{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.05, "global_step": 50000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2.0000000000000003e-06, "loss": 6.7042, "step": 1000 }, { "epoch": 0.0, "learning_rate": 4.000000000000001e-06, "loss": 5.1179, "step": 2000 }, { "epoch": 0.0, "learning_rate": 6e-06, "loss": 4.5505, "step": 3000 }, { "epoch": 0.0, "learning_rate": 8.000000000000001e-06, "loss": 4.3111, "step": 4000 }, { "epoch": 0.01, "learning_rate": 1e-05, "loss": 4.0888, "step": 5000 }, { "epoch": 0.01, "learning_rate": 1.2e-05, "loss": 3.9555, "step": 6000 }, { "epoch": 0.01, "learning_rate": 1.4000000000000001e-05, "loss": 3.8349, "step": 7000 }, { "epoch": 0.01, "learning_rate": 1.6000000000000003e-05, "loss": 3.8199, "step": 8000 }, { "epoch": 0.01, "learning_rate": 1.8e-05, "loss": 3.6237, "step": 9000 }, { "epoch": 0.01, "learning_rate": 2e-05, "loss": 3.7137, "step": 10000 }, { "epoch": 0.01, "learning_rate": 2.2000000000000003e-05, "loss": 3.5308, "step": 11000 }, { "epoch": 0.01, "learning_rate": 2.4e-05, "loss": 3.3471, "step": 12000 }, { "epoch": 0.01, "learning_rate": 2.6000000000000002e-05, "loss": 3.2095, "step": 13000 }, { "epoch": 0.01, "learning_rate": 2.8000000000000003e-05, "loss": 3.1049, "step": 14000 }, { "epoch": 0.01, "learning_rate": 3e-05, "loss": 2.9958, "step": 15000 }, { "epoch": 0.02, "learning_rate": 3.2000000000000005e-05, "loss": 2.8518, "step": 16000 }, { "epoch": 0.02, "learning_rate": 3.4000000000000007e-05, "loss": 2.7929, "step": 17000 }, { "epoch": 0.02, "learning_rate": 3.6e-05, "loss": 2.6958, "step": 18000 }, { "epoch": 0.02, "learning_rate": 3.8e-05, "loss": 2.7341, "step": 19000 }, { "epoch": 0.02, "learning_rate": 4e-05, "loss": 2.6605, "step": 20000 }, { "epoch": 0.02, "learning_rate": 4.2e-05, "loss": 2.5796, "step": 21000 }, { "epoch": 0.02, "learning_rate": 4.4000000000000006e-05, "loss": 2.499, "step": 22000 }, { "epoch": 0.02, "learning_rate": 4.600000000000001e-05, "loss": 2.4217, "step": 23000 }, { "epoch": 0.02, "learning_rate": 4.8e-05, "loss": 2.285, "step": 24000 }, { "epoch": 0.03, "learning_rate": 5e-05, "loss": 2.2433, "step": 25000 }, { "epoch": 0.03, "learning_rate": 5.2000000000000004e-05, "loss": 1.8565, "step": 26000 }, { "epoch": 0.03, "learning_rate": 5.4000000000000005e-05, "loss": 1.6906, "step": 27000 }, { "epoch": 0.03, "learning_rate": 5.6000000000000006e-05, "loss": 1.6053, "step": 28000 }, { "epoch": 0.03, "learning_rate": 5.8e-05, "loss": 1.5208, "step": 29000 }, { "epoch": 0.03, "learning_rate": 6e-05, "loss": 1.4884, "step": 30000 }, { "epoch": 0.03, "learning_rate": 6.2e-05, "loss": 1.4536, "step": 31000 }, { "epoch": 0.03, "learning_rate": 6.400000000000001e-05, "loss": 1.4163, "step": 32000 }, { "epoch": 0.03, "learning_rate": 6.6e-05, "loss": 1.3619, "step": 33000 }, { "epoch": 0.03, "learning_rate": 6.800000000000001e-05, "loss": 1.3432, "step": 34000 }, { "epoch": 0.04, "learning_rate": 7e-05, "loss": 1.3435, "step": 35000 }, { "epoch": 0.04, "learning_rate": 7.2e-05, "loss": 1.3395, "step": 36000 }, { "epoch": 0.04, "learning_rate": 7.4e-05, "loss": 1.3372, "step": 37000 }, { "epoch": 0.04, "learning_rate": 7.6e-05, "loss": 1.3257, "step": 38000 }, { "epoch": 0.04, "learning_rate": 7.800000000000001e-05, "loss": 1.2969, "step": 39000 }, { "epoch": 0.04, "learning_rate": 8e-05, "loss": 1.2716, "step": 40000 }, { "epoch": 0.04, "learning_rate": 8.2e-05, "loss": 1.2637, "step": 41000 }, { "epoch": 0.04, "learning_rate": 8.4e-05, "loss": 1.2254, "step": 42000 }, { "epoch": 0.04, "learning_rate": 8.6e-05, "loss": 1.257, "step": 43000 }, { "epoch": 0.04, "learning_rate": 8.800000000000001e-05, "loss": 1.2555, "step": 44000 }, { "epoch": 0.04, "learning_rate": 9e-05, "loss": 1.258, "step": 45000 }, { "epoch": 0.05, "learning_rate": 9.200000000000001e-05, "loss": 1.2429, "step": 46000 }, { "epoch": 0.05, "learning_rate": 9.4e-05, "loss": 1.2297, "step": 47000 }, { "epoch": 0.05, "learning_rate": 9.6e-05, "loss": 1.2281, "step": 48000 }, { "epoch": 0.05, "learning_rate": 9.8e-05, "loss": 1.1976, "step": 49000 }, { "epoch": 0.05, "learning_rate": 0.0001, "loss": 1.193, "step": 50000 }, { "epoch": 0.05, "eval_loss": 0.6851979494094849, "eval_runtime": 114.3167, "eval_samples_per_second": 43.738, "eval_steps_per_second": 0.691, "step": 50000 } ], "max_steps": 1000000, "num_train_epochs": 9223372036854775807, "total_flos": 2.9834386341888e+18, "trial_name": null, "trial_params": null }