mbruton/gal_en_XLM-R
017
1{2 "best_metric": 0.3108000159263611,3 "best_model_checkpoint": "gal_en_XLM-R/checkpoint-1500",4 "epoch": 7.0,5 "global_step": 1750,6 "is_hyper_param_search": false,7 "is_local_process_zero": true,8 "is_world_process_zero": true,9 "log_history": [10 {11 "epoch": 1.0,12 "eval_accuracy": 0.8780973994111875,13 "eval_f1": 0.5202514522161216,14 "eval_loss": 0.44004401564598083,15 "eval_precision": 0.579507179578089,16 "eval_recall": 0.47198960438925786,17 "eval_runtime": 5.0934,18 "eval_samples_per_second": 195.743,19 "eval_steps_per_second": 12.369,20 "step": 25021 },22 {23 "epoch": 2.0,24 "learning_rate": 1.9600000000000002e-05,25 "loss": 0.5654,26 "step": 50027 },28 {29 "epoch": 2.0,30 "eval_accuracy": 0.9008218842001963,31 "eval_f1": 0.6336264719034134,32 "eval_loss": 0.35249266028404236,33 "eval_precision": 0.6548059149722736,34 "eval_recall": 0.6137741842333237,35 "eval_runtime": 5.0461,36 "eval_samples_per_second": 197.579,37 "eval_steps_per_second": 12.485,38 "step": 50039 },40 {41 "epoch": 3.0,42 "eval_accuracy": 0.8969271344455348,43 "eval_f1": 0.6431970884658454,44 "eval_loss": 0.3467901349067688,45 "eval_precision": 0.6241510459114371,46 "eval_recall": 0.6634421022235056,47 "eval_runtime": 5.0701,48 "eval_samples_per_second": 196.643,49 "eval_steps_per_second": 12.426,50 "step": 75051 },52 {53 "epoch": 4.0,54 "learning_rate": 1.9200000000000003e-05,55 "loss": 0.2931,56 "step": 100057 },58 {59 "epoch": 4.0,60 "eval_accuracy": 0.9097767419038273,61 "eval_f1": 0.6826355817755348,62 "eval_loss": 0.32281672954559326,63 "eval_precision": 0.6722665546689066,64 "eval_recall": 0.6933294831071325,65 "eval_runtime": 5.0717,66 "eval_samples_per_second": 196.581,67 "eval_steps_per_second": 12.422,68 "step": 100069 },70 {71 "epoch": 5.0,72 "eval_accuracy": 0.9145915112855741,73 "eval_f1": 0.6925381860703063,74 "eval_loss": 0.31136175990104675,75 "eval_precision": 0.7011987568447536,76 "eval_recall": 0.6840889402252383,77 "eval_runtime": 5.0357,78 "eval_samples_per_second": 197.986,79 "eval_steps_per_second": 12.511,80 "step": 125081 },82 {83 "epoch": 6.0,84 "learning_rate": 1.88e-05,85 "loss": 0.2226,86 "step": 150087 },88 {89 "epoch": 6.0,90 "eval_accuracy": 0.9143768400392541,91 "eval_f1": 0.6987883107626515,92 "eval_loss": 0.3108000159263611,93 "eval_precision": 0.6900337837837838,94 "eval_recall": 0.7077678313600924,95 "eval_runtime": 5.0908,96 "eval_samples_per_second": 195.845,97 "eval_steps_per_second": 12.375,98 "step": 150099 },100 {101 "epoch": 7.0,102 "eval_accuracy": 0.9163088812561334,103 "eval_f1": 0.7023861171366594,104 "eval_loss": 0.3187449276447296,105 "eval_precision": 0.703505214368482,106 "eval_recall": 0.7012705746462604,107 "eval_runtime": 5.1654,108 "eval_samples_per_second": 193.016,109 "eval_steps_per_second": 12.197,110 "step": 1750111 }112 ],113 "max_steps": 25000,114 "num_train_epochs": 100,115 "total_flos": 1079380891402800.0,116 "trial_name": null,117 "trial_params": null118}119 