| { | |
| "best_metric": 3.3042805194854736, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.027777777777777776, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002777777777777778, | |
| "eval_loss": 3.456601619720459, | |
| "eval_runtime": 1.7458, | |
| "eval_samples_per_second": 174.136, | |
| "eval_steps_per_second": 43.534, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008333333333333333, | |
| "grad_norm": 6.741215229034424, | |
| "learning_rate": 0.00012, | |
| "loss": 13.8937, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013888888888888888, | |
| "eval_loss": 3.3771238327026367, | |
| "eval_runtime": 1.7404, | |
| "eval_samples_per_second": 174.677, | |
| "eval_steps_per_second": 43.669, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016666666666666666, | |
| "grad_norm": 5.106968402862549, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 13.9782, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 5.924384117126465, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 13.3747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "eval_loss": 3.3042805194854736, | |
| "eval_runtime": 1.7655, | |
| "eval_samples_per_second": 172.185, | |
| "eval_steps_per_second": 43.046, | |
| "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": 86222642872320.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |