| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10488043630261502, | |
| "eval_steps": 5000, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006992029086841001, | |
| "grad_norm": 75.90129852294922, | |
| "learning_rate": 6.780845858091577e-07, | |
| "loss": 16.865, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.013984058173682002, | |
| "grad_norm": 71.16612243652344, | |
| "learning_rate": 1.3771408598392172e-06, | |
| "loss": 16.1556, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.020976087260523003, | |
| "grad_norm": 130.67613220214844, | |
| "learning_rate": 2.0761971338692767e-06, | |
| "loss": 14.8008, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.027968116347364003, | |
| "grad_norm": 36.4179801940918, | |
| "learning_rate": 2.7682628451590356e-06, | |
| "loss": 12.4025, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.034960145434205, | |
| "grad_norm": 34.748844146728516, | |
| "learning_rate": 3.467319119189095e-06, | |
| "loss": 9.7465, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04195217452104601, | |
| "grad_norm": 8.039146423339844, | |
| "learning_rate": 4.166375393219155e-06, | |
| "loss": 8.448, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.04894420360788701, | |
| "grad_norm": 10.288451194763184, | |
| "learning_rate": 4.865431667249214e-06, | |
| "loss": 8.1951, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.05593623269472801, | |
| "grad_norm": 6.3236308097839355, | |
| "learning_rate": 5.564487941279273e-06, | |
| "loss": 8.1093, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.06292826178156902, | |
| "grad_norm": 15.230368614196777, | |
| "learning_rate": 6.263544215309333e-06, | |
| "loss": 8.0567, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.06992029086841, | |
| "grad_norm": 5.573168754577637, | |
| "learning_rate": 6.962600489339393e-06, | |
| "loss": 8.0401, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07691231995525101, | |
| "grad_norm": 6.7740325927734375, | |
| "learning_rate": 7.661656763369451e-06, | |
| "loss": 7.9491, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.08390434904209201, | |
| "grad_norm": 6.167610168457031, | |
| "learning_rate": 8.360713037399512e-06, | |
| "loss": 7.9494, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.09089637812893302, | |
| "grad_norm": 5.53561544418335, | |
| "learning_rate": 9.05976931142957e-06, | |
| "loss": 7.9386, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.09788840721577402, | |
| "grad_norm": 6.056953430175781, | |
| "learning_rate": 9.758825585459631e-06, | |
| "loss": 7.9033, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.10488043630261502, | |
| "grad_norm": 5.160706043243408, | |
| "learning_rate": 1.045788185948969e-05, | |
| "loss": 7.9055, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 28604, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |