{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.764705882352941, "eval_steps": 25, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.47058823529411764, "grad_norm": 1.1788485050201416, "learning_rate": 0.000175, "loss": 9.5575, "step": 1 }, { "epoch": 0.9411764705882353, "grad_norm": 1.1715633869171143, "learning_rate": 0.00015000000000000001, "loss": 9.4221, "step": 2 }, { "epoch": 1.4117647058823528, "grad_norm": 1.1546883583068848, "learning_rate": 0.000125, "loss": 9.2273, "step": 3 }, { "epoch": 1.8823529411764706, "grad_norm": 1.3188244104385376, "learning_rate": 0.0001, "loss": 8.9961, "step": 4 }, { "epoch": 2.3529411764705883, "grad_norm": 1.6398780345916748, "learning_rate": 7.500000000000001e-05, "loss": 8.8139, "step": 5 }, { "epoch": 2.8235294117647056, "grad_norm": 1.7775518894195557, "learning_rate": 5e-05, "loss": 8.6995, "step": 6 }, { "epoch": 3.2941176470588234, "grad_norm": 2.1554720401763916, "learning_rate": 2.5e-05, "loss": 8.4987, "step": 7 }, { "epoch": 3.764705882352941, "grad_norm": 2.2282097339630127, "learning_rate": 0.0, "loss": 8.4292, "step": 8 }, { "epoch": 3.764705882352941, "step": 8, "total_flos": 3464493556500.0, "train_loss": 8.955539345741272, "train_runtime": 43.815, "train_samples_per_second": 3.013, "train_steps_per_second": 0.183 } ], "logging_steps": 1.0, "max_steps": 8, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3464493556500.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }