| { | |
| "best_metric": 0.6816527843475342, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.24798512089274644, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009919404835709857, | |
| "grad_norm": 14.22542953491211, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009919404835709857, | |
| "eval_loss": 6.156983375549316, | |
| "eval_runtime": 4.614, | |
| "eval_samples_per_second": 147.162, | |
| "eval_steps_per_second": 18.422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019838809671419714, | |
| "grad_norm": 14.014447212219238, | |
| "learning_rate": 0.0001, | |
| "loss": 5.7084, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029758214507129573, | |
| "grad_norm": 11.578995704650879, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.037, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03967761934283943, | |
| "grad_norm": 11.724237442016602, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.0769, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04959702417854929, | |
| "grad_norm": 13.393182754516602, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.2076, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.059516429014259145, | |
| "grad_norm": 11.202437400817871, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.3867, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.069435833849969, | |
| "grad_norm": 8.223298072814941, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07935523868567886, | |
| "grad_norm": 8.567903518676758, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2064, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08927464352138871, | |
| "grad_norm": 6.670114994049072, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9824, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09919404835709858, | |
| "grad_norm": 4.440275192260742, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7052, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10911345319280844, | |
| "grad_norm": 4.102833271026611, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7221, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11903285802851829, | |
| "grad_norm": 6.891973972320557, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.861, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12895226286422815, | |
| "grad_norm": 6.446341514587402, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.907, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.138871667699938, | |
| "grad_norm": 7.807364463806152, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3164, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14879107253564786, | |
| "grad_norm": 5.236413955688477, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9623, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1587104773713577, | |
| "grad_norm": 4.211988925933838, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6875, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16862988220706757, | |
| "grad_norm": 3.572789192199707, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7002, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17854928704277742, | |
| "grad_norm": 3.022789478302002, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6794, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1884686918784873, | |
| "grad_norm": 3.362051248550415, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5496, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19838809671419716, | |
| "grad_norm": 3.555093288421631, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7896, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20830750154990701, | |
| "grad_norm": 2.8280599117279053, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5434, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21822690638561687, | |
| "grad_norm": 2.1897058486938477, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3792, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22814631122132673, | |
| "grad_norm": 2.137267827987671, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5645, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23806571605703658, | |
| "grad_norm": 3.7149977684020996, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1815, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24798512089274644, | |
| "grad_norm": 5.753180027008057, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9379, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24798512089274644, | |
| "eval_loss": 0.6816527843475342, | |
| "eval_runtime": 4.6096, | |
| "eval_samples_per_second": 147.303, | |
| "eval_steps_per_second": 18.44, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 1.47650456322048e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |