| { | |
| "best_metric": 1.1749109029769897, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.020080321285140562, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002008032128514056, | |
| "eval_loss": 1.3232147693634033, | |
| "eval_runtime": 72.9359, | |
| "eval_samples_per_second": 2.879, | |
| "eval_steps_per_second": 1.44, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006024096385542169, | |
| "grad_norm": 1.1903401613235474, | |
| "learning_rate": 6e-05, | |
| "loss": 5.3337, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010040160642570281, | |
| "eval_loss": 1.29500150680542, | |
| "eval_runtime": 73.686, | |
| "eval_samples_per_second": 2.85, | |
| "eval_steps_per_second": 1.425, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 3.233403444290161, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 5.3897, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018072289156626505, | |
| "grad_norm": 1.7138043642044067, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 4.3576, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "eval_loss": 1.1749109029769897, | |
| "eval_runtime": 73.6686, | |
| "eval_samples_per_second": 2.851, | |
| "eval_steps_per_second": 1.425, | |
| "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": 1.30129688788992e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |