| { | |
| "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": 0.5234657039711191, | |
| "eval_loss": 0.5883553624153137, | |
| "eval_runtime": 8.7854, | |
| "eval_samples_per_second": 31.53, | |
| "eval_steps_per_second": 3.984, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.004866452991452991, | |
| "loss": 0.6001, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.4145338237285614, | |
| "eval_runtime": 8.8107, | |
| "eval_samples_per_second": 31.439, | |
| "eval_steps_per_second": 3.972, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.6337469816207886, | |
| "eval_runtime": 8.7248, | |
| "eval_samples_per_second": 31.748, | |
| "eval_steps_per_second": 4.012, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.004732905982905983, | |
| "loss": 0.5343, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.48375451263537905, | |
| "eval_loss": 0.3934288024902344, | |
| "eval_runtime": 8.7605, | |
| "eval_samples_per_second": 31.619, | |
| "eval_steps_per_second": 3.995, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.004599358974358974, | |
| "loss": 0.5255, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.566152811050415, | |
| "eval_runtime": 8.8523, | |
| "eval_samples_per_second": 31.291, | |
| "eval_steps_per_second": 3.954, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5234657039711191, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.5157924890518188, | |
| "eval_runtime": 8.9667, | |
| "eval_samples_per_second": 30.892, | |
| "eval_steps_per_second": 3.903, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.004465811965811966, | |
| "loss": 0.504, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.3480044901371002, | |
| "eval_runtime": 8.8419, | |
| "eval_samples_per_second": 31.328, | |
| "eval_steps_per_second": 3.958, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 6, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.38455167412757874, | |
| "eval_runtime": 8.9247, | |
| "eval_samples_per_second": 31.037, | |
| "eval_steps_per_second": 3.922, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.004332264957264957, | |
| "loss": 0.4941, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.5111421942710876, | |
| "eval_runtime": 9.2356, | |
| "eval_samples_per_second": 29.993, | |
| "eval_steps_per_second": 3.79, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.004198717948717949, | |
| "loss": 0.5022, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.4620998203754425, | |
| "eval_runtime": 8.9286, | |
| "eval_samples_per_second": 31.024, | |
| "eval_steps_per_second": 3.92, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.3418288826942444, | |
| "eval_runtime": 8.7679, | |
| "eval_samples_per_second": 31.592, | |
| "eval_steps_per_second": 3.992, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6425992779783394, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.00406517094017094, | |
| "loss": 0.453, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5631768953068592, | |
| "eval_loss": 0.3651691675186157, | |
| "eval_runtime": 8.7849, | |
| "eval_samples_per_second": 31.532, | |
| "eval_steps_per_second": 3.984, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6425992779783394, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.003931623931623931, | |
| "loss": 0.3879, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5595667870036101, | |
| "eval_loss": 0.3450925946235657, | |
| "eval_runtime": 8.7727, | |
| "eval_samples_per_second": 31.575, | |
| "eval_steps_per_second": 3.99, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6425992779783394, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.33118629455566406, | |
| "eval_runtime": 8.7741, | |
| "eval_samples_per_second": 31.57, | |
| "eval_steps_per_second": 3.989, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6425992779783394, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.003798076923076923, | |
| "loss": 0.3698, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.3599488437175751, | |
| "eval_runtime": 8.7843, | |
| "eval_samples_per_second": 31.533, | |
| "eval_steps_per_second": 3.984, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6462093862815884, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5992779783393501, | |
| "eval_loss": 0.39469993114471436, | |
| "eval_runtime": 8.7768, | |
| "eval_samples_per_second": 31.561, | |
| "eval_steps_per_second": 3.988, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6462093862815884, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.003664529914529914, | |
| "loss": 0.3705, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6173285198555957, | |
| "eval_loss": 0.38333019614219666, | |
| "eval_runtime": 8.7807, | |
| "eval_samples_per_second": 31.547, | |
| "eval_steps_per_second": 3.986, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6462093862815884, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.003530982905982906, | |
| "loss": 0.3598, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.33536940813064575, | |
| "eval_runtime": 8.765, | |
| "eval_samples_per_second": 31.603, | |
| "eval_steps_per_second": 3.993, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 14, | |
| "best_eval_accuracy": 0.6462093862815884, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 0.33954861760139465, | |
| "eval_runtime": 8.7463, | |
| "eval_samples_per_second": 31.67, | |
| "eval_steps_per_second": 4.002, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0033974358974358976, | |
| "loss": 0.3631, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6389891696750902, | |
| "eval_loss": 0.36644089221954346, | |
| "eval_runtime": 8.72, | |
| "eval_samples_per_second": 31.766, | |
| "eval_steps_per_second": 4.014, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.6714801444043321, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.003263888888888889, | |
| "loss": 0.3515, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.34204551577568054, | |
| "eval_runtime": 8.8321, | |
| "eval_samples_per_second": 31.363, | |
| "eval_steps_per_second": 3.963, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6137184115523465, | |
| "eval_loss": 0.34830158948898315, | |
| "eval_runtime": 8.8779, | |
| "eval_samples_per_second": 31.201, | |
| "eval_steps_per_second": 3.942, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0031303418803418806, | |
| "loss": 0.3486, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 0.3820384442806244, | |
| "eval_runtime": 8.8616, | |
| "eval_samples_per_second": 31.258, | |
| "eval_steps_per_second": 3.95, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.6787003610108303, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.32402852177619934, | |
| "eval_runtime": 8.8647, | |
| "eval_samples_per_second": 31.248, | |
| "eval_steps_per_second": 3.948, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 23, | |
| "best_eval_accuracy": 0.7003610108303249, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0029967948717948716, | |
| "loss": 0.3437, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3299575448036194, | |
| "eval_runtime": 8.8718, | |
| "eval_samples_per_second": 31.223, | |
| "eval_steps_per_second": 3.945, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.002863247863247863, | |
| "loss": 0.3389, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.3404531478881836, | |
| "eval_runtime": 8.8761, | |
| "eval_samples_per_second": 31.208, | |
| "eval_steps_per_second": 3.943, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.32906994223594666, | |
| "eval_runtime": 8.8771, | |
| "eval_samples_per_second": 31.204, | |
| "eval_steps_per_second": 3.943, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.0027297008547008546, | |
| "loss": 0.3363, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.333825945854187, | |
| "eval_runtime": 8.8635, | |
| "eval_samples_per_second": 31.252, | |
| "eval_steps_per_second": 3.949, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 24, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0025961538461538466, | |
| "loss": 0.3381, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.33664965629577637, | |
| "eval_runtime": 9.0918, | |
| "eval_samples_per_second": 30.467, | |
| "eval_steps_per_second": 3.85, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6606498194945848, | |
| "eval_loss": 0.3830634355545044, | |
| "eval_runtime": 10.2562, | |
| "eval_samples_per_second": 27.008, | |
| "eval_steps_per_second": 3.413, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0024626068376068376, | |
| "loss": 0.3302, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3299681842327118, | |
| "eval_runtime": 10.119, | |
| "eval_samples_per_second": 27.374, | |
| "eval_steps_per_second": 3.459, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3223809599876404, | |
| "eval_runtime": 10.1698, | |
| "eval_samples_per_second": 27.238, | |
| "eval_steps_per_second": 3.442, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.002329059829059829, | |
| "loss": 0.33, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.3332250118255615, | |
| "eval_runtime": 10.1039, | |
| "eval_samples_per_second": 27.415, | |
| "eval_steps_per_second": 3.464, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7220216606498195, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0021955128205128206, | |
| "loss": 0.3271, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3412158787250519, | |
| "eval_runtime": 10.1195, | |
| "eval_samples_per_second": 27.373, | |
| "eval_steps_per_second": 3.459, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.3197210431098938, | |
| "eval_runtime": 10.0745, | |
| "eval_samples_per_second": 27.495, | |
| "eval_steps_per_second": 3.474, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.002061965811965812, | |
| "loss": 0.3266, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3236064612865448, | |
| "eval_runtime": 10.0538, | |
| "eval_samples_per_second": 27.552, | |
| "eval_steps_per_second": 3.481, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0019284188034188036, | |
| "loss": 0.3248, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.3621442914009094, | |
| "eval_runtime": 10.1983, | |
| "eval_samples_per_second": 27.161, | |
| "eval_steps_per_second": 3.432, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.33299773931503296, | |
| "eval_runtime": 10.136, | |
| "eval_samples_per_second": 27.328, | |
| "eval_steps_per_second": 3.453, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0017948717948717949, | |
| "loss": 0.3223, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.6823104693140795, | |
| "eval_loss": 0.3635832667350769, | |
| "eval_runtime": 10.2689, | |
| "eval_samples_per_second": 26.975, | |
| "eval_steps_per_second": 3.408, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.3298203647136688, | |
| "eval_runtime": 10.1829, | |
| "eval_samples_per_second": 27.202, | |
| "eval_steps_per_second": 3.437, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.0016613247863247864, | |
| "loss": 0.3205, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.32243612408638, | |
| "eval_runtime": 10.719, | |
| "eval_samples_per_second": 25.842, | |
| "eval_steps_per_second": 3.265, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0015277777777777779, | |
| "loss": 0.3177, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3287702202796936, | |
| "eval_runtime": 10.6219, | |
| "eval_samples_per_second": 26.078, | |
| "eval_steps_per_second": 3.295, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.6823104693140795, | |
| "eval_loss": 0.3464113175868988, | |
| "eval_runtime": 9.1644, | |
| "eval_samples_per_second": 30.226, | |
| "eval_steps_per_second": 3.819, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0013942307692307694, | |
| "loss": 0.3167, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6787003610108303, | |
| "eval_loss": 0.35672882199287415, | |
| "eval_runtime": 9.0166, | |
| "eval_samples_per_second": 30.721, | |
| "eval_steps_per_second": 3.882, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0012606837606837606, | |
| "loss": 0.3159, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.355069100856781, | |
| "eval_runtime": 9.0565, | |
| "eval_samples_per_second": 30.586, | |
| "eval_steps_per_second": 3.865, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.33131033182144165, | |
| "eval_runtime": 9.1597, | |
| "eval_samples_per_second": 30.241, | |
| "eval_steps_per_second": 3.821, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 33, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0011271367521367521, | |
| "loss": 0.3131, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3233274519443512, | |
| "eval_runtime": 9.0766, | |
| "eval_samples_per_second": 30.518, | |
| "eval_steps_per_second": 3.856, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6750902527075813, | |
| "eval_loss": 0.35078391432762146, | |
| "eval_runtime": 9.0843, | |
| "eval_samples_per_second": 30.492, | |
| "eval_steps_per_second": 3.853, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0009935897435897436, | |
| "loss": 0.3118, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.34203651547431946, | |
| "eval_runtime": 9.1363, | |
| "eval_samples_per_second": 30.319, | |
| "eval_steps_per_second": 3.831, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0008600427350427351, | |
| "loss": 0.3088, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.34102147817611694, | |
| "eval_runtime": 9.0781, | |
| "eval_samples_per_second": 30.513, | |
| "eval_steps_per_second": 3.855, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3420613706111908, | |
| "eval_runtime": 8.9032, | |
| "eval_samples_per_second": 31.113, | |
| "eval_steps_per_second": 3.931, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0007264957264957266, | |
| "loss": 0.3082, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3411448895931244, | |
| "eval_runtime": 8.9332, | |
| "eval_samples_per_second": 31.008, | |
| "eval_steps_per_second": 3.918, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.000592948717948718, | |
| "loss": 0.3068, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.6823104693140795, | |
| "eval_loss": 0.3616185486316681, | |
| "eval_runtime": 8.921, | |
| "eval_samples_per_second": 31.05, | |
| "eval_steps_per_second": 3.923, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 0.3554804027080536, | |
| "eval_runtime": 8.9621, | |
| "eval_samples_per_second": 30.908, | |
| "eval_steps_per_second": 3.905, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00045940170940170943, | |
| "loss": 0.3031, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.34177201986312866, | |
| "eval_runtime": 9.1926, | |
| "eval_samples_per_second": 30.133, | |
| "eval_steps_per_second": 3.807, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6859205776173285, | |
| "eval_loss": 0.34597525000572205, | |
| "eval_runtime": 9.1395, | |
| "eval_samples_per_second": 30.308, | |
| "eval_steps_per_second": 3.83, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.00032585470085470087, | |
| "loss": 0.3039, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.335258424282074, | |
| "eval_runtime": 9.0559, | |
| "eval_samples_per_second": 30.588, | |
| "eval_steps_per_second": 3.865, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 0.3025, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.34501808881759644, | |
| "eval_runtime": 3.4803, | |
| "eval_samples_per_second": 79.591, | |
| "eval_steps_per_second": 10.057, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.34273090958595276, | |
| "eval_runtime": 8.911, | |
| "eval_samples_per_second": 31.085, | |
| "eval_steps_per_second": 3.928, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 5.876068376068376e-05, | |
| "loss": 0.3034, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7003610108303249, | |
| "eval_loss": 0.3430791199207306, | |
| "eval_runtime": 8.959, | |
| "eval_samples_per_second": 30.919, | |
| "eval_steps_per_second": 3.907, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 46, | |
| "best_eval_accuracy": 0.7292418772563177, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.36451038132365954, | |
| "train_runtime": 8268.8296, | |
| "train_samples_per_second": 18.068, | |
| "train_steps_per_second": 2.264 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |