{ "best_metric": null, "best_model_checkpoint": null, "epoch": 18.06451612903226, "global_step": 140, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9, "eval_accuracy": 0.7640449438202247, "eval_f1": 0.0, "eval_loss": 1.1711010932922363, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.0905, "eval_samples_per_second": 88.431, "eval_steps_per_second": 11.054, "step": 7 }, { "epoch": 1.94, "eval_accuracy": 0.7640449438202247, "eval_f1": 0.0, "eval_loss": 0.8495532274246216, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.0887, "eval_samples_per_second": 90.205, "eval_steps_per_second": 11.276, "step": 15 }, { "epoch": 2.97, "eval_accuracy": 0.846441947565543, "eval_f1": 0.36, "eval_loss": 0.6479682922363281, "eval_precision": 0.34177215189873417, "eval_recall": 0.38028169014084506, "eval_runtime": 0.0624, "eval_samples_per_second": 128.122, "eval_steps_per_second": 16.015, "step": 23 }, { "epoch": 4.0, "eval_accuracy": 0.8614232209737828, "eval_f1": 0.4657534246575343, "eval_loss": 0.5528039932250977, "eval_precision": 0.4533333333333333, "eval_recall": 0.4788732394366197, "eval_runtime": 0.0609, "eval_samples_per_second": 131.435, "eval_steps_per_second": 16.429, "step": 31 }, { "epoch": 4.9, "eval_accuracy": 0.8876404494382022, "eval_f1": 0.543046357615894, "eval_loss": 0.5004148483276367, "eval_precision": 0.5125, "eval_recall": 0.5774647887323944, "eval_runtime": 0.0771, "eval_samples_per_second": 103.737, "eval_steps_per_second": 12.967, "step": 38 }, { "epoch": 5.94, "eval_accuracy": 0.9038701622971286, "eval_f1": 0.632258064516129, "eval_loss": 0.46185028553009033, "eval_precision": 0.5833333333333334, "eval_recall": 0.6901408450704225, "eval_runtime": 0.0979, "eval_samples_per_second": 81.705, "eval_steps_per_second": 10.213, "step": 46 }, { "epoch": 6.97, "eval_accuracy": 0.8976279650436954, "eval_f1": 0.6143790849673202, "eval_loss": 0.4409206807613373, "eval_precision": 0.573170731707317, "eval_recall": 0.6619718309859155, "eval_runtime": 0.0613, "eval_samples_per_second": 130.58, "eval_steps_per_second": 16.323, "step": 54 }, { "epoch": 8.0, "eval_accuracy": 0.9038701622971286, "eval_f1": 0.6540880503144655, "eval_loss": 0.41902562975883484, "eval_precision": 0.5909090909090909, "eval_recall": 0.7323943661971831, "eval_runtime": 0.0632, "eval_samples_per_second": 126.495, "eval_steps_per_second": 15.812, "step": 62 }, { "epoch": 8.9, "eval_accuracy": 0.9088639200998752, "eval_f1": 0.6075949367088608, "eval_loss": 0.41402581334114075, "eval_precision": 0.5517241379310345, "eval_recall": 0.676056338028169, "eval_runtime": 0.08, "eval_samples_per_second": 99.991, "eval_steps_per_second": 12.499, "step": 69 }, { "epoch": 9.94, "eval_accuracy": 0.9101123595505618, "eval_f1": 0.6463414634146342, "eval_loss": 0.4209658205509186, "eval_precision": 0.5698924731182796, "eval_recall": 0.7464788732394366, "eval_runtime": 0.0753, "eval_samples_per_second": 106.269, "eval_steps_per_second": 13.284, "step": 77 }, { "epoch": 10.97, "eval_accuracy": 0.9176029962546817, "eval_f1": 0.6257668711656442, "eval_loss": 0.4074121415615082, "eval_precision": 0.5543478260869565, "eval_recall": 0.7183098591549296, "eval_runtime": 0.0641, "eval_samples_per_second": 124.724, "eval_steps_per_second": 15.591, "step": 85 }, { "epoch": 12.0, "eval_accuracy": 0.9138576779026217, "eval_f1": 0.6296296296296295, "eval_loss": 0.4206610321998596, "eval_precision": 0.5604395604395604, "eval_recall": 0.7183098591549296, "eval_runtime": 0.0628, "eval_samples_per_second": 127.441, "eval_steps_per_second": 15.93, "step": 93 }, { "epoch": 12.9, "eval_accuracy": 0.9138576779026217, "eval_f1": 0.6380368098159509, "eval_loss": 0.41813310980796814, "eval_precision": 0.5652173913043478, "eval_recall": 0.7323943661971831, "eval_runtime": 0.0843, "eval_samples_per_second": 94.887, "eval_steps_per_second": 11.861, "step": 100 }, { "epoch": 13.94, "eval_accuracy": 0.9151061173533084, "eval_f1": 0.6503067484662577, "eval_loss": 0.42074155807495117, "eval_precision": 0.5760869565217391, "eval_recall": 0.7464788732394366, "eval_runtime": 0.0639, "eval_samples_per_second": 125.197, "eval_steps_per_second": 15.65, "step": 108 }, { "epoch": 14.97, "eval_accuracy": 0.9176029962546817, "eval_f1": 0.6625, "eval_loss": 0.4188980460166931, "eval_precision": 0.5955056179775281, "eval_recall": 0.7464788732394366, "eval_runtime": 0.0909, "eval_samples_per_second": 87.963, "eval_steps_per_second": 10.995, "step": 116 }, { "epoch": 16.0, "eval_accuracy": 0.920099875156055, "eval_f1": 0.6666666666666666, "eval_loss": 0.4166664779186249, "eval_precision": 0.6022727272727273, "eval_recall": 0.7464788732394366, "eval_runtime": 0.0772, "eval_samples_per_second": 103.585, "eval_steps_per_second": 12.948, "step": 124 }, { "epoch": 16.9, "eval_accuracy": 0.9176029962546817, "eval_f1": 0.6583850931677019, "eval_loss": 0.4165511429309845, "eval_precision": 0.5888888888888889, "eval_recall": 0.7464788732394366, "eval_runtime": 0.0861, "eval_samples_per_second": 92.942, "eval_steps_per_second": 11.618, "step": 131 }, { "epoch": 17.94, "eval_accuracy": 0.9176029962546817, "eval_f1": 0.6583850931677019, "eval_loss": 0.41603589057922363, "eval_precision": 0.5888888888888889, "eval_recall": 0.7464788732394366, "eval_runtime": 0.076, "eval_samples_per_second": 105.309, "eval_steps_per_second": 13.164, "step": 139 }, { "epoch": 18.06, "eval_accuracy": 0.9176029962546817, "eval_f1": 0.6583850931677019, "eval_loss": 0.4160560369491577, "eval_precision": 0.5888888888888889, "eval_recall": 0.7464788732394366, "eval_runtime": 0.0925, "eval_samples_per_second": 86.509, "eval_steps_per_second": 10.814, "step": 140 }, { "epoch": 18.06, "step": 140, "total_flos": 142823207204352.0, "train_loss": 0.3585296630859375, "train_runtime": 632.6175, "train_samples_per_second": 3.825, "train_steps_per_second": 0.221 } ], "max_steps": 140, "num_train_epochs": 20, "total_flos": 142823207204352.0, "trial_name": null, "trial_params": null }