{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.7178106774338269, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.07178106774338268, "grad_norm": 0.46034833788871765, "learning_rate": 2.380952380952381e-06, "loss": 1.2735, "step": 10 }, { "epoch": 0.14356213548676536, "grad_norm": 0.17795707285404205, "learning_rate": 4.761904761904762e-06, "loss": 0.9311, "step": 20 }, { "epoch": 0.21534320323014805, "grad_norm": 0.07722567766904831, "learning_rate": 7.1428571428571436e-06, "loss": 0.7258, "step": 30 }, { "epoch": 0.2871242709735307, "grad_norm": 0.058059412986040115, "learning_rate": 9.523809523809525e-06, "loss": 0.6562, "step": 40 }, { "epoch": 0.35890533871691344, "grad_norm": 0.05688474327325821, "learning_rate": 9.786666666666667e-06, "loss": 0.6236, "step": 50 }, { "epoch": 0.4306864064602961, "grad_norm": 0.0652860477566719, "learning_rate": 9.52e-06, "loss": 0.6011, "step": 60 }, { "epoch": 0.5024674742036788, "grad_norm": 0.09465105831623077, "learning_rate": 9.253333333333333e-06, "loss": 0.5775, "step": 70 }, { "epoch": 0.5742485419470614, "grad_norm": 0.16655535995960236, "learning_rate": 8.986666666666666e-06, "loss": 0.5588, "step": 80 }, { "epoch": 0.6460296096904441, "grad_norm": 0.11725710332393646, "learning_rate": 8.720000000000001e-06, "loss": 0.537, "step": 90 }, { "epoch": 0.7178106774338269, "grad_norm": 0.044058505445718765, "learning_rate": 8.453333333333334e-06, "loss": 0.5187, "step": 100 } ], "logging_steps": 10, "max_steps": 417, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.6785962973462528e+17, "train_batch_size": 14, "trial_name": null, "trial_params": null }