{ "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": 0.7458100558659218, "eval_f1": 0.0, "eval_loss": 1.2875592708587646, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.0647, "eval_samples_per_second": 123.718, "eval_steps_per_second": 15.465, "step": 7 }, { "epoch": 1.94, "eval_accuracy": 0.7458100558659218, "eval_f1": 0.0, "eval_loss": 0.9501006007194519, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.1181, "eval_samples_per_second": 67.741, "eval_steps_per_second": 8.468, "step": 15 }, { "epoch": 2.97, "eval_accuracy": 0.7946927374301676, "eval_f1": 0.1605839416058394, "eval_loss": 0.7821663618087769, "eval_precision": 0.15942028985507245, "eval_recall": 0.16176470588235295, "eval_runtime": 0.0656, "eval_samples_per_second": 121.917, "eval_steps_per_second": 15.24, "step": 23 }, { "epoch": 4.0, "eval_accuracy": 0.8240223463687151, "eval_f1": 0.3636363636363636, "eval_loss": 0.6530368328094482, "eval_precision": 0.3466666666666667, "eval_recall": 0.38235294117647056, "eval_runtime": 0.0584, "eval_samples_per_second": 137.09, "eval_steps_per_second": 17.136, "step": 31 }, { "epoch": 4.9, "eval_accuracy": 0.8519553072625698, "eval_f1": 0.5454545454545454, "eval_loss": 0.5587103366851807, "eval_precision": 0.52, "eval_recall": 0.5735294117647058, "eval_runtime": 0.0576, "eval_samples_per_second": 138.924, "eval_steps_per_second": 17.366, "step": 38 }, { "epoch": 5.94, "eval_accuracy": 0.88268156424581, "eval_f1": 0.5732484076433122, "eval_loss": 0.501702070236206, "eval_precision": 0.5056179775280899, "eval_recall": 0.6617647058823529, "eval_runtime": 0.0775, "eval_samples_per_second": 103.223, "eval_steps_per_second": 12.903, "step": 46 }, { "epoch": 6.97, "eval_accuracy": 0.9078212290502793, "eval_f1": 0.5875, "eval_loss": 0.43670037388801575, "eval_precision": 0.5108695652173914, "eval_recall": 0.6911764705882353, "eval_runtime": 0.094, "eval_samples_per_second": 85.063, "eval_steps_per_second": 10.633, "step": 54 }, { "epoch": 8.0, "eval_accuracy": 0.8966480446927374, "eval_f1": 0.5987261146496815, "eval_loss": 0.4147437810897827, "eval_precision": 0.5280898876404494, "eval_recall": 0.6911764705882353, "eval_runtime": 0.0593, "eval_samples_per_second": 134.952, "eval_steps_per_second": 16.869, "step": 62 }, { "epoch": 8.9, "eval_accuracy": 0.9175977653631285, "eval_f1": 0.6933333333333332, "eval_loss": 0.40070846676826477, "eval_precision": 0.6341463414634146, "eval_recall": 0.7647058823529411, "eval_runtime": 0.0605, "eval_samples_per_second": 132.124, "eval_steps_per_second": 16.515, "step": 69 }, { "epoch": 9.94, "eval_accuracy": 0.914804469273743, "eval_f1": 0.6887417218543046, "eval_loss": 0.3914220929145813, "eval_precision": 0.6265060240963856, "eval_recall": 0.7647058823529411, "eval_runtime": 0.0705, "eval_samples_per_second": 113.511, "eval_steps_per_second": 14.189, "step": 77 }, { "epoch": 10.97, "eval_accuracy": 0.9231843575418994, "eval_f1": 0.7012987012987012, "eval_loss": 0.3615421652793884, "eval_precision": 0.627906976744186, "eval_recall": 0.7941176470588235, "eval_runtime": 0.0583, "eval_samples_per_second": 137.228, "eval_steps_per_second": 17.153, "step": 85 }, { "epoch": 12.0, "eval_accuracy": 0.9245810055865922, "eval_f1": 0.7397260273972601, "eval_loss": 0.3441668450832367, "eval_precision": 0.6923076923076923, "eval_recall": 0.7941176470588235, "eval_runtime": 0.088, "eval_samples_per_second": 90.913, "eval_steps_per_second": 11.364, "step": 93 }, { "epoch": 12.9, "eval_accuracy": 0.9287709497206704, "eval_f1": 0.7586206896551725, "eval_loss": 0.3498682677745819, "eval_precision": 0.7142857142857143, "eval_recall": 0.8088235294117647, "eval_runtime": 0.059, "eval_samples_per_second": 135.636, "eval_steps_per_second": 16.955, "step": 100 }, { "epoch": 13.94, "eval_accuracy": 0.9301675977653632, "eval_f1": 0.7837837837837837, "eval_loss": 0.35167065262794495, "eval_precision": 0.725, "eval_recall": 0.8529411764705882, "eval_runtime": 0.0789, "eval_samples_per_second": 101.355, "eval_steps_per_second": 12.669, "step": 108 }, { "epoch": 14.97, "eval_accuracy": 0.9273743016759777, "eval_f1": 0.7482993197278912, "eval_loss": 0.35690194368362427, "eval_precision": 0.6962025316455697, "eval_recall": 0.8088235294117647, "eval_runtime": 0.0589, "eval_samples_per_second": 135.816, "eval_steps_per_second": 16.977, "step": 116 }, { "epoch": 16.0, "eval_accuracy": 0.9287709497206704, "eval_f1": 0.761904761904762, "eval_loss": 0.3552975058555603, "eval_precision": 0.7088607594936709, "eval_recall": 0.8235294117647058, "eval_runtime": 0.0587, "eval_samples_per_second": 136.349, "eval_steps_per_second": 17.044, "step": 124 }, { "epoch": 16.9, "eval_accuracy": 0.9259776536312849, "eval_f1": 0.767123287671233, "eval_loss": 0.35346120595932007, "eval_precision": 0.717948717948718, "eval_recall": 0.8235294117647058, "eval_runtime": 0.0838, "eval_samples_per_second": 95.442, "eval_steps_per_second": 11.93, "step": 131 }, { "epoch": 17.94, "eval_accuracy": 0.9259776536312849, "eval_f1": 0.7567567567567567, "eval_loss": 0.3554823398590088, "eval_precision": 0.7, "eval_recall": 0.8235294117647058, "eval_runtime": 0.061, "eval_samples_per_second": 131.23, "eval_steps_per_second": 16.404, "step": 139 }, { "epoch": 18.06, "eval_accuracy": 0.9259776536312849, "eval_f1": 0.7567567567567567, "eval_loss": 0.355307012796402, "eval_precision": 0.7, "eval_recall": 0.8235294117647058, "eval_runtime": 0.0634, "eval_samples_per_second": 126.271, "eval_steps_per_second": 15.784, "step": 140 }, { "epoch": 18.06, "step": 140, "total_flos": 142823207204352.0, "train_loss": 0.3916678019932338, "train_runtime": 1023.1328, "train_samples_per_second": 2.365, "train_steps_per_second": 0.137 } ], "max_steps": 140, "num_train_epochs": 20, "total_flos": 142823207204352.0, "trial_name": null, "trial_params": null }