| { | |
| "best_metric": 0.48243218660354614, | |
| "best_model_checkpoint": "vit-large-patch16-224-new-dungeon-geo-morphs-015/checkpoint-30", | |
| "epoch": 24.0, | |
| "eval_steps": 10, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 3.838964858005056e-06, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.4951287508010864, | |
| "eval_runtime": 0.7888, | |
| "eval_samples_per_second": 63.385, | |
| "eval_steps_per_second": 5.071, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 3.4401218726998195e-06, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.4892917275428772, | |
| "eval_runtime": 0.7852, | |
| "eval_samples_per_second": 63.68, | |
| "eval_steps_per_second": 5.094, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 3.4685783703025663e-06, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.48243218660354614, | |
| "eval_runtime": 0.8586, | |
| "eval_samples_per_second": 58.234, | |
| "eval_steps_per_second": 4.659, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "step": 30, | |
| "total_flos": 4.733614621883105e+17, | |
| "train_loss": 2.570450305938721e-08, | |
| "train_runtime": 320.776, | |
| "train_samples_per_second": 6.734, | |
| "train_steps_per_second": 0.094 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.733614621883105e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |