
"eval_runtime": 1532.3442,
"eval_samples_per_second": 3.005,
"eval_steps_per_second": 0.188,
"eval_wer": 22.072841964301446,
"step": 5000
},
{
"epoch": 19.02,
"learning_rate": 1e-05,
"loss": 0.0042,
"step": 5500
},
{
"epoch": 21.01,
"learning_rate": 1e-05,
"loss": 0.0034,
"step": 6000
},
{
"epoch": 21.01,
"eval_loss": 0.6112661361694336,
"eval_runtime": 1497.7325,
"eval_samples_per_second": 3.074,
"eval_steps_per_second": 0.192,
"eval_wer": 21.6622909802125,
"step": 6000
},
{
"epoch": 23.0,
"learning_rate": 1e-05,
"loss": 0.004,
"step": 6500
},
{
"epoch": 24.03,
"learning_rate": 1e-05,
"loss": 0.0028,
"step": 7000
},
{
"epoch": 24.03,
"eval_loss": 0.6582160592079163,
"eval_runtime": 1517.5965,
"eval_samples_per_second": 3.034,
"eval_steps_per_second": 0.19,
"eval_wer": 22.326573044596763,
"step": 7000
},
{
"epoch": 26.02,
"learning_rate": 1e-05,
"loss": 0.0027,
"step": 7500
},
{
"epoch": 28.01,
"learning_rate": 1e-05,
"loss": 0.0025,
"step": 8000
},
{
"epoch": 28.01,
"eval_loss": 0.6349595785140991,
"eval_runtime": 1539.4689,
"eval_samples_per_second": 2.991,
"eval_steps_per_second": 0.187,
"eval_wer": 22.23318591087696,
"step": 8000
},
{
"epoch": 30.01,
"learning_rate": 1e-05,
"loss": 0.0027,
"step": 8500
},
{
"epoch": 32.0,
"learning_rate": 1e-05,
"loss": 0.0029,
"step": 9000
},
{
"epoch": 32.0,
"eval_loss": 0.646816074848175,
"eval_runtime": 1531.6588,
"eval_samples_per_second": 3.006,
"eval_steps_per_second": 0.188,
"eval_wer": 22.10984441351118,
"step": 9000
},
{
"epoch": 33.02,
"learning_rate": 1e-05,
"loss": 0.0021,
"step": 9500
},
{
"epoch": 35.02,
"learning_rate": 1e-05,
"loss": 0.0014,
"step": 10000
},
{
"epoch": 35.02,
"eval_loss": 0.6532349586486816,
"eval_runtime": 1526.2981,
"eval_samples_per_second": 3.016,
"eval_steps_per_second": 0.189,
"eval_wer": 21.991788980318223,
"step": 10000
}
],
"max_steps": 10000,
"num_train_epochs": 9223372036854775807,
"total_flos": 2.07052565741568e+19,
"trial_name": null,
"trial_params": null
}