| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998882806390348, | |
| "global_step": 4475, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6919, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6575, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6454, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6269, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6225, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6239, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6038, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5e-06, | |
| "loss": 2.6016, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 4475, | |
| "total_flos": 2.3326754909779395e+18, | |
| "train_runtime": 42410.7529, | |
| "train_samples_per_second": 0.106 | |
| } | |
| ], | |
| "max_steps": 4475, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.3326754909779395e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |