{ "best_metric": 3.3135757446289062, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.002257591150242691, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 4.5151823004853824e-05, "eval_loss": 4.564711093902588, "eval_runtime": 183.5644, "eval_samples_per_second": 50.805, "eval_steps_per_second": 12.704, "step": 1 }, { "epoch": 0.0004515182300485382, "grad_norm": 4.505808353424072, "learning_rate": 4.1e-05, "loss": 3.6345, "step": 10 }, { "epoch": 0.0009030364600970764, "grad_norm": 4.865635395050049, "learning_rate": 8.2e-05, "loss": 3.4077, "step": 20 }, { "epoch": 0.0013545546901456147, "grad_norm": 5.399093151092529, "learning_rate": 0.00012299999999999998, "loss": 3.212, "step": 30 }, { "epoch": 0.0018060729201941528, "grad_norm": 6.037168502807617, "learning_rate": 0.000164, "loss": 3.2546, "step": 40 }, { "epoch": 0.002257591150242691, "grad_norm": 8.842162132263184, "learning_rate": 0.000205, "loss": 3.2376, "step": 50 }, { "epoch": 0.002257591150242691, "eval_loss": 3.3135757446289062, "eval_runtime": 185.7849, "eval_samples_per_second": 50.198, "eval_steps_per_second": 12.552, "step": 50 } ], "logging_steps": 10, "max_steps": 500, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "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": 455102402396160.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }