| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.7391304347826086, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4856, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 1.4885, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 1.458, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.4399, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 1.474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 1.4138, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 1.3794, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 1.3599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 1.343, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0, | |
| "loss": 1.3461, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "step": 10, | |
| "total_flos": 269101715816448.0, | |
| "train_loss": 1.4188124775886535, | |
| "train_runtime": 11.4392, | |
| "train_samples_per_second": 127.106, | |
| "train_steps_per_second": 0.874 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 10, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 269101715816448.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |