| { | |
| "best_metric": 0.9545454545454546, | |
| "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-31", | |
| "epoch": 9.6, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.4772727272727273, | |
| "eval_loss": 0.9944368600845337, | |
| "eval_runtime": 1.008, | |
| "eval_samples_per_second": 43.653, | |
| "eval_steps_per_second": 4.961, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.0159, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.694824755191803, | |
| "eval_runtime": 0.9891, | |
| "eval_samples_per_second": 44.486, | |
| "eval_steps_per_second": 5.055, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.9318181818181818, | |
| "eval_loss": 0.34167394042015076, | |
| "eval_runtime": 0.985, | |
| "eval_samples_per_second": 44.669, | |
| "eval_steps_per_second": 5.076, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5444, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.26416999101638794, | |
| "eval_runtime": 1.3817, | |
| "eval_samples_per_second": 31.845, | |
| "eval_steps_per_second": 3.619, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_accuracy": 0.9545454545454546, | |
| "eval_loss": 0.09864511340856552, | |
| "eval_runtime": 1.0085, | |
| "eval_samples_per_second": 43.627, | |
| "eval_steps_per_second": 4.958, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "eval_accuracy": 0.9545454545454546, | |
| "eval_loss": 0.17346793413162231, | |
| "eval_runtime": 1.0084, | |
| "eval_samples_per_second": 43.634, | |
| "eval_steps_per_second": 4.958, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2596, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "eval_accuracy": 0.9545454545454546, | |
| "eval_loss": 0.1091495230793953, | |
| "eval_runtime": 1.383, | |
| "eval_samples_per_second": 31.815, | |
| "eval_steps_per_second": 3.615, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1737, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9545454545454546, | |
| "eval_loss": 0.0685076043009758, | |
| "eval_runtime": 1.013, | |
| "eval_samples_per_second": 43.435, | |
| "eval_steps_per_second": 4.936, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_accuracy": 0.9545454545454546, | |
| "eval_loss": 0.09951713681221008, | |
| "eval_runtime": 1.0006, | |
| "eval_samples_per_second": 43.975, | |
| "eval_steps_per_second": 4.997, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 0.0, | |
| "loss": 0.1716, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_accuracy": 0.9545454545454546, | |
| "eval_loss": 0.09269092231988907, | |
| "eval_runtime": 1.0041, | |
| "eval_samples_per_second": 43.822, | |
| "eval_steps_per_second": 4.98, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "step": 60, | |
| "total_flos": 5.876119984612147e+16, | |
| "train_loss": 0.3996999263763428, | |
| "train_runtime": 229.426, | |
| "train_samples_per_second": 10.722, | |
| "train_steps_per_second": 0.262 | |
| } | |
| ], | |
| "max_steps": 60, | |
| "num_train_epochs": 10, | |
| "total_flos": 5.876119984612147e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |