| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09984871406959153, | |
| "eval_steps": 100, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.030257186081694403, | |
| "grad_norm": 18.3522235886847, | |
| "learning_rate": 1.796093065705644e-05, | |
| "loss": 6.8937, | |
| "mean_token_accuracy": 0.1434693343937397, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.060514372163388806, | |
| "grad_norm": 10.614870433655174, | |
| "learning_rate": 8.382180034472353e-06, | |
| "loss": 5.3195, | |
| "mean_token_accuracy": 0.1919048972427845, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0907715582450832, | |
| "grad_norm": 7.571339027683935, | |
| "learning_rate": 5.234682881719766e-07, | |
| "loss": 4.707, | |
| "mean_token_accuracy": 0.23758598268032075, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09984871406959153, | |
| "mean_token_accuracy": 0.24127203722794852, | |
| "step": 33, | |
| "total_flos": 541940076511232.0, | |
| "train_loss": 5.546875, | |
| "train_runtime": 36.3584, | |
| "train_samples_per_second": 29.074, | |
| "train_steps_per_second": 0.908 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 541940076511232.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |