| { | |
| "best_metric": 2.383007764816284, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07256894049346879, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001451378809869376, | |
| "eval_loss": 2.528571605682373, | |
| "eval_runtime": 24.4881, | |
| "eval_samples_per_second": 11.843, | |
| "eval_steps_per_second": 2.981, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01451378809869376, | |
| "grad_norm": 1.4596052169799805, | |
| "learning_rate": 4.1400000000000003e-05, | |
| "loss": 2.3431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02902757619738752, | |
| "grad_norm": 1.2653985023498535, | |
| "learning_rate": 8.280000000000001e-05, | |
| "loss": 2.1844, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04354136429608128, | |
| "grad_norm": 1.5904498100280762, | |
| "learning_rate": 0.00012419999999999998, | |
| "loss": 2.2177, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05805515239477504, | |
| "grad_norm": 1.749571442604065, | |
| "learning_rate": 0.00016560000000000001, | |
| "loss": 2.2032, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07256894049346879, | |
| "grad_norm": 5.132608890533447, | |
| "learning_rate": 0.000207, | |
| "loss": 2.2296, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07256894049346879, | |
| "eval_loss": 2.383007764816284, | |
| "eval_runtime": 24.5963, | |
| "eval_samples_per_second": 11.79, | |
| "eval_steps_per_second": 2.968, | |
| "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": 1.319949381402624e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |