| { |
| "best_metric": 0.8770697441043652, |
| "best_model_checkpoint": "xlm-roberta-large-spanish-clinical-medic-attr-ner-cima-cases-early-stop-round5/checkpoint-21714", |
| "epoch": 7.0, |
| "global_step": 21714, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16, |
| "learning_rate": 1.989254244573394e-05, |
| "loss": 0.1565, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.9785084891467873e-05, |
| "loss": 0.0586, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 1.9677627337201807e-05, |
| "loss": 0.0462, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 1.957016978293574e-05, |
| "loss": 0.0375, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.946271222866968e-05, |
| "loss": 0.0346, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 1.9355254674403613e-05, |
| "loss": 0.0349, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9956815585119774, |
| "eval_f1": 0.8532249873031995, |
| "eval_loss": 0.0175024326890707, |
| "eval_precision": 0.8759124087591241, |
| "eval_recall": 0.8316831683168316, |
| "eval_runtime": 11.689, |
| "eval_samples_per_second": 353.838, |
| "eval_steps_per_second": 44.23, |
| "step": 3102 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 1.9247797120137547e-05, |
| "loss": 0.0317, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 1.914033956587148e-05, |
| "loss": 0.0207, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 1.9032882011605418e-05, |
| "loss": 0.0274, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 1.8925424457339352e-05, |
| "loss": 0.0205, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 1.881796690307329e-05, |
| "loss": 0.0254, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 1.8710509348807224e-05, |
| "loss": 0.0187, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9956718759077442, |
| "eval_f1": 0.832442933462846, |
| "eval_loss": 0.016502007842063904, |
| "eval_precision": 0.8169685414680649, |
| "eval_recall": 0.8485148514851485, |
| "eval_runtime": 11.4567, |
| "eval_samples_per_second": 361.013, |
| "eval_steps_per_second": 45.127, |
| "step": 6204 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 1.8603051794541158e-05, |
| "loss": 0.0183, |
| "step": 6500 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 1.849559424027509e-05, |
| "loss": 0.0126, |
| "step": 7000 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 1.838813668600903e-05, |
| "loss": 0.0194, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 1.8280679131742963e-05, |
| "loss": 0.0203, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 1.8173221577476897e-05, |
| "loss": 0.018, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 1.806576402321083e-05, |
| "loss": 0.0206, |
| "step": 9000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9954782238230795, |
| "eval_f1": 0.8585858585858587, |
| "eval_loss": 0.02153652347624302, |
| "eval_precision": 0.8762886597938144, |
| "eval_recall": 0.8415841584158416, |
| "eval_runtime": 11.4248, |
| "eval_samples_per_second": 362.02, |
| "eval_steps_per_second": 45.252, |
| "step": 9306 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 1.795830646894477e-05, |
| "loss": 0.0144, |
| "step": 9500 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 1.7850848914678703e-05, |
| "loss": 0.0142, |
| "step": 10000 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 1.774339136041264e-05, |
| "loss": 0.0114, |
| "step": 10500 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 1.7635933806146574e-05, |
| "loss": 0.0155, |
| "step": 11000 |
| }, |
| { |
| "epoch": 3.71, |
| "learning_rate": 1.7528476251880508e-05, |
| "loss": 0.0128, |
| "step": 11500 |
| }, |
| { |
| "epoch": 3.87, |
| "learning_rate": 1.7421018697614445e-05, |
| "loss": 0.0144, |
