| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.18078074685046042, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.009039037342523022, |
| "grad_norm": 7.855499744415283, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 1.4181, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.018078074685046044, |
| "grad_norm": 3.3778610229492188, |
| "learning_rate": 1.2666666666666669e-06, |
| "loss": 1.2494, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.027117112027569064, |
| "grad_norm": 2.6225311756134033, |
| "learning_rate": 1.9333333333333336e-06, |
| "loss": 1.0602, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03615614937009209, |
| "grad_norm": 1.594939112663269, |
| "learning_rate": 2.6e-06, |
| "loss": 0.9123, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.045195186712615104, |
| "grad_norm": 0.9766483902931213, |
| "learning_rate": 3.266666666666667e-06, |
| "loss": 0.7841, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05423422405513813, |
| "grad_norm": 0.43368658423423767, |
| "learning_rate": 3.9333333333333335e-06, |
| "loss": 0.6803, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06327326139766115, |
| "grad_norm": 0.49014410376548767, |
| "learning_rate": 4.600000000000001e-06, |
| "loss": 0.5921, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.07231229874018417, |
| "grad_norm": 0.46368488669395447, |
| "learning_rate": 5.2666666666666665e-06, |
| "loss": 0.6214, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0813513360827072, |
| "grad_norm": 0.46477940678596497, |
| "learning_rate": 5.933333333333335e-06, |
| "loss": 0.6157, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.09039037342523021, |
| "grad_norm": 0.4853752553462982, |
| "learning_rate": 6.600000000000001e-06, |
| "loss": 0.6628, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09942941076775323, |
| "grad_norm": 0.36940082907676697, |
| "learning_rate": 7.266666666666668e-06, |
| "loss": 0.5775, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.10846844811027626, |
| "grad_norm": 0.34785982966423035, |
| "learning_rate": 7.933333333333334e-06, |
| "loss": 0.6343, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.11750748545279928, |
| "grad_norm": 0.4787227511405945, |
| "learning_rate": 8.6e-06, |
| "loss": 0.6016, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.1265465227953223, |
| "grad_norm": 0.4643513262271881, |
| "learning_rate": 9.266666666666667e-06, |
| "loss": 0.6388, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.1355855601378453, |
| "grad_norm": 0.384676456451416, |
| "learning_rate": 9.933333333333334e-06, |
| "loss": 0.5895, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.14462459748036835, |
| "grad_norm": 0.4324859380722046, |
| "learning_rate": 9.99991503499922e-06, |
| "loss": 0.5942, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.15366363482289136, |
| "grad_norm": 0.41830965876579285, |
| "learning_rate": 9.99962133253095e-06, |
| "loss": 0.6121, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.1627026721654144, |
| "grad_norm": 0.3795354962348938, |
| "learning_rate": 9.999117855964797e-06, |
| "loss": 0.6041, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.1717417095079374, |
| "grad_norm": 0.28756389021873474, |
| "learning_rate": 9.998404626425627e-06, |
| "loss": 0.5529, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.18078074685046042, |
| "grad_norm": 0.40732458233833313, |
| "learning_rate": 9.997481673839125e-06, |
| "loss": 0.6321, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 5000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.364669860258202e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
