| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1779, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 2.1520326137542725, | |
| "eval_runtime": 452.4776, | |
| "eval_samples_per_second": 0.643, | |
| "eval_steps_per_second": 0.643, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1108, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.097604990005493, | |
| "eval_runtime": 452.1046, | |
| "eval_samples_per_second": 0.644, | |
| "eval_steps_per_second": 0.644, | |
| "step": 20 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.541392224485376e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |