{ "best_metric": 1.1316041946411133, "best_model_checkpoint": "miner_id_24/checkpoint-10", "epoch": 0.0005022475578212501, "eval_steps": 5, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.0224755782125007e-05, "eval_loss": 1.3837661743164062, "eval_runtime": 1292.9785, "eval_samples_per_second": 6.484, "eval_steps_per_second": 3.242, "step": 1 }, { "epoch": 0.00015067426734637502, "grad_norm": 2.247525691986084, "learning_rate": 6e-05, "loss": 5.2756, "step": 3 }, { "epoch": 0.00025112377891062503, "eval_loss": 1.3188445568084717, "eval_runtime": 1295.6444, "eval_samples_per_second": 6.471, "eval_steps_per_second": 3.235, "step": 5 }, { "epoch": 0.00030134853469275004, "grad_norm": 1.854863166809082, "learning_rate": 0.00012, "loss": 5.9855, "step": 6 }, { "epoch": 0.00045202280203912506, "grad_norm": 1.2117688655853271, "learning_rate": 0.00018, "loss": 4.9755, "step": 9 }, { "epoch": 0.0005022475578212501, "eval_loss": 1.1316041946411133, "eval_runtime": 1294.9521, "eval_samples_per_second": 6.474, "eval_steps_per_second": 3.237, "step": 10 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "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": 3085503276515328.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }