| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 18720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.51985559566787, | |
| "eval_loss": 0.5319512486457825, | |
| "eval_runtime": 9.1619, | |
| "eval_samples_per_second": 30.234, | |
| "eval_steps_per_second": 3.82, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.51985559566787, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.004866452991452991, | |
| "loss": 0.6084, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.505980372428894, | |
| "eval_runtime": 8.9739, | |
| "eval_samples_per_second": 30.867, | |
| "eval_steps_per_second": 3.9, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.476485937833786, | |
| "eval_runtime": 9.1085, | |
| "eval_samples_per_second": 30.411, | |
| "eval_steps_per_second": 3.843, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.004732905982905983, | |
| "loss": 0.4786, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.38619130849838257, | |
| "eval_runtime": 9.0544, | |
| "eval_samples_per_second": 30.593, | |
| "eval_steps_per_second": 3.866, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.004599358974358974, | |
| "loss": 0.5253, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.5090705156326294, | |
| "eval_runtime": 9.0148, | |
| "eval_samples_per_second": 30.727, | |
| "eval_steps_per_second": 3.882, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4981949458483754, | |
| "eval_loss": 0.376774400472641, | |
| "eval_runtime": 9.0141, | |
| "eval_samples_per_second": 30.73, | |
| "eval_steps_per_second": 3.883, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.004465811965811966, | |
| "loss": 0.5144, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.44060468673706055, | |
| "eval_runtime": 9.0181, | |
| "eval_samples_per_second": 30.716, | |
| "eval_steps_per_second": 3.881, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.631768953068592, | |
| "eval_loss": 0.3461342751979828, | |
| "eval_runtime": 8.9803, | |
| "eval_samples_per_second": 30.845, | |
| "eval_steps_per_second": 3.897, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.631768953068592, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.004332264957264957, | |
| "loss": 0.4407, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.34802812337875366, | |
| "eval_runtime": 8.976, | |
| "eval_samples_per_second": 30.86, | |
| "eval_steps_per_second": 3.899, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.004198717948717949, | |
| "loss": 0.4002, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6642599277978339, | |
| "eval_loss": 0.362854540348053, | |
| "eval_runtime": 9.0085, | |
| "eval_samples_per_second": 30.749, | |
| "eval_steps_per_second": 3.885, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 9, | |
| "best_eval_accuracy": 0.6642599277978339, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.555956678700361, | |
| "eval_loss": 0.39493829011917114, | |
| "eval_runtime": 9.036, | |
| "eval_samples_per_second": 30.655, | |
| "eval_steps_per_second": 3.873, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 9, | |
| "best_eval_accuracy": 0.6642599277978339, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00406517094017094, | |
| "loss": 0.3576, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.336588591337204, | |
| "eval_runtime": 9.0067, | |
| "eval_samples_per_second": 30.755, | |
| "eval_steps_per_second": 3.886, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.003931623931623931, | |
| "loss": 0.346, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3301502466201782, | |
| "eval_runtime": 9.0221, | |
| "eval_samples_per_second": 30.702, | |
| "eval_steps_per_second": 3.879, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.3293074369430542, | |
| "eval_runtime": 9.0321, | |
| "eval_samples_per_second": 30.668, | |
| "eval_steps_per_second": 3.875, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.003798076923076923, | |
| "loss": 0.337, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.33005112409591675, | |
| "eval_runtime": 9.0187, | |
| "eval_samples_per_second": 30.714, | |
| "eval_steps_per_second": 3.881, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.33984842896461487, | |
| "eval_runtime": 9.0474, | |
| "eval_samples_per_second": 30.616, | |
| "eval_steps_per_second": 3.869, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.003664529914529914, | |
| "loss": 0.3323, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.35551536083221436, | |
| "eval_runtime": 9.0226, | |
| "eval_samples_per_second": 30.701, | |
| "eval_steps_per_second": 3.879, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.003530982905982906, | |
| "loss": 0.3245, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.32570627331733704, | |
| "eval_runtime": 9.0171, | |
| "eval_samples_per_second": 30.719, | |
| "eval_steps_per_second": 3.882, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3257431089878082, | |
| "eval_runtime": 9.0276, | |
| "eval_samples_per_second": 30.684, | |
| "eval_steps_per_second": 3.877, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0033974358974358976, | |
| "loss": 0.3243, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.3507075309753418, | |
| "eval_runtime": 8.9982, | |
| "eval_samples_per_second": 30.784, | |
| "eval_steps_per_second": 3.89, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.003263888888888889, | |
| "loss": 0.3144, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.40468713641166687, | |
| "eval_runtime": 9.0484, | |
| "eval_samples_per_second": 30.613, | |
| "eval_steps_per_second": 3.868, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.36198413372039795, | |
| "eval_runtime": 9.0445, | |
| "eval_samples_per_second": 30.626, | |
| "eval_steps_per_second": 3.87, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0031303418803418806, | |
| "loss": 0.3135, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3739970028400421, | |
| "eval_runtime": 9.0931, | |
| "eval_samples_per_second": 30.463, | |
| "eval_steps_per_second": 3.849, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 15, | |
| "best_eval_accuracy": 0.7328519855595668, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.33150357007980347, | |
| "eval_runtime": 9.0913, | |
| "eval_samples_per_second": 30.469, | |
| "eval_steps_per_second": 3.85, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0029967948717948716, | |
| "loss": 0.3063, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3291415572166443, | |
| "eval_runtime": 9.0712, | |
| "eval_samples_per_second": 30.536, | |
| "eval_steps_per_second": 3.858, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.002863247863247863, | |
| "loss": 0.2986, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.36258506774902344, | |
| "eval_runtime": 9.1485, | |
| "eval_samples_per_second": 30.278, | |
| "eval_steps_per_second": 3.826, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3281010687351227, | |
| "eval_runtime": 9.0555, | |
| "eval_samples_per_second": 30.589, | |
| "eval_steps_per_second": 3.865, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0027297008547008546, | |
| "loss": 0.2956, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33756041526794434, | |
| "eval_runtime": 9.1719, | |
| "eval_samples_per_second": 30.201, | |
| "eval_steps_per_second": 3.816, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0025961538461538466, | |
| "loss": 0.2927, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3309880197048187, | |
| "eval_runtime": 9.0985, | |
| "eval_samples_per_second": 30.445, | |
| "eval_steps_per_second": 3.847, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.34706664085388184, | |
| "eval_runtime": 8.8071, | |
| "eval_samples_per_second": 31.452, | |
| "eval_steps_per_second": 3.974, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7545126353790613, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0024626068376068376, | |
| "loss": 0.2853, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.3204677700996399, | |
| "eval_runtime": 9.1308, | |
| "eval_samples_per_second": 30.337, | |
| "eval_steps_per_second": 3.833, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.32714536786079407, | |
| "eval_runtime": 9.0779, | |
| "eval_samples_per_second": 30.514, | |
| "eval_steps_per_second": 3.855, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.002329059829059829, | |
| "loss": 0.2861, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.3423185646533966, | |
| "eval_runtime": 9.1078, | |
| "eval_samples_per_second": 30.414, | |
| "eval_steps_per_second": 3.843, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0021955128205128206, | |
| "loss": 0.2782, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3327659070491791, | |
| "eval_runtime": 9.1866, | |
| "eval_samples_per_second": 30.153, | |
| "eval_steps_per_second": 3.81, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7617328519855595, | |
| "eval_loss": 0.32888853549957275, | |
| "eval_runtime": 9.2412, | |
| "eval_samples_per_second": 29.974, | |
| "eval_steps_per_second": 3.787, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.002061965811965812, | |
| "loss": 0.2756, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.330919086933136, | |
| "eval_runtime": 9.2586, | |
| "eval_samples_per_second": 29.918, | |
| "eval_steps_per_second": 3.78, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0019284188034188036, | |
| "loss": 0.2758, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.37405356764793396, | |
| "eval_runtime": 9.2, | |
| "eval_samples_per_second": 30.109, | |
| "eval_steps_per_second": 3.804, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.33260834217071533, | |
| "eval_runtime": 4.3573, | |
| "eval_samples_per_second": 63.571, | |
| "eval_steps_per_second": 8.032, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0017948717948717949, | |
| "loss": 0.2714, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.36113840341567993, | |
| "eval_runtime": 10.6137, | |
| "eval_samples_per_second": 26.098, | |
| "eval_steps_per_second": 3.298, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.33517616987228394, | |
| "eval_runtime": 10.5938, | |
| "eval_samples_per_second": 26.147, | |
| "eval_steps_per_second": 3.304, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0016613247863247864, | |
| "loss": 0.2687, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.34048405289649963, | |
| "eval_runtime": 10.5168, | |
| "eval_samples_per_second": 26.339, | |
| "eval_steps_per_second": 3.328, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0015277777777777779, | |
| "loss": 0.2685, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.34080803394317627, | |
| "eval_runtime": 10.8178, | |
| "eval_samples_per_second": 25.606, | |
| "eval_steps_per_second": 3.235, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.34136372804641724, | |
| "eval_runtime": 10.56, | |
| "eval_samples_per_second": 26.231, | |
| "eval_steps_per_second": 3.314, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0013942307692307694, | |
| "loss": 0.2649, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3369286060333252, | |
| "eval_runtime": 10.5795, | |
| "eval_samples_per_second": 26.183, | |
| "eval_steps_per_second": 3.308, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0012606837606837606, | |
| "loss": 0.2615, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.33710670471191406, | |
| "eval_runtime": 10.8841, | |
| "eval_samples_per_second": 25.45, | |
| "eval_steps_per_second": 3.216, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.34283646941185, | |
| "eval_runtime": 10.5807, | |
| "eval_samples_per_second": 26.18, | |
| "eval_steps_per_second": 3.308, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0011271367521367521, | |
| "loss": 0.2602, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.32864174246788025, | |
| "eval_runtime": 10.9225, | |
| "eval_samples_per_second": 25.361, | |
| "eval_steps_per_second": 3.204, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.33157122135162354, | |
| "eval_runtime": 10.8742, | |
| "eval_samples_per_second": 25.473, | |
| "eval_steps_per_second": 3.219, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0009935897435897436, | |
| "loss": 0.2595, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3400510847568512, | |
| "eval_runtime": 9.388, | |
| "eval_samples_per_second": 29.506, | |
| "eval_steps_per_second": 3.728, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 34, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0008600427350427351, | |
| "loss": 0.2551, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7653429602888087, | |
| "eval_loss": 0.3362467288970947, | |
| "eval_runtime": 9.2771, | |
| "eval_samples_per_second": 29.859, | |
| "eval_steps_per_second": 3.773, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 49, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7653429602888087, | |
| "eval_loss": 0.34337136149406433, | |
| "eval_runtime": 9.1926, | |
| "eval_samples_per_second": 30.133, | |
| "eval_steps_per_second": 3.807, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 49, | |
| "best_eval_accuracy": 0.7653429602888087, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0007264957264957266, | |
| "loss": 0.2574, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7725631768953068, | |
| "eval_loss": 0.33018356561660767, | |
| "eval_runtime": 9.1431, | |
| "eval_samples_per_second": 30.296, | |
| "eval_steps_per_second": 3.828, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 51, | |
| "best_eval_accuracy": 0.7725631768953068, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.000592948717948718, | |
| "loss": 0.2515, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3463674485683441, | |
| "eval_runtime": 9.139, | |
| "eval_samples_per_second": 30.31, | |
| "eval_steps_per_second": 3.83, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 51, | |
| "best_eval_accuracy": 0.7725631768953068, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7689530685920578, | |
| "eval_loss": 0.3337368667125702, | |
| "eval_runtime": 9.3533, | |
| "eval_samples_per_second": 29.615, | |
| "eval_steps_per_second": 3.742, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 51, | |
| "best_eval_accuracy": 0.7725631768953068, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00045940170940170943, | |
| "loss": 0.252, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7689530685920578, | |
| "eval_loss": 0.33643844723701477, | |
| "eval_runtime": 9.1243, | |
| "eval_samples_per_second": 30.359, | |
| "eval_steps_per_second": 3.836, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 51, | |
| "best_eval_accuracy": 0.7725631768953068, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.3417775630950928, | |
| "eval_runtime": 8.8741, | |
| "eval_samples_per_second": 31.214, | |
| "eval_steps_per_second": 3.944, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 51, | |
| "best_eval_accuracy": 0.7725631768953068, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.00032585470085470087, | |
| "loss": 0.2497, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.340709924697876, | |
| "eval_runtime": 8.9435, | |
| "eval_samples_per_second": 30.972, | |
| "eval_steps_per_second": 3.913, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 51, | |
| "best_eval_accuracy": 0.7725631768953068, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 0.2503, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3418755829334259, | |
| "eval_runtime": 8.9319, | |
| "eval_samples_per_second": 31.012, | |
| "eval_steps_per_second": 3.919, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 51, | |
| "best_eval_accuracy": 0.7725631768953068, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.776173285198556, | |
| "eval_loss": 0.33760103583335876, | |
| "eval_runtime": 9.2259, | |
| "eval_samples_per_second": 30.024, | |
| "eval_steps_per_second": 3.794, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 58, | |
| "best_eval_accuracy": 0.776173285198556, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 5.876068376068376e-05, | |
| "loss": 0.2504, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7725631768953068, | |
| "eval_loss": 0.3379180431365967, | |
| "eval_runtime": 9.2108, | |
| "eval_samples_per_second": 30.073, | |
| "eval_steps_per_second": 3.8, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 58, | |
| "best_eval_accuracy": 0.776173285198556, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.3189461204740736, | |
| "train_runtime": 8512.0872, | |
| "train_samples_per_second": 17.552, | |
| "train_steps_per_second": 2.199 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |