| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024622051509331756, | |
| "eval_steps": 50, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.5e-05, | |
| "loss": 5.161, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9e-05, | |
| "loss": 5.2417, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.5e-05, | |
| "loss": 5.2132, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8e-05, | |
| "loss": 5.1672, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.0757, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7e-05, | |
| "loss": 5.0972, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 5.2191, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6e-05, | |
| "loss": 5.1446, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 5.1846, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-05, | |
| "loss": 5.1827, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.5e-05, | |
| "loss": 4.9039, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4e-05, | |
| "loss": 5.0134, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.5e-05, | |
| "loss": 5.1791, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3e-05, | |
| "loss": 5.0575, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.5e-05, | |
| "loss": 5.0015, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2e-05, | |
| "loss": 5.0853, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5e-05, | |
| "loss": 5.0391, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 5.1997, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-06, | |
| "loss": 5.0387, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0, | |
| "loss": 4.8919, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1000, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 5225784115200000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |