| { | |
| "best_metric": 0.20898549258708954, | |
| "best_model_checkpoint": "deberta-v3-base-funetuned-qqa/checkpoint-2842", | |
| "epoch": 2.999736170961217, | |
| "global_step": 4263, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.912033779028853e-05, | |
| "loss": 0.3671, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.824067558057706e-05, | |
| "loss": 0.2758, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.736101337086559e-05, | |
| "loss": 0.2616, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6481351161154117e-05, | |
| "loss": 0.2469, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.5601688951442647e-05, | |
| "loss": 0.235, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.90576171875, | |
| "eval_binary_crossentropy_loss": 9.43606185913086, | |
| "eval_loss": 0.22764553129673004, | |
| "eval_runtime": 148.7776, | |
| "eval_samples_per_second": 271.748, | |
| "eval_steps_per_second": 16.985, | |
| "step": 1421 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.4722026741731177e-05, | |
| "loss": 0.2228, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.3842364532019705e-05, | |
| "loss": 0.1956, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.2962702322308235e-05, | |
| "loss": 0.1994, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.2083040112596764e-05, | |
| "loss": 0.1957, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.1203377902885292e-05, | |
| "loss": 0.1893, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.0323715693173822e-05, | |
| "loss": 0.1908, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.91357421875, | |
| "eval_binary_crossentropy_loss": 8.624783515930176, | |
| "eval_loss": 0.20898549258708954, | |
| "eval_runtime": 148.8373, | |
| "eval_samples_per_second": 271.639, | |
| "eval_steps_per_second": 16.978, | |
| "step": 2842 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.44405348346235e-06, | |
| "loss": 0.1706, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.56439127375088e-06, | |
| "loss": 0.1574, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.68472906403941e-06, | |
| "loss": 0.1573, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.808585503166785e-06, | |
| "loss": 0.1619, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.928923293455313e-06, | |
| "loss": 0.1574, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.049261083743843e-06, | |
| "loss": 0.1575, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9169921875, | |
| "eval_binary_crossentropy_loss": 8.323027610778809, | |
| "eval_loss": 0.20993904769420624, | |
| "eval_runtime": 148.6942, | |
| "eval_samples_per_second": 271.9, | |
| "eval_steps_per_second": 16.995, | |
| "step": 4263 | |
| } | |
| ], | |
| "max_steps": 5684, | |
| "num_train_epochs": 4, | |
| "total_flos": 7.180021641700454e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |