| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6896551724137931, | |
| "eval_steps": 500, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9980267284282718e-05, | |
| "loss": 1.5581, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 1.555, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 1.5444, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 1.5254, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 1.5003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4763, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 1.4586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.12214747707527e-06, | |
| "loss": 1.4451, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.4448440074920654, | |
| "eval_runtime": 364.9267, | |
| "eval_samples_per_second": 63.328, | |
| "eval_steps_per_second": 0.992, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "step": 35, | |
| "total_flos": 9.151767518380032e+16, | |
| "train_loss": 1.5280099289757865, | |
| "train_runtime": 11248.8271, | |
| "train_samples_per_second": 18.479, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 9.151767518380032e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |