{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.21079258010118043, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.345879896760937e-06, "loss": 1.4454, "step": 10 }, { "epoch": 0.01, "learning_rate": 5.6541201032390644e-06, "loss": 1.4588, "step": 20 }, { "epoch": 0.01, "learning_rate": 6.355406060132516e-06, "loss": 1.3719, "step": 30 }, { "epoch": 0.02, "learning_rate": 6.914575690124303e-06, "loss": 1.256, "step": 40 }, { "epoch": 0.02, "learning_rate": 7.345389165780057e-06, "loss": 1.2855, "step": 50 }, { "epoch": 0.03, "learning_rate": 7.663646266610644e-06, "loss": 1.3919, "step": 60 }, { "epoch": 0.03, "learning_rate": 7.963863644365277e-06, "loss": 1.404, "step": 70 }, { "epoch": 0.03, "learning_rate": 8.222815896602431e-06, "loss": 1.4293, "step": 80 }, { "epoch": 0.04, "learning_rate": 8.450488154497406e-06, "loss": 1.3077, "step": 90 }, { "epoch": 0.04, "learning_rate": 8.653629372258186e-06, "loss": 1.1747, "step": 100 }, { "epoch": 0.05, "learning_rate": 8.837015420566862e-06, "loss": 1.2659, "step": 110 }, { "epoch": 0.05, "learning_rate": 9.004150364012388e-06, "loss": 1.137, "step": 120 }, { "epoch": 0.05, "learning_rate": 9.157681445346895e-06, "loss": 1.0709, "step": 130 }, { "epoch": 0.06, "learning_rate": 9.299657503090295e-06, "loss": 1.021, "step": 140 }, { "epoch": 0.06, "learning_rate": 9.43169675964485e-06, "loss": 1.0298, "step": 150 }, { "epoch": 0.07, "learning_rate": 9.555099634066188e-06, "loss": 0.9256, "step": 160 }, { "epoch": 0.07, "learning_rate": 9.670926871527948e-06, "loss": 0.9835, "step": 170 }, { "epoch": 0.08, "learning_rate": 9.780055047302923e-06, "loss": 0.9704, "step": 180 }, { "epoch": 0.08, "learning_rate": 9.883216879176116e-06, "loss": 0.8905, "step": 190 }, { "epoch": 0.08, "learning_rate": 9.9714746460726e-06, "loss": 0.9926, "step": 200 }, { "epoch": 0.09, "learning_rate": 1e-05, "loss": 0.9701, "step": 210 }, { "epoch": 0.09, "learning_rate": 1e-05, "loss": 0.8021, "step": 220 }, { "epoch": 0.1, "learning_rate": 1e-05, "loss": 0.9571, "step": 230 }, { "epoch": 0.1, "learning_rate": 1e-05, "loss": 0.8937, "step": 240 }, { "epoch": 0.11, "learning_rate": 1e-05, "loss": 0.7971, "step": 250 }, { "epoch": 0.11, "learning_rate": 1e-05, "loss": 0.8399, "step": 260 }, { "epoch": 0.11, "learning_rate": 1e-05, "loss": 0.7557, "step": 270 }, { "epoch": 0.12, "learning_rate": 1e-05, "loss": 0.871, "step": 280 }, { "epoch": 0.12, "learning_rate": 1e-05, "loss": 0.9115, "step": 290 }, { "epoch": 0.13, "learning_rate": 1e-05, "loss": 0.8509, "step": 300 }, { "epoch": 0.13, "learning_rate": 1e-05, "loss": 0.7635, "step": 310 }, { "epoch": 0.13, "learning_rate": 1e-05, "loss": 0.8126, "step": 320 }, { "epoch": 0.14, "learning_rate": 1e-05, "loss": 0.7692, "step": 330 }, { "epoch": 0.14, "learning_rate": 1e-05, "loss": 0.8264, "step": 340 }, { "epoch": 0.15, "learning_rate": 1e-05, "loss": 0.8006, "step": 350 }, { "epoch": 0.15, "learning_rate": 1e-05, "loss": 0.7863, "step": 360 }, { "epoch": 0.16, "learning_rate": 1e-05, "loss": 0.7427, "step": 370 }, { "epoch": 0.16, "learning_rate": 1e-05, "loss": 0.7672, "step": 380 }, { "epoch": 0.16, "learning_rate": 1e-05, "loss": 0.7908, "step": 390 }, { "epoch": 0.17, "learning_rate": 1e-05, "loss": 0.758, "step": 400 }, { "epoch": 0.17, "learning_rate": 1e-05, "loss": 0.7599, "step": 410 }, { "epoch": 0.18, "learning_rate": 1e-05, "loss": 0.7805, "step": 420 }, { "epoch": 0.18, "learning_rate": 1e-05, "loss": 0.7353, "step": 430 }, { "epoch": 0.19, "learning_rate": 1e-05, "loss": 0.7634, "step": 440 }, { "epoch": 0.19, "learning_rate": 1e-05, "loss": 0.822, "step": 450 }, { "epoch": 0.19, "learning_rate": 1e-05, "loss": 0.7312, "step": 460 }, { "epoch": 0.2, "learning_rate": 1e-05, "loss": 0.827, "step": 470 }, { "epoch": 0.2, "learning_rate": 1e-05, "loss": 0.7295, "step": 480 }, { "epoch": 0.21, "learning_rate": 1e-05, "loss": 0.7707, "step": 490 }, { "epoch": 0.21, "learning_rate": 1e-05, "loss": 0.7604, "step": 500 } ], "logging_steps": 10, "max_steps": 10000, "num_train_epochs": 5, "save_steps": 500, "total_flos": 125136682352640.0, "trial_name": null, "trial_params": null }