{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 1000, "global_step": 819, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1221001221001221, "grad_norm": 1.2653954029083252, "learning_rate": 1.9273274812612557e-05, "loss": 0.7694, "step": 100 }, { "epoch": 0.2442002442002442, "grad_norm": 2.224886417388916, "learning_rate": 1.7198725150046886e-05, "loss": 0.6902, "step": 200 }, { "epoch": 0.3663003663003663, "grad_norm": 2.236462354660034, "learning_rate": 1.4077876510757502e-05, "loss": 0.682, "step": 300 }, { "epoch": 0.4884004884004884, "grad_norm": 3.3600499629974365, "learning_rate": 1.0364328757183504e-05, "loss": 0.6664, "step": 400 }, { "epoch": 0.6105006105006106, "grad_norm": 3.620539426803589, "learning_rate": 6.597827626742537e-06, "loss": 0.6666, "step": 500 }, { "epoch": 0.7326007326007326, "grad_norm": 2.775991916656494, "learning_rate": 3.325815367397557e-06, "loss": 0.6593, "step": 600 }, { "epoch": 0.8547008547008547, "grad_norm": 3.9067025184631348, "learning_rate": 1.0238627236098619e-06, "loss": 0.6638, "step": 700 }, { "epoch": 0.9768009768009768, "grad_norm": 2.6926493644714355, "learning_rate": 2.654708866217548e-08, "loss": 0.6488, "step": 800 }, { "epoch": 1.0, "step": 819, "total_flos": 0.0, "train_loss": 0.678250733167115, "train_runtime": 2802.1852, "train_samples_per_second": 2.337, "train_steps_per_second": 0.292 } ], "logging_steps": 100, "max_steps": 819, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 0.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }