| { | |
| "best_metric": 1.5017073154449463, | |
| "best_model_checkpoint": "flower_groups_image_detection/checkpoint-10100", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 10100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.552238805970149e-06, | |
| "loss": 4.6462, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.37973742878375033, | |
| "eval_loss": 4.430595397949219, | |
| "eval_runtime": 39.1113, | |
| "eval_samples_per_second": 103.218, | |
| "eval_steps_per_second": 12.912, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 9.054726368159204e-06, | |
| "loss": 4.1067, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5352984889769631, | |
| "eval_loss": 3.9689955711364746, | |
| "eval_runtime": 38.8252, | |
| "eval_samples_per_second": 103.979, | |
| "eval_steps_per_second": 13.007, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 8.557213930348259e-06, | |
| "loss": 3.6523, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6160515234084717, | |
| "eval_loss": 3.579822540283203, | |
| "eval_runtime": 38.9739, | |
| "eval_samples_per_second": 103.582, | |
| "eval_steps_per_second": 12.957, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 8.059701492537314e-06, | |
| "loss": 3.2819, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6643547188506317, | |
| "eval_loss": 3.252412796020508, | |
| "eval_runtime": 38.8749, | |
| "eval_samples_per_second": 103.846, | |
| "eval_steps_per_second": 12.99, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 7.5621890547263685e-06, | |
| "loss": 2.9632, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7027495665097845, | |
| "eval_loss": 2.9800004959106445, | |
| "eval_runtime": 38.9479, | |
| "eval_samples_per_second": 103.651, | |
| "eval_steps_per_second": 12.966, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 7.064676616915423e-06, | |
| "loss": 2.6887, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7233093881595244, | |
| "eval_loss": 2.730450391769409, | |
| "eval_runtime": 39.2951, | |
| "eval_samples_per_second": 102.735, | |
| "eval_steps_per_second": 12.851, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 6.567164179104478e-06, | |
| "loss": 2.4502, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7413921228635125, | |
| "eval_loss": 2.5192980766296387, | |
| "eval_runtime": 39.3497, | |
| "eval_samples_per_second": 102.593, | |
| "eval_steps_per_second": 12.834, | |
| "step": 3535 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 6.069651741293533e-06, | |
| "loss": 2.2326, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7619519445132524, | |
| "eval_loss": 2.334770917892456, | |
| "eval_runtime": 38.9071, | |
| "eval_samples_per_second": 103.76, | |
| "eval_steps_per_second": 12.98, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 5.572139303482588e-06, | |
| "loss": 2.05, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7674015357939064, | |
| "eval_loss": 2.1747395992279053, | |
| "eval_runtime": 39.2303, | |
| "eval_samples_per_second": 102.905, | |
| "eval_steps_per_second": 12.873, | |
| "step": 4545 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 5.074626865671642e-06, | |
| "loss": 1.8841, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7812732226901165, | |
| "eval_loss": 2.037976026535034, | |
| "eval_runtime": 38.9814, | |
| "eval_samples_per_second": 103.562, | |
| "eval_steps_per_second": 12.955, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 4.577114427860697e-06, | |
| "loss": 1.7503, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7874659400544959, | |
| "eval_loss": 1.9241634607315063, | |
| "eval_runtime": 39.645, | |
| "eval_samples_per_second": 101.829, | |
| "eval_steps_per_second": 12.738, | |
| "step": 5555 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 4.079601990049751e-06, | |
| "loss": 1.6253, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.793163240029725, | |
| "eval_loss": 1.8279324769973755, | |
| "eval_runtime": 39.1015, | |
| "eval_samples_per_second": 103.244, | |
| "eval_steps_per_second": 12.915, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 3.582089552238806e-06, | |
| "loss": 1.5268, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8005945008669805, | |
| "eval_loss": 1.7480475902557373, | |
| "eval_runtime": 39.0157, | |
| "eval_samples_per_second": 103.471, | |
| "eval_steps_per_second": 12.944, | |
| "step": 6565 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 3.0845771144278608e-06, | |
| "loss": 1.4481, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8023284617290067, | |
| "eval_loss": 1.67815363407135, | |
| "eval_runtime": 38.92, | |
| "eval_samples_per_second": 103.726, | |
| "eval_steps_per_second": 12.975, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 2.5870646766169156e-06, | |
| "loss": 1.354, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8045578399801833, | |
| "eval_loss": 1.6218925714492798, | |
| "eval_runtime": 39.3854, | |
| "eval_samples_per_second": 102.5, | |
| "eval_steps_per_second": 12.822, | |
| "step": 7575 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.08955223880597e-06, | |
| "loss": 1.3135, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.808273470398811, | |
| "eval_loss": 1.5784657001495361, | |
| "eval_runtime": 39.5015, | |
| "eval_samples_per_second": 102.199, | |
| "eval_steps_per_second": 12.784, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 1.592039800995025e-06, | |
| "loss": 1.2468, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8102551399554124, | |
| "eval_loss": 1.5451480150222778, | |
| "eval_runtime": 39.2102, | |
| "eval_samples_per_second": 102.958, | |
| "eval_steps_per_second": 12.879, | |
| "step": 8585 | |
| }, | |
| { | |
| "epoch": 17.82, | |
| "learning_rate": 1.0945273631840796e-06, | |
| "loss": 1.2171, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8119891008174387, | |
| "eval_loss": 1.5213581323623657, | |
| "eval_runtime": 38.9612, | |
| "eval_samples_per_second": 103.616, | |
| "eval_steps_per_second": 12.962, | |
| "step": 9090 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 5.970149253731343e-07, | |
| "loss": 1.1976, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8114936834282883, | |
| "eval_loss": 1.5058366060256958, | |
| "eval_runtime": 39.2327, | |
| "eval_samples_per_second": 102.899, | |
| "eval_steps_per_second": 12.872, | |
| "step": 9595 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "learning_rate": 9.950248756218906e-08, | |
| "loss": 1.1832, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8114936834282883, | |
| "eval_loss": 1.5017073154449463, | |
| "eval_runtime": 39.6297, | |
| "eval_samples_per_second": 101.868, | |
| "eval_steps_per_second": 12.743, | |
| "step": 10100 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10100, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 2.505642154385965e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |