| { | |
| "best_metric": 2.153864622116089, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.012070006035003017, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024140012070006034, | |
| "eval_loss": 2.989262819290161, | |
| "eval_runtime": 100.8385, | |
| "eval_samples_per_second": 17.305, | |
| "eval_steps_per_second": 4.334, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024140012070006035, | |
| "grad_norm": 5.14186954498291, | |
| "learning_rate": 4.36e-05, | |
| "loss": 2.1011, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004828002414001207, | |
| "grad_norm": 7.176346778869629, | |
| "learning_rate": 8.72e-05, | |
| "loss": 2.2516, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00724200362100181, | |
| "grad_norm": 6.447731971740723, | |
| "learning_rate": 0.0001308, | |
| "loss": 2.0652, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009656004828002414, | |
| "grad_norm": 6.7839179039001465, | |
| "learning_rate": 0.0001744, | |
| "loss": 2.0828, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012070006035003017, | |
| "grad_norm": 7.772573947906494, | |
| "learning_rate": 0.000218, | |
| "loss": 2.3877, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012070006035003017, | |
| "eval_loss": 2.153864622116089, | |
| "eval_runtime": 100.9581, | |
| "eval_samples_per_second": 17.284, | |
| "eval_steps_per_second": 4.329, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 8315603622297600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |