| { | |
| "best_metric": 11.93446159362793, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.00022732180811766176, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.2732180811766176e-05, | |
| "eval_loss": 11.937361717224121, | |
| "eval_runtime": 376.5768, | |
| "eval_samples_per_second": 49.188, | |
| "eval_steps_per_second": 24.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.819654243529852e-05, | |
| "grad_norm": 0.25319623947143555, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9367, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011366090405883088, | |
| "eval_loss": 11.936665534973145, | |
| "eval_runtime": 373.8091, | |
| "eval_samples_per_second": 49.552, | |
| "eval_steps_per_second": 24.777, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00013639308487059705, | |
| "grad_norm": 0.07899723947048187, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9379, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002045896273058956, | |
| "grad_norm": 0.09688087552785873, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9371, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022732180811766176, | |
| "eval_loss": 11.93446159362793, | |
| "eval_runtime": 373.5824, | |
| "eval_samples_per_second": 49.582, | |
| "eval_steps_per_second": 24.792, | |
| "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": 2856405565440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |