| { | |
| "best_metric": 1.6760838031768799, | |
| "best_model_checkpoint": "bigbird-flight-2/checkpoint-1028", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1028, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09727626459143969, | |
| "grad_norm": 5.640580654144287, | |
| "learning_rate": 1.5197568389057753e-06, | |
| "loss": 2.2808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19455252918287938, | |
| "grad_norm": 6.845468044281006, | |
| "learning_rate": 3.0395136778115506e-06, | |
| "loss": 2.3041, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2918287937743191, | |
| "grad_norm": 4.374593257904053, | |
| "learning_rate": 4.559270516717325e-06, | |
| "loss": 2.303, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38910505836575876, | |
| "grad_norm": 3.985168218612671, | |
| "learning_rate": 6.079027355623101e-06, | |
| "loss": 2.295, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.48638132295719844, | |
| "grad_norm": 6.664238929748535, | |
| "learning_rate": 7.5987841945288756e-06, | |
| "loss": 2.249, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5836575875486382, | |
| "grad_norm": 6.191707611083984, | |
| "learning_rate": 9.11854103343465e-06, | |
| "loss": 2.1323, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6809338521400778, | |
| "grad_norm": 6.4777140617370605, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 2.0151, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7782101167315175, | |
| "grad_norm": 15.601507186889648, | |
| "learning_rate": 1.2158054711246202e-05, | |
| "loss": 1.9318, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8754863813229572, | |
| "grad_norm": 6.998500347137451, | |
| "learning_rate": 1.3677811550151975e-05, | |
| "loss": 1.9021, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9727626459143969, | |
| "grad_norm": 16.937795639038086, | |
| "learning_rate": 1.5197568389057751e-05, | |
| "loss": 1.8199, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2704280155642023, | |
| "eval_f1_macro": 0.18452231398929034, | |
| "eval_f1_micro": 0.2704280155642023, | |
| "eval_f1_weighted": 0.1903075803351923, | |
| "eval_loss": 1.8465327024459839, | |
| "eval_precision_macro": 0.19230244249654188, | |
| "eval_precision_micro": 0.2704280155642023, | |
| "eval_precision_weighted": 0.1960311004178974, | |
| "eval_recall_macro": 0.2598247809762203, | |
| "eval_recall_micro": 0.2704280155642023, | |
| "eval_recall_weighted": 0.2704280155642023, | |
| "eval_runtime": 1595.827, | |
| "eval_samples_per_second": 0.322, | |
| "eval_steps_per_second": 0.041, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.0700389105058365, | |
| "grad_norm": 10.755321502685547, | |
| "learning_rate": 1.6717325227963527e-05, | |
| "loss": 1.8219, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1673151750972763, | |
| "grad_norm": 16.09447479248047, | |
| "learning_rate": 1.82370820668693e-05, | |
| "loss": 1.7428, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.264591439688716, | |
| "grad_norm": 14.368643760681152, | |
| "learning_rate": 1.9756838905775076e-05, | |
| "loss": 1.7054, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3618677042801557, | |
| "grad_norm": 9.273758888244629, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 1.7145, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.4591439688715953, | |
| "grad_norm": 12.411294937133789, | |
| "learning_rate": 2.279635258358663e-05, | |
| "loss": 1.6765, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.556420233463035, | |
| "grad_norm": 27.17559051513672, | |
| "learning_rate": 2.4316109422492404e-05, | |
| "loss": 1.7499, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.6536964980544746, | |
| "grad_norm": 18.921966552734375, | |
| "learning_rate": 2.5835866261398177e-05, | |
| "loss": 1.6988, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7509727626459144, | |
| "grad_norm": 14.716523170471191, | |
| "learning_rate": 2.735562310030395e-05, | |
| "loss": 1.6935, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8482490272373542, | |
| "grad_norm": 20.14253807067871, | |
| "learning_rate": 2.887537993920973e-05, | |
| "loss": 1.7054, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9455252918287937, | |
| "grad_norm": 5.987732887268066, | |
| "learning_rate": 3.0395136778115502e-05, | |
| "loss": 1.7427, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3093385214007782, | |
| "eval_f1_macro": 0.27337963763262785, | |
| "eval_f1_micro": 0.3093385214007782, | |
| "eval_f1_weighted": 0.2814372687206247, | |
| "eval_loss": 1.6760838031768799, | |
| "eval_precision_macro": 0.282150640368379, | |
| "eval_precision_micro": 0.3093385214007782, | |
| "eval_precision_weighted": 0.2911286647426314, | |
| "eval_recall_macro": 0.30072312612988455, | |
| "eval_recall_micro": 0.3093385214007782, | |
| "eval_recall_weighted": 0.3093385214007782, | |
| "eval_runtime": 1588.4184, | |
| "eval_samples_per_second": 0.324, | |
| "eval_steps_per_second": 0.041, | |
| "step": 1028 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 16448, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 32, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2176781982056448.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |