| { | |
| "best_metric": 1.2068699598312378, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0017353278034220663, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.470655606844133e-05, | |
| "eval_loss": 1.5390846729278564, | |
| "eval_runtime": 273.4595, | |
| "eval_samples_per_second": 44.365, | |
| "eval_steps_per_second": 11.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003470655606844133, | |
| "grad_norm": 0.5712449550628662, | |
| "learning_rate": 5.05e-06, | |
| "loss": 0.5196, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006941311213688266, | |
| "grad_norm": 0.9507728815078735, | |
| "learning_rate": 1.01e-05, | |
| "loss": 0.6129, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00104119668205324, | |
| "grad_norm": 2.0956873893737793, | |
| "learning_rate": 9.323076923076924e-06, | |
| "loss": 0.983, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013882622427376532, | |
| "grad_norm": 4.227148532867432, | |
| "learning_rate": 8.546153846153847e-06, | |
| "loss": 1.5109, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017353278034220663, | |
| "grad_norm": 24.842472076416016, | |
| "learning_rate": 7.76923076923077e-06, | |
| "loss": 2.601, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0017353278034220663, | |
| "eval_loss": 1.2068699598312378, | |
| "eval_runtime": 273.0714, | |
| "eval_samples_per_second": 44.428, | |
| "eval_steps_per_second": 11.107, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 150, | |
| "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": 3469845316239360.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |