| { |
| "best_metric": 0.6316497325897217, |
| "best_model_checkpoint": "BERT-ARSEN/checkpoint-55", |
| "epoch": 15.0, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 2.5e-06, |
| "loss": 1.0918, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.43283582089552236, |
| "eval_f1": 0.3532385194509964, |
| "eval_loss": 1.0713645219802856, |
| "eval_precision": 0.4144311230023238, |
| "eval_recall": 0.43283582089552236, |
| "eval_runtime": 0.134, |
| "eval_samples_per_second": 1999.593, |
| "eval_steps_per_second": 22.384, |
| "step": 5 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 5e-06, |
| "loss": 1.0681, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.48134328358208955, |
| "eval_f1": 0.39493626001507154, |
| "eval_loss": 1.0380339622497559, |
| "eval_precision": 0.4866710481682497, |
| "eval_recall": 0.48134328358208955, |
| "eval_runtime": 0.1358, |
| "eval_samples_per_second": 1972.903, |
| "eval_steps_per_second": 22.085, |
| "step": 10 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 7.5e-06, |
| "loss": 1.035, |
| "step": 15 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5373134328358209, |
| "eval_f1": 0.48095672382504345, |
| "eval_loss": 0.9922763109207153, |
| "eval_precision": 0.5399777039880542, |
| "eval_recall": 0.5373134328358209, |
| "eval_runtime": 0.1356, |
| "eval_samples_per_second": 1977.06, |
| "eval_steps_per_second": 22.131, |
| "step": 15 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 1e-05, |
| "loss": 0.9839, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6007462686567164, |
| "eval_f1": 0.5693096769377645, |
| "eval_loss": 0.9435768723487854, |
| "eval_precision": 0.6076634834303061, |
| "eval_recall": 0.6007462686567164, |
| "eval_runtime": 0.1364, |
| "eval_samples_per_second": 1964.679, |
| "eval_steps_per_second": 21.993, |
| "step": 20 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 1.25e-05, |
| "loss": 0.9336, |
| "step": 25 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6231343283582089, |
| "eval_f1": 0.5984336131840795, |
| "eval_loss": 0.8942344784736633, |
| "eval_precision": 0.6523796113770769, |
| "eval_recall": 0.6231343283582089, |
| "eval_runtime": 0.1364, |
| "eval_samples_per_second": 1964.418, |
| "eval_steps_per_second": 21.99, |
| "step": 25 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 1.5e-05, |
| "loss": 0.8809, |
| "step": 30 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6492537313432836, |
| "eval_f1": 0.6324945184020617, |
| "eval_loss": 0.8408194184303284, |
| "eval_precision": 0.6599803255574266, |
| "eval_recall": 0.6492537313432836, |
| "eval_runtime": 0.1336, |
| "eval_samples_per_second": 2006.425, |
| "eval_steps_per_second": 22.46, |
| "step": 30 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 1.75e-05, |
| "loss": 0.8148, |
| "step": 35 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.6716417910447762, |
| "eval_f1": 0.6605334275104363, |
| "eval_loss": 0.782370924949646, |
| "eval_precision": 0.6661882893226178, |
| "eval_recall": 0.6716417910447762, |
| "eval_runtime": 0.1324, |
| "eval_samples_per_second": 2024.26, |
| "eval_steps_per_second": 22.66, |
| "step": 35 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 2e-05, |
| "loss": 0.7508, |
| "step": 40 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.7052238805970149, |
| "eval_f1": 0.6995305661367046, |
| "eval_loss": 0.7225587964057922, |
| "eval_precision": 0.7073670514791276, |
| "eval_recall": 0.7052238805970149, |
| "eval_runtime": 0.1353, |
| "eval_samples_per_second": 1981.169, |
| "eval_steps_per_second": 22.177, |
| "step": 40 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 2.25e-05, |
| "loss": 0.6695, |
| "step": 45 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.7276119402985075, |
| "eval_f1": 0.7236921719692019, |
| "eval_loss": 0.6665202975273132, |
| "eval_precision": 0.7295172823827262, |
| "eval_recall": 0.7276119402985075, |
| "eval_runtime": 0.1351, |
| "eval_samples_per_second": 1983.269, |
| "eval_steps_per_second": 22.201, |
| "step": 45 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 2.5e-05, |
| "loss": 0.584, |
| "step": 50 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.75, |
| "eval_f1": 0.7470690302815178, |
| "eval_loss": 0.6408671140670776, |
| "eval_precision": 0.7550608812622434, |
| "eval_recall": 0.75, |
| "eval_runtime": 0.1362, |
| "eval_samples_per_second": 1967.771, |
| "eval_steps_per_second": 22.027, |
| "step": 50 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.5075, |
| "step": 55 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.746268656716418, |
| "eval_f1": 0.745340347616869, |
| "eval_loss": 0.6316497325897217, |
| "eval_precision": 0.7538392624690169, |
| "eval_recall": 0.746268656716418, |
| "eval_runtime": 0.1325, |
| "eval_samples_per_second": 2022.508, |
| "eval_steps_per_second": 22.64, |
| "step": 55 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4227, |
| "step": 60 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.746268656716418, |
| "eval_f1": 0.748055387005625, |
| "eval_loss": 0.6650494337081909, |
| "eval_precision": 0.7570257710656463, |
| "eval_recall": 0.746268656716418, |
| "eval_runtime": 0.1359, |
| "eval_samples_per_second": 1972.592, |
| "eval_steps_per_second": 22.081, |
| "step": 60 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 3.2500000000000004e-05, |
| "loss": 0.3597, |
| "step": 65 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.753731343283582, |
| "eval_f1": 0.753860434157966, |
| "eval_loss": 0.6879275441169739, |
| "eval_precision": 0.755069115659257, |
| "eval_recall": 0.753731343283582, |
| "eval_runtime": 0.1345, |
| "eval_samples_per_second": 1991.993, |
| "eval_steps_per_second": 22.298, |
| "step": 65 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 3.5e-05, |
| "loss": 0.3033, |
| "step": 70 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.7425373134328358, |
| "eval_f1": 0.7406282233338326, |
| "eval_loss": 0.7484950423240662, |
| "eval_precision": 0.7440711204425821, |
| "eval_recall": 0.7425373134328358, |
| "eval_runtime": 0.1394, |
| "eval_samples_per_second": 1922.006, |
| "eval_steps_per_second": 21.515, |
| "step": 70 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.2552, |
| "step": 75 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.7276119402985075, |
| "eval_f1": 0.7291799866625598, |
| "eval_loss": 0.8274917602539062, |
| "eval_precision": 0.7334363284641777, |
| "eval_recall": 0.7276119402985075, |
| "eval_runtime": 0.1356, |
| "eval_samples_per_second": 1976.511, |
| "eval_steps_per_second": 22.125, |
| "step": 75 |
| } |
| ], |
| "max_steps": 250, |
| "num_train_epochs": 50, |
| "total_flos": 1416297902264910.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
