{ "best_metric": 0.2485116571187973, "best_model_checkpoint": "finetuned-ai-real-swin/checkpoint-50", "epoch": 3.0, "eval_steps": 50, "global_step": 66, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.45454545454545453, "grad_norm": 0.09391414374113083, "learning_rate": 0.0001787878787878788, "loss": 0.7516, "step": 10 }, { "epoch": 0.9090909090909091, "grad_norm": 0.2578066289424896, "learning_rate": 0.00014848484848484849, "loss": 0.0201, "step": 20 }, { "epoch": 1.3636363636363638, "grad_norm": 0.00015799676475580782, "learning_rate": 0.0001181818181818182, "loss": 0.0052, "step": 30 }, { "epoch": 1.8181818181818183, "grad_norm": 1.3355179362406489e-05, "learning_rate": 8.787878787878789e-05, "loss": 0.0149, "step": 40 }, { "epoch": 2.2727272727272725, "grad_norm": 1.1458600759506226, "learning_rate": 5.757575757575758e-05, "loss": 0.0141, "step": 50 }, { "epoch": 2.2727272727272725, "eval_accuracy": 0.9752066115702479, "eval_loss": 0.2485116571187973, "eval_runtime": 1.6634, "eval_samples_per_second": 72.74, "eval_steps_per_second": 9.619, "step": 50 }, { "epoch": 2.7272727272727275, "grad_norm": 0.00010308358469046652, "learning_rate": 2.7272727272727273e-05, "loss": 0.0159, "step": 60 }, { "epoch": 3.0, "step": 66, "total_flos": 1.5982493348118528e+17, "train_loss": 0.12485574473711578, "train_runtime": 55.5816, "train_samples_per_second": 36.703, "train_steps_per_second": 1.187 } ], "logging_steps": 10, "max_steps": 66, "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": true }, "attributes": {} } }, "total_flos": 1.5982493348118528e+17, "train_batch_size": 32, "trial_name": null, "trial_params": null }