| { | |
| "best_metric": 1.7371251583099365, | |
| "best_model_checkpoint": "cat_breed_image_detection/checkpoint-2541", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2541, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19677292404565133, | |
| "grad_norm": 4.561705112457275, | |
| "learning_rate": 7.3741469289442e-07, | |
| "loss": 1.7223, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39354584809130266, | |
| "grad_norm": 6.119686603546143, | |
| "learning_rate": 5.567643516659976e-07, | |
| "loss": 1.725, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5903187721369539, | |
| "grad_norm": 6.317899227142334, | |
| "learning_rate": 3.7611401043757525e-07, | |
| "loss": 1.6978, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7870916961826053, | |
| "grad_norm": 5.751919746398926, | |
| "learning_rate": 1.9546366920915295e-07, | |
| "loss": 1.7098, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9838646202282566, | |
| "grad_norm": 5.932868957519531, | |
| "learning_rate": 1.481332798073063e-08, | |
| "loss": 1.7143, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5582004723944494, | |
| "eval_loss": 1.7371251583099365, | |
| "eval_runtime": 1197.2141, | |
| "eval_samples_per_second": 90.53, | |
| "eval_steps_per_second": 2.829, | |
| "step": 2541 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2541, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.2603531789715636e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |