| { | |
| "best_metric": 0.9142857142857143, | |
| "best_model_checkpoint": "Cvt-finetuned-thyroid/checkpoint-18", | |
| "epoch": 149.88888888888889, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 0.6600533127784729, | |
| "eval_runtime": 0.4026, | |
| "eval_samples_per_second": 173.882, | |
| "eval_steps_per_second": 7.452, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.6563708186149597, | |
| "eval_runtime": 0.3922, | |
| "eval_samples_per_second": 178.495, | |
| "eval_steps_per_second": 7.65, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.7428571428571429, | |
| "eval_loss": 0.6498632431030273, | |
| "eval_runtime": 0.3916, | |
| "eval_samples_per_second": 178.774, | |
| "eval_steps_per_second": 7.662, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.6404139399528503, | |
| "eval_runtime": 0.3913, | |
| "eval_samples_per_second": 178.878, | |
| "eval_steps_per_second": 7.666, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.62859708070755, | |
| "eval_runtime": 0.3923, | |
| "eval_samples_per_second": 178.448, | |
| "eval_steps_per_second": 7.648, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6146815419197083, | |
| "eval_runtime": 0.3861, | |
| "eval_samples_per_second": 181.308, | |
| "eval_steps_per_second": 7.77, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.5986873507499695, | |
| "eval_runtime": 0.3853, | |
| "eval_samples_per_second": 181.687, | |
| "eval_steps_per_second": 7.787, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.5808569192886353, | |
| "eval_runtime": 0.391, | |
| "eval_samples_per_second": 179.013, | |
| "eval_steps_per_second": 7.672, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.5618674755096436, | |
| "eval_runtime": 0.3861, | |
| "eval_samples_per_second": 181.318, | |
| "eval_steps_per_second": 7.771, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.5425492525100708, | |
| "eval_runtime": 0.3895, | |
| "eval_samples_per_second": 179.718, | |
| "eval_steps_per_second": 7.702, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.5230604410171509, | |
| "eval_runtime": 0.3908, | |
| "eval_samples_per_second": 179.109, | |
| "eval_steps_per_second": 7.676, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.5035112500190735, | |
| "eval_runtime": 0.3841, | |
| "eval_samples_per_second": 182.262, | |
| "eval_steps_per_second": 7.811, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.6786, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.4828525483608246, | |
| "eval_runtime": 0.3958, | |
| "eval_samples_per_second": 176.835, | |
| "eval_steps_per_second": 7.579, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.4621497690677643, | |
| "eval_runtime": 0.3893, | |
| "eval_samples_per_second": 179.815, | |
| "eval_steps_per_second": 7.706, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.44225531816482544, | |
| "eval_runtime": 0.3936, | |
| "eval_samples_per_second": 177.866, | |
| "eval_steps_per_second": 7.623, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.4237878918647766, | |
| "eval_runtime": 0.3885, | |
| "eval_samples_per_second": 180.201, | |
| "eval_steps_per_second": 7.723, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.4087783396244049, | |
| "eval_runtime": 0.3869, | |
| "eval_samples_per_second": 180.93, | |
| "eval_steps_per_second": 7.754, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.39638686180114746, | |
| "eval_runtime": 0.3919, | |
| "eval_samples_per_second": 178.599, | |
| "eval_steps_per_second": 7.654, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3871336281299591, | |
| "eval_runtime": 0.3895, | |
| "eval_samples_per_second": 179.725, | |
| "eval_steps_per_second": 7.703, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.37913817167282104, | |
| "eval_runtime": 0.3975, | |
| "eval_samples_per_second": 176.113, | |
| "eval_steps_per_second": 7.548, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.37276408076286316, | |
| "eval_runtime": 0.3884, | |
| "eval_samples_per_second": 180.205, | |
| "eval_steps_per_second": 7.723, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.36989572644233704, | |
| "eval_runtime": 0.3857, | |
| "eval_samples_per_second": 181.502, | |
| "eval_steps_per_second": 7.779, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.36899128556251526, | |
| "eval_runtime": 0.3889, | |
| "eval_samples_per_second": 180.008, | |
| "eval_steps_per_second": 7.715, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.36841970682144165, | |
| "eval_runtime": 0.3867, | |
| "eval_samples_per_second": 181.0, | |
| "eval_steps_per_second": 7.757, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.544, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.36657989025115967, | |
| "eval_runtime": 0.4003, | |
| "eval_samples_per_second": 174.876, | |
| "eval_steps_per_second": 7.495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.36433330178260803, | |
| "eval_runtime": 0.386, | |
| "eval_samples_per_second": 181.342, | |
| "eval_steps_per_second": 7.772, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 26.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3611242175102234, | |
| "eval_runtime": 0.3881, | |
| "eval_samples_per_second": 180.356, | |
| "eval_steps_per_second": 7.73, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.356433242559433, | |
| "eval_runtime": 0.3885, | |
| "eval_samples_per_second": 180.192, | |
| "eval_steps_per_second": 7.723, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3520072400569916, | |
| "eval_runtime": 0.3869, | |
| "eval_samples_per_second": 180.937, | |
| "eval_steps_per_second": 7.754, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 29.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3477487862110138, | |
| "eval_runtime": 0.39, | |
| "eval_samples_per_second": 179.492, | |
| "eval_steps_per_second": 7.693, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 30.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3445895314216614, | |
| "eval_runtime": 0.4111, | |
| "eval_samples_per_second": 170.276, | |
| "eval_steps_per_second": 7.298, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 31.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3390456736087799, | |
| "eval_runtime": 0.3852, | |
| "eval_samples_per_second": 181.703, | |
| "eval_steps_per_second": 7.787, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3347129821777344, | |
| "eval_runtime": 0.4506, | |
| "eval_samples_per_second": 155.353, | |
| "eval_steps_per_second": 6.658, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.33145877718925476, | |
| "eval_runtime": 0.394, | |
| "eval_samples_per_second": 177.648, | |
| "eval_steps_per_second": 7.613, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 34.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3286542296409607, | |
| "eval_runtime": 0.4325, | |
| "eval_samples_per_second": 161.841, | |
| "eval_steps_per_second": 6.936, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 35.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3254566192626953, | |
| "eval_runtime": 0.3901, | |
| "eval_samples_per_second": 179.436, | |
| "eval_steps_per_second": 7.69, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3226519525051117, | |
| "eval_runtime": 0.3957, | |
| "eval_samples_per_second": 176.889, | |
| "eval_steps_per_second": 7.581, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 37.44, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.4904, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 37.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.32086578011512756, | |
| "eval_runtime": 0.3917, | |
| "eval_samples_per_second": 178.712, | |
| "eval_steps_per_second": 7.659, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.32166367769241333, | |
| "eval_runtime": 0.3879, | |
| "eval_samples_per_second": 180.476, | |
| "eval_steps_per_second": 7.735, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 39.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3228186070919037, | |
| "eval_runtime": 0.3945, | |
| "eval_samples_per_second": 177.444, | |
| "eval_steps_per_second": 7.605, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 40.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.32248714566230774, | |
| "eval_runtime": 0.3925, | |
| "eval_samples_per_second": 178.361, | |
| "eval_steps_per_second": 7.644, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 41.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.32159554958343506, | |
| "eval_runtime": 0.3914, | |
| "eval_samples_per_second": 178.848, | |
| "eval_steps_per_second": 7.665, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 42.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.31996870040893555, | |
| "eval_runtime": 0.3902, | |
| "eval_samples_per_second": 179.374, | |
| "eval_steps_per_second": 7.687, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 43.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.31838318705558777, | |
| "eval_runtime": 0.3951, | |
| "eval_samples_per_second": 177.183, | |
| "eval_steps_per_second": 7.594, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 44.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3160267174243927, | |
| "eval_runtime": 0.3892, | |
| "eval_samples_per_second": 179.849, | |
| "eval_steps_per_second": 7.708, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 45.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.31339019536972046, | |
| "eval_runtime": 0.3914, | |
| "eval_samples_per_second": 178.826, | |
| "eval_steps_per_second": 7.664, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 46.89, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3097696900367737, | |
| "eval_runtime": 0.3909, | |
| "eval_samples_per_second": 179.096, | |
| "eval_steps_per_second": 7.676, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 47.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.3083226680755615, | |
| "eval_runtime": 0.3975, | |
| "eval_samples_per_second": 176.094, | |
| "eval_steps_per_second": 7.547, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.306194543838501, | |
| "eval_runtime": 0.39, | |
| "eval_samples_per_second": 179.464, | |
| "eval_steps_per_second": 7.691, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 49.89, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.4468, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 49.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.3034059703350067, | |
| "eval_runtime": 0.3988, | |
| "eval_samples_per_second": 175.515, | |
| "eval_steps_per_second": 7.522, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 50.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.3030487298965454, | |
| "eval_runtime": 0.3912, | |
| "eval_samples_per_second": 178.919, | |
| "eval_steps_per_second": 7.668, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 51.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.3037838339805603, | |
| "eval_runtime": 0.4036, | |
| "eval_samples_per_second": 173.422, | |
| "eval_steps_per_second": 7.432, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 52.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.30441269278526306, | |
| "eval_runtime": 0.3905, | |
| "eval_samples_per_second": 179.272, | |
| "eval_steps_per_second": 7.683, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 53.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.30462566018104553, | |
| "eval_runtime": 0.4004, | |
| "eval_samples_per_second": 174.832, | |
| "eval_steps_per_second": 7.493, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 54.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.30405017733573914, | |
| "eval_runtime": 0.3926, | |
| "eval_samples_per_second": 178.307, | |
| "eval_steps_per_second": 7.642, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 55.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.3027400076389313, | |
| "eval_runtime": 0.3921, | |
| "eval_samples_per_second": 178.52, | |
| "eval_steps_per_second": 7.651, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 56.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.3015061914920807, | |
| "eval_runtime": 0.3917, | |
| "eval_samples_per_second": 178.717, | |
| "eval_steps_per_second": 7.659, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 57.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.298301637172699, | |
| "eval_runtime": 0.3901, | |
| "eval_samples_per_second": 179.444, | |
| "eval_steps_per_second": 7.69, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 58.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2965472638607025, | |
| "eval_runtime": 0.3941, | |
| "eval_samples_per_second": 177.631, | |
| "eval_steps_per_second": 7.613, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 59.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2955659329891205, | |
| "eval_runtime": 0.3929, | |
| "eval_samples_per_second": 178.161, | |
| "eval_steps_per_second": 7.635, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 60.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2953043282032013, | |
| "eval_runtime": 0.3961, | |
| "eval_samples_per_second": 176.718, | |
| "eval_steps_per_second": 7.574, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 61.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2960428297519684, | |
| "eval_runtime": 0.3894, | |
| "eval_samples_per_second": 179.751, | |
| "eval_steps_per_second": 7.704, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 62.44, | |
| "learning_rate": 6.481481481481482e-06, | |
| "loss": 0.411, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 62.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.29606738686561584, | |
| "eval_runtime": 0.3907, | |
| "eval_samples_per_second": 179.177, | |
| "eval_steps_per_second": 7.679, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 63.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.29615068435668945, | |
| "eval_runtime": 0.3957, | |
| "eval_samples_per_second": 176.884, | |
| "eval_steps_per_second": 7.581, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 64.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.29546239972114563, | |
| "eval_runtime": 0.4028, | |
| "eval_samples_per_second": 173.791, | |
| "eval_steps_per_second": 7.448, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 65.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.29375123977661133, | |
| "eval_runtime": 0.3984, | |
| "eval_samples_per_second": 175.721, | |
| "eval_steps_per_second": 7.531, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 66.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.293165922164917, | |
| "eval_runtime": 0.3896, | |
| "eval_samples_per_second": 179.657, | |
| "eval_steps_per_second": 7.7, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 67.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2927437126636505, | |
| "eval_runtime": 0.3965, | |
| "eval_samples_per_second": 176.563, | |
| "eval_steps_per_second": 7.567, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2911137044429779, | |
| "eval_runtime": 0.3982, | |
| "eval_samples_per_second": 175.784, | |
| "eval_steps_per_second": 7.534, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 69.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.29145926237106323, | |
| "eval_runtime": 0.3948, | |
| "eval_samples_per_second": 177.308, | |
| "eval_steps_per_second": 7.599, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 70.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.291074275970459, | |
| "eval_runtime": 0.3933, | |
| "eval_samples_per_second": 177.964, | |
| "eval_steps_per_second": 7.627, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 71.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2896248400211334, | |
| "eval_runtime": 0.3962, | |
| "eval_samples_per_second": 176.685, | |
| "eval_steps_per_second": 7.572, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 72.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2880937457084656, | |
| "eval_runtime": 0.3944, | |
| "eval_samples_per_second": 177.463, | |
| "eval_steps_per_second": 7.606, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 73.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.28765279054641724, | |
| "eval_runtime": 0.3966, | |
| "eval_samples_per_second": 176.488, | |
| "eval_steps_per_second": 7.564, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 74.89, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.3705, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 74.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.2876226603984833, | |
| "eval_runtime": 0.3888, | |
| "eval_samples_per_second": 180.054, | |
| "eval_steps_per_second": 7.717, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 75.89, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.28748172521591187, | |
| "eval_runtime": 0.411, | |
| "eval_samples_per_second": 170.337, | |
| "eval_steps_per_second": 7.3, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 76.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2876095473766327, | |
| "eval_runtime": 0.4294, | |
| "eval_samples_per_second": 163.0, | |
| "eval_steps_per_second": 6.986, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 77.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.28670457005500793, | |
| "eval_runtime": 0.3949, | |
| "eval_samples_per_second": 177.274, | |
| "eval_steps_per_second": 7.597, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 78.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.28570595383644104, | |
| "eval_runtime": 0.3939, | |
| "eval_samples_per_second": 177.69, | |
| "eval_steps_per_second": 7.615, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 79.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.28557589650154114, | |
| "eval_runtime": 0.3949, | |
| "eval_samples_per_second": 177.268, | |
| "eval_steps_per_second": 7.597, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 80.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2853609621524811, | |
| "eval_runtime": 0.3898, | |
| "eval_samples_per_second": 179.59, | |
| "eval_steps_per_second": 7.697, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 81.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2859923243522644, | |
| "eval_runtime": 0.3917, | |
| "eval_samples_per_second": 178.729, | |
| "eval_steps_per_second": 7.66, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 82.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2853332459926605, | |
| "eval_runtime": 0.3898, | |
| "eval_samples_per_second": 179.566, | |
| "eval_steps_per_second": 7.696, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 83.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.28681549429893494, | |
| "eval_runtime": 0.3903, | |
| "eval_samples_per_second": 179.364, | |
| "eval_steps_per_second": 7.687, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 84.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2884899079799652, | |
| "eval_runtime": 0.4004, | |
| "eval_samples_per_second": 174.808, | |
| "eval_steps_per_second": 7.492, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 85.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2893112599849701, | |
| "eval_runtime": 0.3932, | |
| "eval_samples_per_second": 178.006, | |
| "eval_steps_per_second": 7.629, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 86.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.29076695442199707, | |
| "eval_runtime": 0.4006, | |
| "eval_samples_per_second": 174.727, | |
| "eval_steps_per_second": 7.488, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 87.44, | |
| "learning_rate": 4.62962962962963e-06, | |
| "loss": 0.3442, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 87.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.29055681824684143, | |
| "eval_runtime": 0.3948, | |
| "eval_samples_per_second": 177.302, | |
| "eval_steps_per_second": 7.599, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.29001426696777344, | |
| "eval_runtime": 0.4034, | |
| "eval_samples_per_second": 173.528, | |
| "eval_steps_per_second": 7.437, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 89.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.287276953458786, | |
| "eval_runtime": 0.3919, | |
| "eval_samples_per_second": 178.62, | |
| "eval_steps_per_second": 7.655, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 90.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.28426897525787354, | |
| "eval_runtime": 0.4018, | |
| "eval_samples_per_second": 174.231, | |
| "eval_steps_per_second": 7.467, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 91.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.28223827481269836, | |
| "eval_runtime": 0.3886, | |
| "eval_samples_per_second": 180.111, | |
| "eval_steps_per_second": 7.719, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 92.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.28137001395225525, | |
| "eval_runtime": 0.3867, | |
| "eval_samples_per_second": 181.016, | |
| "eval_steps_per_second": 7.758, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 93.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2821663022041321, | |
| "eval_runtime": 0.395, | |
| "eval_samples_per_second": 177.23, | |
| "eval_steps_per_second": 7.596, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 94.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2825068235397339, | |
| "eval_runtime": 0.3994, | |
| "eval_samples_per_second": 175.263, | |
| "eval_steps_per_second": 7.511, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 95.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2831081449985504, | |
| "eval_runtime": 0.3997, | |
| "eval_samples_per_second": 175.112, | |
| "eval_steps_per_second": 7.505, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 96.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2835954427719116, | |
| "eval_runtime": 0.3968, | |
| "eval_samples_per_second": 176.408, | |
| "eval_steps_per_second": 7.56, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 97.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.28326863050460815, | |
| "eval_runtime": 0.3965, | |
| "eval_samples_per_second": 176.561, | |
| "eval_steps_per_second": 7.567, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 98.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.281973272562027, | |
| "eval_runtime": 0.3973, | |
| "eval_samples_per_second": 176.206, | |
| "eval_steps_per_second": 7.552, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 99.89, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.3159, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 99.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.28054317831993103, | |
| "eval_runtime": 0.3966, | |
| "eval_samples_per_second": 176.5, | |
| "eval_steps_per_second": 7.564, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 100.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.27876371145248413, | |
| "eval_runtime": 0.393, | |
| "eval_samples_per_second": 178.117, | |
| "eval_steps_per_second": 7.634, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 101.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.27795442938804626, | |
| "eval_runtime": 0.388, | |
| "eval_samples_per_second": 180.426, | |
| "eval_steps_per_second": 7.733, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 102.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.27797621488571167, | |
| "eval_runtime": 0.3898, | |
| "eval_samples_per_second": 179.574, | |
| "eval_steps_per_second": 7.696, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 103.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.27778205275535583, | |
| "eval_runtime": 0.3946, | |
| "eval_samples_per_second": 177.402, | |
| "eval_steps_per_second": 7.603, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 104.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2783416509628296, | |
| "eval_runtime": 0.3956, | |
| "eval_samples_per_second": 176.929, | |
| "eval_steps_per_second": 7.583, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 105.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2788624167442322, | |
| "eval_runtime": 0.3965, | |
| "eval_samples_per_second": 176.537, | |
| "eval_steps_per_second": 7.566, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 106.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27885138988494873, | |
| "eval_runtime": 0.401, | |
| "eval_samples_per_second": 174.562, | |
| "eval_steps_per_second": 7.481, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 107.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2788878381252289, | |
| "eval_runtime": 0.3934, | |
| "eval_samples_per_second": 177.953, | |
| "eval_steps_per_second": 7.627, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 108.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27941665053367615, | |
| "eval_runtime": 0.3952, | |
| "eval_samples_per_second": 177.139, | |
| "eval_steps_per_second": 7.592, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 109.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2792874872684479, | |
| "eval_runtime": 0.3992, | |
| "eval_samples_per_second": 175.358, | |
| "eval_steps_per_second": 7.515, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 110.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27895817160606384, | |
| "eval_runtime": 0.393, | |
| "eval_samples_per_second": 178.121, | |
| "eval_steps_per_second": 7.634, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 111.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2787097692489624, | |
| "eval_runtime": 0.3941, | |
| "eval_samples_per_second": 177.636, | |
| "eval_steps_per_second": 7.613, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 112.44, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 0.2982, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 112.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2774018943309784, | |
| "eval_runtime": 0.3953, | |
| "eval_samples_per_second": 177.084, | |
| "eval_steps_per_second": 7.589, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 113.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2765597105026245, | |
| "eval_runtime": 0.389, | |
| "eval_samples_per_second": 179.928, | |
| "eval_steps_per_second": 7.711, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 114.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27541905641555786, | |
| "eval_runtime": 0.3931, | |
| "eval_samples_per_second": 178.054, | |
| "eval_steps_per_second": 7.631, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 115.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.27446889877319336, | |
| "eval_runtime": 0.3931, | |
| "eval_samples_per_second": 178.076, | |
| "eval_steps_per_second": 7.632, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 116.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.2735791802406311, | |
| "eval_runtime": 0.3922, | |
| "eval_samples_per_second": 178.501, | |
| "eval_steps_per_second": 7.65, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 117.89, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.27332428097724915, | |
| "eval_runtime": 0.3911, | |
| "eval_samples_per_second": 178.974, | |
| "eval_steps_per_second": 7.67, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 118.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2734207212924957, | |
| "eval_runtime": 0.396, | |
| "eval_samples_per_second": 176.768, | |
| "eval_steps_per_second": 7.576, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 119.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27379804849624634, | |
| "eval_runtime": 0.3939, | |
| "eval_samples_per_second": 177.731, | |
| "eval_steps_per_second": 7.617, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 120.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2744147777557373, | |
| "eval_runtime": 0.3947, | |
| "eval_samples_per_second": 177.362, | |
| "eval_steps_per_second": 7.601, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 121.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2748957574367523, | |
| "eval_runtime": 0.4048, | |
| "eval_samples_per_second": 172.911, | |
| "eval_steps_per_second": 7.41, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 122.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27517834305763245, | |
| "eval_runtime": 0.398, | |
| "eval_samples_per_second": 175.867, | |
| "eval_steps_per_second": 7.537, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 123.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2754015624523163, | |
| "eval_runtime": 0.394, | |
| "eval_samples_per_second": 177.676, | |
| "eval_steps_per_second": 7.615, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 124.89, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.2757, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 124.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27559223771095276, | |
| "eval_runtime": 0.3999, | |
| "eval_samples_per_second": 175.064, | |
| "eval_steps_per_second": 7.503, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 125.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27577343583106995, | |
| "eval_runtime": 0.3951, | |
| "eval_samples_per_second": 177.152, | |
| "eval_steps_per_second": 7.592, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 126.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2756122648715973, | |
| "eval_runtime": 0.3965, | |
| "eval_samples_per_second": 176.526, | |
| "eval_steps_per_second": 7.565, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 127.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2754615247249603, | |
| "eval_runtime": 0.3971, | |
| "eval_samples_per_second": 176.293, | |
| "eval_steps_per_second": 7.555, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 128.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27490970492362976, | |
| "eval_runtime": 0.3981, | |
| "eval_samples_per_second": 175.828, | |
| "eval_steps_per_second": 7.535, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 129.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27434810996055603, | |
| "eval_runtime": 0.3988, | |
| "eval_samples_per_second": 175.52, | |
| "eval_steps_per_second": 7.522, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 130.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27393919229507446, | |
| "eval_runtime": 0.3964, | |
| "eval_samples_per_second": 176.607, | |
| "eval_steps_per_second": 7.569, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 131.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2735598385334015, | |
| "eval_runtime": 0.3963, | |
| "eval_samples_per_second": 176.647, | |
| "eval_steps_per_second": 7.571, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 132.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27345114946365356, | |
| "eval_runtime": 0.3943, | |
| "eval_samples_per_second": 177.525, | |
| "eval_steps_per_second": 7.608, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 133.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27316632866859436, | |
| "eval_runtime": 0.3968, | |
| "eval_samples_per_second": 176.395, | |
| "eval_steps_per_second": 7.56, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 134.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2731429636478424, | |
| "eval_runtime": 0.3964, | |
| "eval_samples_per_second": 176.608, | |
| "eval_steps_per_second": 7.569, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 135.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2727990746498108, | |
| "eval_runtime": 0.3965, | |
| "eval_samples_per_second": 176.545, | |
| "eval_steps_per_second": 7.566, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 136.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2725311815738678, | |
| "eval_runtime": 0.3934, | |
| "eval_samples_per_second": 177.937, | |
| "eval_steps_per_second": 7.626, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 137.44, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.2724, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 137.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27232787013053894, | |
| "eval_runtime": 0.397, | |
| "eval_samples_per_second": 176.334, | |
| "eval_steps_per_second": 7.557, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 138.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2722608149051666, | |
| "eval_runtime": 0.3984, | |
| "eval_samples_per_second": 175.719, | |
| "eval_steps_per_second": 7.531, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 139.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2721470594406128, | |
| "eval_runtime": 0.3948, | |
| "eval_samples_per_second": 177.289, | |
| "eval_steps_per_second": 7.598, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 140.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2720603346824646, | |
| "eval_runtime": 0.4008, | |
| "eval_samples_per_second": 174.65, | |
| "eval_steps_per_second": 7.485, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 141.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27187877893447876, | |
| "eval_runtime": 0.3937, | |
| "eval_samples_per_second": 177.785, | |
| "eval_steps_per_second": 7.619, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 142.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27186280488967896, | |
| "eval_runtime": 0.3942, | |
| "eval_samples_per_second": 177.564, | |
| "eval_steps_per_second": 7.61, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 143.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27189135551452637, | |
| "eval_runtime": 0.3939, | |
| "eval_samples_per_second": 177.73, | |
| "eval_steps_per_second": 7.617, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 144.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27191561460494995, | |
| "eval_runtime": 0.4045, | |
| "eval_samples_per_second": 173.067, | |
| "eval_steps_per_second": 7.417, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 145.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2719388008117676, | |
| "eval_runtime": 0.3958, | |
| "eval_samples_per_second": 176.858, | |
| "eval_steps_per_second": 7.58, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 146.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.2719106674194336, | |
| "eval_runtime": 0.3928, | |
| "eval_samples_per_second": 178.226, | |
| "eval_steps_per_second": 7.638, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 147.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.271912157535553, | |
| "eval_runtime": 0.3948, | |
| "eval_samples_per_second": 177.319, | |
| "eval_steps_per_second": 7.599, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 148.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.271916002035141, | |
| "eval_runtime": 0.3979, | |
| "eval_samples_per_second": 175.916, | |
| "eval_steps_per_second": 7.539, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 149.89, | |
| "learning_rate": 0.0, | |
| "loss": 0.2614, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 149.89, | |
| "eval_accuracy": 0.8857142857142857, | |
| "eval_loss": 0.27192050218582153, | |
| "eval_runtime": 0.3918, | |
| "eval_samples_per_second": 178.659, | |
| "eval_steps_per_second": 7.657, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 149.89, | |
| "step": 300, | |
| "total_flos": 1.0435256966870508e+18, | |
| "train_loss": 0.39242326736450195, | |
| "train_runtime": 677.2441, | |
| "train_samples_per_second": 61.352, | |
| "train_steps_per_second": 0.443 | |
| } | |
| ], | |
| "max_steps": 300, | |
| "num_train_epochs": 150, | |
| "total_flos": 1.0435256966870508e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |