| { | |
| "best_metric": 2.2354156970977783, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.04672897196261682, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004672897196261682, | |
| "eval_loss": 2.919769525527954, | |
| "eval_runtime": 5.8335, | |
| "eval_samples_per_second": 15.6, | |
| "eval_steps_per_second": 7.885, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014018691588785047, | |
| "grad_norm": 1.5106477737426758, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9451, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02336448598130841, | |
| "eval_loss": 2.5764288902282715, | |
| "eval_runtime": 5.2723, | |
| "eval_samples_per_second": 17.26, | |
| "eval_steps_per_second": 8.725, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 1.4866009950637817, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.6873, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04205607476635514, | |
| "grad_norm": 1.3173651695251465, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.4428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04672897196261682, | |
| "eval_loss": 2.2354156970977783, | |
| "eval_runtime": 5.2644, | |
| "eval_samples_per_second": 17.286, | |
| "eval_steps_per_second": 8.738, | |
| "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": 3709436417802240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |