| { | |
| "best_metric": 0.6463924646377563, | |
| "best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-1b-bigcgen-combined-5hrs/checkpoint-1100", | |
| "epoch": 6.3298097251585626, | |
| "eval_steps": 100, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.42283298097251587, | |
| "eval_loss": 3.778658151626587, | |
| "eval_runtime": 52.4177, | |
| "eval_samples_per_second": 13.011, | |
| "eval_steps_per_second": 3.262, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8456659619450317, | |
| "eval_loss": 2.864159107208252, | |
| "eval_runtime": 52.0708, | |
| "eval_samples_per_second": 13.098, | |
| "eval_steps_per_second": 3.284, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.266384778012685, | |
| "eval_loss": 1.1326375007629395, | |
| "eval_runtime": 52.4633, | |
| "eval_samples_per_second": 13.0, | |
| "eval_steps_per_second": 3.259, | |
| "eval_wer": 0.9986222099751998, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.6892177589852009, | |
| "eval_loss": 0.8747416138648987, | |
| "eval_runtime": 52.4977, | |
| "eval_samples_per_second": 12.991, | |
| "eval_steps_per_second": 3.257, | |
| "eval_wer": 0.8280518049049325, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.109936575052854, | |
| "grad_norm": 3.907411575317383, | |
| "learning_rate": 3e-05, | |
| "loss": 5.818, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.109936575052854, | |
| "eval_loss": 0.7864503264427185, | |
| "eval_runtime": 52.9346, | |
| "eval_samples_per_second": 12.884, | |
| "eval_steps_per_second": 3.23, | |
| "eval_wer": 0.8027004684486084, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.53276955602537, | |
| "eval_loss": 0.6710236668586731, | |
| "eval_runtime": 52.4221, | |
| "eval_samples_per_second": 13.01, | |
| "eval_steps_per_second": 3.262, | |
| "eval_wer": 0.6953706255166713, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.955602536997886, | |
| "eval_loss": 0.723403811454773, | |
| "eval_runtime": 52.5023, | |
| "eval_samples_per_second": 12.99, | |
| "eval_steps_per_second": 3.257, | |
| "eval_wer": 0.793882612289887, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.376321353065539, | |
| "eval_loss": 0.6657159924507141, | |
| "eval_runtime": 52.5331, | |
| "eval_samples_per_second": 12.982, | |
| "eval_steps_per_second": 3.255, | |
| "eval_wer": 0.6705704050702673, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.7991543340380547, | |
| "eval_loss": 0.683569073677063, | |
| "eval_runtime": 52.9444, | |
| "eval_samples_per_second": 12.881, | |
| "eval_steps_per_second": 3.23, | |
| "eval_wer": 0.7245797740424359, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.219873150105708, | |
| "grad_norm": 3.2278690338134766, | |
| "learning_rate": 2.7720364741641338e-05, | |
| "loss": 1.2021, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.219873150105708, | |
| "eval_loss": 0.6893664598464966, | |
| "eval_runtime": 52.2867, | |
| "eval_samples_per_second": 13.043, | |
| "eval_steps_per_second": 3.27, | |
| "eval_wer": 0.6897216864149903, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.642706131078224, | |
| "eval_loss": 0.6463924646377563, | |
| "eval_runtime": 52.2676, | |
| "eval_samples_per_second": 13.048, | |
| "eval_steps_per_second": 3.272, | |
| "eval_wer": 0.6642325709561863, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.063424947145878, | |
| "eval_loss": 0.6663212776184082, | |
| "eval_runtime": 52.3377, | |
| "eval_samples_per_second": 13.031, | |
| "eval_steps_per_second": 3.267, | |
| "eval_wer": 0.6777349131992284, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.486257928118393, | |
| "eval_loss": 0.6701002717018127, | |
| "eval_runtime": 52.8656, | |
| "eval_samples_per_second": 12.901, | |
| "eval_steps_per_second": 3.235, | |
| "eval_wer": 0.6704326260677873, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.909090909090909, | |
| "eval_loss": 0.6833611726760864, | |
| "eval_runtime": 52.569, | |
| "eval_samples_per_second": 12.973, | |
| "eval_steps_per_second": 3.253, | |
| "eval_wer": 0.6898594654174703, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.3298097251585626, | |
| "grad_norm": 4.171246528625488, | |
| "learning_rate": 2.5440729483282676e-05, | |
| "loss": 0.8307, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.3298097251585626, | |
| "eval_loss": 0.6944476962089539, | |
| "eval_runtime": 52.4546, | |
| "eval_samples_per_second": 13.002, | |
| "eval_steps_per_second": 3.26, | |
| "eval_wer": 0.6599614218793056, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.3298097251585626, | |
| "step": 1500, | |
| "total_flos": 8.934809903427992e+18, | |
| "train_loss": 2.616910949707031, | |
| "train_runtime": 2875.9904, | |
| "train_samples_per_second": 19.736, | |
| "train_steps_per_second": 2.462 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7080, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.934809903427992e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |