Invalid JSON:
Unexpected token 'I', ..."ad_norm": Infinity,
"... is not valid JSON
| { | |
| "best_metric": 0.9501333333333334, | |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0294/checkpoints/checkpoint-1665", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1665, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.3953490257263184, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1695, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9333333333333333, | |
| "eval_loss": 0.2927524745464325, | |
| "eval_runtime": 7.2625, | |
| "eval_samples_per_second": 516.351, | |
| "eval_steps_per_second": 8.124, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1645, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9429333333333333, | |
| "eval_loss": 0.21913030743598938, | |
| "eval_runtime": 7.6084, | |
| "eval_samples_per_second": 492.874, | |
| "eval_steps_per_second": 7.755, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.11856577545404434, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0748, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9416, | |
| "eval_loss": 0.21393008530139923, | |
| "eval_runtime": 7.3451, | |
| "eval_samples_per_second": 510.543, | |
| "eval_steps_per_second": 8.033, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.05327155068516731, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0367, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9442666666666667, | |
| "eval_loss": 0.22114548087120056, | |
| "eval_runtime": 7.2478, | |
| "eval_samples_per_second": 517.396, | |
| "eval_steps_per_second": 8.14, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.2861299514770508, | |
| "learning_rate": 3e-05, | |
| "loss": 0.023, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9501333333333334, | |
| "eval_loss": 0.20542556047439575, | |
| "eval_runtime": 6.8524, | |
| "eval_samples_per_second": 547.253, | |
| "eval_steps_per_second": 8.61, | |
| "step": 1665 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2664, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 8.2370660311296e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |