| { | |
| "best_metric": 0.8010535836219788, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.021197668256491786, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021197668256491787, | |
| "eval_loss": 1.146639108657837, | |
| "eval_runtime": 116.7748, | |
| "eval_samples_per_second": 3.408, | |
| "eval_steps_per_second": 0.856, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006359300476947536, | |
| "grad_norm": 0.7560529708862305, | |
| "learning_rate": 0.00012, | |
| "loss": 4.3738, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010598834128245893, | |
| "eval_loss": 1.0721842050552368, | |
| "eval_runtime": 120.2006, | |
| "eval_samples_per_second": 3.311, | |
| "eval_steps_per_second": 0.832, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012718600953895072, | |
| "grad_norm": 0.9589040279388428, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 4.1859, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019077901430842606, | |
| "grad_norm": 0.9749143719673157, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 3.6312, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021197668256491786, | |
| "eval_loss": 0.8010535836219788, | |
| "eval_runtime": 120.0012, | |
| "eval_samples_per_second": 3.317, | |
| "eval_steps_per_second": 0.833, | |
| "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": 1.306929288708096e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |