| { |
| "best_metric": 0.1237926334142685, |
| "best_model_checkpoint": "/home/gz66/analog_model/analog_LLM_model_flanT5/FM-data5-6-dataaug-epoch120-dnum1000/checkpoint-1400", |
| "epoch": 33.333333333333336, |
| "eval_steps": 200, |
| "global_step": 1400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.48, |
| "learning_rate": 1.9999999999999998e-05, |
| "loss": 4.6089, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 3.9999999999999996e-05, |
| "loss": 3.1589, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 1.6568, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 7.999999999999999e-05, |
| "loss": 0.8994, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 0.5677, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.3986, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 0.00014, |
| "loss": 0.3327, |
| "step": 140 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 0.00015999999999999999, |
| "loss": 0.2885, |
| "step": 160 |
| }, |
| { |
| "epoch": 4.29, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.2546, |
| "step": 180 |
| }, |
| { |
| "epoch": 4.76, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 0.257, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.76, |
| "eval_loss": 0.14169558882713318, |
| "eval_runtime": 50.821, |
| "eval_samples_per_second": 198.245, |
| "eval_steps_per_second": 24.793, |
| "step": 200 |
| }, |
| { |
| "epoch": 5.24, |
| "learning_rate": 0.00021999999999999995, |
| "loss": 0.2281, |
| "step": 220 |
| }, |
| { |
| "epoch": 5.71, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 0.2314, |
| "step": 240 |
| }, |
| { |
| "epoch": 6.19, |
| "learning_rate": 0.00026, |
| "loss": 0.2501, |
| "step": 260 |
| }, |
| { |
| "epoch": 6.67, |
| "learning_rate": 0.00028, |
| "loss": 0.2213, |
| "step": 280 |
| }, |
| { |
| "epoch": 7.14, |
| "learning_rate": 0.0003, |
| "loss": 0.2072, |
| "step": 300 |
| }, |
| { |
| "epoch": 7.62, |
| "learning_rate": 0.0002987341772151899, |
| "loss": 0.1958, |
| "step": 320 |
| }, |
| { |
| "epoch": 8.1, |
| "learning_rate": 0.00029746835443037974, |
| "loss": 0.2004, |
| "step": 340 |
| }, |
| { |
| "epoch": 8.57, |
| "learning_rate": 0.0002962025316455696, |
| "loss": 0.188, |
| "step": 360 |
| }, |
| { |
| "epoch": 9.05, |
| "learning_rate": 0.00029493670886075946, |
| "loss": 0.2117, |
| "step": 380 |
| }, |
| { |
| "epoch": 9.52, |
| "learning_rate": 0.0002936708860759494, |
| "loss": 0.1892, |
| "step": 400 |
| }, |
| { |
| "epoch": 9.52, |
| "eval_loss": 0.13606849312782288, |
| "eval_runtime": 50.8082, |
| "eval_samples_per_second": 198.295, |
| "eval_steps_per_second": 24.799, |
| "step": 400 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.00029240506329113923, |
| "loss": 0.181, |
| "step": 420 |
| }, |
| { |
| "epoch": 10.48, |
| "learning_rate": 0.0002911392405063291, |
| "loss": 0.1875, |
| "step": 440 |
| }, |
| { |
| "epoch": 10.95, |
| "learning_rate": 0.00028987341772151895, |
| "loss": 0.1983, |
| "step": 460 |
| }, |
| { |
| "epoch": 11.43, |
| "learning_rate": 0.00028860759493670886, |
| "loss": 0.2003, |
| "step": 480 |
| }, |
| { |
| "epoch": 11.9, |
| "learning_rate": 0.0002873417721518987, |
| "loss": 0.1986, |
| "step": 500 |
| }, |
| { |
| "epoch": 12.38, |
| "learning_rate": 0.0002860759493670886, |
| "loss": 0.1929, |
| "step": 520 |
| }, |
| { |
| "epoch": 12.86, |
| "learning_rate": 0.00028481012658227844, |
| "loss": 0.1762, |
| "step": 540 |
| }, |
| { |
| "epoch": 13.33, |
| "learning_rate": 0.00028354430379746835, |
| "loss": 0.1685, |
| "step": 560 |
| }, |
| { |
| "epoch": 13.81, |
| "learning_rate": 0.0002822784810126582, |
| "loss": 0.1698, |
| "step": 580 |
| }, |
| { |
| "epoch": 14.29, |
| "learning_rate": 0.00028101265822784807, |
| "loss": 0.1582, |
| "step": 600 |
| }, |
| { |
| "epoch": 14.29, |
| "eval_loss": 0.13090607523918152, |
| "eval_runtime": 50.6708, |
| "eval_samples_per_second": 198.832, |
| "eval_steps_per_second": 24.866, |
| "step": 600 |
| }, |
| { |
| "epoch": 14.76, |
| "learning_rate": 0.000279746835443038, |
| "loss": 0.1575, |
| "step": 620 |
| }, |
| { |
| "epoch": 15.24, |
| "learning_rate": 0.00027848101265822784, |
| "loss": 0.1548, |
| "step": 640 |
| }, |
| { |
| "epoch": 15.71, |
| "learning_rate": 0.0002772151898734177, |
| "loss": 0.1513, |
| "step": 660 |
| }, |
| { |
| "epoch": 16.19, |
| "learning_rate": 0.00027594936708860755, |
| "loss": 0.1508, |
| "step": 680 |
| }, |
| { |
| "epoch": 16.67, |
| "learning_rate": 0.00027468354430379747, |
| "loss": 0.1494, |
| "step": 700 |
| }, |
| { |
| "epoch": 17.14, |
| "learning_rate": 0.0002734177215189873, |
| "loss": 0.1488, |
| "step": 720 |
| }, |
| { |
| "epoch": 17.62, |
| "learning_rate": 0.0002721518987341772, |
| "loss": 0.1483, |
| "step": 740 |
| }, |
| { |
| "epoch": 18.1, |
| "learning_rate": 0.00027088607594936704, |
| "loss": 0.1464, |
| "step": 760 |
| }, |
| { |
| "epoch": 18.57, |
| "learning_rate": 0.00026962025316455696, |
| "loss": 0.1461, |
| "step": 780 |
| }, |
| { |
| "epoch": 19.05, |
| "learning_rate": 0.0002683544303797468, |
| "loss": 0.1457, |
| "step": 800 |
| }, |
| { |
| "epoch": 19.05, |
| "eval_loss": 0.12519289553165436, |
| "eval_runtime": 51.1791, |
| "eval_samples_per_second": 196.858, |
| "eval_steps_per_second": 24.619, |
| "step": 800 |
| }, |
| { |
| "epoch": 19.52, |
| "learning_rate": 0.00026708860759493667, |
| "loss": 0.1482, |
| "step": 820 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 0.00026582278481012653, |
| "loss": 0.1498, |
| "step": 840 |
| }, |
| { |
| "epoch": 20.48, |
| "learning_rate": 0.00026455696202531644, |
| "loss": 0.1542, |
| "step": 860 |
| }, |
| { |
| "epoch": 20.95, |
| "learning_rate": 0.0002632911392405063, |
| "loss": 0.1605, |
| "step": 880 |
| }, |
| { |
| "epoch": 21.43, |
| "learning_rate": 0.00026202531645569616, |
| "loss": 0.15, |
| "step": 900 |
| }, |
| { |
| "epoch": 21.9, |
| "learning_rate": 0.0002607594936708861, |
| "loss": 0.1452, |
| "step": 920 |
| }, |
| { |
| "epoch": 22.38, |
| "learning_rate": 0.00025949367088607593, |
| "loss": 0.1457, |
| "step": 940 |
| }, |
| { |
| "epoch": 22.86, |
| "learning_rate": 0.0002582278481012658, |
| "loss": 0.1453, |
| "step": 960 |
| }, |
| { |
| "epoch": 23.33, |
| "learning_rate": 0.00025696202531645565, |
| "loss": 0.1444, |
| "step": 980 |
| }, |
| { |
| "epoch": 23.81, |
| "learning_rate": 0.00025569620253164556, |
| "loss": 0.1435, |
| "step": 1000 |
| }, |
| { |
| "epoch": 23.81, |
| "eval_loss": 0.12461867928504944, |
| "eval_runtime": 53.232, |
| "eval_samples_per_second": 189.266, |
| "eval_steps_per_second": 23.67, |
| "step": 1000 |
| }, |
| { |
| "epoch": 24.29, |
| "learning_rate": 0.0002544303797468354, |
| "loss": 0.1414, |
| "step": 1020 |
| }, |
| { |
| "epoch": 24.76, |
| "learning_rate": 0.0002531645569620253, |
| "loss": 0.1427, |
| "step": 1040 |
| }, |
| { |
| "epoch": 25.24, |
| "learning_rate": 0.00025189873417721514, |
| "loss": 0.1406, |
| "step": 1060 |
| }, |
| { |
| "epoch": 25.71, |
| "learning_rate": 0.00025063291139240505, |
| "loss": 0.143, |
| "step": 1080 |
| }, |
| { |
| "epoch": 26.19, |
| "learning_rate": 0.0002493670886075949, |
| "loss": 0.1434, |
| "step": 1100 |
| }, |
| { |
| "epoch": 26.67, |
| "learning_rate": 0.00024810126582278477, |
| "loss": 0.1435, |
| "step": 1120 |
| }, |
| { |
| "epoch": 27.14, |
| "learning_rate": 0.0002468354430379747, |
| "loss": 0.1433, |
| "step": 1140 |
| }, |
| { |
| "epoch": 27.62, |
| "learning_rate": 0.00024556962025316454, |
| "loss": 0.1421, |
| "step": 1160 |
| }, |
| { |
| "epoch": 28.1, |
| "learning_rate": 0.00024430379746835445, |
| "loss": 0.1403, |
| "step": 1180 |
| }, |
| { |
| "epoch": 28.57, |
| "learning_rate": 0.00024303797468354428, |
| "loss": 0.1425, |
| "step": 1200 |
| }, |
| { |
| "epoch": 28.57, |
| "eval_loss": 0.12540313601493835, |
| "eval_runtime": 52.2087, |
| "eval_samples_per_second": 192.976, |
| "eval_steps_per_second": 24.134, |
| "step": 1200 |
| }, |
| { |
| "epoch": 29.05, |
| "learning_rate": 0.00024177215189873417, |
| "loss": 0.1398, |
| "step": 1220 |
| }, |
| { |
| "epoch": 29.52, |
| "learning_rate": 0.00024050632911392402, |
| "loss": 0.1416, |
| "step": 1240 |
| }, |
| { |
| "epoch": 30.0, |
| "learning_rate": 0.0002392405063291139, |
| "loss": 0.1383, |
| "step": 1260 |
| }, |
| { |
| "epoch": 30.48, |
| "learning_rate": 0.00023797468354430377, |
| "loss": 0.1417, |
| "step": 1280 |
| }, |
| { |
| "epoch": 30.95, |
| "learning_rate": 0.00023670886075949365, |
| "loss": 0.1403, |
| "step": 1300 |
| }, |
| { |
| "epoch": 31.43, |
| "learning_rate": 0.0002354430379746835, |
| "loss": 0.1419, |
| "step": 1320 |
| }, |
| { |
| "epoch": 31.9, |
| "learning_rate": 0.0002341772151898734, |
| "loss": 0.1408, |
| "step": 1340 |
| }, |
| { |
| "epoch": 32.38, |
| "learning_rate": 0.00023291139240506326, |
| "loss": 0.1405, |
| "step": 1360 |
| }, |
| { |
| "epoch": 32.86, |
| "learning_rate": 0.00023164556962025314, |
| "loss": 0.1409, |
| "step": 1380 |
| }, |
| { |
| "epoch": 33.33, |
| "learning_rate": 0.000230379746835443, |
| "loss": 0.1389, |
| "step": 1400 |
| }, |
| { |
| "epoch": 33.33, |
| "eval_loss": 0.1237926334142685, |
| "eval_runtime": 53.5272, |
| "eval_samples_per_second": 188.222, |
| "eval_steps_per_second": 23.539, |
| "step": 1400 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 5040, |
| "num_train_epochs": 120, |
| "save_steps": 200, |
| "total_flos": 4561981476102144.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
