| { | |
| "best_metric": 0.8701333333333333, | |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0340/checkpoints/checkpoint-1332", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1332, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.24325436353683472, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6502, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8448, | |
| "eval_loss": 0.5524691939353943, | |
| "eval_runtime": 5.9896, | |
| "eval_samples_per_second": 626.081, | |
| "eval_steps_per_second": 9.85, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.041981909424066544, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3307, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8616, | |
| "eval_loss": 0.48100098967552185, | |
| "eval_runtime": 6.2759, | |
| "eval_samples_per_second": 597.524, | |
| "eval_steps_per_second": 9.401, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.537958562374115, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2365, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8557333333333333, | |
| "eval_loss": 0.5295482873916626, | |
| "eval_runtime": 5.794, | |
| "eval_samples_per_second": 647.219, | |
| "eval_steps_per_second": 10.183, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.49246400594711304, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1884, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8701333333333333, | |
| "eval_loss": 0.5043964385986328, | |
| "eval_runtime": 6.4059, | |
| "eval_samples_per_second": 585.394, | |
| "eval_steps_per_second": 9.21, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1998, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.58965282490368e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |