| { | |
| "best_metric": 0.07812394201755524, | |
| "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-008/checkpoint-20", | |
| "epoch": 23.285714285714285, | |
| "eval_steps": 10, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 10.188948631286621, | |
| "learning_rate": 1.6774193548387098e-05, | |
| "loss": 0.6526, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_loss": 0.1925116628408432, | |
| "eval_runtime": 0.5168, | |
| "eval_samples_per_second": 69.66, | |
| "eval_steps_per_second": 9.675, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 13.285714285714286, | |
| "grad_norm": 0.3271343410015106, | |
| "learning_rate": 1.0322580645161291e-05, | |
| "loss": 0.0388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 13.285714285714286, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_loss": 0.07812394201755524, | |
| "eval_runtime": 0.5529, | |
| "eval_samples_per_second": 65.108, | |
| "eval_steps_per_second": 9.043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 19.857142857142858, | |
| "grad_norm": 0.0802752748131752, | |
| "learning_rate": 3.870967741935484e-06, | |
| "loss": 0.002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 19.857142857142858, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_loss": 0.0781446322798729, | |
| "eval_runtime": 0.5935, | |
| "eval_samples_per_second": 60.658, | |
| "eval_steps_per_second": 8.425, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 23.285714285714285, | |
| "step": 35, | |
| "total_flos": 3.068073182851891e+17, | |
| "train_loss": 0.1982296261404242, | |
| "train_runtime": 182.696, | |
| "train_samples_per_second": 9.579, | |
| "train_steps_per_second": 0.192 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 35, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.068073182851891e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |