| { | |
| "best_metric": 0.9159040316596587, | |
| "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-56855", | |
| "epoch": 5.0, | |
| "global_step": 56855, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.777760406488177e-05, | |
| "loss": 0.3275, | |
| "step": 11371 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8883502349740292, | |
| "eval_combined_score": 0.8730347279011859, | |
| "eval_f1": 0.8577192208283426, | |
| "eval_loss": 0.2622373104095459, | |
| "eval_runtime": 105.6916, | |
| "eval_samples_per_second": 382.528, | |
| "eval_steps_per_second": 47.818, | |
| "step": 11371 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.3333203048661326e-05, | |
| "loss": 0.225, | |
| "step": 22742 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9034380410586198, | |
| "eval_combined_score": 0.8891589282275344, | |
| "eval_f1": 0.874879815396449, | |
| "eval_loss": 0.24025394022464752, | |
| "eval_runtime": 105.7158, | |
| "eval_samples_per_second": 382.44, | |
| "eval_steps_per_second": 47.807, | |
| "step": 22742 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.888802032440885e-06, | |
| "loss": 0.171, | |
| "step": 34113 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9104625278258719, | |
| "eval_combined_score": 0.8967687316131944, | |
| "eval_f1": 0.8830749354005168, | |
| "eval_loss": 0.2317567765712738, | |
| "eval_runtime": 106.0625, | |
| "eval_samples_per_second": 381.19, | |
| "eval_steps_per_second": 47.651, | |
| "step": 34113 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.4444010162204425e-06, | |
| "loss": 0.1315, | |
| "step": 45484 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9156814246846401, | |
| "eval_combined_score": 0.9015178097880459, | |
| "eval_f1": 0.8873541948914516, | |
| "eval_loss": 0.27421835064888, | |
| "eval_runtime": 106.1272, | |
| "eval_samples_per_second": 380.958, | |
| "eval_steps_per_second": 47.622, | |
| "step": 45484 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.107, | |
| "step": 56855 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9159040316596587, | |
| "eval_combined_score": 0.9019646623849604, | |
| "eval_f1": 0.8880252931102622, | |
| "eval_loss": 0.3268052935600281, | |
| "eval_runtime": 106.2134, | |
| "eval_samples_per_second": 380.649, | |
| "eval_steps_per_second": 47.583, | |
| "step": 56855 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 56855, | |
| "total_flos": 1.196648813106432e+17, | |
| "train_loss": 0.1924241087868811, | |
| "train_runtime": 13385.1324, | |
| "train_samples_per_second": 135.914, | |
| "train_steps_per_second": 4.248 | |
| } | |
| ], | |
| "max_steps": 56855, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.196648813106432e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |