{ "best_metric": 1.0, "best_model_checkpoint": "convnext-xlarge-224-22k-1k-v12-d-v_6_p2/checkpoint-27", "epoch": 3.0, "eval_steps": 500, "global_step": 27, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.9126984126984127, "eval_loss": 0.17189963161945343, "eval_runtime": 1.6572, "eval_samples_per_second": 76.032, "eval_steps_per_second": 2.414, "step": 9 }, { "epoch": 1.1111111111111112, "grad_norm": 28.37516975402832, "learning_rate": 3.541666666666667e-05, "loss": 0.3998, "step": 10 }, { "epoch": 2.0, "eval_accuracy": 0.9603174603174603, "eval_loss": 0.08088867366313934, "eval_runtime": 1.6511, "eval_samples_per_second": 76.313, "eval_steps_per_second": 2.423, "step": 18 }, { "epoch": 2.2222222222222223, "grad_norm": 20.384654998779297, "learning_rate": 1.4583333333333335e-05, "loss": 0.0664, "step": 20 }, { "epoch": 3.0, "eval_accuracy": 1.0, "eval_loss": 0.015638969838619232, "eval_runtime": 1.7069, "eval_samples_per_second": 73.818, "eval_steps_per_second": 2.343, "step": 27 }, { "epoch": 3.0, "step": 27, "total_flos": 1.0659509394418483e+18, "train_loss": 0.17736133325982978, "train_runtime": 184.7464, "train_samples_per_second": 18.349, "train_steps_per_second": 0.146 } ], "logging_steps": 10, "max_steps": 27, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 1.0659509394418483e+18, "train_batch_size": 32, "trial_name": null, "trial_params": null }