Invalid JSON:
Unexpected token 'I', ..."ad_norm": Infinity,
"... is not valid JSON
| { | |
| "best_metric": 0.9082666666666667, | |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0244/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": 1.6641900539398193, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7567, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8877333333333334, | |
| "eval_loss": 0.3570614159107208, | |
| "eval_runtime": 5.7807, | |
| "eval_samples_per_second": 648.707, | |
| "eval_steps_per_second": 10.206, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": Infinity, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1638, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9005333333333333, | |
| "eval_loss": 0.34019163250923157, | |
| "eval_runtime": 7.9194, | |
| "eval_samples_per_second": 473.518, | |
| "eval_steps_per_second": 7.45, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.9905290007591248, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0663, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9037333333333334, | |
| "eval_loss": 0.3687500059604645, | |
| "eval_runtime": 7.0405, | |
| "eval_samples_per_second": 532.634, | |
| "eval_steps_per_second": 8.38, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.15115317702293396, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0407, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8930666666666667, | |
| "eval_loss": 0.4446985721588135, | |
| "eval_runtime": 5.8263, | |
| "eval_samples_per_second": 643.631, | |
| "eval_steps_per_second": 10.126, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.3764224052429199, | |
| "learning_rate": 3e-05, | |
| "loss": 0.031, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9082666666666667, | |
| "eval_loss": 0.3889778256416321, | |
| "eval_runtime": 6.2672, | |
| "eval_samples_per_second": 598.355, | |
| "eval_steps_per_second": 9.414, | |
| "step": 1665 | |
| } | |
| ], | |
| "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": 8.2370660311296e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |