| { | |
| "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": 0.51985559566787, | |
| "eval_loss": 0.00757412426173687, | |
| "eval_runtime": 4.16, | |
| "eval_samples_per_second": 66.586, | |
| "eval_steps_per_second": 8.413, | |
| "step": 156 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.51985559566787, | |
| "epoch": 1.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5342960288808665, | |
| "eval_loss": 0.04179096594452858, | |
| "eval_runtime": 4.2511, | |
| "eval_samples_per_second": 65.159, | |
| "eval_steps_per_second": 8.233, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 2.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5054151624548736, | |
| "eval_loss": 0.004435110837221146, | |
| "eval_runtime": 4.2687, | |
| "eval_samples_per_second": 64.891, | |
| "eval_steps_per_second": 8.199, | |
| "step": 468 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 3.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0028397435897435895, | |
| "loss": 0.0669, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.01173881534487009, | |
| "eval_runtime": 4.2726, | |
| "eval_samples_per_second": 64.832, | |
| "eval_steps_per_second": 8.192, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 4.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.033335305750370026, | |
| "eval_runtime": 4.2774, | |
| "eval_samples_per_second": 64.758, | |
| "eval_steps_per_second": 8.182, | |
| "step": 780 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 5.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.0013900818303227425, | |
| "eval_runtime": 4.2808, | |
| "eval_samples_per_second": 64.708, | |
| "eval_steps_per_second": 8.176, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 6.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.00267948717948718, | |
| "loss": 0.0209, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007993517792783678, | |
| "eval_runtime": 4.3048, | |
| "eval_samples_per_second": 64.346, | |
| "eval_steps_per_second": 8.13, | |
| "step": 1092 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 7.0, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0030970817897468805, | |
| "eval_runtime": 4.2737, | |
| "eval_samples_per_second": 64.815, | |
| "eval_steps_per_second": 8.19, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 8.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.4981949458483754, | |
| "eval_loss": 0.004927648231387138, | |
| "eval_runtime": 4.2737, | |
| "eval_samples_per_second": 64.815, | |
| "eval_steps_per_second": 8.19, | |
| "step": 1404 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 9.0, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.0025192307692307693, | |
| "loss": 0.0144, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006902324385009706, | |
| "eval_runtime": 4.2727, | |
| "eval_samples_per_second": 64.83, | |
| "eval_steps_per_second": 8.192, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 10.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4693140794223827, | |
| "eval_loss": 0.001355065149255097, | |
| "eval_runtime": 4.3031, | |
| "eval_samples_per_second": 64.372, | |
| "eval_steps_per_second": 8.134, | |
| "step": 1716 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 11.0, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5054151624548736, | |
| "eval_loss": 0.002226953860372305, | |
| "eval_runtime": 4.3156, | |
| "eval_samples_per_second": 64.186, | |
| "eval_steps_per_second": 8.11, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 12.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.002358974358974359, | |
| "loss": 0.0094, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007688578334636986, | |
| "eval_runtime": 4.2786, | |
| "eval_samples_per_second": 64.74, | |
| "eval_steps_per_second": 8.18, | |
| "step": 2028 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 13.0, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0011682923650369048, | |
| "eval_runtime": 4.3112, | |
| "eval_samples_per_second": 64.252, | |
| "eval_steps_per_second": 8.118, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 14.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0018351555336266756, | |
| "eval_runtime": 4.3007, | |
| "eval_samples_per_second": 64.409, | |
| "eval_steps_per_second": 8.138, | |
| "step": 2340 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 15.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007866995292715728, | |
| "eval_runtime": 4.2927, | |
| "eval_samples_per_second": 64.529, | |
| "eval_steps_per_second": 8.153, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 16.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0021987179487179486, | |
| "loss": 0.0087, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.001059322850778699, | |
| "eval_runtime": 4.2897, | |
| "eval_samples_per_second": 64.573, | |
| "eval_steps_per_second": 8.159, | |
| "step": 2652 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 17.0, | |
| "step": 2652 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0008964231819845736, | |
| "eval_runtime": 4.2913, | |
| "eval_samples_per_second": 64.549, | |
| "eval_steps_per_second": 8.156, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 18.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0009917899733409286, | |
| "eval_runtime": 4.2906, | |
| "eval_samples_per_second": 64.56, | |
| "eval_steps_per_second": 8.157, | |
| "step": 2964 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 19.0, | |
| "step": 2964 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0020384615384615385, | |
| "loss": 0.0091, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4584837545126354, | |
| "eval_loss": 0.002107406733557582, | |
| "eval_runtime": 4.2956, | |
| "eval_samples_per_second": 64.485, | |
| "eval_steps_per_second": 8.148, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 20.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0008094427757896483, | |
| "eval_runtime": 4.3018, | |
| "eval_samples_per_second": 64.392, | |
| "eval_steps_per_second": 8.136, | |
| "step": 3276 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 21.0, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0010112057207152247, | |
| "eval_runtime": 4.2947, | |
| "eval_samples_per_second": 64.498, | |
| "eval_steps_per_second": 8.15, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 22.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0018782051282051281, | |
| "loss": 0.0087, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007026080274954438, | |
| "eval_runtime": 4.2959, | |
| "eval_samples_per_second": 64.48, | |
| "eval_steps_per_second": 8.147, | |
| "step": 3588 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 23.0, | |
| "step": 3588 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.0012016486143693328, | |
| "eval_runtime": 4.2934, | |
| "eval_samples_per_second": 64.518, | |
| "eval_steps_per_second": 8.152, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 24.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0013125467812642455, | |
| "eval_runtime": 4.2925, | |
| "eval_samples_per_second": 64.531, | |
| "eval_steps_per_second": 8.154, | |
| "step": 3900 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 25.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0017179487179487178, | |
| "loss": 0.0088, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 0.000969512271694839, | |
| "eval_runtime": 4.2949, | |
| "eval_samples_per_second": 64.495, | |
| "eval_steps_per_second": 8.149, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 26.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.47653429602888087, | |
| "eval_loss": 0.001213469309732318, | |
| "eval_runtime": 4.2909, | |
| "eval_samples_per_second": 64.556, | |
| "eval_steps_per_second": 8.157, | |
| "step": 4212 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 27.0, | |
| "step": 4212 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0011853750329464674, | |
| "eval_runtime": 4.293, | |
| "eval_samples_per_second": 64.524, | |
| "eval_steps_per_second": 8.153, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 28.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0015576923076923079, | |
| "loss": 0.0087, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.49097472924187724, | |
| "eval_loss": 0.0012697704369202256, | |
| "eval_runtime": 4.2941, | |
| "eval_samples_per_second": 64.507, | |
| "eval_steps_per_second": 8.151, | |
| "step": 4524 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 29.0, | |
| "step": 4524 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0008673242991790175, | |
| "eval_runtime": 4.2937, | |
| "eval_samples_per_second": 64.513, | |
| "eval_steps_per_second": 8.151, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 30.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.001185604021884501, | |
| "eval_runtime": 4.2957, | |
| "eval_samples_per_second": 64.484, | |
| "eval_steps_per_second": 8.148, | |
| "step": 4836 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 31.0, | |
| "step": 4836 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006753391353413463, | |
| "eval_runtime": 4.2927, | |
| "eval_samples_per_second": 64.529, | |
| "eval_steps_per_second": 8.153, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 32.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0013974358974358976, | |
| "loss": 0.0089, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0009245880064554513, | |
| "eval_runtime": 4.2912, | |
| "eval_samples_per_second": 64.55, | |
| "eval_steps_per_second": 8.156, | |
| "step": 5148 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 33.0, | |
| "step": 5148 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0008024222333915532, | |
| "eval_runtime": 4.294, | |
| "eval_samples_per_second": 64.509, | |
| "eval_steps_per_second": 8.151, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 34.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007070166175253689, | |
| "eval_runtime": 4.2926, | |
| "eval_samples_per_second": 64.53, | |
| "eval_steps_per_second": 8.154, | |
| "step": 5460 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 35.0, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0012371794871794872, | |
| "loss": 0.0087, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0008649426745250821, | |
| "eval_runtime": 4.2928, | |
| "eval_samples_per_second": 64.527, | |
| "eval_steps_per_second": 8.153, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 36.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.48014440433212996, | |
| "eval_loss": 0.0006594746373593807, | |
| "eval_runtime": 4.2922, | |
| "eval_samples_per_second": 64.536, | |
| "eval_steps_per_second": 8.154, | |
| "step": 5772 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 37.0, | |
| "step": 5772 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007161492831073701, | |
| "eval_runtime": 4.2938, | |
| "eval_samples_per_second": 64.512, | |
| "eval_steps_per_second": 8.151, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 38.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0010769230769230769, | |
| "loss": 0.0093, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006771078915335238, | |
| "eval_runtime": 4.2959, | |
| "eval_samples_per_second": 64.48, | |
| "eval_steps_per_second": 8.147, | |
| "step": 6084 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 39.0, | |
| "step": 6084 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007806611829437315, | |
| "eval_runtime": 4.2905, | |
| "eval_samples_per_second": 64.561, | |
| "eval_steps_per_second": 8.157, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 40.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0011038266820833087, | |
| "eval_runtime": 4.2933, | |
| "eval_samples_per_second": 64.52, | |
| "eval_steps_per_second": 8.152, | |
| "step": 6396 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 41.0, | |
| "step": 6396 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0009166666666666668, | |
| "loss": 0.0086, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007803016342222691, | |
| "eval_runtime": 4.2875, | |
| "eval_samples_per_second": 64.607, | |
| "eval_steps_per_second": 8.163, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 42.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.001678149332292378, | |
| "eval_runtime": 4.2895, | |
| "eval_samples_per_second": 64.577, | |
| "eval_steps_per_second": 8.159, | |
| "step": 6708 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 43.0, | |
| "step": 6708 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0008550164639018476, | |
| "eval_runtime": 4.2923, | |
| "eval_samples_per_second": 64.534, | |
| "eval_steps_per_second": 8.154, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 44.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0007564102564102564, | |
| "loss": 0.0085, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006565186777152121, | |
| "eval_runtime": 4.288, | |
| "eval_samples_per_second": 64.598, | |
| "eval_steps_per_second": 8.162, | |
| "step": 7020 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 45.0, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0022354116663336754, | |
| "eval_runtime": 4.292, | |
| "eval_samples_per_second": 64.539, | |
| "eval_steps_per_second": 8.155, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 46.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.000903658801689744, | |
| "eval_runtime": 4.2892, | |
| "eval_samples_per_second": 64.581, | |
| "eval_steps_per_second": 8.16, | |
| "step": 7332 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 47.0, | |
| "step": 7332 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007766391499899328, | |
| "eval_runtime": 4.2894, | |
| "eval_samples_per_second": 64.577, | |
| "eval_steps_per_second": 8.16, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 48.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0005961538461538461, | |
| "loss": 0.0087, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007370923412963748, | |
| "eval_runtime": 4.2874, | |
| "eval_samples_per_second": 64.608, | |
| "eval_steps_per_second": 8.163, | |
| "step": 7644 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 49.0, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.000995746231637895, | |
| "eval_runtime": 4.2916, | |
| "eval_samples_per_second": 64.544, | |
| "eval_steps_per_second": 8.155, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 50.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006885773618705571, | |
| "eval_runtime": 4.2918, | |
| "eval_samples_per_second": 64.542, | |
| "eval_steps_per_second": 8.155, | |
| "step": 7956 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 51.0, | |
| "step": 7956 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.00043589743589743596, | |
| "loss": 0.0084, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0012769113527610898, | |
| "eval_runtime": 4.2932, | |
| "eval_samples_per_second": 64.521, | |
| "eval_steps_per_second": 8.152, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 52.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0010381898609921336, | |
| "eval_runtime": 4.293, | |
| "eval_samples_per_second": 64.524, | |
| "eval_steps_per_second": 8.153, | |
| "step": 8268 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 53.0, | |
| "step": 8268 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0010403883643448353, | |
| "eval_runtime": 4.2921, | |
| "eval_samples_per_second": 64.537, | |
| "eval_steps_per_second": 8.155, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 54.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.0002756410256410257, | |
| "loss": 0.0083, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006681613740511239, | |
| "eval_runtime": 4.2933, | |
| "eval_samples_per_second": 64.519, | |
| "eval_steps_per_second": 8.152, | |
| "step": 8580 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 55.0, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006536916480399668, | |
| "eval_runtime": 4.2936, | |
| "eval_samples_per_second": 64.514, | |
| "eval_steps_per_second": 8.152, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 56.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007098207133822143, | |
| "eval_runtime": 4.2932, | |
| "eval_samples_per_second": 64.521, | |
| "eval_steps_per_second": 8.152, | |
| "step": 8892 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 57.0, | |
| "step": 8892 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 0.0082, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006599544431082904, | |
| "eval_runtime": 4.2926, | |
| "eval_samples_per_second": 64.529, | |
| "eval_steps_per_second": 8.154, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 58.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0006803370197303593, | |
| "eval_runtime": 4.2908, | |
| "eval_samples_per_second": 64.557, | |
| "eval_steps_per_second": 8.157, | |
| "step": 9204 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 59.0, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.0007155144703574479, | |
| "eval_runtime": 4.292, | |
| "eval_samples_per_second": 64.538, | |
| "eval_steps_per_second": 8.155, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5342960288808665, | |
| "epoch": 60.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 9360, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.012766934969486334, | |
| "train_runtime": 3693.8313, | |
| "train_samples_per_second": 40.446, | |
| "train_steps_per_second": 2.534 | |
| } | |
| ], | |
| "max_steps": 9360, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |