| { | |
| "best_metric": 0.8701333333333333, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0345/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": 63.9189567565918, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 3.5977, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5861333333333333, | |
| "eval_loss": 2.8822615146636963, | |
| "eval_runtime": 14.0377, | |
| "eval_samples_per_second": 267.138, | |
| "eval_steps_per_second": 4.203, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 369.0137634277344, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 1.6254, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7650666666666667, | |
| "eval_loss": 0.9426801204681396, | |
| "eval_runtime": 13.7789, | |
| "eval_samples_per_second": 272.154, | |
| "eval_steps_per_second": 4.282, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 394.1136169433594, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.7619, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8258666666666666, | |
| "eval_loss": 0.6223153471946716, | |
| "eval_runtime": 13.7725, | |
| "eval_samples_per_second": 272.282, | |
| "eval_steps_per_second": 4.284, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 357.5818176269531, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 0.563, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8496, | |
| "eval_loss": 0.5120093822479248, | |
| "eval_runtime": 13.7843, | |
| "eval_samples_per_second": 272.049, | |
| "eval_steps_per_second": 4.28, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 360.3973388671875, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.4509, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8544, | |
| "eval_loss": 0.4910653829574585, | |
| "eval_runtime": 13.7255, | |
| "eval_samples_per_second": 273.214, | |
| "eval_steps_per_second": 4.299, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 422.3824462890625, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.4049, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8594666666666667, | |
| "eval_loss": 0.4643794894218445, | |
| "eval_runtime": 13.7421, | |
| "eval_samples_per_second": 272.884, | |
| "eval_steps_per_second": 4.293, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 56.444664001464844, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 0.3589, | |
| "step": 2331 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8666666666666667, | |
| "eval_loss": 0.4446803033351898, | |
| "eval_runtime": 14.5777, | |
| "eval_samples_per_second": 257.243, | |
| "eval_steps_per_second": 4.047, | |
| "step": 2331 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 91.45018005371094, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 0.3509, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8685333333333334, | |
| "eval_loss": 0.4416220784187317, | |
| "eval_runtime": 13.6404, | |
| "eval_samples_per_second": 274.919, | |
| "eval_steps_per_second": 4.325, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 94.1056137084961, | |
| "learning_rate": 0.0, | |
| "loss": 0.3339, | |
| "step": 2997 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8701333333333333, | |
| "eval_loss": 0.4372040331363678, | |
| "eval_runtime": 13.7037, | |
| "eval_samples_per_second": 273.648, | |
| "eval_steps_per_second": 4.305, | |
| "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 | |
| } | |