| { | |
| "best_metric": 0.5634785890579224, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2331002331002331, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004662004662004662, | |
| "eval_loss": 0.7121074199676514, | |
| "eval_runtime": 7.0933, | |
| "eval_samples_per_second": 12.829, | |
| "eval_steps_per_second": 3.242, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.046620046620046623, | |
| "grad_norm": 0.5039583444595337, | |
| "learning_rate": 4.22e-05, | |
| "loss": 0.6299, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09324009324009325, | |
| "grad_norm": 0.983407199382782, | |
| "learning_rate": 8.44e-05, | |
| "loss": 0.6324, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13986013986013987, | |
| "grad_norm": 0.9202139377593994, | |
| "learning_rate": 0.0001266, | |
| "loss": 0.5562, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1864801864801865, | |
| "grad_norm": 1.4665826559066772, | |
| "learning_rate": 0.0001688, | |
| "loss": 0.5768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2331002331002331, | |
| "grad_norm": 2.6910219192504883, | |
| "learning_rate": 0.000211, | |
| "loss": 0.5501, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2331002331002331, | |
| "eval_loss": 0.5634785890579224, | |
| "eval_runtime": 7.092, | |
| "eval_samples_per_second": 12.831, | |
| "eval_steps_per_second": 3.243, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 215, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.0976590137655296e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |