| { | |
| "best_metric": 0.732569302631819, | |
| "best_model_checkpoint": "trained/hebban-reviews/bert-base-dutch-cased/checkpoint-3000", | |
| "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": 4.5000999800039995e-05, | |
| "loss": 0.6824, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.7763806706114399, | |
| "eval_f1": 0.7835745137864604, | |
| "eval_loss": 0.602776288986206, | |
| "eval_precision": 0.8014359034966511, | |
| "eval_qwk": 0.6748032105430382, | |
| "eval_recall": 0.7763806706114399, | |
| "eval_runtime": 23.7871, | |
| "eval_samples_per_second": 682.05, | |
| "eval_steps_per_second": 5.339, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.000199960007999e-05, | |
| "loss": 0.5903, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.7441444773175543, | |
| "eval_f1": 0.7623993009582866, | |
| "eval_loss": 0.5676863789558411, | |
| "eval_precision": 0.8079269153410689, | |
| "eval_qwk": 0.6673976411458487, | |
| "eval_recall": 0.7441444773175543, | |
| "eval_runtime": 23.3353, | |
| "eval_samples_per_second": 695.257, | |
| "eval_steps_per_second": 5.442, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.50129974005199e-05, | |
| "loss": 0.487, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.7938239644970414, | |
| "eval_f1": 0.8033347539691899, | |
| "eval_loss": 0.5801703333854675, | |
| "eval_precision": 0.8206089090362688, | |
| "eval_qwk": 0.7239594229437711, | |
| "eval_recall": 0.7938239644970414, | |
| "eval_runtime": 23.5912, | |
| "eval_samples_per_second": 687.714, | |
| "eval_steps_per_second": 5.383, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.001399720055989e-05, | |
| "loss": 0.4465, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.7809418145956607, | |
| "eval_f1": 0.7939963208456309, | |
| "eval_loss": 0.5808519721031189, | |
| "eval_precision": 0.8222816466721266, | |
| "eval_qwk": 0.7118880899721043, | |
| "eval_recall": 0.7809418145956607, | |
| "eval_runtime": 23.7528, | |
| "eval_samples_per_second": 683.034, | |
| "eval_steps_per_second": 5.347, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.501499700059988e-05, | |
| "loss": 0.3808, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.8011587771203156, | |
| "eval_f1": 0.8108361051205994, | |
| "eval_loss": 0.7650117874145508, | |
| "eval_precision": 0.8317278803823261, | |
| "eval_qwk": 0.7224991347098964, | |
| "eval_recall": 0.8011587771203156, | |
| "eval_runtime": 23.668, | |
| "eval_samples_per_second": 685.482, | |
| "eval_steps_per_second": 5.366, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.001599680063987e-05, | |
| "loss": 0.2909, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_accuracy": 0.8086168639053254, | |
| "eval_f1": 0.8166494576368075, | |
| "eval_loss": 0.7910537719726562, | |
| "eval_precision": 0.8320947395056137, | |
| "eval_qwk": 0.732569302631819, | |
| "eval_recall": 0.8086168639053254, | |
| "eval_runtime": 23.5554, | |
| "eval_samples_per_second": 688.761, | |
| "eval_steps_per_second": 5.392, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.5026994601079786e-05, | |
| "loss": 0.2746, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_accuracy": 0.7985083826429981, | |
| "eval_f1": 0.8084609549617363, | |
| "eval_loss": 0.9503954648971558, | |
| "eval_precision": 0.8285545185236465, | |
| "eval_qwk": 0.7236034727222331, | |
| "eval_recall": 0.7985083826429981, | |
| "eval_runtime": 23.5785, | |
| "eval_samples_per_second": 688.084, | |
| "eval_steps_per_second": 5.386, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.0027994401119777e-05, | |
| "loss": 0.1939, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.7966592702169625, | |
| "eval_f1": 0.8064656300991808, | |
| "eval_loss": 0.9597578048706055, | |
| "eval_precision": 0.8249666716932728, | |
| "eval_qwk": 0.7250412688400546, | |
| "eval_recall": 0.7966592702169625, | |
| "eval_runtime": 23.6525, | |
| "eval_samples_per_second": 685.931, | |
| "eval_steps_per_second": 5.369, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 5.028994201159768e-06, | |
| "loss": 0.1824, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.8023298816568047, | |
| "eval_f1": 0.810968480495596, | |
| "eval_loss": 1.060992956161499, | |
| "eval_precision": 0.8277405554545381, | |
| "eval_qwk": 0.7252407399333649, | |
| "eval_recall": 0.8023298816568047, | |
| "eval_runtime": 23.7166, | |
| "eval_samples_per_second": 684.077, | |
| "eval_steps_per_second": 5.355, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.999400119976005e-08, | |
| "loss": 0.1426, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_accuracy": 0.8090483234714004, | |
| "eval_f1": 0.8157426407187547, | |
| "eval_loss": 1.1207919120788574, | |
| "eval_precision": 0.8273912560003507, | |
| "eval_qwk": 0.7316045159099166, | |
| "eval_recall": 0.8090483234714004, | |
| "eval_runtime": 23.6323, | |
| "eval_samples_per_second": 686.518, | |
| "eval_steps_per_second": 5.374, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "step": 5001, | |
| "total_flos": 1.6838837781764506e+17, | |
| "train_loss": 0.3670836862052257, | |
| "train_runtime": 2628.6927, | |
| "train_samples_per_second": 243.516, | |
| "train_steps_per_second": 1.902 | |
| } | |
| ], | |
| "max_steps": 5001, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.6838837781764506e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |