| { |
| "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 |
| } |
|
|
