| { | |
| "best_metric": 0.9310344827586207, | |
| "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-40", | |
| "epoch": 8.88888888888889, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.5862068965517241, | |
| "eval_loss": 1.0178804397583008, | |
| "eval_runtime": 1.1426, | |
| "eval_samples_per_second": 25.38, | |
| "eval_steps_per_second": 2.626, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.9897, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_accuracy": 0.7241379310344828, | |
| "eval_loss": 0.760027289390564, | |
| "eval_runtime": 0.8084, | |
| "eval_samples_per_second": 35.874, | |
| "eval_steps_per_second": 3.711, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.5862068965517241, | |
| "eval_loss": 0.8368268609046936, | |
| "eval_runtime": 1.6581, | |
| "eval_samples_per_second": 17.49, | |
| "eval_steps_per_second": 1.809, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8620689655172413, | |
| "eval_loss": 0.4708000719547272, | |
| "eval_runtime": 0.8189, | |
| "eval_samples_per_second": 35.414, | |
| "eval_steps_per_second": 3.663, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2747, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_accuracy": 0.896551724137931, | |
| "eval_loss": 0.37271812558174133, | |
| "eval_runtime": 0.8067, | |
| "eval_samples_per_second": 35.951, | |
| "eval_steps_per_second": 3.719, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2259, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_accuracy": 0.9310344827586207, | |
| "eval_loss": 0.3100181221961975, | |
| "eval_runtime": 1.1422, | |
| "eval_samples_per_second": 25.389, | |
| "eval_steps_per_second": 2.626, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_accuracy": 0.9310344827586207, | |
| "eval_loss": 0.22938820719718933, | |
| "eval_runtime": 0.7944, | |
| "eval_samples_per_second": 36.504, | |
| "eval_steps_per_second": 3.776, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1596, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.896551724137931, | |
| "eval_loss": 0.26314061880111694, | |
| "eval_runtime": 1.212, | |
| "eval_samples_per_second": 23.927, | |
| "eval_steps_per_second": 2.475, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 0.0, | |
| "loss": 0.1844, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_accuracy": 0.9310344827586207, | |
| "eval_loss": 0.26064130663871765, | |
| "eval_runtime": 0.8176, | |
| "eval_samples_per_second": 35.469, | |
| "eval_steps_per_second": 3.669, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "step": 60, | |
| "total_flos": 5.786635923932774e+16, | |
| "train_loss": 0.40318952401479086, | |
| "train_runtime": 239.9675, | |
| "train_samples_per_second": 10.876, | |
| "train_steps_per_second": 0.25 | |
| } | |
| ], | |
| "max_steps": 60, | |
| "num_train_epochs": 10, | |
| "total_flos": 5.786635923932774e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |