| { | |
| "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": 0.5306859205776173, | |
| "eval_loss": 0.17852023243904114, | |
| "eval_runtime": 4.2873, | |
| "eval_samples_per_second": 64.61, | |
| "eval_steps_per_second": 8.164, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.002919871794871795, | |
| "loss": 0.2552, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5054151624548736, | |
| "eval_loss": 0.18264690041542053, | |
| "eval_runtime": 4.3896, | |
| "eval_samples_per_second": 63.104, | |
| "eval_steps_per_second": 7.973, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.33281320333480835, | |
| "eval_runtime": 4.433, | |
| "eval_samples_per_second": 62.486, | |
| "eval_steps_per_second": 7.895, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0028397435897435895, | |
| "loss": 0.24, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.2049672156572342, | |
| "eval_runtime": 4.4533, | |
| "eval_samples_per_second": 62.201, | |
| "eval_steps_per_second": 7.859, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0027596153846153847, | |
| "loss": 0.2369, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6064981949458483, | |
| "eval_loss": 0.17499716579914093, | |
| "eval_runtime": 4.4615, | |
| "eval_samples_per_second": 62.087, | |
| "eval_steps_per_second": 7.845, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.6064981949458483, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.17517220973968506, | |
| "eval_runtime": 4.4386, | |
| "eval_samples_per_second": 62.407, | |
| "eval_steps_per_second": 7.885, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.6064981949458483, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00267948717948718, | |
| "loss": 0.2199, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.592057761732852, | |
| "eval_loss": 0.17986096441745758, | |
| "eval_runtime": 4.441, | |
| "eval_samples_per_second": 62.373, | |
| "eval_steps_per_second": 7.881, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.6064981949458483, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.18959033489227295, | |
| "eval_runtime": 4.4419, | |
| "eval_samples_per_second": 62.361, | |
| "eval_steps_per_second": 7.88, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.6064981949458483, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0025993589743589745, | |
| "loss": 0.1955, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6245487364620939, | |
| "eval_loss": 0.1726665496826172, | |
| "eval_runtime": 4.4446, | |
| "eval_samples_per_second": 62.322, | |
| "eval_steps_per_second": 7.875, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6245487364620939, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0025192307692307693, | |
| "loss": 0.185, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5667870036101083, | |
| "eval_loss": 0.1733800321817398, | |
| "eval_runtime": 4.4393, | |
| "eval_samples_per_second": 62.397, | |
| "eval_steps_per_second": 7.884, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6245487364620939, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5812274368231047, | |
| "eval_loss": 0.1781184822320938, | |
| "eval_runtime": 4.4403, | |
| "eval_samples_per_second": 62.383, | |
| "eval_steps_per_second": 7.882, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6245487364620939, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.002439102564102564, | |
| "loss": 0.184, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.631768953068592, | |
| "eval_loss": 0.17108257114887238, | |
| "eval_runtime": 4.4449, | |
| "eval_samples_per_second": 62.319, | |
| "eval_steps_per_second": 7.874, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.631768953068592, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.002358974358974359, | |
| "loss": 0.1819, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 0.17825525999069214, | |
| "eval_runtime": 4.4419, | |
| "eval_samples_per_second": 62.361, | |
| "eval_steps_per_second": 7.88, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.631768953068592, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.1702543944120407, | |
| "eval_runtime": 4.4448, | |
| "eval_samples_per_second": 62.32, | |
| "eval_steps_per_second": 7.874, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 13, | |
| "best_eval_accuracy": 0.6534296028880866, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.002278846153846154, | |
| "loss": 0.1793, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.16970041394233704, | |
| "eval_runtime": 4.4427, | |
| "eval_samples_per_second": 62.35, | |
| "eval_steps_per_second": 7.878, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6642599277978339, | |
| "eval_loss": 0.1709691882133484, | |
| "eval_runtime": 4.4418, | |
| "eval_samples_per_second": 62.362, | |
| "eval_steps_per_second": 7.88, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0021987179487179486, | |
| "loss": 0.179, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.17275716364383698, | |
| "eval_runtime": 4.4437, | |
| "eval_samples_per_second": 62.335, | |
| "eval_steps_per_second": 7.876, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.0021185897435897437, | |
| "loss": 0.1784, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 0.1711890995502472, | |
| "eval_runtime": 4.4513, | |
| "eval_samples_per_second": 62.229, | |
| "eval_steps_per_second": 7.863, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6064981949458483, | |
| "eval_loss": 0.1725841462612152, | |
| "eval_runtime": 4.4464, | |
| "eval_samples_per_second": 62.297, | |
| "eval_steps_per_second": 7.872, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0020384615384615385, | |
| "loss": 0.1778, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.17198872566223145, | |
| "eval_runtime": 4.4507, | |
| "eval_samples_per_second": 62.237, | |
| "eval_steps_per_second": 7.864, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0019583333333333336, | |
| "loss": 0.1761, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6606498194945848, | |
| "eval_loss": 0.17243142426013947, | |
| "eval_runtime": 4.4385, | |
| "eval_samples_per_second": 62.408, | |
| "eval_steps_per_second": 7.886, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6534296028880866, | |
| "eval_loss": 0.17924970388412476, | |
| "eval_runtime": 4.4358, | |
| "eval_samples_per_second": 62.447, | |
| "eval_steps_per_second": 7.89, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0018782051282051281, | |
| "loss": 0.1761, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 0.1700066775083542, | |
| "eval_runtime": 4.4501, | |
| "eval_samples_per_second": 62.246, | |
| "eval_steps_per_second": 7.865, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6678700361010831, | |
| "eval_loss": 0.16977772116661072, | |
| "eval_runtime": 4.4334, | |
| "eval_samples_per_second": 62.48, | |
| "eval_steps_per_second": 7.895, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.001798076923076923, | |
| "loss": 0.1748, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.16966477036476135, | |
| "eval_runtime": 4.4363, | |
| "eval_samples_per_second": 62.44, | |
| "eval_steps_per_second": 7.89, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0017179487179487178, | |
| "loss": 0.1744, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6859205776173285, | |
| "eval_loss": 0.17290985584259033, | |
| "eval_runtime": 4.4401, | |
| "eval_samples_per_second": 62.387, | |
| "eval_steps_per_second": 7.883, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.1702173352241516, | |
| "eval_runtime": 4.4312, | |
| "eval_samples_per_second": 62.511, | |
| "eval_steps_per_second": 7.898, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0016378205128205127, | |
| "loss": 0.1736, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.1707705557346344, | |
| "eval_runtime": 4.4336, | |
| "eval_samples_per_second": 62.477, | |
| "eval_steps_per_second": 7.894, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0015576923076923079, | |
| "loss": 0.1723, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.16975490748882294, | |
| "eval_runtime": 4.4304, | |
| "eval_samples_per_second": 62.523, | |
| "eval_steps_per_second": 7.9, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.17993663251399994, | |
| "eval_runtime": 4.437, | |
| "eval_samples_per_second": 62.429, | |
| "eval_steps_per_second": 7.888, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0014775641025641026, | |
| "loss": 0.1735, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.17266085743904114, | |
| "eval_runtime": 4.4358, | |
| "eval_samples_per_second": 62.447, | |
| "eval_steps_per_second": 7.89, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 0.17320023477077484, | |
| "eval_runtime": 4.4326, | |
| "eval_samples_per_second": 62.491, | |
| "eval_steps_per_second": 7.896, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0013974358974358976, | |
| "loss": 0.1722, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.1702079027891159, | |
| "eval_runtime": 4.4347, | |
| "eval_samples_per_second": 62.463, | |
| "eval_steps_per_second": 7.892, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0013173076923076923, | |
| "loss": 0.1709, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.17065663635730743, | |
| "eval_runtime": 4.4365, | |
| "eval_samples_per_second": 62.437, | |
| "eval_steps_per_second": 7.889, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.17139047384262085, | |
| "eval_runtime": 4.4388, | |
| "eval_samples_per_second": 62.405, | |
| "eval_steps_per_second": 7.885, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0012371794871794872, | |
| "loss": 0.1697, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.17118841409683228, | |
| "eval_runtime": 4.4402, | |
| "eval_samples_per_second": 62.385, | |
| "eval_steps_per_second": 7.883, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0011570512820512822, | |
| "loss": 0.1696, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.17884960770606995, | |
| "eval_runtime": 4.4456, | |
| "eval_samples_per_second": 62.309, | |
| "eval_steps_per_second": 7.873, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.17026345431804657, | |
| "eval_runtime": 4.4452, | |
| "eval_samples_per_second": 62.315, | |
| "eval_steps_per_second": 7.874, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0010769230769230769, | |
| "loss": 0.1697, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.17346355319023132, | |
| "eval_runtime": 4.4459, | |
| "eval_samples_per_second": 62.305, | |
| "eval_steps_per_second": 7.872, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.17404569685459137, | |
| "eval_runtime": 4.4468, | |
| "eval_samples_per_second": 62.292, | |
| "eval_steps_per_second": 7.871, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0009967948717948718, | |
| "loss": 0.1683, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.1709529161453247, | |
| "eval_runtime": 4.4491, | |
| "eval_samples_per_second": 62.26, | |
| "eval_steps_per_second": 7.867, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.6967509025270758, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0009166666666666668, | |
| "loss": 0.1688, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.17236575484275818, | |
| "eval_runtime": 4.4523, | |
| "eval_samples_per_second": 62.215, | |
| "eval_steps_per_second": 7.861, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.17182697355747223, | |
| "eval_runtime": 4.4464, | |
| "eval_samples_per_second": 62.298, | |
| "eval_steps_per_second": 7.872, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0008365384615384616, | |
| "loss": 0.1679, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.17357730865478516, | |
| "eval_runtime": 4.4496, | |
| "eval_samples_per_second": 62.253, | |
| "eval_steps_per_second": 7.866, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0007564102564102564, | |
| "loss": 0.1681, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.17195428907871246, | |
| "eval_runtime": 4.4504, | |
| "eval_samples_per_second": 62.242, | |
| "eval_steps_per_second": 7.865, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.17170363664627075, | |
| "eval_runtime": 4.4496, | |
| "eval_samples_per_second": 62.253, | |
| "eval_steps_per_second": 7.866, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0006762820512820514, | |
| "loss": 0.1664, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.17101722955703735, | |
| "eval_runtime": 4.454, | |
| "eval_samples_per_second": 62.192, | |
| "eval_steps_per_second": 7.858, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.17659461498260498, | |
| "eval_runtime": 4.4486, | |
| "eval_samples_per_second": 62.267, | |
| "eval_steps_per_second": 7.868, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0005961538461538461, | |
| "loss": 0.1662, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.1728653609752655, | |
| "eval_runtime": 4.4498, | |
| "eval_samples_per_second": 62.25, | |
| "eval_steps_per_second": 7.865, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.000516025641025641, | |
| "loss": 0.1655, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.17041344940662384, | |
| "eval_runtime": 4.4544, | |
| "eval_samples_per_second": 62.185, | |
| "eval_steps_per_second": 7.857, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 41, | |
| "best_eval_accuracy": 0.7075812274368231, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.1710704118013382, | |
| "eval_runtime": 4.4496, | |
| "eval_samples_per_second": 62.252, | |
| "eval_steps_per_second": 7.866, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00043589743589743596, | |
| "loss": 0.1665, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.1708567589521408, | |
| "eval_runtime": 4.4539, | |
| "eval_samples_per_second": 62.192, | |
| "eval_steps_per_second": 7.858, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00035576923076923074, | |
| "loss": 0.1651, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.1710604727268219, | |
| "eval_runtime": 4.4518, | |
| "eval_samples_per_second": 62.222, | |
| "eval_steps_per_second": 7.862, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.173600971698761, | |
| "eval_runtime": 4.4493, | |
| "eval_samples_per_second": 62.257, | |
| "eval_steps_per_second": 7.866, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0002756410256410257, | |
| "loss": 0.1646, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.17123006284236908, | |
| "eval_runtime": 4.452, | |
| "eval_samples_per_second": 62.219, | |
| "eval_steps_per_second": 7.862, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.17398422956466675, | |
| "eval_runtime": 4.4571, | |
| "eval_samples_per_second": 62.149, | |
| "eval_steps_per_second": 7.853, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.00019551282051282054, | |
| "loss": 0.1647, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.17230337858200073, | |
| "eval_runtime": 4.446, | |
| "eval_samples_per_second": 62.303, | |
| "eval_steps_per_second": 7.872, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 0.1642, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.1714901179075241, | |
| "eval_runtime": 4.4636, | |
| "eval_samples_per_second": 62.057, | |
| "eval_steps_per_second": 7.841, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.17266467213630676, | |
| "eval_runtime": 4.446, | |
| "eval_samples_per_second": 62.303, | |
| "eval_steps_per_second": 7.872, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 3.5256410256410254e-05, | |
| "loss": 0.1643, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.1723625361919403, | |
| "eval_runtime": 4.4235, | |
| "eval_samples_per_second": 62.62, | |
| "eval_steps_per_second": 7.912, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 50, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.17944894468682443, | |
| "train_runtime": 4049.329, | |
| "train_samples_per_second": 36.895, | |
| "train_steps_per_second": 4.623 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |