| { | |
| "best_metric": 0.7846992611885071, | |
| "best_model_checkpoint": "/output/zgt-roberta-large-finetuned-Gu21schedule-BS256-10ep/checkpoint-31926", | |
| "epoch": 9.99912662907937, | |
| "global_step": 32200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.12095168799057326, | |
| "eval_loss": 6.969939231872559, | |
| "eval_runtime": 4175.606, | |
| "eval_samples_per_second": 24.712, | |
| "eval_steps_per_second": 3.089, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.5527950310559007e-05, | |
| "loss": 7.8141, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.1524057089518688, | |
| "eval_loss": 6.233978271484375, | |
| "eval_runtime": 4177.4061, | |
| "eval_samples_per_second": 24.701, | |
| "eval_steps_per_second": 3.088, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.16394060788435189, | |
| "eval_loss": 6.122518539428711, | |
| "eval_runtime": 4179.7801, | |
| "eval_samples_per_second": 24.687, | |
| "eval_steps_per_second": 3.086, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.1055900621118014e-05, | |
| "loss": 6.1501, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.16842972332423103, | |
| "eval_loss": 6.045305252075195, | |
| "eval_runtime": 4182.1677, | |
| "eval_samples_per_second": 24.673, | |
| "eval_steps_per_second": 3.084, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.658385093167702e-05, | |
| "loss": 6.0737, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.16725142510331475, | |
| "eval_loss": 5.987020969390869, | |
| "eval_runtime": 4177.226, | |
| "eval_samples_per_second": 24.702, | |
| "eval_steps_per_second": 3.088, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.17195286451581493, | |
| "eval_loss": 5.9314141273498535, | |
| "eval_runtime": 4165.2923, | |
| "eval_samples_per_second": 24.773, | |
| "eval_steps_per_second": 3.097, | |
| "step": 1878 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.211180124223603e-05, | |
| "loss": 5.9753, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.17336381929439706, | |
| "eval_loss": 5.887312412261963, | |
| "eval_runtime": 4179.8742, | |
| "eval_samples_per_second": 24.687, | |
| "eval_steps_per_second": 3.086, | |
| "step": 2191 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 7.763975155279503e-05, | |
| "loss": 5.9008, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.1737213537890283, | |
| "eval_loss": 5.851128101348877, | |
| "eval_runtime": 4181.0014, | |
| "eval_samples_per_second": 24.68, | |
| "eval_steps_per_second": 3.085, | |
| "step": 2504 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.1730111369884377, | |
| "eval_loss": 5.819331645965576, | |
| "eval_runtime": 4182.8162, | |
| "eval_samples_per_second": 24.669, | |
| "eval_steps_per_second": 3.084, | |
| "step": 2817 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.316770186335404e-05, | |
| "loss": 5.8379, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.17577215201939525, | |
| "eval_loss": 5.785292625427246, | |
| "eval_runtime": 4184.6612, | |
| "eval_samples_per_second": 24.658, | |
| "eval_steps_per_second": 3.082, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.1759501659892642, | |
| "eval_loss": 5.762609481811523, | |
| "eval_runtime": 4182.8465, | |
| "eval_samples_per_second": 24.669, | |
| "eval_steps_per_second": 3.084, | |
| "step": 3443 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.903381642512077e-05, | |
| "loss": 5.7885, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.17622262356212584, | |
| "eval_loss": 5.739773273468018, | |
| "eval_runtime": 4170.2068, | |
| "eval_samples_per_second": 24.744, | |
| "eval_steps_per_second": 3.093, | |
| "step": 3756 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 9.730848861283644e-05, | |
| "loss": 5.7464, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_accuracy": 0.1766708743216783, | |
| "eval_loss": 5.720291614532471, | |
| "eval_runtime": 4172.2987, | |
| "eval_samples_per_second": 24.731, | |
| "eval_steps_per_second": 3.092, | |
| "step": 4069 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_accuracy": 0.17642257605364067, | |
| "eval_loss": 5.696093559265137, | |
| "eval_runtime": 4172.9563, | |
| "eval_samples_per_second": 24.728, | |
| "eval_steps_per_second": 3.091, | |
| "step": 4382 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 9.558316080055211e-05, | |
| "loss": 5.7149, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_accuracy": 0.17737878845804067, | |
| "eval_loss": 5.683297634124756, | |
| "eval_runtime": 4185.0558, | |
| "eval_samples_per_second": 24.656, | |
| "eval_steps_per_second": 3.082, | |
| "step": 4695 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 9.385783298826778e-05, | |
| "loss": 5.6885, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.1773234355905989, | |
| "eval_loss": 5.670944690704346, | |
| "eval_runtime": 4184.0795, | |
| "eval_samples_per_second": 24.662, | |
| "eval_steps_per_second": 3.083, | |
| "step": 5008 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_accuracy": 0.1774909217337557, | |
| "eval_loss": 5.6566619873046875, | |
| "eval_runtime": 4185.5299, | |
| "eval_samples_per_second": 24.653, | |
| "eval_steps_per_second": 3.082, | |
| "step": 5321 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.213250517598345e-05, | |
| "loss": 5.666, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.17712345558640866, | |
| "eval_loss": 5.647720813751221, | |
| "eval_runtime": 4178.6309, | |
| "eval_samples_per_second": 24.694, | |
| "eval_steps_per_second": 3.087, | |
| "step": 5634 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.1778983102903151, | |
| "eval_loss": 5.632648944854736, | |
| "eval_runtime": 4179.5279, | |
| "eval_samples_per_second": 24.689, | |
| "eval_steps_per_second": 3.086, | |
| "step": 5947 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 9.04071773636991e-05, | |
| "loss": 5.6458, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.1767171879623295, | |
| "eval_loss": 5.626438140869141, | |
| "eval_runtime": 4166.358, | |
| "eval_samples_per_second": 24.767, | |
| "eval_steps_per_second": 3.096, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.868184955141477e-05, | |
| "loss": 5.6293, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_accuracy": 0.18033812690505616, | |
| "eval_loss": 5.371770858764648, | |
| "eval_runtime": 4187.0608, | |
| "eval_samples_per_second": 24.644, | |
| "eval_steps_per_second": 3.081, | |
| "step": 6573 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.22889979190190532, | |
| "eval_loss": 4.608296871185303, | |
| "eval_runtime": 4185.2213, | |
| "eval_samples_per_second": 24.655, | |
| "eval_steps_per_second": 3.082, | |
| "step": 6886 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.695652173913044e-05, | |
| "loss": 4.9883, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.4614915191453084, | |
| "eval_loss": 3.1735970973968506, | |
| "eval_runtime": 4184.0355, | |
| "eval_samples_per_second": 24.662, | |
| "eval_steps_per_second": 3.083, | |
| "step": 7199 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.523119392684611e-05, | |
| "loss": 3.2514, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.5874539351791631, | |
| "eval_loss": 2.3033511638641357, | |
| "eval_runtime": 4180.5231, | |
| "eval_samples_per_second": 24.683, | |
| "eval_steps_per_second": 3.085, | |
| "step": 7512 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_accuracy": 0.6407011451986726, | |
| "eval_loss": 1.915069818496704, | |
| "eval_runtime": 4169.2257, | |
| "eval_samples_per_second": 24.75, | |
| "eval_steps_per_second": 3.094, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.350586611456177e-05, | |
| "loss": 2.1211, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_accuracy": 0.6671589447070213, | |
| "eval_loss": 1.7218379974365234, | |
| "eval_runtime": 4169.0733, | |
| "eval_samples_per_second": 24.751, | |
| "eval_steps_per_second": 3.094, | |
| "step": 8138 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.6849309492119486, | |
| "eval_loss": 1.5953431129455566, | |
| "eval_runtime": 4186.0587, | |
| "eval_samples_per_second": 24.65, | |
| "eval_steps_per_second": 3.081, | |
| "step": 8451 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 8.178053830227743e-05, | |
| "loss": 1.7698, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.6977890826334601, | |
| "eval_loss": 1.5040490627288818, | |
| "eval_runtime": 4187.545, | |
| "eval_samples_per_second": 24.641, | |
| "eval_steps_per_second": 3.08, | |
| "step": 8764 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 8.00552104899931e-05, | |
| "loss": 1.5907, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_accuracy": 0.7089186346832345, | |
| "eval_loss": 1.4300199747085571, | |
| "eval_runtime": 4186.4554, | |
| "eval_samples_per_second": 24.648, | |
| "eval_steps_per_second": 3.081, | |
| "step": 9077 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.716823811317197, | |
| "eval_loss": 1.3781534433364868, | |
| "eval_runtime": 4180.8901, | |
| "eval_samples_per_second": 24.681, | |
| "eval_steps_per_second": 3.085, | |
| "step": 9390 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.832988267770877e-05, | |
| "loss": 1.4757, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_accuracy": 0.7239590766169688, | |
| "eval_loss": 1.3298745155334473, | |
| "eval_runtime": 4169.3417, | |
| "eval_samples_per_second": 24.749, | |
| "eval_steps_per_second": 3.094, | |
| "step": 9703 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.660455486542444e-05, | |
| "loss": 1.3919, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_accuracy": 0.7302072364465025, | |
| "eval_loss": 1.2895771265029907, | |
| "eval_runtime": 4181.4693, | |
| "eval_samples_per_second": 24.677, | |
| "eval_steps_per_second": 3.085, | |
| "step": 10016 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "eval_accuracy": 0.7356055265010495, | |
| "eval_loss": 1.25456964969635, | |
| "eval_runtime": 4169.8649, | |
| "eval_samples_per_second": 24.746, | |
| "eval_steps_per_second": 3.093, | |
| "step": 10329 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 7.48792270531401e-05, | |
| "loss": 1.328, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.7406319445625766, | |
| "eval_loss": 1.2240813970565796, | |
| "eval_runtime": 4170.5091, | |
| "eval_samples_per_second": 24.742, | |
| "eval_steps_per_second": 3.093, | |
| "step": 10642 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.745277920243707, | |
| "eval_loss": 1.1944962739944458, | |
| "eval_runtime": 4174.7942, | |
| "eval_samples_per_second": 24.717, | |
| "eval_steps_per_second": 3.09, | |
| "step": 10955 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 7.315389924085577e-05, | |
| "loss": 1.2782, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_accuracy": 0.7494278825432492, | |
| "eval_loss": 1.1713906526565552, | |
| "eval_runtime": 4174.964, | |
| "eval_samples_per_second": 24.716, | |
| "eval_steps_per_second": 3.09, | |
| "step": 11268 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 1.2357, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.7529051534363226, | |
| "eval_loss": 1.1493370532989502, | |
| "eval_runtime": 4169.6928, | |
| "eval_samples_per_second": 24.747, | |
| "eval_steps_per_second": 3.094, | |
| "step": 11581 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_accuracy": 0.7561643316896146, | |
| "eval_loss": 1.1291333436965942, | |
| "eval_runtime": 4170.8848, | |
| "eval_samples_per_second": 24.74, | |
| "eval_steps_per_second": 3.093, | |
| "step": 11894 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 6.970324361628709e-05, | |
| "loss": 1.1986, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.7596194578598549, | |
| "eval_loss": 1.1110583543777466, | |
| "eval_runtime": 4174.4741, | |
| "eval_samples_per_second": 24.719, | |
| "eval_steps_per_second": 3.09, | |
| "step": 12207 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 6.797791580400277e-05, | |
| "loss": 1.1673, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_accuracy": 0.7632696453538697, | |
| "eval_loss": 1.091315507888794, | |
| "eval_runtime": 4175.4221, | |
| "eval_samples_per_second": 24.713, | |
| "eval_steps_per_second": 3.089, | |
| "step": 12520 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.7654154836189226, | |
| "eval_loss": 1.0766664743423462, | |
| "eval_runtime": 4173.9192, | |
| "eval_samples_per_second": 24.722, | |
| "eval_steps_per_second": 3.09, | |
| "step": 12833 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 6.625258799171843e-05, | |
| "loss": 1.1387, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_accuracy": 0.7681167597878354, | |
| "eval_loss": 1.0629887580871582, | |
| "eval_runtime": 4175.5718, | |
| "eval_samples_per_second": 24.712, | |
| "eval_steps_per_second": 3.089, | |
| "step": 13146 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_accuracy": 0.7707155612474973, | |
| "eval_loss": 1.046230673789978, | |
| "eval_runtime": 4175.7461, | |
| "eval_samples_per_second": 24.711, | |
| "eval_steps_per_second": 3.089, | |
| "step": 13459 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.45272601794341e-05, | |
| "loss": 1.1074, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "eval_accuracy": 0.7731418474891986, | |
| "eval_loss": 1.0337274074554443, | |
| "eval_runtime": 4174.5, | |
| "eval_samples_per_second": 24.718, | |
| "eval_steps_per_second": 3.09, | |
| "step": 13772 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 6.280193236714976e-05, | |
| "loss": 1.0893, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_accuracy": 0.7748741121676294, | |
| "eval_loss": 1.0239219665527344, | |
| "eval_runtime": 4175.3624, | |
| "eval_samples_per_second": 24.713, | |
| "eval_steps_per_second": 3.089, | |
| "step": 14085 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_accuracy": 0.7766543779252701, | |
| "eval_loss": 1.014146089553833, | |
| "eval_runtime": 4181.6475, | |
| "eval_samples_per_second": 24.676, | |
| "eval_steps_per_second": 3.085, | |
| "step": 14398 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 6.107660455486542e-05, | |
| "loss": 1.0682, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_accuracy": 0.7785186060053325, | |
| "eval_loss": 1.0032246112823486, | |
| "eval_runtime": 4180.7422, | |
| "eval_samples_per_second": 24.682, | |
| "eval_steps_per_second": 3.085, | |
| "step": 14711 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 5.9351276742581096e-05, | |
| "loss": 1.0524, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "eval_accuracy": 0.7806327231861181, | |
| "eval_loss": 0.9907068014144897, | |
| "eval_runtime": 4180.8503, | |
| "eval_samples_per_second": 24.681, | |
| "eval_steps_per_second": 3.085, | |
| "step": 15024 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "eval_accuracy": 0.7826726152932884, | |
| "eval_loss": 0.9796966910362244, | |
| "eval_runtime": 4176.9966, | |
| "eval_samples_per_second": 24.704, | |
| "eval_steps_per_second": 3.088, | |
| "step": 15337 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 5.762594893029676e-05, | |
| "loss": 1.0338, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.7838565333062765, | |
| "eval_loss": 0.9712271690368652, | |
| "eval_runtime": 4181.1547, | |
| "eval_samples_per_second": 24.679, | |
| "eval_steps_per_second": 3.085, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_accuracy": 0.7854880736072989, | |
| "eval_loss": 0.9626355767250061, | |
| "eval_runtime": 4176.3487, | |
| "eval_samples_per_second": 24.707, | |
| "eval_steps_per_second": 3.089, | |
| "step": 15963 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 5.590062111801242e-05, | |
| "loss": 1.0188, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_accuracy": 0.7867994298371893, | |
| "eval_loss": 0.9558107256889343, | |
| "eval_runtime": 4179.0241, | |
| "eval_samples_per_second": 24.692, | |
| "eval_steps_per_second": 3.087, | |
| "step": 16276 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 5.417529330572809e-05, | |
| "loss": 1.003, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "eval_accuracy": 0.7884956846420655, | |
| "eval_loss": 0.9470182657241821, | |
| "eval_runtime": 4176.2829, | |
| "eval_samples_per_second": 24.708, | |
| "eval_steps_per_second": 3.089, | |
| "step": 16589 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "eval_accuracy": 0.789320227965163, | |
| "eval_loss": 0.9419927597045898, | |
| "eval_runtime": 4176.4362, | |
| "eval_samples_per_second": 24.707, | |
| "eval_steps_per_second": 3.089, | |
| "step": 16902 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 5.244996549344375e-05, | |
| "loss": 0.989, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_accuracy": 0.7911368944368907, | |
| "eval_loss": 0.9319880604743958, | |
| "eval_runtime": 4173.211, | |
| "eval_samples_per_second": 24.726, | |
| "eval_steps_per_second": 3.091, | |
| "step": 17215 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 5.072463768115943e-05, | |
| "loss": 0.9786, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "eval_accuracy": 0.7913904624057875, | |
| "eval_loss": 0.9292972683906555, | |
| "eval_runtime": 4172.1427, | |
| "eval_samples_per_second": 24.732, | |
| "eval_steps_per_second": 3.092, | |
| "step": 17528 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "eval_accuracy": 0.7932201930680667, | |
| "eval_loss": 0.9203895330429077, | |
| "eval_runtime": 4172.1933, | |
| "eval_samples_per_second": 24.732, | |
| "eval_steps_per_second": 3.092, | |
| "step": 17841 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 4.899930986887509e-05, | |
| "loss": 0.9688, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "eval_accuracy": 0.7938784128863696, | |
| "eval_loss": 0.9155610799789429, | |
| "eval_runtime": 4171.4989, | |
| "eval_samples_per_second": 24.736, | |
| "eval_steps_per_second": 3.092, | |
| "step": 18154 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_accuracy": 0.7952068414816341, | |
| "eval_loss": 0.9091127514839172, | |
| "eval_runtime": 4177.1927, | |
| "eval_samples_per_second": 24.702, | |
| "eval_steps_per_second": 3.088, | |
| "step": 18467 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 4.727398205659075e-05, | |
| "loss": 0.9576, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "eval_accuracy": 0.7959312809475213, | |
| "eval_loss": 0.9035018682479858, | |
| "eval_runtime": 4178.199, | |
| "eval_samples_per_second": 24.697, | |
| "eval_steps_per_second": 3.087, | |
| "step": 18780 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 4.554865424430642e-05, | |
| "loss": 0.9489, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_accuracy": 0.7968186229313537, | |
| "eval_loss": 0.8974489569664001, | |
| "eval_runtime": 4175.3753, | |
| "eval_samples_per_second": 24.713, | |
| "eval_steps_per_second": 3.089, | |
| "step": 19093 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "eval_accuracy": 0.7980068894657456, | |
| "eval_loss": 0.8927856087684631, | |
| "eval_runtime": 4174.5551, | |
| "eval_samples_per_second": 24.718, | |
| "eval_steps_per_second": 3.09, | |
| "step": 19406 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 4.382332643202209e-05, | |
| "loss": 0.9384, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "eval_accuracy": 0.7989207834455775, | |
| "eval_loss": 0.8878790140151978, | |
| "eval_runtime": 4176.0286, | |
| "eval_samples_per_second": 24.709, | |
| "eval_steps_per_second": 3.089, | |
| "step": 19719 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 4.209799861973775e-05, | |
| "loss": 0.9292, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "eval_accuracy": 0.7995861067424526, | |
| "eval_loss": 0.8841228485107422, | |
| "eval_runtime": 4174.1874, | |
| "eval_samples_per_second": 24.72, | |
| "eval_steps_per_second": 3.09, | |
| "step": 20032 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "eval_accuracy": 0.8005012964274263, | |
| "eval_loss": 0.8798208236694336, | |
| "eval_runtime": 4177.291, | |
| "eval_samples_per_second": 24.702, | |
| "eval_steps_per_second": 3.088, | |
| "step": 20345 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 4.0372670807453414e-05, | |
| "loss": 0.921, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "eval_accuracy": 0.8013221542890863, | |
| "eval_loss": 0.8738238215446472, | |
| "eval_runtime": 4179.3089, | |
| "eval_samples_per_second": 24.69, | |
| "eval_steps_per_second": 3.086, | |
| "step": 20658 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "eval_accuracy": 0.8020292962858104, | |
| "eval_loss": 0.8702828288078308, | |
| "eval_runtime": 4183.644, | |
| "eval_samples_per_second": 24.664, | |
| "eval_steps_per_second": 3.083, | |
| "step": 20971 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 3.864734299516908e-05, | |
| "loss": 0.9142, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "eval_accuracy": 0.8031108659339165, | |
| "eval_loss": 0.8653974533081055, | |
| "eval_runtime": 4177.1307, | |
| "eval_samples_per_second": 24.703, | |
| "eval_steps_per_second": 3.088, | |
| "step": 21284 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 3.692201518288475e-05, | |
| "loss": 0.9059, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "eval_accuracy": 0.803630800811672, | |
| "eval_loss": 0.8622693419456482, | |
| "eval_runtime": 4177.9531, | |
| "eval_samples_per_second": 24.698, | |
| "eval_steps_per_second": 3.087, | |
| "step": 21597 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_accuracy": 0.8044488106784644, | |
| "eval_loss": 0.8577073812484741, | |
| "eval_runtime": 4179.042, | |
| "eval_samples_per_second": 24.692, | |
| "eval_steps_per_second": 3.087, | |
| "step": 21910 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 3.519668737060042e-05, | |
| "loss": 0.9, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "eval_accuracy": 0.8051737023740322, | |
| "eval_loss": 0.8543989062309265, | |
| "eval_runtime": 4184.397, | |
| "eval_samples_per_second": 24.66, | |
| "eval_steps_per_second": 3.083, | |
| "step": 22223 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 3.347135955831608e-05, | |
| "loss": 0.8938, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8057043385627138, | |
| "eval_loss": 0.8503552079200745, | |
| "eval_runtime": 4183.5003, | |
| "eval_samples_per_second": 24.665, | |
| "eval_steps_per_second": 3.083, | |
| "step": 22536 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.8066939882795919, | |
| "eval_loss": 0.8455684781074524, | |
| "eval_runtime": 4184.5066, | |
| "eval_samples_per_second": 24.659, | |
| "eval_steps_per_second": 3.083, | |
| "step": 22849 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.8863, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "eval_accuracy": 0.8068218962399752, | |
| "eval_loss": 0.8439931273460388, | |
| "eval_runtime": 4178.7482, | |
| "eval_samples_per_second": 24.693, | |
| "eval_steps_per_second": 3.087, | |
| "step": 23162 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "eval_accuracy": 0.8075830543867027, | |
| "eval_loss": 0.8405274152755737, | |
| "eval_runtime": 4175.082, | |
| "eval_samples_per_second": 24.715, | |
| "eval_steps_per_second": 3.09, | |
| "step": 23475 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 3.0020703933747414e-05, | |
| "loss": 0.8804, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_accuracy": 0.8083236702044754, | |
| "eval_loss": 0.8358407616615295, | |
| "eval_runtime": 4173.8003, | |
| "eval_samples_per_second": 24.723, | |
| "eval_steps_per_second": 3.09, | |
| "step": 23788 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 2.829537612146308e-05, | |
| "loss": 0.8743, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "eval_accuracy": 0.8087474534271941, | |
| "eval_loss": 0.8344011306762695, | |
| "eval_runtime": 4174.341, | |
| "eval_samples_per_second": 24.719, | |
| "eval_steps_per_second": 3.09, | |
| "step": 24101 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "eval_accuracy": 0.8092334825727566, | |
| "eval_loss": 0.8311472535133362, | |
| "eval_runtime": 4174.6403, | |
| "eval_samples_per_second": 24.718, | |
| "eval_steps_per_second": 3.09, | |
| "step": 24414 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 2.6570048309178748e-05, | |
| "loss": 0.8706, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "eval_accuracy": 0.8097197803323306, | |
| "eval_loss": 0.8285520672798157, | |
| "eval_runtime": 4174.1958, | |
| "eval_samples_per_second": 24.72, | |
| "eval_steps_per_second": 3.09, | |
| "step": 24727 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 2.484472049689441e-05, | |
| "loss": 0.8645, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_accuracy": 0.810216617587347, | |
| "eval_loss": 0.8253086805343628, | |
| "eval_runtime": 4174.8315, | |
| "eval_samples_per_second": 24.716, | |
| "eval_steps_per_second": 3.09, | |
| "step": 25040 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "eval_accuracy": 0.8111007973238641, | |
| "eval_loss": 0.8211511373519897, | |
| "eval_runtime": 4173.759, | |
| "eval_samples_per_second": 24.723, | |
| "eval_steps_per_second": 3.09, | |
| "step": 25353 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 2.311939268461008e-05, | |
| "loss": 0.8602, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "eval_accuracy": 0.8111680475751303, | |
| "eval_loss": 0.8205570578575134, | |
| "eval_runtime": 4174.1596, | |
| "eval_samples_per_second": 24.72, | |
| "eval_steps_per_second": 3.09, | |
| "step": 25666 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "eval_accuracy": 0.8120529685373788, | |
| "eval_loss": 0.8158560991287231, | |
| "eval_runtime": 4175.0585, | |
| "eval_samples_per_second": 24.715, | |
| "eval_steps_per_second": 3.09, | |
| "step": 25979 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 2.139406487232574e-05, | |
| "loss": 0.8538, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "eval_accuracy": 0.8122099938117417, | |
| "eval_loss": 0.814548134803772, | |
| "eval_runtime": 4175.6451, | |
| "eval_samples_per_second": 24.712, | |
| "eval_steps_per_second": 3.089, | |
| "step": 26292 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 1.966873706004141e-05, | |
| "loss": 0.8482, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "eval_accuracy": 0.8130589470835723, | |
| "eval_loss": 0.8115074634552002, | |
| "eval_runtime": 4173.7083, | |
| "eval_samples_per_second": 24.723, | |
| "eval_steps_per_second": 3.091, | |
| "step": 26605 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "eval_accuracy": 0.8134356257072347, | |
| "eval_loss": 0.8089998364448547, | |
| "eval_runtime": 4174.6745, | |
| "eval_samples_per_second": 24.717, | |
| "eval_steps_per_second": 3.09, | |
| "step": 26918 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 1.7943409247757076e-05, | |
| "loss": 0.8488, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_accuracy": 0.8134433401076823, | |
| "eval_loss": 0.8088431358337402, | |
| "eval_runtime": 4174.8389, | |
| "eval_samples_per_second": 24.716, | |
| "eval_steps_per_second": 3.09, | |
| "step": 27231 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 1.621808143547274e-05, | |
| "loss": 0.8423, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "eval_accuracy": 0.8137619275792424, | |
| "eval_loss": 0.8057170510292053, | |
| "eval_runtime": 4176.6965, | |
| "eval_samples_per_second": 24.705, | |
| "eval_steps_per_second": 3.088, | |
| "step": 27544 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "eval_accuracy": 0.8144356879652452, | |
| "eval_loss": 0.8039630651473999, | |
| "eval_runtime": 4175.7093, | |
| "eval_samples_per_second": 24.711, | |
| "eval_steps_per_second": 3.089, | |
| "step": 27857 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 1.4492753623188407e-05, | |
| "loss": 0.8396, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "eval_accuracy": 0.8145382455874637, | |
| "eval_loss": 0.8026472926139832, | |
| "eval_runtime": 4180.1354, | |
| "eval_samples_per_second": 24.685, | |
| "eval_steps_per_second": 3.086, | |
| "step": 28170 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_accuracy": 0.8152832629079341, | |
| "eval_loss": 0.7988529205322266, | |
| "eval_runtime": 4179.9334, | |
| "eval_samples_per_second": 24.686, | |
| "eval_steps_per_second": 3.086, | |
| "step": 28483 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 1.276742581090407e-05, | |
| "loss": 0.8377, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_accuracy": 0.8155252212471398, | |
| "eval_loss": 0.7979427576065063, | |
| "eval_runtime": 4178.4294, | |
| "eval_samples_per_second": 24.695, | |
| "eval_steps_per_second": 3.087, | |
| "step": 28796 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 1.1042097998619738e-05, | |
| "loss": 0.8319, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "eval_accuracy": 0.8159056442908116, | |
| "eval_loss": 0.7969533801078796, | |
| "eval_runtime": 4174.229, | |
| "eval_samples_per_second": 24.72, | |
| "eval_steps_per_second": 3.09, | |
| "step": 29109 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_accuracy": 0.816157387607754, | |
| "eval_loss": 0.7945725917816162, | |
| "eval_runtime": 4172.4325, | |
| "eval_samples_per_second": 24.731, | |
| "eval_steps_per_second": 3.091, | |
| "step": 29422 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 9.316770186335403e-06, | |
| "loss": 0.8262, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "eval_accuracy": 0.8161445368180659, | |
| "eval_loss": 0.7940195202827454, | |
| "eval_runtime": 4171.791, | |
| "eval_samples_per_second": 24.734, | |
| "eval_steps_per_second": 3.092, | |
| "step": 29735 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 7.591442374051071e-06, | |
| "loss": 0.8255, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_accuracy": 0.8167732822776922, | |
| "eval_loss": 0.7918646931648254, | |
| "eval_runtime": 4178.9618, | |
| "eval_samples_per_second": 24.692, | |
| "eval_steps_per_second": 3.087, | |
| "step": 30048 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "eval_accuracy": 0.8168878384273093, | |
| "eval_loss": 0.7914555072784424, | |
| "eval_runtime": 4176.3937, | |
| "eval_samples_per_second": 24.707, | |
| "eval_steps_per_second": 3.089, | |
| "step": 30361 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 5.866114561766736e-06, | |
| "loss": 0.824, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_accuracy": 0.817306118390898, | |
| "eval_loss": 0.7896197438240051, | |
| "eval_runtime": 4176.9927, | |
| "eval_samples_per_second": 24.704, | |
| "eval_steps_per_second": 3.088, | |
| "step": 30674 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "eval_accuracy": 0.8175610442353789, | |
| "eval_loss": 0.7872260212898254, | |
| "eval_runtime": 4173.6592, | |
| "eval_samples_per_second": 24.723, | |
| "eval_steps_per_second": 3.091, | |
| "step": 30987 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 4.140786749482402e-06, | |
| "loss": 0.8218, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "eval_accuracy": 0.8176242146063594, | |
| "eval_loss": 0.7876725792884827, | |
| "eval_runtime": 4174.4186, | |
| "eval_samples_per_second": 24.719, | |
| "eval_steps_per_second": 3.09, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 2.4154589371980677e-06, | |
| "loss": 0.8204, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "eval_accuracy": 0.8176433057924909, | |
| "eval_loss": 0.7873775959014893, | |
| "eval_runtime": 4173.4522, | |
| "eval_samples_per_second": 24.725, | |
| "eval_steps_per_second": 3.091, | |
| "step": 31613 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "eval_accuracy": 0.8180999846708549, | |
| "eval_loss": 0.7846992611885071, | |
| "eval_runtime": 4174.7361, | |
| "eval_samples_per_second": 24.717, | |
| "eval_steps_per_second": 3.09, | |
| "step": 31926 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 6.901311249137336e-07, | |
| "loss": 0.8177, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 32200, | |
| "total_flos": 7.683327485823698e+18, | |
| "train_loss": 1.915723304985473, | |
| "train_runtime": 1372706.2896, | |
| "train_samples_per_second": 6.006, | |
| "train_steps_per_second": 0.023 | |
| } | |
| ], | |
| "max_steps": 32200, | |
| "num_train_epochs": 10, | |
| "total_flos": 7.683327485823698e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |