| { | |
| "best_metric": 1.1935243606567383, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.12876227265411236, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005150490906164494, | |
| "grad_norm": 1.6360301971435547, | |
| "learning_rate": 5e-05, | |
| "loss": 1.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005150490906164494, | |
| "eval_loss": 1.8850927352905273, | |
| "eval_runtime": 3.9577, | |
| "eval_samples_per_second": 12.634, | |
| "eval_steps_per_second": 3.285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010300981812328988, | |
| "grad_norm": 1.687415361404419, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01545147271849348, | |
| "grad_norm": 1.6830966472625732, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.741, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020601963624657976, | |
| "grad_norm": 1.520763874053955, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.5323, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02575245453082247, | |
| "grad_norm": 1.2332735061645508, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.4831, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03090294543698696, | |
| "grad_norm": 0.957449734210968, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3928, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03605343634315146, | |
| "grad_norm": 0.9580352902412415, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3336, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04120392724931595, | |
| "grad_norm": 0.9211961030960083, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3421, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04635441815548044, | |
| "grad_norm": 0.9401556253433228, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.2484, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05150490906164494, | |
| "grad_norm": 1.0537054538726807, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1164, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05665539996780943, | |
| "grad_norm": 1.024180293083191, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0345, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06180589087397392, | |
| "grad_norm": 1.2686243057250977, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0674, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06695638178013842, | |
| "grad_norm": 1.3576205968856812, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6091, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07210687268630292, | |
| "grad_norm": 0.9457244873046875, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.4211, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0772573635924674, | |
| "grad_norm": 0.6527680158615112, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.3348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0824078544986319, | |
| "grad_norm": 0.8764634132385254, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.3786, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0875583454047964, | |
| "grad_norm": 0.7613826394081116, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.26, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09270883631096088, | |
| "grad_norm": 0.8126055598258972, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2384, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09785932721712538, | |
| "grad_norm": 0.7038941979408264, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1189, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10300981812328988, | |
| "grad_norm": 0.7687941193580627, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10816030902945437, | |
| "grad_norm": 0.8610501885414124, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2106, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11331079993561886, | |
| "grad_norm": 0.7789077758789062, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.08, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11846129084178336, | |
| "grad_norm": 0.8925905227661133, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.0633, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12361178174794785, | |
| "grad_norm": 1.111682653427124, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0581, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "grad_norm": 1.133190393447876, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.9546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "eval_loss": 1.1935243606567383, | |
| "eval_runtime": 4.029, | |
| "eval_samples_per_second": 12.41, | |
| "eval_steps_per_second": 3.227, | |
| "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": 3.087239672233984e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |