| { | |
| "best_metric": 0.0996587723493576, | |
| "best_model_checkpoint": "vit-large-patch16-224-new-dungeon-geo-morphs-009/checkpoint-30", | |
| "epoch": 26.666666666666668, | |
| "eval_steps": 10, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 17.004777908325195, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 1.1702, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "eval_accuracy": 0.94, | |
| "eval_loss": 0.5498571991920471, | |
| "eval_runtime": 0.7038, | |
| "eval_samples_per_second": 71.044, | |
| "eval_steps_per_second": 9.946, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 2.7007291316986084, | |
| "learning_rate": 1.5185185185185187e-05, | |
| "loss": 0.1925, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "eval_accuracy": 0.94, | |
| "eval_loss": 0.16446274518966675, | |
| "eval_runtime": 1.0453, | |
| "eval_samples_per_second": 47.831, | |
| "eval_steps_per_second": 6.696, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 0.15752829611301422, | |
| "learning_rate": 1.1481481481481482e-05, | |
| "loss": 0.0112, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.0996587723493576, | |
| "eval_runtime": 0.7964, | |
| "eval_samples_per_second": 62.782, | |
| "eval_steps_per_second": 8.789, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 0.05391625314950943, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.0011, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.12545597553253174, | |
| "eval_runtime": 0.6889, | |
| "eval_samples_per_second": 72.584, | |
| "eval_steps_per_second": 10.162, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 0.029494116082787514, | |
| "learning_rate": 4.074074074074074e-06, | |
| "loss": 0.0005, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.13129658997058868, | |
| "eval_runtime": 0.7146, | |
| "eval_samples_per_second": 69.972, | |
| "eval_steps_per_second": 9.796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 0.026276130229234695, | |
| "learning_rate": 3.7037037037037036e-07, | |
| "loss": 0.0004, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "eval_accuracy": 0.96, | |
| "eval_loss": 0.12384122610092163, | |
| "eval_runtime": 0.7523, | |
| "eval_samples_per_second": 66.461, | |
| "eval_steps_per_second": 9.305, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "step": 60, | |
| "total_flos": 5.259571802092339e+17, | |
| "train_loss": 0.22930119341860214, | |
| "train_runtime": 240.7204, | |
| "train_samples_per_second": 8.973, | |
| "train_steps_per_second": 0.249 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 60, | |
| "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": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.259571802092339e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |