| { | |
| "best_metric": 0.8629333333333333, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0112/checkpoints/checkpoint-2331", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 2331, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 65.84174346923828, | |
| "learning_rate": 8.554359905560886e-05, | |
| "loss": 3.0039, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6909333333333333, | |
| "eval_loss": 1.2213996648788452, | |
| "eval_runtime": 8.386, | |
| "eval_samples_per_second": 447.173, | |
| "eval_steps_per_second": 7.036, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 76.97315216064453, | |
| "learning_rate": 7.305704108364301e-05, | |
| "loss": 0.8648, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8152, | |
| "eval_loss": 0.6010051369667053, | |
| "eval_runtime": 8.4335, | |
| "eval_samples_per_second": 444.653, | |
| "eval_steps_per_second": 6.996, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 85.03634643554688, | |
| "learning_rate": 5.501344202803415e-05, | |
| "loss": 0.5567, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8352, | |
| "eval_loss": 0.5037257075309753, | |
| "eval_runtime": 8.296, | |
| "eval_samples_per_second": 452.025, | |
| "eval_steps_per_second": 7.112, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 81.15449523925781, | |
| "learning_rate": 3.498655797196586e-05, | |
| "loss": 0.4408, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8570666666666666, | |
| "eval_loss": 0.4541216790676117, | |
| "eval_runtime": 8.3084, | |
| "eval_samples_per_second": 451.352, | |
| "eval_steps_per_second": 7.101, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 56.88452911376953, | |
| "learning_rate": 1.6942958916356995e-05, | |
| "loss": 0.3848, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8592, | |
| "eval_loss": 0.44605720043182373, | |
| "eval_runtime": 8.3486, | |
| "eval_samples_per_second": 449.179, | |
| "eval_steps_per_second": 7.067, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 80.1556625366211, | |
| "learning_rate": 4.456400944391144e-06, | |
| "loss": 0.3541, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8626666666666667, | |
| "eval_loss": 0.43431544303894043, | |
| "eval_runtime": 8.7203, | |
| "eval_samples_per_second": 430.031, | |
| "eval_steps_per_second": 6.766, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 156.7079620361328, | |
| "learning_rate": 0.0, | |
| "loss": 0.3383, | |
| "step": 2331 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8629333333333333, | |
| "eval_loss": 0.43689587712287903, | |
| "eval_runtime": 8.2775, | |
| "eval_samples_per_second": 453.037, | |
| "eval_steps_per_second": 7.128, | |
| "step": 2331 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2331, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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": 5.7235004676864e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |