| { | |
| "best_metric": 2.2068374156951904, | |
| "best_model_checkpoint": "card_type_image_detection/checkpoint-12573", | |
| "epoch": 99.0, | |
| "eval_steps": 500, | |
| "global_step": 12573, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.023209876543209877, | |
| "eval_loss": 3.959347724914551, | |
| "eval_runtime": 16.3056, | |
| "eval_samples_per_second": 124.191, | |
| "eval_steps_per_second": 3.925, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.047407407407407405, | |
| "eval_loss": 3.927157163619995, | |
| "eval_runtime": 16.3398, | |
| "eval_samples_per_second": 123.93, | |
| "eval_steps_per_second": 3.917, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0819753086419753, | |
| "eval_loss": 3.8877668380737305, | |
| "eval_runtime": 16.2853, | |
| "eval_samples_per_second": 124.345, | |
| "eval_steps_per_second": 3.93, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.9288537549407114e-06, | |
| "loss": 3.9022, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.09876543209876543, | |
| "eval_loss": 3.8418056964874268, | |
| "eval_runtime": 16.2864, | |
| "eval_samples_per_second": 124.337, | |
| "eval_steps_per_second": 3.93, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.12, | |
| "eval_loss": 3.7911477088928223, | |
| "eval_runtime": 16.2971, | |
| "eval_samples_per_second": 124.255, | |
| "eval_steps_per_second": 3.927, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.1382716049382716, | |
| "eval_loss": 3.7379021644592285, | |
| "eval_runtime": 16.4902, | |
| "eval_samples_per_second": 122.8, | |
| "eval_steps_per_second": 3.881, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.1580246913580247, | |
| "eval_loss": 3.6840596199035645, | |
| "eval_runtime": 16.2622, | |
| "eval_samples_per_second": 124.522, | |
| "eval_steps_per_second": 3.936, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 1.849802371541502e-06, | |
| "loss": 3.6821, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.17777777777777778, | |
| "eval_loss": 3.6320221424102783, | |
| "eval_runtime": 16.3988, | |
| "eval_samples_per_second": 123.485, | |
| "eval_steps_per_second": 3.903, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.19654320987654322, | |
| "eval_loss": 3.580777883529663, | |
| "eval_runtime": 16.325, | |
| "eval_samples_per_second": 124.043, | |
| "eval_steps_per_second": 3.92, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.21580246913580248, | |
| "eval_loss": 3.5295674800872803, | |
| "eval_runtime": 16.3625, | |
| "eval_samples_per_second": 123.758, | |
| "eval_steps_per_second": 3.911, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.23703703703703705, | |
| "eval_loss": 3.479665994644165, | |
| "eval_runtime": 16.5252, | |
| "eval_samples_per_second": 122.54, | |
| "eval_steps_per_second": 3.873, | |
| "step": 1397 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 1.7707509881422924e-06, | |
| "loss": 3.4599, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.24592592592592594, | |
| "eval_loss": 3.431598663330078, | |
| "eval_runtime": 16.3048, | |
| "eval_samples_per_second": 124.197, | |
| "eval_steps_per_second": 3.925, | |
| "step": 1524 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.25728395061728393, | |
| "eval_loss": 3.38520884513855, | |
| "eval_runtime": 16.3716, | |
| "eval_samples_per_second": 123.69, | |
| "eval_steps_per_second": 3.909, | |
| "step": 1651 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.2730864197530864, | |
| "eval_loss": 3.341092348098755, | |
| "eval_runtime": 16.4208, | |
| "eval_samples_per_second": 123.319, | |
| "eval_steps_per_second": 3.897, | |
| "step": 1778 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.291358024691358, | |
| "eval_loss": 3.299830198287964, | |
| "eval_runtime": 16.349, | |
| "eval_samples_per_second": 123.861, | |
| "eval_steps_per_second": 3.915, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 1.691699604743083e-06, | |
| "loss": 3.2748, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.305679012345679, | |
| "eval_loss": 3.2592811584472656, | |
| "eval_runtime": 16.2664, | |
| "eval_samples_per_second": 124.49, | |
| "eval_steps_per_second": 3.934, | |
| "step": 2032 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.32641975308641974, | |
| "eval_loss": 3.2209341526031494, | |
| "eval_runtime": 16.4355, | |
| "eval_samples_per_second": 123.209, | |
| "eval_steps_per_second": 3.894, | |
| "step": 2159 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.3437037037037037, | |
| "eval_loss": 3.184448003768921, | |
| "eval_runtime": 16.3387, | |
| "eval_samples_per_second": 123.939, | |
| "eval_steps_per_second": 3.917, | |
| "step": 2286 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.345679012345679, | |
| "eval_loss": 3.1492130756378174, | |
| "eval_runtime": 16.2457, | |
| "eval_samples_per_second": 124.648, | |
| "eval_steps_per_second": 3.939, | |
| "step": 2413 | |
| }, | |
| { | |
| "epoch": 19.69, | |
| "learning_rate": 1.6126482213438735e-06, | |
| "loss": 3.1183, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.3634567901234568, | |
| "eval_loss": 3.117238998413086, | |
| "eval_runtime": 16.3142, | |
| "eval_samples_per_second": 124.125, | |
| "eval_steps_per_second": 3.923, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.37382716049382714, | |
| "eval_loss": 3.0856010913848877, | |
| "eval_runtime": 16.4136, | |
| "eval_samples_per_second": 123.374, | |
| "eval_steps_per_second": 3.899, | |
| "step": 2667 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.38469135802469134, | |
| "eval_loss": 3.0540201663970947, | |
| "eval_runtime": 16.404, | |
| "eval_samples_per_second": 123.446, | |
| "eval_steps_per_second": 3.901, | |
| "step": 2794 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.3916049382716049, | |
| "eval_loss": 3.025864362716675, | |
| "eval_runtime": 16.3387, | |
| "eval_samples_per_second": 123.939, | |
| "eval_steps_per_second": 3.917, | |
| "step": 2921 | |
| }, | |
| { | |
| "epoch": 23.62, | |
| "learning_rate": 1.533596837944664e-06, | |
| "loss": 2.9883, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4014814814814815, | |
| "eval_loss": 2.9977123737335205, | |
| "eval_runtime": 16.5183, | |
| "eval_samples_per_second": 122.592, | |
| "eval_steps_per_second": 3.874, | |
| "step": 3048 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4103703703703704, | |
| "eval_loss": 2.970736503601074, | |
| "eval_runtime": 16.4478, | |
| "eval_samples_per_second": 123.117, | |
| "eval_steps_per_second": 3.891, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.42962962962962964, | |
| "eval_loss": 2.9437484741210938, | |
| "eval_runtime": 16.3805, | |
| "eval_samples_per_second": 123.623, | |
| "eval_steps_per_second": 3.907, | |
| "step": 3302 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4365432098765432, | |
| "eval_loss": 2.918938636779785, | |
| "eval_runtime": 16.4584, | |
| "eval_samples_per_second": 123.038, | |
| "eval_steps_per_second": 3.889, | |
| "step": 3429 | |
| }, | |
| { | |
| "epoch": 27.56, | |
| "learning_rate": 1.4545454545454544e-06, | |
| "loss": 2.8743, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.44592592592592595, | |
| "eval_loss": 2.8959240913391113, | |
| "eval_runtime": 16.8148, | |
| "eval_samples_per_second": 120.43, | |
| "eval_steps_per_second": 3.806, | |
| "step": 3556 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4597530864197531, | |
| "eval_loss": 2.8701860904693604, | |
| "eval_runtime": 16.5161, | |
| "eval_samples_per_second": 122.607, | |
| "eval_steps_per_second": 3.875, | |
| "step": 3683 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.46469135802469136, | |
| "eval_loss": 2.848033905029297, | |
| "eval_runtime": 16.6005, | |
| "eval_samples_per_second": 121.984, | |
| "eval_steps_per_second": 3.855, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.4730864197530864, | |
| "eval_loss": 2.825526714324951, | |
| "eval_runtime": 16.5596, | |
| "eval_samples_per_second": 122.286, | |
| "eval_steps_per_second": 3.865, | |
| "step": 3937 | |
| }, | |
| { | |
| "epoch": 31.5, | |
| "learning_rate": 1.375494071146245e-06, | |
| "loss": 2.773, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.47802469135802467, | |
| "eval_loss": 2.804414749145508, | |
| "eval_runtime": 16.6816, | |
| "eval_samples_per_second": 121.391, | |
| "eval_steps_per_second": 3.837, | |
| "step": 4064 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.47555555555555556, | |
| "eval_loss": 2.7853612899780273, | |
| "eval_runtime": 16.7524, | |
| "eval_samples_per_second": 120.878, | |
| "eval_steps_per_second": 3.82, | |
| "step": 4191 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4918518518518519, | |
| "eval_loss": 2.7612335681915283, | |
| "eval_runtime": 16.5289, | |
| "eval_samples_per_second": 122.513, | |
| "eval_steps_per_second": 3.872, | |
| "step": 4318 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.497283950617284, | |
| "eval_loss": 2.741335391998291, | |
| "eval_runtime": 16.6912, | |
| "eval_samples_per_second": 121.321, | |
| "eval_steps_per_second": 3.834, | |
| "step": 4445 | |
| }, | |
| { | |
| "epoch": 35.43, | |
| "learning_rate": 1.2964426877470356e-06, | |
| "loss": 2.6822, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.49876543209876545, | |
| "eval_loss": 2.724756956100464, | |
| "eval_runtime": 16.517, | |
| "eval_samples_per_second": 122.601, | |
| "eval_steps_per_second": 3.875, | |
| "step": 4572 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.49777777777777776, | |
| "eval_loss": 2.7084524631500244, | |
| "eval_runtime": 16.6709, | |
| "eval_samples_per_second": 121.469, | |
| "eval_steps_per_second": 3.839, | |
| "step": 4699 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5150617283950617, | |
| "eval_loss": 2.6876704692840576, | |
| "eval_runtime": 16.6152, | |
| "eval_samples_per_second": 121.876, | |
| "eval_steps_per_second": 3.852, | |
| "step": 4826 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5106172839506172, | |
| "eval_loss": 2.6705734729766846, | |
| "eval_runtime": 16.5075, | |
| "eval_samples_per_second": 122.671, | |
| "eval_steps_per_second": 3.877, | |
| "step": 4953 | |
| }, | |
| { | |
| "epoch": 39.37, | |
| "learning_rate": 1.217391304347826e-06, | |
| "loss": 2.5988, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5116049382716049, | |
| "eval_loss": 2.655836343765259, | |
| "eval_runtime": 16.7707, | |
| "eval_samples_per_second": 120.746, | |
| "eval_steps_per_second": 3.816, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5125925925925926, | |
| "eval_loss": 2.6394340991973877, | |
| "eval_runtime": 16.7747, | |
| "eval_samples_per_second": 120.718, | |
| "eval_steps_per_second": 3.815, | |
| "step": 5207 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5209876543209877, | |
| "eval_loss": 2.623532295227051, | |
| "eval_runtime": 16.7009, | |
| "eval_samples_per_second": 121.251, | |
| "eval_steps_per_second": 3.832, | |
| "step": 5334 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5249382716049382, | |
| "eval_loss": 2.6078622341156006, | |
| "eval_runtime": 16.3629, | |
| "eval_samples_per_second": 123.756, | |
| "eval_steps_per_second": 3.911, | |
| "step": 5461 | |
| }, | |
| { | |
| "epoch": 43.31, | |
| "learning_rate": 1.1383399209486167e-06, | |
| "loss": 2.5306, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5293827160493827, | |
| "eval_loss": 2.592928647994995, | |
| "eval_runtime": 16.7766, | |
| "eval_samples_per_second": 120.704, | |
| "eval_steps_per_second": 3.815, | |
| "step": 5588 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5338271604938272, | |
| "eval_loss": 2.575329542160034, | |
| "eval_runtime": 17.0334, | |
| "eval_samples_per_second": 118.884, | |
| "eval_steps_per_second": 3.757, | |
| "step": 5715 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.542716049382716, | |
| "eval_loss": 2.5605058670043945, | |
| "eval_runtime": 16.7153, | |
| "eval_samples_per_second": 121.146, | |
| "eval_steps_per_second": 3.829, | |
| "step": 5842 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.548641975308642, | |
| "eval_loss": 2.548151969909668, | |
| "eval_runtime": 16.3632, | |
| "eval_samples_per_second": 123.754, | |
| "eval_steps_per_second": 3.911, | |
| "step": 5969 | |
| }, | |
| { | |
| "epoch": 47.24, | |
| "learning_rate": 1.0592885375494072e-06, | |
| "loss": 2.4638, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5530864197530864, | |
| "eval_loss": 2.5332412719726562, | |
| "eval_runtime": 16.2257, | |
| "eval_samples_per_second": 124.802, | |
| "eval_steps_per_second": 3.944, | |
| "step": 6096 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5535802469135802, | |
| "eval_loss": 2.521514654159546, | |
| "eval_runtime": 16.2855, | |
| "eval_samples_per_second": 124.344, | |
| "eval_steps_per_second": 3.93, | |
| "step": 6223 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5619753086419753, | |
| "eval_loss": 2.507723569869995, | |
| "eval_runtime": 16.2945, | |
| "eval_samples_per_second": 124.275, | |
| "eval_steps_per_second": 3.928, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.5595061728395062, | |
| "eval_loss": 2.4946696758270264, | |
| "eval_runtime": 16.2486, | |
| "eval_samples_per_second": 124.626, | |
| "eval_steps_per_second": 3.939, | |
| "step": 6477 | |
| }, | |
| { | |
| "epoch": 51.18, | |
| "learning_rate": 9.802371541501976e-07, | |
| "loss": 2.405, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5580246913580247, | |
| "eval_loss": 2.4835174083709717, | |
| "eval_runtime": 16.5375, | |
| "eval_samples_per_second": 122.449, | |
| "eval_steps_per_second": 3.87, | |
| "step": 6604 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5585185185185185, | |
| "eval_loss": 2.473555088043213, | |
| "eval_runtime": 17.2437, | |
| "eval_samples_per_second": 117.434, | |
| "eval_steps_per_second": 3.711, | |
| "step": 6731 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5644444444444444, | |
| "eval_loss": 2.4599006175994873, | |
| "eval_runtime": 17.2017, | |
| "eval_samples_per_second": 117.721, | |
| "eval_steps_per_second": 3.721, | |
| "step": 6858 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.5708641975308641, | |
| "eval_loss": 2.444490432739258, | |
| "eval_runtime": 16.4767, | |
| "eval_samples_per_second": 122.901, | |
| "eval_steps_per_second": 3.884, | |
| "step": 6985 | |
| }, | |
| { | |
| "epoch": 55.12, | |
| "learning_rate": 9.011857707509881e-07, | |
| "loss": 2.3499, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5718518518518518, | |
| "eval_loss": 2.43546199798584, | |
| "eval_runtime": 17.1098, | |
| "eval_samples_per_second": 118.353, | |
| "eval_steps_per_second": 3.741, | |
| "step": 7112 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5738271604938272, | |
| "eval_loss": 2.424128532409668, | |
| "eval_runtime": 16.3356, | |
| "eval_samples_per_second": 123.962, | |
| "eval_steps_per_second": 3.918, | |
| "step": 7239 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5679012345679012, | |
| "eval_loss": 2.4162774085998535, | |
| "eval_runtime": 16.3093, | |
| "eval_samples_per_second": 124.162, | |
| "eval_steps_per_second": 3.924, | |
| "step": 7366 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5733333333333334, | |
| "eval_loss": 2.404547929763794, | |
| "eval_runtime": 16.3838, | |
| "eval_samples_per_second": 123.598, | |
| "eval_steps_per_second": 3.906, | |
| "step": 7493 | |
| }, | |
| { | |
| "epoch": 59.06, | |
| "learning_rate": 8.221343873517787e-07, | |
| "loss": 2.3047, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5767901234567901, | |
| "eval_loss": 2.3955578804016113, | |
| "eval_runtime": 16.4961, | |
| "eval_samples_per_second": 122.756, | |
| "eval_steps_per_second": 3.88, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.5733333333333334, | |
| "eval_loss": 2.3882274627685547, | |
| "eval_runtime": 16.5941, | |
| "eval_samples_per_second": 122.031, | |
| "eval_steps_per_second": 3.857, | |
| "step": 7747 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.5758024691358025, | |
| "eval_loss": 2.3768720626831055, | |
| "eval_runtime": 16.3063, | |
| "eval_samples_per_second": 124.185, | |
| "eval_steps_per_second": 3.925, | |
| "step": 7874 | |
| }, | |
| { | |
| "epoch": 62.99, | |
| "learning_rate": 7.430830039525692e-07, | |
| "loss": 2.2616, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.5802469135802469, | |
| "eval_loss": 2.3649182319641113, | |
| "eval_runtime": 16.4383, | |
| "eval_samples_per_second": 123.188, | |
| "eval_steps_per_second": 3.893, | |
| "step": 8001 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.5782716049382716, | |
| "eval_loss": 2.3605239391326904, | |
| "eval_runtime": 16.5048, | |
| "eval_samples_per_second": 122.691, | |
| "eval_steps_per_second": 3.878, | |
| "step": 8128 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.5881481481481482, | |
| "eval_loss": 2.348599433898926, | |
| "eval_runtime": 16.6986, | |
| "eval_samples_per_second": 121.268, | |
| "eval_steps_per_second": 3.833, | |
| "step": 8255 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.5891358024691358, | |
| "eval_loss": 2.3403825759887695, | |
| "eval_runtime": 16.6528, | |
| "eval_samples_per_second": 121.601, | |
| "eval_steps_per_second": 3.843, | |
| "step": 8382 | |
| }, | |
| { | |
| "epoch": 66.93, | |
| "learning_rate": 6.640316205533597e-07, | |
| "loss": 2.224, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.5876543209876544, | |
| "eval_loss": 2.333630323410034, | |
| "eval_runtime": 16.323, | |
| "eval_samples_per_second": 124.058, | |
| "eval_steps_per_second": 3.921, | |
| "step": 8509 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.5881481481481482, | |
| "eval_loss": 2.3267500400543213, | |
| "eval_runtime": 16.3769, | |
| "eval_samples_per_second": 123.649, | |
| "eval_steps_per_second": 3.908, | |
| "step": 8636 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.5871604938271605, | |
| "eval_loss": 2.3214409351348877, | |
| "eval_runtime": 16.4152, | |
| "eval_samples_per_second": 123.361, | |
| "eval_steps_per_second": 3.899, | |
| "step": 8763 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.5920987654320987, | |
| "eval_loss": 2.3111300468444824, | |
| "eval_runtime": 16.7406, | |
| "eval_samples_per_second": 120.963, | |
| "eval_steps_per_second": 3.823, | |
| "step": 8890 | |
| }, | |
| { | |
| "epoch": 70.87, | |
| "learning_rate": 5.849802371541502e-07, | |
| "loss": 2.1885, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.5906172839506173, | |
| "eval_loss": 2.304325580596924, | |
| "eval_runtime": 16.5534, | |
| "eval_samples_per_second": 122.331, | |
| "eval_steps_per_second": 3.866, | |
| "step": 9017 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.5960493827160493, | |
| "eval_loss": 2.297461986541748, | |
| "eval_runtime": 16.4435, | |
| "eval_samples_per_second": 123.149, | |
| "eval_steps_per_second": 3.892, | |
| "step": 9144 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.5871604938271605, | |
| "eval_loss": 2.296058177947998, | |
| "eval_runtime": 16.3403, | |
| "eval_samples_per_second": 123.927, | |
| "eval_steps_per_second": 3.917, | |
| "step": 9271 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.5960493827160493, | |
| "eval_loss": 2.2856781482696533, | |
| "eval_runtime": 16.6488, | |
| "eval_samples_per_second": 121.63, | |
| "eval_steps_per_second": 3.844, | |
| "step": 9398 | |
| }, | |
| { | |
| "epoch": 74.8, | |
| "learning_rate": 5.059288537549406e-07, | |
| "loss": 2.1603, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.5965432098765432, | |
| "eval_loss": 2.2791759967803955, | |
| "eval_runtime": 17.0015, | |
| "eval_samples_per_second": 119.107, | |
| "eval_steps_per_second": 3.764, | |
| "step": 9525 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.5955555555555555, | |
| "eval_loss": 2.2750935554504395, | |
| "eval_runtime": 16.6586, | |
| "eval_samples_per_second": 121.559, | |
| "eval_steps_per_second": 3.842, | |
| "step": 9652 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.5965432098765432, | |
| "eval_loss": 2.268305540084839, | |
| "eval_runtime": 16.6007, | |
| "eval_samples_per_second": 121.983, | |
| "eval_steps_per_second": 3.855, | |
| "step": 9779 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.6049382716049383, | |
| "eval_loss": 2.2604947090148926, | |
| "eval_runtime": 16.3684, | |
| "eval_samples_per_second": 123.714, | |
| "eval_steps_per_second": 3.91, | |
| "step": 9906 | |
| }, | |
| { | |
| "epoch": 78.74, | |
| "learning_rate": 4.268774703557312e-07, | |
| "loss": 2.1357, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.6064197530864197, | |
| "eval_loss": 2.254981756210327, | |
| "eval_runtime": 16.4537, | |
| "eval_samples_per_second": 123.072, | |
| "eval_steps_per_second": 3.89, | |
| "step": 10033 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.6034567901234568, | |
| "eval_loss": 2.2524936199188232, | |
| "eval_runtime": 16.3798, | |
| "eval_samples_per_second": 123.628, | |
| "eval_steps_per_second": 3.907, | |
| "step": 10160 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.6054320987654321, | |
| "eval_loss": 2.2475554943084717, | |
| "eval_runtime": 16.2339, | |
| "eval_samples_per_second": 124.739, | |
| "eval_steps_per_second": 3.942, | |
| "step": 10287 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.6004938271604938, | |
| "eval_loss": 2.244779586791992, | |
| "eval_runtime": 16.19, | |
| "eval_samples_per_second": 125.077, | |
| "eval_steps_per_second": 3.953, | |
| "step": 10414 | |
| }, | |
| { | |
| "epoch": 82.68, | |
| "learning_rate": 3.478260869565217e-07, | |
| "loss": 2.1153, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.6009876543209877, | |
| "eval_loss": 2.242079973220825, | |
| "eval_runtime": 16.2447, | |
| "eval_samples_per_second": 124.656, | |
| "eval_steps_per_second": 3.94, | |
| "step": 10541 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.6009876543209877, | |
| "eval_loss": 2.237128973007202, | |
| "eval_runtime": 16.3552, | |
| "eval_samples_per_second": 123.814, | |
| "eval_steps_per_second": 3.913, | |
| "step": 10668 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.6034567901234568, | |
| "eval_loss": 2.2331736087799072, | |
| "eval_runtime": 16.4131, | |
| "eval_samples_per_second": 123.377, | |
| "eval_steps_per_second": 3.899, | |
| "step": 10795 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.6064197530864197, | |
| "eval_loss": 2.230192184448242, | |
| "eval_runtime": 16.263, | |
| "eval_samples_per_second": 124.516, | |
| "eval_steps_per_second": 3.935, | |
| "step": 10922 | |
| }, | |
| { | |
| "epoch": 86.61, | |
| "learning_rate": 2.6877470355731227e-07, | |
| "loss": 2.0969, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.6083950617283951, | |
| "eval_loss": 2.2269179821014404, | |
| "eval_runtime": 16.4471, | |
| "eval_samples_per_second": 123.122, | |
| "eval_steps_per_second": 3.891, | |
| "step": 11049 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.6054320987654321, | |
| "eval_loss": 2.224729537963867, | |
| "eval_runtime": 16.5547, | |
| "eval_samples_per_second": 122.322, | |
| "eval_steps_per_second": 3.866, | |
| "step": 11176 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.6098765432098765, | |
| "eval_loss": 2.2210581302642822, | |
| "eval_runtime": 16.3636, | |
| "eval_samples_per_second": 123.75, | |
| "eval_steps_per_second": 3.911, | |
| "step": 11303 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.6049382716049383, | |
| "eval_loss": 2.2199292182922363, | |
| "eval_runtime": 16.5723, | |
| "eval_samples_per_second": 122.192, | |
| "eval_steps_per_second": 3.862, | |
| "step": 11430 | |
| }, | |
| { | |
| "epoch": 90.55, | |
| "learning_rate": 1.8972332015810276e-07, | |
| "loss": 2.0851, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.6103703703703703, | |
| "eval_loss": 2.2158267498016357, | |
| "eval_runtime": 16.2141, | |
| "eval_samples_per_second": 124.892, | |
| "eval_steps_per_second": 3.947, | |
| "step": 11557 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.6079012345679012, | |
| "eval_loss": 2.214700937271118, | |
| "eval_runtime": 16.2859, | |
| "eval_samples_per_second": 124.341, | |
| "eval_steps_per_second": 3.93, | |
| "step": 11684 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.6064197530864197, | |
| "eval_loss": 2.2131123542785645, | |
| "eval_runtime": 16.337, | |
| "eval_samples_per_second": 123.952, | |
| "eval_steps_per_second": 3.917, | |
| "step": 11811 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.6098765432098765, | |
| "eval_loss": 2.2114579677581787, | |
| "eval_runtime": 16.393, | |
| "eval_samples_per_second": 123.528, | |
| "eval_steps_per_second": 3.904, | |
| "step": 11938 | |
| }, | |
| { | |
| "epoch": 94.49, | |
| "learning_rate": 1.1067193675889327e-07, | |
| "loss": 2.0754, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.6138271604938271, | |
| "eval_loss": 2.209113597869873, | |
| "eval_runtime": 16.4652, | |
| "eval_samples_per_second": 122.987, | |
| "eval_steps_per_second": 3.887, | |
| "step": 12065 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.6128395061728396, | |
| "eval_loss": 2.2085654735565186, | |
| "eval_runtime": 16.3862, | |
| "eval_samples_per_second": 123.579, | |
| "eval_steps_per_second": 3.906, | |
| "step": 12192 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.6123456790123457, | |
| "eval_loss": 2.207934617996216, | |
| "eval_runtime": 16.3381, | |
| "eval_samples_per_second": 123.943, | |
| "eval_steps_per_second": 3.917, | |
| "step": 12319 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.6128395061728396, | |
| "eval_loss": 2.206979513168335, | |
| "eval_runtime": 16.3485, | |
| "eval_samples_per_second": 123.865, | |
| "eval_steps_per_second": 3.915, | |
| "step": 12446 | |
| }, | |
| { | |
| "epoch": 98.43, | |
| "learning_rate": 3.162055335968379e-08, | |
| "loss": 2.0667, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.6133333333333333, | |
| "eval_loss": 2.2068374156951904, | |
| "eval_runtime": 16.2194, | |
| "eval_samples_per_second": 124.851, | |
| "eval_steps_per_second": 3.946, | |
| "step": 12573 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12700, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 6.215388042176161e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |