| { | |
| "best_metric": 0.5856660604476929, | |
| "best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-1b-bigcgen-combined-15hrs-model/checkpoint-1200", | |
| "epoch": 2.2566995768688294, | |
| "eval_steps": 100, | |
| "global_step": 1600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14104372355430184, | |
| "eval_loss": 3.8893141746520996, | |
| "eval_runtime": 53.0152, | |
| "eval_samples_per_second": 12.864, | |
| "eval_steps_per_second": 3.225, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2820874471086037, | |
| "eval_loss": 2.6866326332092285, | |
| "eval_runtime": 52.8101, | |
| "eval_samples_per_second": 12.914, | |
| "eval_steps_per_second": 3.238, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4231311706629055, | |
| "eval_loss": 1.4204449653625488, | |
| "eval_runtime": 53.002, | |
| "eval_samples_per_second": 12.867, | |
| "eval_steps_per_second": 3.226, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5641748942172073, | |
| "eval_loss": 0.8780319094657898, | |
| "eval_runtime": 53.1195, | |
| "eval_samples_per_second": 12.839, | |
| "eval_steps_per_second": 3.219, | |
| "eval_wer": 0.8846789749242215, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7052186177715092, | |
| "grad_norm": 4.491549491882324, | |
| "learning_rate": 3e-05, | |
| "loss": 5.5784, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7052186177715092, | |
| "eval_loss": 0.8820701241493225, | |
| "eval_runtime": 53.4186, | |
| "eval_samples_per_second": 12.767, | |
| "eval_steps_per_second": 3.201, | |
| "eval_wer": 0.9582529622485533, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.846262341325811, | |
| "eval_loss": 0.6897755861282349, | |
| "eval_runtime": 53.3341, | |
| "eval_samples_per_second": 12.787, | |
| "eval_steps_per_second": 3.206, | |
| "eval_wer": 0.7508955635161202, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9873060648801129, | |
| "eval_loss": 0.6909680962562561, | |
| "eval_runtime": 53.3024, | |
| "eval_samples_per_second": 12.795, | |
| "eval_steps_per_second": 3.208, | |
| "eval_wer": 0.8689721686414991, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1283497884344147, | |
| "eval_loss": 0.6632267832756042, | |
| "eval_runtime": 53.2656, | |
| "eval_samples_per_second": 12.804, | |
| "eval_steps_per_second": 3.21, | |
| "eval_wer": 0.681041609258749, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2693935119887165, | |
| "eval_loss": 0.6164674758911133, | |
| "eval_runtime": 53.6138, | |
| "eval_samples_per_second": 12.721, | |
| "eval_steps_per_second": 3.189, | |
| "eval_wer": 0.6048498208872968, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4104372355430184, | |
| "grad_norm": 6.964908599853516, | |
| "learning_rate": 2.9277804525758308e-05, | |
| "loss": 1.2954, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4104372355430184, | |
| "eval_loss": 0.60063636302948, | |
| "eval_runtime": 53.8102, | |
| "eval_samples_per_second": 12.674, | |
| "eval_steps_per_second": 3.178, | |
| "eval_wer": 0.6133921190410582, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5514809590973202, | |
| "eval_loss": 0.6859056353569031, | |
| "eval_runtime": 53.6927, | |
| "eval_samples_per_second": 12.702, | |
| "eval_steps_per_second": 3.185, | |
| "eval_wer": 0.7683934968310829, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.692524682651622, | |
| "eval_loss": 0.5856660604476929, | |
| "eval_runtime": 53.9146, | |
| "eval_samples_per_second": 12.65, | |
| "eval_steps_per_second": 3.172, | |
| "eval_wer": 0.6273077982915404, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.8335684062059239, | |
| "eval_loss": 0.6304970383644104, | |
| "eval_runtime": 53.5646, | |
| "eval_samples_per_second": 12.732, | |
| "eval_steps_per_second": 3.192, | |
| "eval_wer": 0.6154588040782585, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.9746121297602257, | |
| "eval_loss": 0.6212508678436279, | |
| "eval_runtime": 53.3498, | |
| "eval_samples_per_second": 12.784, | |
| "eval_steps_per_second": 3.205, | |
| "eval_wer": 0.5855607605400936, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.1156558533145273, | |
| "grad_norm": 4.57673978805542, | |
| "learning_rate": 2.855560905151661e-05, | |
| "loss": 1.1582, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.1156558533145273, | |
| "eval_loss": 0.5891425609588623, | |
| "eval_runtime": 53.7029, | |
| "eval_samples_per_second": 12.699, | |
| "eval_steps_per_second": 3.184, | |
| "eval_wer": 0.5983742077707357, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.2566995768688294, | |
| "eval_loss": 0.6605567932128906, | |
| "eval_runtime": 53.1853, | |
| "eval_samples_per_second": 12.823, | |
| "eval_steps_per_second": 3.215, | |
| "eval_wer": 0.7040507026729127, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.2566995768688294, | |
| "step": 1600, | |
| "total_flos": 9.492183580866103e+18, | |
| "train_loss": 2.5750148630142213, | |
| "train_runtime": 3143.2537, | |
| "train_samples_per_second": 54.106, | |
| "train_steps_per_second": 6.767 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 21270, | |
| "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": 4 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.492183580866103e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |