| { | |
| "best_metric": 2.351407289505005, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.018040772145047807, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036081544290095615, | |
| "eval_loss": 2.921983242034912, | |
| "eval_runtime": 73.4498, | |
| "eval_samples_per_second": 15.888, | |
| "eval_steps_per_second": 3.976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036081544290095615, | |
| "grad_norm": 1.535165548324585, | |
| "learning_rate": 4.36e-05, | |
| "loss": 2.4652, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007216308858019123, | |
| "grad_norm": 1.88742196559906, | |
| "learning_rate": 8.72e-05, | |
| "loss": 2.3561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010824463287028685, | |
| "grad_norm": 1.9067068099975586, | |
| "learning_rate": 0.0001308, | |
| "loss": 2.2395, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014432617716038246, | |
| "grad_norm": 2.238699436187744, | |
| "learning_rate": 0.0001744, | |
| "loss": 2.1678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018040772145047807, | |
| "grad_norm": 4.385190963745117, | |
| "learning_rate": 0.000218, | |
| "loss": 2.1124, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018040772145047807, | |
| "eval_loss": 2.351407289505005, | |
| "eval_runtime": 73.4767, | |
| "eval_samples_per_second": 15.883, | |
| "eval_steps_per_second": 3.974, | |
| "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": 9711056163176448.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |