| { | |
| "best_metric": 0.0719214677810669, | |
| "best_model_checkpoint": "vit-large-patch16-224-dungeon-geo-morphs-005/checkpoint-30", | |
| "epoch": 19.857142857142858, | |
| "eval_steps": 10, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.571428571428571, | |
| "grad_norm": 8.417182922363281, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.582, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.571428571428571, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_loss": 0.1846093088388443, | |
| "eval_runtime": 0.5165, | |
| "eval_samples_per_second": 69.702, | |
| "eval_steps_per_second": 9.681, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 13.285714285714286, | |
| "grad_norm": 0.3049335479736328, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0293, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 13.285714285714286, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_loss": 0.0765586718916893, | |
| "eval_runtime": 0.7074, | |
| "eval_samples_per_second": 50.89, | |
| "eval_steps_per_second": 7.068, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 19.857142857142858, | |
| "grad_norm": 0.10486782342195511, | |
| "learning_rate": 0.0, | |
| "loss": 0.0021, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 19.857142857142858, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_loss": 0.0719214677810669, | |
| "eval_runtime": 0.5559, | |
| "eval_samples_per_second": 64.756, | |
| "eval_steps_per_second": 8.994, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 19.857142857142858, | |
| "step": 30, | |
| "total_flos": 2.6297770138730496e+17, | |
| "train_loss": 0.20446500703692436, | |
| "train_runtime": 171.6149, | |
| "train_samples_per_second": 8.741, | |
| "train_steps_per_second": 0.175 | |
| } | |
| ], | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6297770138730496e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |