| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.4628, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 1.6203, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.9516, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.9485, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.906, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.7973, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 0.6553, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.795, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 10, | |
| "total_flos": 3104932303470592.0, | |
| "train_loss": 1.0743137300014496, | |
| "train_runtime": 58.1517, | |
| "train_samples_per_second": 2.648, | |
| "train_steps_per_second": 0.172 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50000, | |
| "total_flos": 3104932303470592.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |