{ "best_metric": 0.06769324094057083, "best_model_checkpoint": "clip_base_4a_aug/checkpoint-1125", "epoch": 3.0, "eval_steps": 500, "global_step": 1125, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.9677083333333333, "eval_loss": 0.08766181766986847, "eval_runtime": 236.1218, "eval_samples_per_second": 101.642, "eval_steps_per_second": 1.588, "step": 375 }, { "epoch": 1.3333333333333333, "grad_norm": 15.12252140045166, "learning_rate": 5.813953488372093e-07, "loss": 0.1764, "step": 500 }, { "epoch": 2.0, "eval_accuracy": 0.973, "eval_loss": 0.07185973972082138, "eval_runtime": 104.3493, "eval_samples_per_second": 229.997, "eval_steps_per_second": 3.594, "step": 750 }, { "epoch": 2.6666666666666665, "grad_norm": 13.257657051086426, "learning_rate": 1.1627906976744186e-07, "loss": 0.0644, "step": 1000 }, { "epoch": 3.0, "eval_accuracy": 0.975, "eval_loss": 0.06769324094057083, "eval_runtime": 104.5633, "eval_samples_per_second": 229.526, "eval_steps_per_second": 3.586, "step": 1125 } ], "logging_steps": 500, "max_steps": 1125, "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": 2.273880039240499e+19, "train_batch_size": 256, "trial_name": null, "trial_params": null }