| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.666666666666666, | |
| "eval_steps": 500, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019805941782534764, | |
| "loss": 2.2515, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00019605881764529358, | |
| "loss": 2.2515, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00019405821746523957, | |
| "loss": 2.2204, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00019205761728518557, | |
| "loss": 2.1854, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00019005701710513156, | |
| "loss": 2.1461, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00018805641692507753, | |
| "loss": 2.1013, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.00018605581674502352, | |
| "loss": 2.0539, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.00018405521656496952, | |
| "loss": 2.0019, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00018205461638491548, | |
| "loss": 1.9467, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00018005401620486148, | |
| "loss": 1.887, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.00017805341602480744, | |
| "loss": 1.8227, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.00017605281584475344, | |
| "loss": 1.7543, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.00017405221566469943, | |
| "loss": 1.682, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 0.00017205161548464542, | |
| "loss": 1.6024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00017005101530459136, | |
| "loss": 1.5171, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.00016805041512453736, | |
| "loss": 1.4308, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 0.00016604981494448335, | |
| "loss": 1.3407, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00016404921476442935, | |
| "loss": 1.2479, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.0001620486145843753, | |
| "loss": 1.1525, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 0.0001600480144043213, | |
| "loss": 1.0553, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 0.0001580474142242673, | |
| "loss": 0.9591, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 0.00015604681404421327, | |
| "loss": 0.8655, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.00015404621386415926, | |
| "loss": 0.7722, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 0.00015204561368410523, | |
| "loss": 0.6823, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 0.00015004501350405122, | |
| "loss": 0.5956, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.00014804441332399721, | |
| "loss": 0.5104, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 0.0001460438131439432, | |
| "loss": 0.4314, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 0.00014404321296388918, | |
| "loss": 0.359, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 0.00014204261278383514, | |
| "loss": 0.2952, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.00014004201260378114, | |
| "loss": 0.2375, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 0.00013804141242372713, | |
| "loss": 0.1853, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 0.00013604081224367312, | |
| "loss": 0.1398, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 0.0001340402120636191, | |
| "loss": 0.1033, | |
| "step": 33 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 1.38542793652224e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |