| { | |
| "best_metric": 1.048563838005066, | |
| "best_model_checkpoint": "hand_gestures_image_detection/checkpoint-7484", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 7484, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 2.2655653953552246, | |
| "learning_rate": 3.757869249394673e-07, | |
| "loss": 1.2432, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.7733244895935059, | |
| "learning_rate": 3.488835082055421e-07, | |
| "loss": 1.2086, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 2.5758512020111084, | |
| "learning_rate": 3.2198009147161687e-07, | |
| "loss": 1.1738, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 1.8766041994094849, | |
| "learning_rate": 2.950766747376917e-07, | |
| "loss": 1.1446, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 1.6818866729736328, | |
| "learning_rate": 2.6817325800376645e-07, | |
| "loss": 1.1166, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.216224431991577, | |
| "learning_rate": 2.4126984126984124e-07, | |
| "loss": 1.0913, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 2.9839746952056885, | |
| "learning_rate": 2.1436642453591606e-07, | |
| "loss": 1.0774, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 2.420858860015869, | |
| "learning_rate": 1.8746300780199085e-07, | |
| "loss": 1.0558, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.0462467670440674, | |
| "learning_rate": 1.6055959106806564e-07, | |
| "loss": 1.0431, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 1.9844759702682495, | |
| "learning_rate": 1.3365617433414043e-07, | |
| "loss": 1.03, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 1.858327031135559, | |
| "learning_rate": 1.0675275760021523e-07, | |
| "loss": 1.0144, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.135549783706665, | |
| "learning_rate": 7.984934086629002e-08, | |
| "loss": 1.0051, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 1.8743281364440918, | |
| "learning_rate": 5.2945924132364805e-08, | |
| "loss": 1.0045, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.7080762386322021, | |
| "learning_rate": 2.6042507398439602e-08, | |
| "loss": 1.0008, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9126202645820806, | |
| "eval_loss": 1.048563838005066, | |
| "eval_runtime": 688.7849, | |
| "eval_samples_per_second": 77.261, | |
| "eval_steps_per_second": 2.414, | |
| "step": 7484 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7484, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 3.711902575222466e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |