| { |
| "best_metric": 0.8746666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0373/checkpoints/checkpoint-2664", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 2664, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 59.09840393066406, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 3.6303, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5946666666666667, |
| "eval_loss": 2.955594062805176, |
| "eval_runtime": 12.4023, |
| "eval_samples_per_second": 302.363, |
| "eval_steps_per_second": 4.757, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 219.09280395507812, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 1.6894, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.772, |
| "eval_loss": 0.9063711166381836, |
| "eval_runtime": 12.5318, |
| "eval_samples_per_second": 299.24, |
| "eval_steps_per_second": 4.708, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 136.07955932617188, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.732, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8218666666666666, |
| "eval_loss": 0.6259603500366211, |
| "eval_runtime": 12.8754, |
| "eval_samples_per_second": 291.253, |
| "eval_steps_per_second": 4.582, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 453.58392333984375, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.5083, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8509333333333333, |
| "eval_loss": 0.5213587284088135, |
| "eval_runtime": 12.6226, |
| "eval_samples_per_second": 297.085, |
| "eval_steps_per_second": 4.674, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 300.1756896972656, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.4098, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8613333333333333, |
| "eval_loss": 0.48238372802734375, |
| "eval_runtime": 12.3443, |
| "eval_samples_per_second": 303.785, |
| "eval_steps_per_second": 4.78, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 232.54443359375, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.3385, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8677333333333334, |
| "eval_loss": 0.43990689516067505, |
| "eval_runtime": 12.5081, |
| "eval_samples_per_second": 299.806, |
| "eval_steps_per_second": 4.717, |
| "step": 1998 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 493.5278625488281, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.289, |
| "step": 2331 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8709333333333333, |
| "eval_loss": 0.43837565183639526, |
| "eval_runtime": 12.3146, |
| "eval_samples_per_second": 304.517, |
| "eval_steps_per_second": 4.791, |
| "step": 2331 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 163.03846740722656, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.2647, |
| "step": 2664 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8746666666666667, |
| "eval_loss": 0.4282410144805908, |
| "eval_runtime": 14.0091, |
| "eval_samples_per_second": 267.683, |
| "eval_steps_per_second": 4.212, |
| "step": 2664 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2997, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "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": 6.5411433916416e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