| "step": 12000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9957783845543098, |
| "eval_f1": 0.86, |
| "eval_loss": 0.021290840581059456, |
| "eval_precision": 0.8686868686868687, |
| "eval_recall": 0.8514851485148515, |
| "eval_runtime": 11.4556, |
| "eval_samples_per_second": 361.046, |
| "eval_steps_per_second": 45.131, |
| "step": 12408 |
| }, |
| { |
| "epoch": 4.03, |
| "learning_rate": 1.731356114334838e-05, |
| "loss": 0.0159, |
| "step": 12500 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 1.7206103589082313e-05, |
| "loss": 0.0091, |
| "step": 13000 |
| }, |
| { |
| "epoch": 4.35, |
| "learning_rate": 1.7098646034816248e-05, |
| "loss": 0.0105, |
| "step": 13500 |
| }, |
| { |
| "epoch": 4.51, |
| "learning_rate": 1.6991188480550185e-05, |
| "loss": 0.0109, |
| "step": 14000 |
| }, |
| { |
| "epoch": 4.67, |
| "learning_rate": 1.688373092628412e-05, |
| "loss": 0.011, |
| "step": 14500 |
| }, |
| { |
| "epoch": 4.84, |
| "learning_rate": 1.6776273372018056e-05, |
| "loss": 0.0154, |
| "step": 15000 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 1.666881581775199e-05, |
| "loss": 0.0136, |
| "step": 15500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9955750498654118, |
| "eval_f1": 0.8574190430159497, |
| "eval_loss": 0.023742612451314926, |
| "eval_precision": 0.8375826251180358, |
| "eval_recall": 0.8782178217821782, |
| "eval_runtime": 11.5216, |
| "eval_samples_per_second": 358.978, |
| "eval_steps_per_second": 44.872, |
| "step": 15510 |
| }, |
| { |
| "epoch": 5.16, |
| "learning_rate": 1.6561358263485924e-05, |
| "loss": 0.0078, |
| "step": 16000 |
| }, |
| { |
| "epoch": 5.32, |
| "learning_rate": 1.645390070921986e-05, |
| "loss": 0.0086, |
| "step": 16500 |
| }, |
| { |
| "epoch": 5.48, |
| "learning_rate": 1.6346443154953796e-05, |
| "loss": 0.0088, |
| "step": 17000 |
| }, |
| { |
| "epoch": 5.64, |
| "learning_rate": 1.623898560068773e-05, |
| "loss": 0.0124, |
| "step": 17500 |
| }, |
| { |
| "epoch": 5.8, |
| "learning_rate": 1.6131528046421664e-05, |
| "loss": 0.0097, |
| "step": 18000 |
| }, |
| { |
| "epoch": 5.96, |
| "learning_rate": 1.6024070492155598e-05, |
| "loss": 0.0062, |
| "step": 18500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.995255523925715, |
| "eval_f1": 0.847248576850095, |
| "eval_loss": 0.02595967799425125, |
| "eval_precision": 0.8132969034608379, |
| "eval_recall": 0.8841584158415842, |
| "eval_runtime": 11.399, |
| "eval_samples_per_second": 362.839, |
| "eval_steps_per_second": 45.355, |
| "step": 18612 |
| }, |
| { |
| "epoch": 6.13, |
| "learning_rate": 1.5916612937889535e-05, |
| "loss": 0.008, |
| "step": 19000 |
| }, |
| { |
| "epoch": 6.29, |
| "learning_rate": 1.580915538362347e-05, |
| "loss": 0.0108, |
| "step": 19500 |
| }, |
| { |
| "epoch": 6.45, |
| "learning_rate": 1.5701697829357407e-05, |
| "loss": 0.0065, |
| "step": 20000 |
| }, |
| { |
| "epoch": 6.61, |
| "learning_rate": 1.559424027509134e-05, |
| "loss": 0.0076, |
| "step": 20500 |
| }, |
| { |
| "epoch": 6.77, |
| "learning_rate": 1.5486782720825275e-05, |
| "loss": 0.0108, |
| "step": 21000 |
| }, |
| { |
| "epoch": 6.93, |
| "learning_rate": 1.5379325166559212e-05, |
| "loss": 0.0117, |
| "step": 21500 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9962721973702047, |
| "eval_f1": 0.8770697441043652, |
| "eval_loss": 0.025852469727396965, |
| "eval_precision": 0.8891149542217701, |
| "eval_recall": 0.8653465346534653, |
| "eval_runtime": 11.3646, |
| "eval_samples_per_second": 363.939, |
| "eval_steps_per_second": 45.492, |
| "step": 21714 |
| } |
| ], |
| "max_steps": 93060, |
| "num_train_epochs": 30, |
| "total_flos": 1.869620608557659e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
