{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.20151133501259447, "eval_steps": 500, "global_step": 180, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00559753708368318, "grad_norm": 1.2421875, "learning_rate": 0.0001, "loss": 4.5193, "step": 5 }, { "epoch": 0.01119507416736636, "grad_norm": 0.68359375, "learning_rate": 0.0001, "loss": 2.8387, "step": 10 }, { "epoch": 0.016792611251049538, "grad_norm": 0.484375, "learning_rate": 0.0001, "loss": 2.1966, "step": 15 }, { "epoch": 0.02239014833473272, "grad_norm": 0.51953125, "learning_rate": 0.0001, "loss": 2.0024, "step": 20 }, { "epoch": 0.027987685418415897, "grad_norm": 0.296875, "learning_rate": 0.0001, "loss": 1.7735, "step": 25 }, { "epoch": 0.033585222502099076, "grad_norm": 0.263671875, "learning_rate": 0.0001, "loss": 1.6781, "step": 30 }, { "epoch": 0.039182759585782254, "grad_norm": 0.291015625, "learning_rate": 0.0001, "loss": 1.6619, "step": 35 }, { "epoch": 0.04478029666946544, "grad_norm": 0.3125, "learning_rate": 0.0001, "loss": 1.6361, "step": 40 }, { "epoch": 0.05037783375314862, "grad_norm": 0.298828125, "learning_rate": 0.0001, "loss": 1.6153, "step": 45 }, { "epoch": 0.055975370836831795, "grad_norm": 0.306640625, "learning_rate": 0.0001, "loss": 1.5201, "step": 50 }, { "epoch": 0.06157290792051497, "grad_norm": 0.296875, "learning_rate": 0.0001, "loss": 1.5211, "step": 55 }, { "epoch": 0.06717044500419815, "grad_norm": 0.2392578125, "learning_rate": 0.0001, "loss": 1.5359, "step": 60 }, { "epoch": 0.07276798208788134, "grad_norm": 0.251953125, "learning_rate": 0.0001, "loss": 1.5686, "step": 65 }, { "epoch": 0.07836551917156451, "grad_norm": 0.255859375, "learning_rate": 0.0001, "loss": 1.5732, "step": 70 }, { "epoch": 0.08396305625524769, "grad_norm": 0.244140625, "learning_rate": 0.0001, "loss": 1.5958, "step": 75 }, { "epoch": 0.08956059333893088, "grad_norm": 0.25390625, "learning_rate": 0.0001, "loss": 1.5006, "step": 80 }, { "epoch": 0.09515813042261405, "grad_norm": 0.2890625, "learning_rate": 0.0001, "loss": 1.5051, "step": 85 }, { "epoch": 0.10075566750629723, "grad_norm": 0.314453125, "learning_rate": 0.0001, "loss": 1.5649, "step": 90 }, { "epoch": 0.1063532045899804, "grad_norm": 0.263671875, "learning_rate": 0.0001, "loss": 1.5, "step": 95 }, { "epoch": 0.11195074167366359, "grad_norm": 0.310546875, "learning_rate": 0.0001, "loss": 1.4951, "step": 100 }, { "epoch": 0.11754827875734676, "grad_norm": 0.2412109375, "learning_rate": 0.0001, "loss": 1.5258, "step": 105 }, { "epoch": 0.12314581584102995, "grad_norm": 0.2236328125, "learning_rate": 0.0001, "loss": 1.556, "step": 110 }, { "epoch": 0.12874335292471312, "grad_norm": 0.1982421875, "learning_rate": 0.0001, "loss": 1.5306, "step": 115 }, { "epoch": 0.1343408900083963, "grad_norm": 0.203125, "learning_rate": 0.0001, "loss": 1.4242, "step": 120 }, { "epoch": 0.1399384270920795, "grad_norm": 0.2216796875, "learning_rate": 0.0001, "loss": 1.4403, "step": 125 }, { "epoch": 0.14553596417576267, "grad_norm": 0.2265625, "learning_rate": 0.0001, "loss": 1.4604, "step": 130 }, { "epoch": 0.15113350125944586, "grad_norm": 0.2275390625, "learning_rate": 0.0001, "loss": 1.5809, "step": 135 }, { "epoch": 0.15673103834312901, "grad_norm": 0.2421875, "learning_rate": 0.0001, "loss": 1.4282, "step": 140 }, { "epoch": 0.1623285754268122, "grad_norm": 0.228515625, "learning_rate": 0.0001, "loss": 1.5452, "step": 145 }, { "epoch": 0.16792611251049538, "grad_norm": 0.359375, "learning_rate": 0.0001, "loss": 1.3127, "step": 150 }, { "epoch": 0.17352364959417857, "grad_norm": 0.46875, "learning_rate": 0.0001, "loss": 1.5287, "step": 155 }, { "epoch": 0.17912118667786175, "grad_norm": 0.28515625, "learning_rate": 0.0001, "loss": 1.5197, "step": 160 }, { "epoch": 0.1847187237615449, "grad_norm": 0.201171875, "learning_rate": 0.0001, "loss": 1.5512, "step": 165 }, { "epoch": 0.1903162608452281, "grad_norm": 0.2490234375, "learning_rate": 0.0001, "loss": 1.4973, "step": 170 }, { "epoch": 0.19591379792891128, "grad_norm": 0.220703125, "learning_rate": 0.0001, "loss": 1.503, "step": 175 }, { "epoch": 0.20151133501259447, "grad_norm": 0.2080078125, "learning_rate": 0.0001, "loss": 1.4571, "step": 180 } ], "logging_steps": 5, "max_steps": 450, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 90, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.8132901640749056e+17, "train_batch_size": 4, "trial_name": null, "trial_params": null }