| { | |
| "best_metric": 0.24537943303585052, | |
| "best_model_checkpoint": "spa_en_XLM-R/checkpoint-5376", | |
| "epoch": 7.0, | |
| "global_step": 6272, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.988839285714286e-05, | |
| "loss": 1.0832, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8977022223104879, | |
| "eval_f1": 0.700260468843919, | |
| "eval_loss": 0.40005847811698914, | |
| "eval_precision": 0.70720356131121, | |
| "eval_recall": 0.6934523809523809, | |
| "eval_runtime": 6.1063, | |
| "eval_samples_per_second": 270.867, | |
| "eval_steps_per_second": 17.032, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.9776785714285716e-05, | |
| "loss": 0.4679, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.9665178571428575e-05, | |
| "loss": 0.3483, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9241753222250909, | |
| "eval_f1": 0.7838645418326693, | |
| "eval_loss": 0.29495811462402344, | |
| "eval_precision": 0.787, | |
| "eval_recall": 0.7807539682539683, | |
| "eval_runtime": 6.0415, | |
| "eval_samples_per_second": 273.772, | |
| "eval_steps_per_second": 17.214, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.955357142857143e-05, | |
| "loss": 0.2969, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.944196428571429e-05, | |
| "loss": 0.255, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9284054574702599, | |
| "eval_f1": 0.7996062346185396, | |
| "eval_loss": 0.26967716217041016, | |
| "eval_precision": 0.7934874633669814, | |
| "eval_recall": 0.8058201058201058, | |
| "eval_runtime": 6.0465, | |
| "eval_samples_per_second": 273.548, | |
| "eval_steps_per_second": 17.2, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.9330357142857144e-05, | |
| "loss": 0.2169, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.9218750000000003e-05, | |
| "loss": 0.1974, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9298750819216333, | |
| "eval_f1": 0.8009127587803426, | |
| "eval_loss": 0.26213282346725464, | |
| "eval_precision": 0.8009657362084932, | |
| "eval_recall": 0.8008597883597883, | |
| "eval_runtime": 6.0415, | |
| "eval_samples_per_second": 273.772, | |
| "eval_steps_per_second": 17.214, | |
| "step": 3584 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 1.910714285714286e-05, | |
| "loss": 0.1762, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.93652811153258, | |
| "eval_f1": 0.8240402644823843, | |
| "eval_loss": 0.24596205353736877, | |
| "eval_precision": 0.819752601610053, | |
| "eval_recall": 0.8283730158730159, | |
| "eval_runtime": 6.0563, | |
| "eval_samples_per_second": 273.104, | |
| "eval_steps_per_second": 17.172, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 1.8995535714285717e-05, | |
| "loss": 0.1653, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 1.8883928571428573e-05, | |
| "loss": 0.1407, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9387524079995234, | |
| "eval_f1": 0.8292650658199379, | |
| "eval_loss": 0.24537943303585052, | |
| "eval_precision": 0.8294296678576154, | |
| "eval_recall": 0.8291005291005291, | |
| "eval_runtime": 6.1619, | |
| "eval_samples_per_second": 268.424, | |
| "eval_steps_per_second": 16.878, | |
| "step": 5376 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 1.8772321428571428e-05, | |
| "loss": 0.1362, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.8660714285714287e-05, | |
| "loss": 0.1214, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.937699839135702, | |
| "eval_f1": 0.826859776168532, | |
| "eval_loss": 0.2580417990684509, | |
| "eval_precision": 0.8230668414154653, | |
| "eval_recall": 0.8306878306878307, | |
| "eval_runtime": 6.2734, | |
| "eval_samples_per_second": 263.652, | |
| "eval_steps_per_second": 16.578, | |
| "step": 6272 | |
| } | |
| ], | |
| "max_steps": 89600, | |
| "num_train_epochs": 100, | |
| "total_flos": 4856704636063104.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |