| { |
| "best_metric": 0.9085333333333333, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0741/checkpoints/checkpoint-2997", |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 2997, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 65.8919906616211, |
| "learning_rate": 0.0004849231551964771, |
| "loss": 1.2447, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8218666666666666, |
| "eval_loss": 0.5886217951774597, |
| "eval_runtime": 7.7303, |
| "eval_samples_per_second": 485.105, |
| "eval_steps_per_second": 7.632, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 31.910045623779297, |
| "learning_rate": 0.0004415111107797445, |
| "loss": 0.3894, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8714666666666666, |
| "eval_loss": 0.4274978041648865, |
| "eval_runtime": 7.9334, |
| "eval_samples_per_second": 472.684, |
| "eval_steps_per_second": 7.437, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 56.76421356201172, |
| "learning_rate": 0.000375, |
| "loss": 0.2258, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8792, |
| "eval_loss": 0.42400309443473816, |
| "eval_runtime": 8.0831, |
| "eval_samples_per_second": 463.933, |
| "eval_steps_per_second": 7.299, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 28.23626708984375, |
| "learning_rate": 0.00029341204441673266, |
| "loss": 0.1125, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8877333333333334, |
| "eval_loss": 0.43529486656188965, |
| "eval_runtime": 7.9064, |
| "eval_samples_per_second": 474.301, |
| "eval_steps_per_second": 7.462, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 20.729154586791992, |
| "learning_rate": 0.00020658795558326743, |
| "loss": 0.0629, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8978666666666667, |
| "eval_loss": 0.4219927191734314, |
| "eval_runtime": 8.1112, |
| "eval_samples_per_second": 462.322, |
| "eval_steps_per_second": 7.274, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 34.96220016479492, |
| "learning_rate": 0.00012500000000000006, |
| "loss": 0.0305, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9034666666666666, |
| "eval_loss": 0.410978764295578, |
| "eval_runtime": 8.101, |
| "eval_samples_per_second": 462.906, |
| "eval_steps_per_second": 7.283, |
| "step": 1998 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 41.63066101074219, |
| "learning_rate": 5.848888922025553e-05, |
| "loss": 0.0134, |
| "step": 2331 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9032, |
| "eval_loss": 0.4195844531059265, |
| "eval_runtime": 8.0678, |
| "eval_samples_per_second": 464.809, |
| "eval_steps_per_second": 7.313, |
| "step": 2331 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 28.09171485900879, |
| "learning_rate": 1.5076844803522921e-05, |
| "loss": 0.0079, |
| "step": 2664 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9056, |
| "eval_loss": 0.42568886280059814, |
| "eval_runtime": 7.7853, |
| "eval_samples_per_second": 481.678, |
| "eval_steps_per_second": 7.578, |
| "step": 2664 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 45.25759506225586, |
| "learning_rate": 0.0, |
| "loss": 0.0095, |
| "step": 2997 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9085333333333333, |
| "eval_loss": 0.42178812623023987, |
| "eval_runtime": 8.0518, |
| "eval_samples_per_second": 465.733, |
| "eval_steps_per_second": 7.328, |
| "step": 2997 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.3587863155968e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
