| { |
| "best_metric": 0.18770882487297058, |
| "best_model_checkpoint": "./models/results_one_liners_453/checkpoint-225", |
| "epoch": 0.6489994591671173, |
| "global_step": 225, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.6902, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.6955, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 1.2e-05, |
| "loss": 0.6911, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.07, |
| "eval_accuracy": 0.49842271293375395, |
| "eval_f1": 0.6618460229689495, |
| "eval_loss": 0.6824508309364319, |
| "eval_precision": 0.494596312778131, |
| "eval_recall": 1.0, |
| "eval_runtime": 18.4237, |
| "eval_samples_per_second": 172.061, |
| "eval_steps_per_second": 21.548, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.674, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 2e-05, |
| "loss": 0.611, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 2.4e-05, |
| "loss": 0.4327, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.14, |
| "eval_accuracy": 0.8712933753943217, |
| "eval_f1": 0.8696485623003196, |
| "eval_loss": 0.31961607933044434, |
| "eval_precision": 0.8646759847522236, |
| "eval_recall": 0.8746786632390745, |
| "eval_runtime": 18.2327, |
| "eval_samples_per_second": 173.864, |
| "eval_steps_per_second": 21.774, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 0.3598, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.392, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 3.6e-05, |
| "loss": 0.3812, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.22, |
| "eval_accuracy": 0.8914826498422713, |
| "eval_f1": 0.8940234134319162, |
| "eval_loss": 0.2683391869068146, |
| "eval_precision": 0.8585798816568048, |
| "eval_recall": 0.9325192802056556, |
| "eval_runtime": 18.1749, |
| "eval_samples_per_second": 174.416, |
| "eval_steps_per_second": 21.843, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 4e-05, |
| "loss": 0.3055, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.3159, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 4.8e-05, |
| "loss": 0.3093, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.29, |
| "eval_accuracy": 0.9025236593059937, |
| "eval_f1": 0.896551724137931, |
| "eval_loss": 0.26234087347984314, |
| "eval_precision": 0.9357092941998603, |
| "eval_recall": 0.8605398457583547, |
| "eval_runtime": 18.2515, |
| "eval_samples_per_second": 173.684, |
| "eval_steps_per_second": 21.752, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 4.9186991869918704e-05, |
| "loss": 0.3469, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 4.75609756097561e-05, |
| "loss": 0.3545, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 4.613821138211382e-05, |
| "loss": 0.3241, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.36, |
| "eval_accuracy": 0.8858044164037855, |
| "eval_f1": 0.8927725118483413, |
| "eval_loss": 0.30523255467414856, |
| "eval_precision": 0.828021978021978, |
| "eval_recall": 0.968508997429306, |
| "eval_runtime": 18.1682, |
| "eval_samples_per_second": 174.481, |
| "eval_steps_per_second": 21.851, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 4.451219512195122e-05, |
| "loss": 0.2721, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 4.2886178861788616e-05, |
| "loss": 0.3343, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 4.126016260162602e-05, |
| "loss": 0.3455, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.43, |
| "eval_accuracy": 0.9141955835962146, |
| "eval_f1": 0.9128205128205129, |
| "eval_loss": 0.22679537534713745, |
| "eval_precision": 0.9104859335038363, |
| "eval_recall": 0.9151670951156813, |
| "eval_runtime": 18.2508, |
| "eval_samples_per_second": 173.691, |
| "eval_steps_per_second": 21.752, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 3.9634146341463416e-05, |
| "loss": 0.2462, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 3.800813008130081e-05, |
| "loss": 0.2843, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 3.6382113821138216e-05, |
| "loss": 0.1991, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_accuracy": 0.9170347003154574, |
| "eval_f1": 0.9147487844408428, |
| "eval_loss": 0.20860691368579865, |
| "eval_precision": 0.9228253760627861, |
| "eval_recall": 0.9068123393316195, |
| "eval_runtime": 18.2871, |
| "eval_samples_per_second": 173.346, |
| "eval_steps_per_second": 21.709, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 3.475609756097561e-05, |
| "loss": 0.276, |
| "step": 176 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 3.313008130081301e-05, |
| "loss": 0.2483, |
| "step": 184 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 3.150406504065041e-05, |
| "loss": 0.2568, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 2.9878048780487805e-05, |
| "loss": 0.227, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.58, |
| "eval_accuracy": 0.9198738170347003, |
| "eval_f1": 0.9166666666666666, |
| "eval_loss": 0.20122328400611877, |
| "eval_precision": 0.9363270777479893, |
| "eval_recall": 0.8978149100257069, |
| "eval_runtime": 18.2795, |
| "eval_samples_per_second": 173.418, |
| "eval_steps_per_second": 21.718, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 2.8252032520325205e-05, |
| "loss": 0.2167, |
| "step": 208 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 2.66260162601626e-05, |
| "loss": 0.2033, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 2.5e-05, |
| "loss": 0.2357, |
| "step": 224 |
| }, |
| { |
| "epoch": 0.65, |
| "eval_accuracy": 0.9261829652996846, |
| "eval_f1": 0.9254302103250478, |
| "eval_loss": 0.18770882487297058, |
| "eval_precision": 0.9178255372945638, |
| "eval_recall": 0.9331619537275064, |
| "eval_runtime": 18.2243, |
| "eval_samples_per_second": 173.943, |
| "eval_steps_per_second": 21.784, |
| "step": 225 |
| } |
| ], |
| "max_steps": 346, |
| "num_train_epochs": 1, |
| "total_flos": 429199909056000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
