{ "best_metric": 0.27752024, "best_model_checkpoint": "/home/patrickbarker/output/qwen2-vl-7b-instruct/v6-20241217-211630/checkpoint-21", "epoch": 7.0, "eval_steps": 200, "global_step": 21, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "acc": 0.74467719, "epoch": 0.3333333333333333, "grad_norm": 55.43380029282607, "learning_rate": 0.0, "loss": 1.59800482, "memory(GiB)": 54.43, "step": 1, "train_speed(iter/s)": 0.023634 }, { "acc": 0.84537655, "epoch": 1.6666666666666665, "grad_norm": 29.87643905463888, "learning_rate": 9.397429019156841e-06, "loss": 0.94584751, "memory(GiB)": 73.87, "step": 5, "train_speed(iter/s)": 0.030329 }, { "acc": 0.8904459, "epoch": 3.3333333333333335, "grad_norm": 17.143445492807736, "learning_rate": 6.2278046929604265e-06, "loss": 0.61749249, "memory(GiB)": 73.87, "step": 10, "train_speed(iter/s)": 0.031584 }, { "acc": 0.92681417, "epoch": 5.0, "grad_norm": 6.080266576328639, "learning_rate": 2.266032683466926e-06, "loss": 0.3995486, "memory(GiB)": 73.87, "step": 15, "train_speed(iter/s)": 0.032115 }, { "acc": 0.94627581, "epoch": 6.666666666666667, "grad_norm": 4.274402198449314, "learning_rate": 6.918666363808976e-08, "loss": 0.29283824, "memory(GiB)": 73.87, "step": 20, "train_speed(iter/s)": 0.032329 }, { "epoch": 7.0, "eval_acc": 0.8805031446540881, "eval_loss": 0.27752023935317993, "eval_runtime": 5.1006, "eval_samples_per_second": 0.98, "eval_steps_per_second": 0.196, "step": 21 } ], "logging_steps": 5, "max_steps": 21, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 48727043735552.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }