| { | |
| "best_metric": 0.014940645545721054, | |
| "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-003/checkpoint-30", | |
| "epoch": 20.0, | |
| "eval_steps": 10, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 16.259380340576172, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 0.8585, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.22037966549396515, | |
| "eval_runtime": 0.4272, | |
| "eval_samples_per_second": 70.221, | |
| "eval_steps_per_second": 9.363, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 11.522974014282227, | |
| "learning_rate": 8.148148148148148e-06, | |
| "loss": 0.2115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0530446358025074, | |
| "eval_runtime": 0.4534, | |
| "eval_samples_per_second": 66.17, | |
| "eval_steps_per_second": 8.823, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.805919885635376, | |
| "learning_rate": 7.407407407407407e-07, | |
| "loss": 0.0562, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.014940645545721054, | |
| "eval_runtime": 0.4826, | |
| "eval_samples_per_second": 62.163, | |
| "eval_steps_per_second": 8.288, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 30, | |
| "total_flos": 2.5749899927506944e+17, | |
| "train_loss": 0.3753979325294495, | |
| "train_runtime": 261.4196, | |
| "train_samples_per_second": 5.394, | |
| "train_steps_per_second": 0.115 | |
| } | |
| ], | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5749899927506944e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |