| { | |
| "best_metric": 0.46875, | |
| "best_model_checkpoint": "resnet-18-please-work/checkpoint-6", | |
| "epoch": 2.6666666666666665, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_accuracy": 0.46875, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.5279, | |
| "eval_samples_per_second": 181.87, | |
| "eval_steps_per_second": 5.683, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.925925925925926, | |
| "eval_accuracy": 0.46875, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.3091, | |
| "eval_samples_per_second": 310.537, | |
| "eval_steps_per_second": 9.704, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "eval_accuracy": 0.46875, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.2963, | |
| "eval_samples_per_second": 323.973, | |
| "eval_steps_per_second": 10.124, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "step": 18, | |
| "total_flos": 2.326039595266867e+16, | |
| "train_loss": 0.0, | |
| "train_runtime": 17.8085, | |
| "train_samples_per_second": 145.549, | |
| "train_steps_per_second": 1.011 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 18, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.326039595266867e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |