| { | |
| "best_metric": 0.5862595419847328, | |
| "best_model_checkpoint": "roberta-base-go_emotions/checkpoint-16281", | |
| "epoch": 3.0, | |
| "global_step": 16281, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9815736134144095e-05, | |
| "loss": 0.1826, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.963147226828819e-05, | |
| "loss": 0.1317, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.9447208402432286e-05, | |
| "loss": 0.1146, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.9262944536576377e-05, | |
| "loss": 0.1078, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.9078680670720474e-05, | |
| "loss": 0.1006, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.8894416804864568e-05, | |
| "loss": 0.0976, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.871015293900866e-05, | |
| "loss": 0.096, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.8525889073152755e-05, | |
| "loss": 0.0925, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.8341625207296852e-05, | |
| "loss": 0.0921, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.8157361341440943e-05, | |
| "loss": 0.0911, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.40213785477331365, | |
| "eval_f1": 0.5346146303196705, | |
| "eval_loss": 0.08816272765398026, | |
| "eval_roc_auc": 0.7098850238721621, | |
| "eval_runtime": 11.8306, | |
| "eval_samples_per_second": 458.641, | |
| "eval_steps_per_second": 57.394, | |
| "step": 5427 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.797309747558504e-05, | |
| "loss": 0.0897, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.7788833609729134e-05, | |
| "loss": 0.0856, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1.7604569743873227e-05, | |
| "loss": 0.0816, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.742030587801732e-05, | |
| "loss": 0.0853, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 1.7236042012161415e-05, | |
| "loss": 0.0846, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.7051778146305512e-05, | |
| "loss": 0.0843, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.6867514280449606e-05, | |
| "loss": 0.0807, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.66832504145937e-05, | |
| "loss": 0.0796, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.6498986548737793e-05, | |
| "loss": 0.081, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.6314722682881887e-05, | |
| "loss": 0.0798, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.613045881702598e-05, | |
| "loss": 0.0821, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.44010320678216, | |
| "eval_f1": 0.5612426312342098, | |
| "eval_loss": 0.08432479202747345, | |
| "eval_roc_auc": 0.7305379849481191, | |
| "eval_runtime": 11.8056, | |
| "eval_samples_per_second": 459.613, | |
| "eval_steps_per_second": 57.515, | |
| "step": 10854 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5946194951170078e-05, | |
| "loss": 0.0776, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.5761931085314172e-05, | |
| "loss": 0.0726, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.5577667219458266e-05, | |
| "loss": 0.0718, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.539340335360236e-05, | |
| "loss": 0.0735, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.5209139487746453e-05, | |
| "loss": 0.0735, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 1.5024875621890549e-05, | |
| "loss": 0.0721, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.4840611756034643e-05, | |
| "loss": 0.0722, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.4656347890178736e-05, | |
| "loss": 0.0751, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.4472084024322832e-05, | |
| "loss": 0.0727, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.4287820158466926e-05, | |
| "loss": 0.0735, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.4103556292611021e-05, | |
| "loss": 0.0714, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.47475119793586434, | |
| "eval_f1": 0.5862595419847328, | |
| "eval_loss": 0.0838962271809578, | |
| "eval_roc_auc": 0.7506773514396311, | |
| "eval_runtime": 11.8261, | |
| "eval_samples_per_second": 458.814, | |
| "eval_steps_per_second": 57.415, | |
| "step": 16281 | |
| } | |
| ], | |
| "max_steps": 54270, | |
| "num_train_epochs": 10, | |
| "total_flos": 8568237917583360.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |