| { | |
| "best_metric": 0.3662590980529785, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.010303967027305513, | |
| "eval_steps": 20, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.58663918942126e-05, | |
| "eval_loss": 1.2680586576461792, | |
| "eval_runtime": 137.1384, | |
| "eval_samples_per_second": 35.76, | |
| "eval_steps_per_second": 1.123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001717327837884252, | |
| "eval_loss": 0.8298065066337585, | |
| "eval_runtime": 136.9762, | |
| "eval_samples_per_second": 35.802, | |
| "eval_steps_per_second": 1.124, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003434655675768504, | |
| "eval_loss": 0.4227403402328491, | |
| "eval_runtime": 137.3821, | |
| "eval_samples_per_second": 35.696, | |
| "eval_steps_per_second": 1.121, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005151983513652756, | |
| "eval_loss": 0.39482441544532776, | |
| "eval_runtime": 137.0671, | |
| "eval_samples_per_second": 35.778, | |
| "eval_steps_per_second": 1.124, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.006869311351537008, | |
| "eval_loss": 0.37885797023773193, | |
| "eval_runtime": 137.1197, | |
| "eval_samples_per_second": 35.764, | |
| "eval_steps_per_second": 1.123, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00858663918942126, | |
| "grad_norm": 11.635492324829102, | |
| "learning_rate": 0.00013774104683195594, | |
| "loss": 1.1408, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00858663918942126, | |
| "eval_loss": 0.3662590980529785, | |
| "eval_runtime": 137.243, | |
| "eval_samples_per_second": 35.732, | |
| "eval_steps_per_second": 1.122, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.010303967027305513, | |
| "eval_loss": 0.3811986744403839, | |
| "eval_runtime": 137.1238, | |
| "eval_samples_per_second": 35.763, | |
| "eval_steps_per_second": 1.123, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 58230, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1733105345757184e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |