| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 9360, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.8690470457077026, | |
| "eval_runtime": 4.1588, | |
| "eval_samples_per_second": 66.605, | |
| "eval_steps_per_second": 8.416, | |
| "step": 156 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.4729241877256318, | |
| "epoch": 1.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5270758122743683, | |
| "eval_loss": 0.7261884212493896, | |
| "eval_runtime": 4.2514, | |
| "eval_samples_per_second": 65.154, | |
| "eval_steps_per_second": 8.233, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 2.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.7646142244338989, | |
| "eval_runtime": 4.264, | |
| "eval_samples_per_second": 64.963, | |
| "eval_steps_per_second": 8.208, | |
| "step": 468 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5270758122743683, | |
| "epoch": 3.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0028397435897435895, | |
| "loss": 0.8294, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5884476534296029, | |
| "eval_loss": 0.7043800354003906, | |
| "eval_runtime": 4.2676, | |
| "eval_samples_per_second": 64.907, | |
| "eval_steps_per_second": 8.201, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 4.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5884476534296029, | |
| "eval_loss": 0.7099267840385437, | |
| "eval_runtime": 4.2759, | |
| "eval_samples_per_second": 64.781, | |
| "eval_steps_per_second": 8.185, | |
| "step": 780 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5884476534296029, | |
| "epoch": 5.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6245487364620939, | |
| "eval_loss": 0.6449177265167236, | |
| "eval_runtime": 4.2742, | |
| "eval_samples_per_second": 64.808, | |
| "eval_steps_per_second": 8.189, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.6245487364620939, | |
| "epoch": 6.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00267948717948718, | |
| "loss": 0.785, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6245487364620939, | |
| "eval_loss": 0.7755226492881775, | |
| "eval_runtime": 4.2724, | |
| "eval_samples_per_second": 64.834, | |
| "eval_steps_per_second": 8.192, | |
| "step": 1092 | |
| }, | |
| { | |
| "best_epoch": 5, | |
| "best_eval_accuracy": 0.6245487364620939, | |
| "epoch": 7.0, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6606498194945848, | |
| "eval_loss": 0.6442985534667969, | |
| "eval_runtime": 4.2721, | |
| "eval_samples_per_second": 64.84, | |
| "eval_steps_per_second": 8.193, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 7, | |
| "best_eval_accuracy": 0.6606498194945848, | |
| "epoch": 8.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6859205776173285, | |
| "eval_loss": 0.6348857879638672, | |
| "eval_runtime": 4.2715, | |
| "eval_samples_per_second": 64.849, | |
| "eval_steps_per_second": 8.194, | |
| "step": 1404 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 9.0, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0025192307692307693, | |
| "loss": 0.6665, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6462093862815884, | |
| "eval_loss": 0.9543846845626831, | |
| "eval_runtime": 4.2724, | |
| "eval_samples_per_second": 64.835, | |
| "eval_steps_per_second": 8.192, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6859205776173285, | |
| "epoch": 10.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.6008003354072571, | |
| "eval_runtime": 4.2739, | |
| "eval_samples_per_second": 64.811, | |
| "eval_steps_per_second": 8.189, | |
| "step": 1716 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 11.0, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.6502608060836792, | |
| "eval_runtime": 4.2753, | |
| "eval_samples_per_second": 64.791, | |
| "eval_steps_per_second": 8.187, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 12.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.002358974358974359, | |
| "loss": 0.6276, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.626946210861206, | |
| "eval_runtime": 4.2756, | |
| "eval_samples_per_second": 64.787, | |
| "eval_steps_per_second": 8.186, | |
| "step": 2028 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 13.0, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.5787616968154907, | |
| "eval_runtime": 4.2726, | |
| "eval_samples_per_second": 64.832, | |
| "eval_steps_per_second": 8.192, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 14.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.664523720741272, | |
| "eval_runtime": 4.2707, | |
| "eval_samples_per_second": 64.861, | |
| "eval_steps_per_second": 8.195, | |
| "step": 2340 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 15.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.9684011936187744, | |
| "eval_runtime": 4.273, | |
| "eval_samples_per_second": 64.825, | |
| "eval_steps_per_second": 8.191, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 16.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0021987179487179486, | |
| "loss": 0.587, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.6227187514305115, | |
| "eval_runtime": 4.2714, | |
| "eval_samples_per_second": 64.85, | |
| "eval_steps_per_second": 8.194, | |
| "step": 2652 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 17.0, | |
| "step": 2652 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.6448877453804016, | |
| "eval_runtime": 4.2744, | |
| "eval_samples_per_second": 64.804, | |
| "eval_steps_per_second": 8.188, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.7184115523465704, | |
| "epoch": 18.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.6650940179824829, | |
| "eval_runtime": 4.271, | |
| "eval_samples_per_second": 64.857, | |
| "eval_steps_per_second": 8.195, | |
| "step": 2964 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 19.0, | |
| "step": 2964 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0020384615384615385, | |
| "loss": 0.5287, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 1.132426142692566, | |
| "eval_runtime": 4.2727, | |
| "eval_samples_per_second": 64.83, | |
| "eval_steps_per_second": 8.191, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 20.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6895306859205776, | |
| "eval_loss": 0.7391165494918823, | |
| "eval_runtime": 4.2755, | |
| "eval_samples_per_second": 64.787, | |
| "eval_steps_per_second": 8.186, | |
| "step": 3276 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 21.0, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6642599277978339, | |
| "eval_loss": 1.0194385051727295, | |
| "eval_runtime": 4.2717, | |
| "eval_samples_per_second": 64.845, | |
| "eval_steps_per_second": 8.193, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 22.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0018782051282051281, | |
| "loss": 0.5035, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.7837710380554199, | |
| "eval_runtime": 4.2729, | |
| "eval_samples_per_second": 64.826, | |
| "eval_steps_per_second": 8.191, | |
| "step": 3588 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 23.0, | |
| "step": 3588 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7184115523465704, | |
| "eval_loss": 0.8647497296333313, | |
| "eval_runtime": 4.2733, | |
| "eval_samples_per_second": 64.821, | |
| "eval_steps_per_second": 8.19, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 24.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6714801444043321, | |
| "eval_loss": 1.0973684787750244, | |
| "eval_runtime": 4.2735, | |
| "eval_samples_per_second": 64.817, | |
| "eval_steps_per_second": 8.19, | |
| "step": 3900 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 25.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0017179487179487178, | |
| "loss": 0.4533, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.5861077308654785, | |
| "eval_runtime": 4.2708, | |
| "eval_samples_per_second": 64.86, | |
| "eval_steps_per_second": 8.195, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 26.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.6684616804122925, | |
| "eval_runtime": 4.2664, | |
| "eval_samples_per_second": 64.925, | |
| "eval_steps_per_second": 8.204, | |
| "step": 4212 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 27.0, | |
| "step": 4212 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.6998275518417358, | |
| "eval_runtime": 4.2768, | |
| "eval_samples_per_second": 64.768, | |
| "eval_steps_per_second": 8.184, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 28.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0015576923076923079, | |
| "loss": 0.4398, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.7596197128295898, | |
| "eval_runtime": 4.2737, | |
| "eval_samples_per_second": 64.815, | |
| "eval_steps_per_second": 8.19, | |
| "step": 4524 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 29.0, | |
| "step": 4524 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.696681797504425, | |
| "eval_runtime": 4.2817, | |
| "eval_samples_per_second": 64.695, | |
| "eval_steps_per_second": 8.174, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 26, | |
| "best_eval_accuracy": 0.7436823104693141, | |
| "epoch": 30.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.7040970325469971, | |
| "eval_runtime": 4.2717, | |
| "eval_samples_per_second": 64.845, | |
| "eval_steps_per_second": 8.193, | |
| "step": 4836 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 31.0, | |
| "step": 4836 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.7616851925849915, | |
| "eval_runtime": 4.2802, | |
| "eval_samples_per_second": 64.716, | |
| "eval_steps_per_second": 8.177, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 32.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0013974358974358976, | |
| "loss": 0.3837, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.7990546822547913, | |
| "eval_runtime": 4.2772, | |
| "eval_samples_per_second": 64.762, | |
| "eval_steps_per_second": 8.183, | |
| "step": 5148 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 33.0, | |
| "step": 5148 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.8228901028633118, | |
| "eval_runtime": 4.2769, | |
| "eval_samples_per_second": 64.766, | |
| "eval_steps_per_second": 8.183, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 34.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.7745354175567627, | |
| "eval_runtime": 4.2809, | |
| "eval_samples_per_second": 64.706, | |
| "eval_steps_per_second": 8.176, | |
| "step": 5460 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 35.0, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0012371794871794872, | |
| "loss": 0.3471, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.778685450553894, | |
| "eval_runtime": 4.2824, | |
| "eval_samples_per_second": 64.684, | |
| "eval_steps_per_second": 8.173, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 36.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.7990731596946716, | |
| "eval_runtime": 4.2833, | |
| "eval_samples_per_second": 64.669, | |
| "eval_steps_per_second": 8.171, | |
| "step": 5772 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 37.0, | |
| "step": 5772 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 1.0205601453781128, | |
| "eval_runtime": 4.2801, | |
| "eval_samples_per_second": 64.718, | |
| "eval_steps_per_second": 8.177, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 38.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0010769230769230769, | |
| "loss": 0.3303, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.8976525664329529, | |
| "eval_runtime": 4.2827, | |
| "eval_samples_per_second": 64.679, | |
| "eval_steps_per_second": 8.172, | |
| "step": 6084 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 39.0, | |
| "step": 6084 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.7327412366867065, | |
| "eval_runtime": 4.2744, | |
| "eval_samples_per_second": 64.805, | |
| "eval_steps_per_second": 8.188, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 40.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.810184895992279, | |
| "eval_runtime": 4.2816, | |
| "eval_samples_per_second": 64.696, | |
| "eval_steps_per_second": 8.175, | |
| "step": 6396 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 41.0, | |
| "step": 6396 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0009166666666666668, | |
| "loss": 0.2991, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.7347400784492493, | |
| "eval_runtime": 4.2774, | |
| "eval_samples_per_second": 64.759, | |
| "eval_steps_per_second": 8.182, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 42.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.867670476436615, | |
| "eval_runtime": 4.2777, | |
| "eval_samples_per_second": 64.754, | |
| "eval_steps_per_second": 8.182, | |
| "step": 6708 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 43.0, | |
| "step": 6708 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.9773887991905212, | |
| "eval_runtime": 4.2767, | |
| "eval_samples_per_second": 64.77, | |
| "eval_steps_per_second": 8.184, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 30, | |
| "best_eval_accuracy": 0.7472924187725631, | |
| "epoch": 44.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0007564102564102564, | |
| "loss": 0.275, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.8556901216506958, | |
| "eval_runtime": 4.277, | |
| "eval_samples_per_second": 64.765, | |
| "eval_steps_per_second": 8.183, | |
| "step": 7020 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 45.0, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.9789180755615234, | |
| "eval_runtime": 4.2782, | |
| "eval_samples_per_second": 64.747, | |
| "eval_steps_per_second": 8.181, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 46.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 1.001485824584961, | |
| "eval_runtime": 4.2769, | |
| "eval_samples_per_second": 64.767, | |
| "eval_steps_per_second": 8.184, | |
| "step": 7332 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 47.0, | |
| "step": 7332 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.8449525833129883, | |
| "eval_runtime": 4.2736, | |
| "eval_samples_per_second": 64.816, | |
| "eval_steps_per_second": 8.19, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 48.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0005961538461538461, | |
| "loss": 0.2596, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.8222180008888245, | |
| "eval_runtime": 4.278, | |
| "eval_samples_per_second": 64.75, | |
| "eval_steps_per_second": 8.181, | |
| "step": 7644 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 49.0, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.8967640995979309, | |
| "eval_runtime": 4.286, | |
| "eval_samples_per_second": 64.629, | |
| "eval_steps_per_second": 8.166, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 50.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.8584460616111755, | |
| "eval_runtime": 4.2772, | |
| "eval_samples_per_second": 64.762, | |
| "eval_steps_per_second": 8.183, | |
| "step": 7956 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 51.0, | |
| "step": 7956 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00043589743589743596, | |
| "loss": 0.2469, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.9157448410987854, | |
| "eval_runtime": 4.2727, | |
| "eval_samples_per_second": 64.83, | |
| "eval_steps_per_second": 8.191, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 52.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.9731793403625488, | |
| "eval_runtime": 4.2736, | |
| "eval_samples_per_second": 64.817, | |
| "eval_steps_per_second": 8.19, | |
| "step": 8268 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 53.0, | |
| "step": 8268 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 1.0671247243881226, | |
| "eval_runtime": 4.2701, | |
| "eval_samples_per_second": 64.87, | |
| "eval_steps_per_second": 8.197, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 54.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0002756410256410257, | |
| "loss": 0.2303, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.9512353539466858, | |
| "eval_runtime": 4.2682, | |
| "eval_samples_per_second": 64.899, | |
| "eval_steps_per_second": 8.2, | |
| "step": 8580 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 55.0, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.8708024621009827, | |
| "eval_runtime": 4.2721, | |
| "eval_samples_per_second": 64.839, | |
| "eval_steps_per_second": 8.193, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 56.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.9289500117301941, | |
| "eval_runtime": 4.2714, | |
| "eval_samples_per_second": 64.849, | |
| "eval_steps_per_second": 8.194, | |
| "step": 8892 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 57.0, | |
| "step": 8892 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 0.2275, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.8866466283798218, | |
| "eval_runtime": 4.2702, | |
| "eval_samples_per_second": 64.868, | |
| "eval_steps_per_second": 8.196, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 58.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.936638593673706, | |
| "eval_runtime": 4.2724, | |
| "eval_samples_per_second": 64.835, | |
| "eval_steps_per_second": 8.192, | |
| "step": 9204 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 59.0, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.9555269479751587, | |
| "eval_runtime": 4.279, | |
| "eval_samples_per_second": 64.735, | |
| "eval_steps_per_second": 8.179, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 44, | |
| "best_eval_accuracy": 0.7581227436823105, | |
| "epoch": 60.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 9360, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.4369181796016856, | |
| "train_runtime": 3671.2013, | |
| "train_samples_per_second": 40.695, | |
| "train_steps_per_second": 2.55 | |
| } | |
| ], | |
| "max_steps": 9360, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |