| { | |
| "best_metric": 0.7412639349881154, | |
| "best_model_checkpoint": "trained/hebban-reviews/robbert-v2-dutch-base/checkpoint-3500", | |
| "epoch": 4.382997370727432, | |
| "global_step": 5001, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.501099780043991e-05, | |
| "loss": 0.6723, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.8079388560157791, | |
| "eval_f1": 0.8117501994363496, | |
| "eval_loss": 0.5760409235954285, | |
| "eval_precision": 0.8174343819162313, | |
| "eval_qwk": 0.7302784941209646, | |
| "eval_recall": 0.8079388560157791, | |
| "eval_runtime": 23.4439, | |
| "eval_samples_per_second": 692.036, | |
| "eval_steps_per_second": 5.417, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.0011997600479906e-05, | |
| "loss": 0.5754, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.7649778106508875, | |
| "eval_f1": 0.7798244436633573, | |
| "eval_loss": 0.5568957328796387, | |
| "eval_precision": 0.8129894746393622, | |
| "eval_qwk": 0.6942695698574534, | |
| "eval_recall": 0.7649778106508875, | |
| "eval_runtime": 23.1665, | |
| "eval_samples_per_second": 700.32, | |
| "eval_steps_per_second": 5.482, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.50129974005199e-05, | |
| "loss": 0.5052, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.7829758382642998, | |
| "eval_f1": 0.7967934169486903, | |
| "eval_loss": 0.5705748200416565, | |
| "eval_precision": 0.8279826615797163, | |
| "eval_qwk": 0.7174911347556729, | |
| "eval_recall": 0.7829758382642998, | |
| "eval_runtime": 23.1285, | |
| "eval_samples_per_second": 701.473, | |
| "eval_steps_per_second": 5.491, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.001399720055989e-05, | |
| "loss": 0.4723, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.7924063116370809, | |
| "eval_f1": 0.8033559165914831, | |
| "eval_loss": 0.5601416230201721, | |
| "eval_precision": 0.8252798007612112, | |
| "eval_qwk": 0.7270656679689509, | |
| "eval_recall": 0.7924063116370809, | |
| "eval_runtime": 23.2157, | |
| "eval_samples_per_second": 698.837, | |
| "eval_steps_per_second": 5.47, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.5024995000999802e-05, | |
| "loss": 0.4285, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.8101577909270217, | |
| "eval_f1": 0.8186486636369545, | |
| "eval_loss": 0.691852867603302, | |
| "eval_precision": 0.8361687645268726, | |
| "eval_qwk": 0.7349979059232339, | |
| "eval_recall": 0.8101577909270217, | |
| "eval_runtime": 23.1035, | |
| "eval_samples_per_second": 702.232, | |
| "eval_steps_per_second": 5.497, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.0025994801039795e-05, | |
| "loss": 0.3553, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_accuracy": 0.7843318540433925, | |
| "eval_f1": 0.7982445447583074, | |
| "eval_loss": 0.674355685710907, | |
| "eval_precision": 0.8311821725851122, | |
| "eval_qwk": 0.7133869717906458, | |
| "eval_recall": 0.7843318540433925, | |
| "eval_runtime": 23.1222, | |
| "eval_samples_per_second": 701.663, | |
| "eval_steps_per_second": 5.493, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.5026994601079786e-05, | |
| "loss": 0.3433, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_accuracy": 0.813732741617357, | |
| "eval_f1": 0.821008951036937, | |
| "eval_loss": 0.8146640658378601, | |
| "eval_precision": 0.8342737114916078, | |
| "eval_qwk": 0.7412639349881154, | |
| "eval_recall": 0.813732741617357, | |
| "eval_runtime": 23.1151, | |
| "eval_samples_per_second": 701.878, | |
| "eval_steps_per_second": 5.494, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.0037992401519696e-05, | |
| "loss": 0.2751, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.8128698224852071, | |
| "eval_f1": 0.8199992286734568, | |
| "eval_loss": 0.8419223427772522, | |
| "eval_precision": 0.8332550382998175, | |
| "eval_qwk": 0.7383621154665407, | |
| "eval_recall": 0.8128698224852071, | |
| "eval_runtime": 23.1425, | |
| "eval_samples_per_second": 701.047, | |
| "eval_steps_per_second": 5.488, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 5.038992201559688e-06, | |
| "loss": 0.2659, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.8022682445759369, | |
| "eval_f1": 0.8125481330626305, | |
| "eval_loss": 0.8309345841407776, | |
| "eval_precision": 0.8344366995643693, | |
| "eval_qwk": 0.7292405615679007, | |
| "eval_recall": 0.8022682445759369, | |
| "eval_runtime": 23.1428, | |
| "eval_samples_per_second": 701.039, | |
| "eval_steps_per_second": 5.488, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 3.9992001599680065e-08, | |
| "loss": 0.2346, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_accuracy": 0.8102810650887574, | |
| "eval_f1": 0.8179537922797215, | |
| "eval_loss": 0.8737895488739014, | |
| "eval_precision": 0.8320255779887702, | |
| "eval_qwk": 0.7367921505621005, | |
| "eval_recall": 0.8102810650887574, | |
| "eval_runtime": 23.1382, | |
| "eval_samples_per_second": 701.178, | |
| "eval_steps_per_second": 5.489, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "step": 5001, | |
| "total_flos": 1.6838837781764506e+17, | |
| "train_loss": 0.4127759954567505, | |
| "train_runtime": 2598.1165, | |
| "train_samples_per_second": 246.382, | |
| "train_steps_per_second": 1.925 | |
| } | |
| ], | |
| "max_steps": 5001, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.6838837781764506e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |