| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 22.516803741455078, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 9.6314, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.688298225402832, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 5.1075, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 19.711145401000977, | |
| "learning_rate": 0.0001, | |
| "loss": 8.2415, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.4154276847839355, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.5098, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 25.797412872314453, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 7.5803, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.132017135620117, | |
| "learning_rate": 0.0, | |
| "loss": 4.3452, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 12, | |
| "total_flos": 25094075608584.0, | |
| "train_loss": 6.569292863210042, | |
| "train_runtime": 89.1968, | |
| "train_samples_per_second": 2.242, | |
| "train_steps_per_second": 0.135 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 25094075608584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |