| { |
| "best_metric": 2.2837178707122803, |
| "best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/longt5_xl_sfd_memsum_40/checkpoint-57", |
| "epoch": 38.95652173913044, |
| "eval_steps": 500, |
| "global_step": 1120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "grad_norm": 1.5414308309555054, |
| "learning_rate": 0.001, |
| "loss": 3.1508, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 1.1113317012786865, |
| "learning_rate": 0.001, |
| "loss": 3.2124, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.21, |
| "grad_norm": 0.7978044152259827, |
| "learning_rate": 0.001, |
| "loss": 2.9466, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 0.6611266136169434, |
| "learning_rate": 0.001, |
| "loss": 2.8914, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 0.6737671494483948, |
| "learning_rate": 0.001, |
| "loss": 2.7507, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.41579362750053406, |
| "learning_rate": 0.001, |
| "loss": 2.6653, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.49, |
| "grad_norm": 0.37621861696243286, |
| "learning_rate": 0.001, |
| "loss": 2.579, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.581123411655426, |
| "learning_rate": 0.001, |
| "loss": 2.631, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.63, |
| "grad_norm": 0.6653873920440674, |
| "learning_rate": 0.001, |
| "loss": 2.6978, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.45471808314323425, |
| "learning_rate": 0.001, |
| "loss": 2.6541, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.77, |
| "grad_norm": 0.38716837763786316, |
| "learning_rate": 0.001, |
| "loss": 2.5325, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.83, |
| "grad_norm": 0.40614280104637146, |
| "learning_rate": 0.001, |
| "loss": 2.5584, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.3157476484775543, |
| "learning_rate": 0.001, |
| "loss": 2.5054, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.97, |
| "grad_norm": 0.3763532042503357, |
| "learning_rate": 0.001, |
| "loss": 2.5238, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.97, |
| "eval_loss": 2.314685106277466, |
| "eval_runtime": 14.2455, |
| "eval_samples_per_second": 23.727, |
| "eval_steps_per_second": 3.018, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 0.3202365040779114, |
| "learning_rate": 0.001, |
| "loss": 2.3018, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.11, |
| "grad_norm": 0.4395117461681366, |
| "learning_rate": 0.001, |
| "loss": 2.1284, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.18, |
| "grad_norm": 0.47938525676727295, |
| "learning_rate": 0.001, |
| "loss": 2.1782, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 1.0489932298660278, |
| "learning_rate": 0.001, |
| "loss": 2.1666, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.32, |
| "grad_norm": 0.34978240728378296, |
| "learning_rate": 0.001, |
| "loss": 2.1598, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.39, |
| "grad_norm": 0.28448227047920227, |
| "learning_rate": 0.001, |
| "loss": 2.023, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.46, |
| "grad_norm": 0.3449482023715973, |
| "learning_rate": 0.001, |
| "loss": 2.0545, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.53, |
| "grad_norm": 0.6303105354309082, |
| "learning_rate": 0.001, |
| "loss": 2.1264, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.3750413656234741, |
| "learning_rate": 0.001, |
| "loss": 2.1176, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.67, |
| "grad_norm": 0.44775936007499695, |
| "learning_rate": 0.001, |
| "loss": 2.1624, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.74, |
| "grad_norm": 0.34849441051483154, |
| "learning_rate": 0.001, |
| "loss": 2.0809, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.81, |
| "grad_norm": 0.28750795125961304, |
| "learning_rate": 0.001, |
| "loss": 2.0913, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.88, |
| "grad_norm": 0.2710261940956116, |
| "learning_rate": 0.001, |
| "loss": 2.0855, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.95, |
| "grad_norm": 0.28888803720474243, |
| "learning_rate": 0.001, |
| "loss": 2.1298, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.98, |
| "eval_loss": 2.2837178707122803, |
| "eval_runtime": 14.2329, |
| "eval_samples_per_second": 23.748, |
| "eval_steps_per_second": 3.021, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.02, |
| "grad_norm": 0.2953917682170868, |
| "learning_rate": 0.001, |
| "loss": 1.9808, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.09, |
| "grad_norm": 2.0295698642730713, |
| "learning_rate": 0.001, |
| "loss": 1.7208, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.16, |
| "grad_norm": 0.4198295772075653, |
| "learning_rate": 0.001, |
| "loss": 1.7108, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.23, |
| "grad_norm": 0.3806304335594177, |
| "learning_rate": 0.001, |
| "loss": 1.677, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.3, |
| "grad_norm": 0.36914414167404175, |
| "learning_rate": 0.001, |
| "loss": 1.6717, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.37, |
| "grad_norm": 0.34834641218185425, |
| "learning_rate": 0.001, |
| "loss": 1.6516, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.43, |
| "grad_norm": 0.3333311080932617, |
| "learning_rate": 0.001, |
| "loss": 1.6677, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.41852736473083496, |
| "learning_rate": 0.001, |
| "loss": 1.6135, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.57, |
| "grad_norm": 0.40690872073173523, |
| "learning_rate": 0.001, |
| "loss": 1.6447, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.64, |
| "grad_norm": 0.4816026985645294, |
| "learning_rate": 0.001, |
| "loss": 1.7096, |
| "step": 76 |
| }, |
| { |
| "epoch": 2.71, |
| "grad_norm": 0.8278970122337341, |
| "learning_rate": 0.001, |
| "loss": 1.6721, |
| "step": 78 |
| }, |
| { |
| "epoch": 2.78, |
| "grad_norm": 0.27179405093193054, |
| "learning_rate": 0.001, |
| "loss": 1.6351, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.85, |
| "grad_norm": 0.2935534417629242, |
| "learning_rate": 0.001, |
| "loss": 1.6402, |
| "step": 82 |
| }, |
| { |
| "epoch": 2.92, |
| "grad_norm": 0.3557533919811249, |
| "learning_rate": 0.001, |
| "loss": 1.6755, |
| "step": 84 |
| }, |
| { |
| "epoch": 2.99, |
| "grad_norm": 0.3663090169429779, |
| "learning_rate": 0.001, |
| "loss": 1.7525, |
| "step": 86 |
| }, |
| { |
| "epoch": 2.99, |
| "eval_loss": 2.333530902862549, |
| "eval_runtime": 14.2215, |
| "eval_samples_per_second": 23.767, |
| "eval_steps_per_second": 3.024, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.06, |
| "grad_norm": 0.37869980931282043, |
| "learning_rate": 0.001, |
| "loss": 1.3103, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.13, |
| "grad_norm": 0.32068952918052673, |
| "learning_rate": 0.001, |
| "loss": 1.2763, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.33284562826156616, |
| "learning_rate": 0.001, |
| "loss": 1.2235, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.27, |
| "grad_norm": 0.4027257561683655, |
| "learning_rate": 0.001, |
| "loss": 1.2606, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.34, |
| "grad_norm": 0.8390576839447021, |
| "learning_rate": 0.001, |
| "loss": 1.2426, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.41, |
| "grad_norm": 0.3938799798488617, |
| "learning_rate": 0.001, |
| "loss": 1.2499, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.48, |
| "grad_norm": 0.39702850580215454, |
| "learning_rate": 0.001, |
| "loss": 1.3165, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.55, |
| "grad_norm": 0.4196929633617401, |
| "learning_rate": 0.001, |
| "loss": 1.2884, |
| "step": 102 |
| }, |
| { |
| "epoch": 3.62, |
| "grad_norm": 0.4435763657093048, |
| "learning_rate": 0.001, |
| "loss": 1.3407, |
| "step": 104 |
| }, |
| { |
| "epoch": 3.69, |
| "grad_norm": 0.3989652395248413, |
| "learning_rate": 0.001, |
| "loss": 1.3119, |
| "step": 106 |
| }, |
| { |
| "epoch": 3.76, |
| "grad_norm": 0.35742542147636414, |
| "learning_rate": 0.001, |
| "loss": 1.2882, |
| "step": 108 |
| }, |
| { |
| "epoch": 3.83, |
| "grad_norm": 0.3512905538082123, |
| "learning_rate": 0.001, |
| "loss": 1.276, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.9, |
| "grad_norm": 0.35384494066238403, |
| "learning_rate": 0.001, |
| "loss": 1.31, |
| "step": 112 |
| }, |
| { |
| "epoch": 3.97, |
| "grad_norm": 0.38055282831192017, |
| "learning_rate": 0.001, |
| "loss": 1.2954, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 2.4995365142822266, |
| "eval_runtime": 14.2261, |
| "eval_samples_per_second": 23.759, |
| "eval_steps_per_second": 3.023, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.03, |
| "grad_norm": 0.33426040410995483, |
| "learning_rate": 0.001, |
| "loss": 1.0702, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.1, |
| "grad_norm": 0.3915540277957916, |
| "learning_rate": 0.001, |
| "loss": 0.93, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.17, |
| "grad_norm": 0.3885715901851654, |
| "learning_rate": 0.001, |
| "loss": 0.8923, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.24, |
| "grad_norm": 0.3450148105621338, |
| "learning_rate": 0.001, |
| "loss": 0.9367, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.31, |
| "grad_norm": 0.34307780861854553, |
| "learning_rate": 0.001, |
| "loss": 0.9471, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.38, |
| "grad_norm": 0.3358236253261566, |
| "learning_rate": 0.001, |
| "loss": 0.9597, |
| "step": 126 |
| }, |
| { |
| "epoch": 4.45, |
| "grad_norm": 0.32632964849472046, |
| "learning_rate": 0.001, |
| "loss": 0.9678, |
| "step": 128 |
| }, |
| { |
| "epoch": 4.52, |
| "grad_norm": 0.3462707996368408, |
| "learning_rate": 0.001, |
| "loss": 0.975, |
| "step": 130 |
| }, |
| { |
| "epoch": 4.59, |
| "grad_norm": 0.4402617812156677, |
| "learning_rate": 0.001, |
| "loss": 0.9908, |
| "step": 132 |
| }, |
| { |
| "epoch": 4.66, |
| "grad_norm": 0.4284449815750122, |
| "learning_rate": 0.001, |
| "loss": 0.9721, |
| "step": 134 |
| }, |
| { |
| "epoch": 4.73, |
| "grad_norm": 0.3820173144340515, |
| "learning_rate": 0.001, |
| "loss": 0.983, |
| "step": 136 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 0.5288845300674438, |
| "learning_rate": 0.001, |
| "loss": 0.9376, |
| "step": 138 |
| }, |
| { |
| "epoch": 4.87, |
| "grad_norm": 0.489346981048584, |
| "learning_rate": 0.001, |
| "loss": 0.9801, |
| "step": 140 |
| }, |
| { |
| "epoch": 4.94, |
| "grad_norm": 0.4548284709453583, |
| "learning_rate": 0.001, |
| "loss": 1.0518, |
| "step": 142 |
| }, |
| { |
| "epoch": 4.97, |
| "eval_loss": 2.832628011703491, |
| "eval_runtime": 14.24, |
| "eval_samples_per_second": 23.736, |
| "eval_steps_per_second": 3.02, |
| "step": 143 |
| }, |
| { |
| "epoch": 5.01, |
| "grad_norm": 0.4093753397464752, |
| "learning_rate": 0.001, |
| "loss": 0.9381, |
| "step": 144 |
| }, |
| { |
| "epoch": 5.08, |
| "grad_norm": 0.5986877679824829, |
| "learning_rate": 0.001, |
| "loss": 0.6649, |
| "step": 146 |
| }, |
| { |
| "epoch": 5.15, |
| "grad_norm": 0.4789908230304718, |
| "learning_rate": 0.001, |
| "loss": 0.6925, |
| "step": 148 |
| }, |
| { |
| "epoch": 5.22, |
| "grad_norm": 0.4392305612564087, |
| "learning_rate": 0.001, |
| "loss": 0.6901, |
| "step": 150 |
| }, |
| { |
| "epoch": 5.29, |
| "grad_norm": 0.49618610739707947, |
| "learning_rate": 0.001, |
| "loss": 0.7173, |
| "step": 152 |
| }, |
| { |
| "epoch": 5.36, |
| "grad_norm": 0.513729453086853, |
| "learning_rate": 0.001, |
| "loss": 0.6951, |
| "step": 154 |
| }, |
| { |
| "epoch": 5.43, |
| "grad_norm": 0.4622480571269989, |
| "learning_rate": 0.001, |
| "loss": 0.6757, |
| "step": 156 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 0.4192960560321808, |
| "learning_rate": 0.001, |
| "loss": 0.7125, |
| "step": 158 |
| }, |
| { |
| "epoch": 5.57, |
| "grad_norm": 0.3887766897678375, |
| "learning_rate": 0.001, |
| "loss": 0.6905, |
| "step": 160 |
| }, |
| { |
| "epoch": 5.63, |
| "grad_norm": 0.3633786141872406, |
| "learning_rate": 0.001, |
| "loss": 0.73, |
| "step": 162 |
| }, |
| { |
| "epoch": 5.7, |
| "grad_norm": 0.4010884761810303, |
| "learning_rate": 0.001, |
| "loss": 0.7473, |
| "step": 164 |
| }, |
| { |
| "epoch": 5.77, |
| "grad_norm": 0.4541136920452118, |
| "learning_rate": 0.001, |
| "loss": 0.7659, |
| "step": 166 |
| }, |
| { |
| "epoch": 5.84, |
| "grad_norm": 0.4243777394294739, |
| "learning_rate": 0.001, |
| "loss": 0.7742, |
| "step": 168 |
| }, |
| { |
| "epoch": 5.91, |
| "grad_norm": 0.40389642119407654, |
| "learning_rate": 0.001, |
| "loss": 0.7312, |
| "step": 170 |
| }, |
| { |
| "epoch": 5.98, |
| "grad_norm": 0.39572134613990784, |
| "learning_rate": 0.001, |
| "loss": 0.7083, |
| "step": 172 |
| }, |
| { |
| "epoch": 5.98, |
| "eval_loss": 2.9095335006713867, |
| "eval_runtime": 14.2201, |
| "eval_samples_per_second": 23.769, |
| "eval_steps_per_second": 3.024, |
| "step": 172 |
| }, |
| { |
| "epoch": 6.05, |
| "grad_norm": 0.34924399852752686, |
| "learning_rate": 0.001, |
| "loss": 0.5277, |
| "step": 174 |
| }, |
| { |
| "epoch": 6.12, |
| "grad_norm": 0.42162197828292847, |
| "learning_rate": 0.001, |
| "loss": 0.5141, |
| "step": 176 |
| }, |
| { |
| "epoch": 6.19, |
| "grad_norm": 0.43131959438323975, |
| "learning_rate": 0.001, |
| "loss": 0.5295, |
| "step": 178 |
| }, |
| { |
| "epoch": 6.26, |
| "grad_norm": 0.3414030075073242, |
| "learning_rate": 0.001, |
| "loss": 0.5293, |
| "step": 180 |
| }, |
| { |
| "epoch": 6.33, |
| "grad_norm": 0.2947409451007843, |
| "learning_rate": 0.001, |
| "loss": 0.5094, |
| "step": 182 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 0.3493882119655609, |
| "learning_rate": 0.001, |
| "loss": 0.5103, |
| "step": 184 |
| }, |
| { |
| "epoch": 6.47, |
| "grad_norm": 0.32564929127693176, |
| "learning_rate": 0.001, |
| "loss": 0.4955, |
| "step": 186 |
| }, |
| { |
| "epoch": 6.54, |
| "grad_norm": 0.3580136299133301, |
| "learning_rate": 0.001, |
| "loss": 0.4923, |
| "step": 188 |
| }, |
| { |
| "epoch": 6.61, |
| "grad_norm": 0.40878280997276306, |
| "learning_rate": 0.001, |
| "loss": 0.5312, |
| "step": 190 |
| }, |
| { |
| "epoch": 6.68, |
| "grad_norm": 0.42687222361564636, |
| "learning_rate": 0.001, |
| "loss": 0.5977, |
| "step": 192 |
| }, |
| { |
| "epoch": 6.75, |
| "grad_norm": 0.3438556492328644, |
| "learning_rate": 0.001, |
| "loss": 0.5811, |
| "step": 194 |
| }, |
| { |
| "epoch": 6.82, |
| "grad_norm": 0.3497261703014374, |
| "learning_rate": 0.001, |
| "loss": 0.542, |
| "step": 196 |
| }, |
| { |
| "epoch": 6.89, |
| "grad_norm": 0.5538045167922974, |
| "learning_rate": 0.001, |
| "loss": 0.5392, |
| "step": 198 |
| }, |
| { |
| "epoch": 6.96, |
| "grad_norm": 0.40168508887290955, |
| "learning_rate": 0.001, |
| "loss": 0.5124, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.99, |
| "eval_loss": 3.4108099937438965, |
| "eval_runtime": 14.2162, |
| "eval_samples_per_second": 23.776, |
| "eval_steps_per_second": 3.025, |
| "step": 201 |
| }, |
| { |
| "epoch": 7.03, |
| "grad_norm": 0.45531949400901794, |
| "learning_rate": 0.001, |
| "loss": 0.4621, |
| "step": 202 |
| }, |
| { |
| "epoch": 7.1, |
| "grad_norm": 0.420217901468277, |
| "learning_rate": 0.001, |
| "loss": 0.3526, |
| "step": 204 |
| }, |
| { |
| "epoch": 7.17, |
| "grad_norm": 0.39295145869255066, |
| "learning_rate": 0.001, |
| "loss": 0.3522, |
| "step": 206 |
| }, |
| { |
| "epoch": 7.23, |
| "grad_norm": 0.42002934217453003, |
| "learning_rate": 0.001, |
| "loss": 0.37, |
| "step": 208 |
| }, |
| { |
| "epoch": 7.3, |
| "grad_norm": 0.3919942378997803, |
| "learning_rate": 0.001, |
| "loss": 0.4123, |
| "step": 210 |
| }, |
| { |
| "epoch": 7.37, |
| "grad_norm": 0.34964632987976074, |
| "learning_rate": 0.001, |
| "loss": 0.4155, |
| "step": 212 |
| }, |
| { |
| "epoch": 7.44, |
| "grad_norm": 0.3752292990684509, |
| "learning_rate": 0.001, |
| "loss": 0.392, |
| "step": 214 |
| }, |
| { |
| "epoch": 7.51, |
| "grad_norm": 0.31345558166503906, |
| "learning_rate": 0.001, |
| "loss": 0.3973, |
| "step": 216 |
| }, |
| { |
| "epoch": 7.58, |
| "grad_norm": 0.32503190636634827, |
| "learning_rate": 0.001, |
| "loss": 0.3788, |
| "step": 218 |
| }, |
| { |
| "epoch": 7.65, |
| "grad_norm": 0.40439680218696594, |
| "learning_rate": 0.001, |
| "loss": 0.3997, |
| "step": 220 |
| }, |
| { |
| "epoch": 7.72, |
| "grad_norm": 0.5034092664718628, |
| "learning_rate": 0.001, |
| "loss": 0.3934, |
| "step": 222 |
| }, |
| { |
| "epoch": 7.79, |
| "grad_norm": 0.4480283260345459, |
| "learning_rate": 0.001, |
| "loss": 0.4095, |
| "step": 224 |
| }, |
| { |
| "epoch": 7.86, |
| "grad_norm": 0.44010230898857117, |
| "learning_rate": 0.001, |
| "loss": 0.3963, |
| "step": 226 |
| }, |
| { |
| "epoch": 7.93, |
| "grad_norm": 0.4241428077220917, |
| "learning_rate": 0.001, |
| "loss": 0.4081, |
| "step": 228 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 1.4331179857254028, |
| "learning_rate": 0.001, |
| "loss": 0.4503, |
| "step": 230 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 3.445927858352661, |
| "eval_runtime": 14.2138, |
| "eval_samples_per_second": 23.78, |
| "eval_steps_per_second": 3.025, |
| "step": 230 |
| }, |
| { |
| "epoch": 8.07, |
| "grad_norm": 0.26638248562812805, |
| "learning_rate": 0.001, |
| "loss": 0.2491, |
| "step": 232 |
| }, |
| { |
| "epoch": 8.14, |
| "grad_norm": 0.30395275354385376, |
| "learning_rate": 0.001, |
| "loss": 0.2501, |
| "step": 234 |
| }, |
| { |
| "epoch": 8.21, |
| "grad_norm": 0.36178329586982727, |
| "learning_rate": 0.001, |
| "loss": 0.2818, |
| "step": 236 |
| }, |
| { |
| "epoch": 8.28, |
| "grad_norm": 0.33713603019714355, |
| "learning_rate": 0.001, |
| "loss": 0.3005, |
| "step": 238 |
| }, |
| { |
| "epoch": 8.35, |
| "grad_norm": 0.2999133765697479, |
| "learning_rate": 0.001, |
| "loss": 0.2863, |
| "step": 240 |
| }, |
| { |
| "epoch": 8.42, |
| "grad_norm": 0.4105747938156128, |
| "learning_rate": 0.001, |
| "loss": 0.2946, |
| "step": 242 |
| }, |
| { |
| "epoch": 8.49, |
| "grad_norm": 0.3367477357387543, |
| "learning_rate": 0.001, |
| "loss": 0.3052, |
| "step": 244 |
| }, |
| { |
| "epoch": 8.56, |
| "grad_norm": 0.3373625874519348, |
| "learning_rate": 0.001, |
| "loss": 0.3166, |
| "step": 246 |
| }, |
| { |
| "epoch": 8.63, |
| "grad_norm": 0.2816782295703888, |
| "learning_rate": 0.001, |
| "loss": 0.2819, |
| "step": 248 |
| }, |
| { |
| "epoch": 8.7, |
| "grad_norm": 0.30990245938301086, |
| "learning_rate": 0.001, |
| "loss": 0.3023, |
| "step": 250 |
| }, |
| { |
| "epoch": 8.77, |
| "grad_norm": 0.317903608083725, |
| "learning_rate": 0.001, |
| "loss": 0.3128, |
| "step": 252 |
| }, |
| { |
| "epoch": 8.83, |
| "grad_norm": 0.3024023473262787, |
| "learning_rate": 0.001, |
| "loss": 0.3167, |
| "step": 254 |
| }, |
| { |
| "epoch": 8.9, |
| "grad_norm": 0.3257545828819275, |
| "learning_rate": 0.001, |
| "loss": 0.3121, |
| "step": 256 |
| }, |
| { |
| "epoch": 8.97, |
| "grad_norm": 0.34182751178741455, |
| "learning_rate": 0.001, |
| "loss": 0.3145, |
| "step": 258 |
| }, |
| { |
| "epoch": 8.97, |
| "eval_loss": 3.52162766456604, |
| "eval_runtime": 14.1996, |
| "eval_samples_per_second": 23.804, |
| "eval_steps_per_second": 3.028, |
| "step": 258 |
| }, |
| { |
| "epoch": 9.04, |
| "grad_norm": 0.2942521274089813, |
| "learning_rate": 0.001, |
| "loss": 0.2462, |
| "step": 260 |
| }, |
| { |
| "epoch": 9.11, |
| "grad_norm": 0.2955419719219208, |
| "learning_rate": 0.001, |
| "loss": 0.205, |
| "step": 262 |
| }, |
| { |
| "epoch": 9.18, |
| "grad_norm": 0.29875773191452026, |
| "learning_rate": 0.001, |
| "loss": 0.2185, |
| "step": 264 |
| }, |
| { |
| "epoch": 9.25, |
| "grad_norm": 0.9682367444038391, |
| "learning_rate": 0.001, |
| "loss": 0.5828, |
| "step": 266 |
| }, |
| { |
| "epoch": 9.32, |
| "grad_norm": 0.32209742069244385, |
| "learning_rate": 0.001, |
| "loss": 0.2255, |
| "step": 268 |
| }, |
| { |
| "epoch": 9.39, |
| "grad_norm": 0.2810392379760742, |
| "learning_rate": 0.001, |
| "loss": 0.2157, |
| "step": 270 |
| }, |
| { |
| "epoch": 9.46, |
| "grad_norm": 0.26448503136634827, |
| "learning_rate": 0.001, |
| "loss": 0.2136, |
| "step": 272 |
| }, |
| { |
| "epoch": 9.53, |
| "grad_norm": 0.2602413296699524, |
| "learning_rate": 0.001, |
| "loss": 0.2264, |
| "step": 274 |
| }, |
| { |
| "epoch": 9.6, |
| "grad_norm": 0.30358317494392395, |
| "learning_rate": 0.001, |
| "loss": 0.2349, |
| "step": 276 |
| }, |
| { |
| "epoch": 9.67, |
| "grad_norm": 0.2755320966243744, |
| "learning_rate": 0.001, |
| "loss": 0.2346, |
| "step": 278 |
| }, |
| { |
| "epoch": 9.74, |
| "grad_norm": 0.257522314786911, |
| "learning_rate": 0.001, |
| "loss": 0.2312, |
| "step": 280 |
| }, |
| { |
| "epoch": 9.81, |
| "grad_norm": 0.3185376524925232, |
| "learning_rate": 0.001, |
| "loss": 0.2519, |
| "step": 282 |
| }, |
| { |
| "epoch": 9.88, |
| "grad_norm": 0.352522611618042, |
| "learning_rate": 0.001, |
| "loss": 0.2678, |
| "step": 284 |
| }, |
| { |
| "epoch": 9.95, |
| "grad_norm": 0.3061072826385498, |
| "learning_rate": 0.001, |
| "loss": 0.2573, |
| "step": 286 |
| }, |
| { |
| "epoch": 9.98, |
| "eval_loss": 4.012668609619141, |
| "eval_runtime": 14.2083, |
| "eval_samples_per_second": 23.789, |
| "eval_steps_per_second": 3.026, |
| "step": 287 |
| }, |
| { |
| "epoch": 10.02, |
| "grad_norm": 0.34469902515411377, |
| "learning_rate": 0.001, |
| "loss": 0.2394, |
| "step": 288 |
| }, |
| { |
| "epoch": 10.09, |
| "grad_norm": 0.26758918166160583, |
| "learning_rate": 0.001, |
| "loss": 0.1749, |
| "step": 290 |
| }, |
| { |
| "epoch": 10.16, |
| "grad_norm": 0.24024738371372223, |
| "learning_rate": 0.001, |
| "loss": 0.1687, |
| "step": 292 |
| }, |
| { |
| "epoch": 10.23, |
| "grad_norm": 0.2440188080072403, |
| "learning_rate": 0.001, |
| "loss": 0.1634, |
| "step": 294 |
| }, |
| { |
| "epoch": 10.3, |
| "grad_norm": 0.2564130425453186, |
| "learning_rate": 0.001, |
| "loss": 0.1759, |
| "step": 296 |
| }, |
| { |
| "epoch": 10.37, |
| "grad_norm": 0.27317214012145996, |
| "learning_rate": 0.001, |
| "loss": 0.19, |
| "step": 298 |
| }, |
| { |
| "epoch": 10.43, |
| "grad_norm": 0.3196158707141876, |
| "learning_rate": 0.001, |
| "loss": 0.1903, |
| "step": 300 |
| }, |
| { |
| "epoch": 10.5, |
| "grad_norm": 0.3399882912635803, |
| "learning_rate": 0.001, |
| "loss": 0.2016, |
| "step": 302 |
| }, |
| { |
| "epoch": 10.57, |
| "grad_norm": 0.28635892271995544, |
| "learning_rate": 0.001, |
| "loss": 0.189, |
| "step": 304 |
| }, |
| { |
| "epoch": 10.64, |
| "grad_norm": 0.2602458596229553, |
| "learning_rate": 0.001, |
| "loss": 0.1792, |
| "step": 306 |
| }, |
| { |
| "epoch": 10.71, |
| "grad_norm": 0.29866456985473633, |
| "learning_rate": 0.001, |
| "loss": 0.1974, |
| "step": 308 |
| }, |
| { |
| "epoch": 10.78, |
| "grad_norm": 0.2757103443145752, |
| "learning_rate": 0.001, |
| "loss": 0.2025, |
| "step": 310 |
| }, |
| { |
| "epoch": 10.85, |
| "grad_norm": 0.2643924355506897, |
| "learning_rate": 0.001, |
| "loss": 0.2106, |
| "step": 312 |
| }, |
| { |
| "epoch": 10.92, |
| "grad_norm": 0.27770230174064636, |
| "learning_rate": 0.001, |
| "loss": 0.1999, |
| "step": 314 |
| }, |
| { |
| "epoch": 10.99, |
| "grad_norm": 0.2809506356716156, |
| "learning_rate": 0.001, |
| "loss": 0.213, |
| "step": 316 |
| }, |
| { |
| "epoch": 10.99, |
| "eval_loss": 3.9713540077209473, |
| "eval_runtime": 14.2091, |
| "eval_samples_per_second": 23.788, |
| "eval_steps_per_second": 3.026, |
| "step": 316 |
| }, |
| { |
| "epoch": 11.06, |
| "grad_norm": 0.19931960105895996, |
| "learning_rate": 0.001, |
| "loss": 0.1467, |
| "step": 318 |
| }, |
| { |
| "epoch": 11.13, |
| "grad_norm": 0.20454713702201843, |
| "learning_rate": 0.001, |
| "loss": 0.1357, |
| "step": 320 |
| }, |
| { |
| "epoch": 11.2, |
| "grad_norm": 0.22833150625228882, |
| "learning_rate": 0.001, |
| "loss": 0.1357, |
| "step": 322 |
| }, |
| { |
| "epoch": 11.27, |
| "grad_norm": 0.45052453875541687, |
| "learning_rate": 0.001, |
| "loss": 0.1401, |
| "step": 324 |
| }, |
| { |
| "epoch": 11.34, |
| "grad_norm": 0.2621672451496124, |
| "learning_rate": 0.001, |
| "loss": 0.1402, |
| "step": 326 |
| }, |
| { |
| "epoch": 11.41, |
| "grad_norm": 0.2570265829563141, |
| "learning_rate": 0.001, |
| "loss": 0.1743, |
| "step": 328 |
| }, |
| { |
| "epoch": 11.48, |
| "grad_norm": 0.2333604246377945, |
| "learning_rate": 0.001, |
| "loss": 0.1572, |
| "step": 330 |
| }, |
| { |
| "epoch": 11.55, |
| "grad_norm": 0.2325439304113388, |
| "learning_rate": 0.001, |
| "loss": 0.1505, |
| "step": 332 |
| }, |
| { |
| "epoch": 11.62, |
| "grad_norm": 0.2524455487728119, |
| "learning_rate": 0.001, |
| "loss": 0.1574, |
| "step": 334 |
| }, |
| { |
| "epoch": 11.69, |
| "grad_norm": 0.2821509838104248, |
| "learning_rate": 0.001, |
| "loss": 0.162, |
| "step": 336 |
| }, |
| { |
| "epoch": 11.76, |
| "grad_norm": 0.2627921402454376, |
| "learning_rate": 0.001, |
| "loss": 0.1823, |
| "step": 338 |
| }, |
| { |
| "epoch": 11.83, |
| "grad_norm": 0.20858174562454224, |
| "learning_rate": 0.001, |
| "loss": 0.1581, |
| "step": 340 |
| }, |
| { |
| "epoch": 11.9, |
| "grad_norm": 0.24444954097270966, |
| "learning_rate": 0.001, |
| "loss": 0.1528, |
| "step": 342 |
| }, |
| { |
| "epoch": 11.97, |
| "grad_norm": 0.23985397815704346, |
| "learning_rate": 0.001, |
| "loss": 0.1682, |
| "step": 344 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 3.842698097229004, |
| "eval_runtime": 14.2204, |
| "eval_samples_per_second": 23.769, |
| "eval_steps_per_second": 3.024, |
| "step": 345 |
| }, |
| { |
| "epoch": 12.03, |
| "grad_norm": 0.20599780976772308, |
| "learning_rate": 0.001, |
| "loss": 0.1472, |
| "step": 346 |
| }, |
| { |
| "epoch": 12.1, |
| "grad_norm": 0.20421436429023743, |
| "learning_rate": 0.001, |
| "loss": 0.1136, |
| "step": 348 |
| }, |
| { |
| "epoch": 12.17, |
| "grad_norm": 0.21933647990226746, |
| "learning_rate": 0.001, |
| "loss": 0.1137, |
| "step": 350 |
| }, |
| { |
| "epoch": 12.24, |
| "grad_norm": 0.2488287091255188, |
| "learning_rate": 0.001, |
| "loss": 0.1223, |
| "step": 352 |
| }, |
| { |
| "epoch": 12.31, |
| "grad_norm": 0.21850407123565674, |
| "learning_rate": 0.001, |
| "loss": 0.1266, |
| "step": 354 |
| }, |
| { |
| "epoch": 12.38, |
| "grad_norm": 0.219721257686615, |
| "learning_rate": 0.001, |
| "loss": 0.1266, |
| "step": 356 |
| }, |
| { |
| "epoch": 12.45, |
| "grad_norm": 0.44860273599624634, |
| "learning_rate": 0.001, |
| "loss": 0.1271, |
| "step": 358 |
| }, |
| { |
| "epoch": 12.52, |
| "grad_norm": 0.20995499193668365, |
| "learning_rate": 0.001, |
| "loss": 0.1201, |
| "step": 360 |
| }, |
| { |
| "epoch": 12.59, |
| "grad_norm": 0.2180211991071701, |
| "learning_rate": 0.001, |
| "loss": 0.1325, |
| "step": 362 |
| }, |
| { |
| "epoch": 12.66, |
| "grad_norm": 0.23486308753490448, |
| "learning_rate": 0.001, |
| "loss": 0.1316, |
| "step": 364 |
| }, |
| { |
| "epoch": 12.73, |
| "grad_norm": 0.26361599564552307, |
| "learning_rate": 0.001, |
| "loss": 0.1417, |
| "step": 366 |
| }, |
| { |
| "epoch": 12.8, |
| "grad_norm": 0.27585896849632263, |
| "learning_rate": 0.001, |
| "loss": 0.1514, |
| "step": 368 |
| }, |
| { |
| "epoch": 12.87, |
| "grad_norm": 0.23249991238117218, |
| "learning_rate": 0.001, |
| "loss": 0.1387, |
| "step": 370 |
| }, |
| { |
| "epoch": 12.94, |
| "grad_norm": 0.2378188967704773, |
| "learning_rate": 0.001, |
| "loss": 0.1396, |
| "step": 372 |
| }, |
| { |
| "epoch": 12.97, |
| "eval_loss": 4.202455520629883, |
| "eval_runtime": 14.2176, |
| "eval_samples_per_second": 23.773, |
| "eval_steps_per_second": 3.024, |
| "step": 373 |
| }, |
| { |
| "epoch": 13.01, |
| "grad_norm": 0.25618231296539307, |
| "learning_rate": 0.001, |
| "loss": 0.1403, |
| "step": 374 |
| }, |
| { |
| "epoch": 13.08, |
| "grad_norm": 0.19359038770198822, |
| "learning_rate": 0.001, |
| "loss": 0.1048, |
| "step": 376 |
| }, |
| { |
| "epoch": 13.15, |
| "grad_norm": 0.20456379652023315, |
| "learning_rate": 0.001, |
| "loss": 0.102, |
| "step": 378 |
| }, |
| { |
| "epoch": 13.22, |
| "grad_norm": 0.20489871501922607, |
| "learning_rate": 0.001, |
| "loss": 0.1039, |
| "step": 380 |
| }, |
| { |
| "epoch": 13.29, |
| "grad_norm": 0.20058828592300415, |
| "learning_rate": 0.001, |
| "loss": 0.1066, |
| "step": 382 |
| }, |
| { |
| "epoch": 13.36, |
| "grad_norm": 0.20939727127552032, |
| "learning_rate": 0.001, |
| "loss": 0.1017, |
| "step": 384 |
| }, |
| { |
| "epoch": 13.43, |
| "grad_norm": 0.20905180275440216, |
| "learning_rate": 0.001, |
| "loss": 0.1074, |
| "step": 386 |
| }, |
| { |
| "epoch": 13.5, |
| "grad_norm": 0.2082565426826477, |
| "learning_rate": 0.001, |
| "loss": 0.1122, |
| "step": 388 |
| }, |
| { |
| "epoch": 13.57, |
| "grad_norm": 0.20671486854553223, |
| "learning_rate": 0.001, |
| "loss": 0.1137, |
| "step": 390 |
| }, |
| { |
| "epoch": 13.63, |
| "grad_norm": 0.20714151859283447, |
| "learning_rate": 0.001, |
| "loss": 0.1085, |
| "step": 392 |
| }, |
| { |
| "epoch": 13.7, |
| "grad_norm": 0.21117734909057617, |
| "learning_rate": 0.001, |
| "loss": 0.1225, |
| "step": 394 |
| }, |
| { |
| "epoch": 13.77, |
| "grad_norm": 0.20374175906181335, |
| "learning_rate": 0.001, |
| "loss": 0.1135, |
| "step": 396 |
| }, |
| { |
| "epoch": 13.84, |
| "grad_norm": 0.2223602831363678, |
| "learning_rate": 0.001, |
| "loss": 0.1188, |
| "step": 398 |
| }, |
| { |
| "epoch": 13.91, |
| "grad_norm": 0.2405446618795395, |
| "learning_rate": 0.001, |
| "loss": 0.1329, |
| "step": 400 |
| }, |
| { |
| "epoch": 13.98, |
| "grad_norm": 0.25538983941078186, |
| "learning_rate": 0.001, |
| "loss": 0.1363, |
| "step": 402 |
| }, |
| { |
| "epoch": 13.98, |
| "eval_loss": 4.401235103607178, |
| "eval_runtime": 14.2163, |
| "eval_samples_per_second": 23.776, |
| "eval_steps_per_second": 3.025, |
| "step": 402 |
| }, |
| { |
| "epoch": 14.05, |
| "grad_norm": 0.20007029175758362, |
| "learning_rate": 0.001, |
| "loss": 0.0995, |
| "step": 404 |
| }, |
| { |
| "epoch": 14.12, |
| "grad_norm": 0.17897407710552216, |
| "learning_rate": 0.001, |
| "loss": 0.0927, |
| "step": 406 |
| }, |
| { |
| "epoch": 14.19, |
| "grad_norm": 0.18746937811374664, |
| "learning_rate": 0.001, |
| "loss": 0.0898, |
| "step": 408 |
| }, |
| { |
| "epoch": 14.26, |
| "grad_norm": 0.1855156570672989, |
| "learning_rate": 0.001, |
| "loss": 0.0913, |
| "step": 410 |
| }, |
| { |
| "epoch": 14.33, |
| "grad_norm": 0.1712156981229782, |
| "learning_rate": 0.001, |
| "loss": 0.0891, |
| "step": 412 |
| }, |
| { |
| "epoch": 14.4, |
| "grad_norm": 0.193171888589859, |
| "learning_rate": 0.001, |
| "loss": 0.0871, |
| "step": 414 |
| }, |
| { |
| "epoch": 14.47, |
| "grad_norm": 0.19764076173305511, |
| "learning_rate": 0.001, |
| "loss": 0.0892, |
| "step": 416 |
| }, |
| { |
| "epoch": 14.54, |
| "grad_norm": 0.20630787312984467, |
| "learning_rate": 0.001, |
| "loss": 0.0984, |
| "step": 418 |
| }, |
| { |
| "epoch": 14.61, |
| "grad_norm": 0.18784281611442566, |
| "learning_rate": 0.001, |
| "loss": 0.1002, |
| "step": 420 |
| }, |
| { |
| "epoch": 14.68, |
| "grad_norm": 0.2134091705083847, |
| "learning_rate": 0.001, |
| "loss": 0.0994, |
| "step": 422 |
| }, |
| { |
| "epoch": 14.75, |
| "grad_norm": 0.20559023320674896, |
| "learning_rate": 0.001, |
| "loss": 0.1036, |
| "step": 424 |
| }, |
| { |
| "epoch": 14.82, |
| "grad_norm": 0.22063368558883667, |
| "learning_rate": 0.001, |
| "loss": 0.1008, |
| "step": 426 |
| }, |
| { |
| "epoch": 14.89, |
| "grad_norm": 0.21584555506706238, |
| "learning_rate": 0.001, |
| "loss": 0.1137, |
| "step": 428 |
| }, |
| { |
| "epoch": 14.96, |
| "grad_norm": 0.20185333490371704, |
| "learning_rate": 0.001, |
| "loss": 0.1148, |
| "step": 430 |
| }, |
| { |
| "epoch": 14.99, |
| "eval_loss": 4.717379093170166, |
| "eval_runtime": 14.2112, |
| "eval_samples_per_second": 23.784, |
| "eval_steps_per_second": 3.026, |
| "step": 431 |
| }, |
| { |
| "epoch": 15.03, |
| "grad_norm": 0.22225050628185272, |
| "learning_rate": 0.001, |
| "loss": 0.0942, |
| "step": 432 |
| }, |
| { |
| "epoch": 15.1, |
| "grad_norm": 0.2037811130285263, |
| "learning_rate": 0.001, |
| "loss": 0.0776, |
| "step": 434 |
| }, |
| { |
| "epoch": 15.17, |
| "grad_norm": 0.1820273995399475, |
| "learning_rate": 0.001, |
| "loss": 0.0849, |
| "step": 436 |
| }, |
| { |
| "epoch": 15.23, |
| "grad_norm": 0.18018700182437897, |
| "learning_rate": 0.001, |
| "loss": 0.0744, |
| "step": 438 |
| }, |
| { |
| "epoch": 15.3, |
| "grad_norm": 0.21271073818206787, |
| "learning_rate": 0.001, |
| "loss": 0.0836, |
| "step": 440 |
| }, |
| { |
| "epoch": 15.37, |
| "grad_norm": 0.19622232019901276, |
| "learning_rate": 0.001, |
| "loss": 0.0841, |
| "step": 442 |
| }, |
| { |
| "epoch": 15.44, |
| "grad_norm": 0.19101227819919586, |
| "learning_rate": 0.001, |
| "loss": 0.085, |
| "step": 444 |
| }, |
| { |
| "epoch": 15.51, |
| "grad_norm": 0.18909965455532074, |
| "learning_rate": 0.001, |
| "loss": 0.093, |
| "step": 446 |
| }, |
| { |
| "epoch": 15.58, |
| "grad_norm": 0.2003660649061203, |
| "learning_rate": 0.001, |
| "loss": 0.0877, |
| "step": 448 |
| }, |
| { |
| "epoch": 15.65, |
| "grad_norm": 0.2101544439792633, |
| "learning_rate": 0.001, |
| "loss": 0.0908, |
| "step": 450 |
| }, |
| { |
| "epoch": 15.72, |
| "grad_norm": 0.20344135165214539, |
| "learning_rate": 0.001, |
| "loss": 0.0943, |
| "step": 452 |
| }, |
| { |
| "epoch": 15.79, |
| "grad_norm": 0.28948044776916504, |
| "learning_rate": 0.001, |
| "loss": 0.1094, |
| "step": 454 |
| }, |
| { |
| "epoch": 15.86, |
| "grad_norm": 0.29758819937705994, |
| "learning_rate": 0.001, |
| "loss": 0.1247, |
| "step": 456 |
| }, |
| { |
| "epoch": 15.93, |
| "grad_norm": 0.24994027614593506, |
| "learning_rate": 0.001, |
| "loss": 0.1106, |
| "step": 458 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.2185268998146057, |
| "learning_rate": 0.001, |
| "loss": 0.0907, |
| "step": 460 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 4.497994899749756, |
| "eval_runtime": 14.2114, |
| "eval_samples_per_second": 23.784, |
| "eval_steps_per_second": 3.026, |
| "step": 460 |
| }, |
| { |
| "epoch": 16.07, |
| "grad_norm": 0.1781373769044876, |
| "learning_rate": 0.001, |
| "loss": 0.0698, |
| "step": 462 |
| }, |
| { |
| "epoch": 16.14, |
| "grad_norm": 0.20170117914676666, |
| "learning_rate": 0.001, |
| "loss": 0.0763, |
| "step": 464 |
| }, |
| { |
| "epoch": 16.21, |
| "grad_norm": 0.20545266568660736, |
| "learning_rate": 0.001, |
| "loss": 0.0858, |
| "step": 466 |
| }, |
| { |
| "epoch": 16.28, |
| "grad_norm": 0.18228977918624878, |
| "learning_rate": 0.001, |
| "loss": 0.0802, |
| "step": 468 |
| }, |
| { |
| "epoch": 16.35, |
| "grad_norm": 0.17187969386577606, |
| "learning_rate": 0.001, |
| "loss": 0.0803, |
| "step": 470 |
| }, |
| { |
| "epoch": 16.42, |
| "grad_norm": 0.17641624808311462, |
| "learning_rate": 0.001, |
| "loss": 0.0796, |
| "step": 472 |
| }, |
| { |
| "epoch": 16.49, |
| "grad_norm": 0.19069235026836395, |
| "learning_rate": 0.001, |
| "loss": 0.0798, |
| "step": 474 |
| }, |
| { |
| "epoch": 16.56, |
| "grad_norm": 0.1968899667263031, |
| "learning_rate": 0.001, |
| "loss": 0.081, |
| "step": 476 |
| }, |
| { |
| "epoch": 16.63, |
| "grad_norm": 0.196567103266716, |
| "learning_rate": 0.001, |
| "loss": 0.0891, |
| "step": 478 |
| }, |
| { |
| "epoch": 16.7, |
| "grad_norm": 0.18010011315345764, |
| "learning_rate": 0.001, |
| "loss": 0.0795, |
| "step": 480 |
| }, |
| { |
| "epoch": 16.77, |
| "grad_norm": 0.31678447127342224, |
| "learning_rate": 0.001, |
| "loss": 0.0819, |
| "step": 482 |
| }, |
| { |
| "epoch": 16.83, |
| "grad_norm": 0.20116592943668365, |
| "learning_rate": 0.001, |
| "loss": 0.0873, |
| "step": 484 |
| }, |
| { |
| "epoch": 16.9, |
| "grad_norm": 0.19425255060195923, |
| "learning_rate": 0.001, |
| "loss": 0.0898, |
| "step": 486 |
| }, |
| { |
| "epoch": 16.97, |
| "grad_norm": 0.21240267157554626, |
| "learning_rate": 0.001, |
| "loss": 0.0942, |
| "step": 488 |
| }, |
| { |
| "epoch": 16.97, |
| "eval_loss": 4.70243501663208, |
| "eval_runtime": 14.2157, |
| "eval_samples_per_second": 23.777, |
| "eval_steps_per_second": 3.025, |
| "step": 488 |
| }, |
| { |
| "epoch": 17.04, |
| "grad_norm": 0.16432495415210724, |
| "learning_rate": 0.001, |
| "loss": 0.0762, |
| "step": 490 |
| }, |
| { |
| "epoch": 17.11, |
| "grad_norm": 0.19645223021507263, |
| "learning_rate": 0.001, |
| "loss": 0.0638, |
| "step": 492 |
| }, |
| { |
| "epoch": 17.18, |
| "grad_norm": 0.1714513599872589, |
| "learning_rate": 0.001, |
| "loss": 0.0669, |
| "step": 494 |
| }, |
| { |
| "epoch": 17.25, |
| "grad_norm": 0.16747209429740906, |
| "learning_rate": 0.001, |
| "loss": 0.064, |
| "step": 496 |
| }, |
| { |
| "epoch": 17.32, |
| "grad_norm": 0.17507390677928925, |
| "learning_rate": 0.001, |
| "loss": 0.0675, |
| "step": 498 |
| }, |
| { |
| "epoch": 17.39, |
| "grad_norm": 0.1752365380525589, |
| "learning_rate": 0.001, |
| "loss": 0.0716, |
| "step": 500 |
| }, |
| { |
| "epoch": 17.46, |
| "grad_norm": 0.1760423481464386, |
| "learning_rate": 0.001, |
| "loss": 0.0736, |
| "step": 502 |
| }, |
| { |
| "epoch": 17.53, |
| "grad_norm": 0.17969931662082672, |
| "learning_rate": 0.001, |
| "loss": 0.0725, |
| "step": 504 |
| }, |
| { |
| "epoch": 17.6, |
| "grad_norm": 0.20572717487812042, |
| "learning_rate": 0.001, |
| "loss": 0.0751, |
| "step": 506 |
| }, |
| { |
| "epoch": 17.67, |
| "grad_norm": 0.20842702686786652, |
| "learning_rate": 0.001, |
| "loss": 0.0796, |
| "step": 508 |
| }, |
| { |
| "epoch": 17.74, |
| "grad_norm": 0.18587857484817505, |
| "learning_rate": 0.001, |
| "loss": 0.0757, |
| "step": 510 |
| }, |
| { |
| "epoch": 17.81, |
| "grad_norm": 0.17455922067165375, |
| "learning_rate": 0.001, |
| "loss": 0.0792, |
| "step": 512 |
| }, |
| { |
| "epoch": 17.88, |
| "grad_norm": 0.181496262550354, |
| "learning_rate": 0.001, |
| "loss": 0.0711, |
| "step": 514 |
| }, |
| { |
| "epoch": 17.95, |
| "grad_norm": 0.1918957382440567, |
| "learning_rate": 0.001, |
| "loss": 0.0765, |
| "step": 516 |
| }, |
| { |
| "epoch": 17.98, |
| "eval_loss": 4.348242282867432, |
| "eval_runtime": 14.2133, |
| "eval_samples_per_second": 23.78, |
| "eval_steps_per_second": 3.025, |
| "step": 517 |
| }, |
| { |
| "epoch": 18.02, |
| "grad_norm": 0.23215439915657043, |
| "learning_rate": 0.001, |
| "loss": 0.0854, |
| "step": 518 |
| }, |
| { |
| "epoch": 18.09, |
| "grad_norm": 0.16362574696540833, |
| "learning_rate": 0.001, |
| "loss": 0.0636, |
| "step": 520 |
| }, |
| { |
| "epoch": 18.16, |
| "grad_norm": 0.18604953587055206, |
| "learning_rate": 0.001, |
| "loss": 0.0632, |
| "step": 522 |
| }, |
| { |
| "epoch": 18.23, |
| "grad_norm": 0.20401595532894135, |
| "learning_rate": 0.001, |
| "loss": 0.077, |
| "step": 524 |
| }, |
| { |
| "epoch": 18.3, |
| "grad_norm": 0.1713324785232544, |
| "learning_rate": 0.001, |
| "loss": 0.0743, |
| "step": 526 |
| }, |
| { |
| "epoch": 18.37, |
| "grad_norm": 0.1794094294309616, |
| "learning_rate": 0.001, |
| "loss": 0.0693, |
| "step": 528 |
| }, |
| { |
| "epoch": 18.43, |
| "grad_norm": 0.1892070323228836, |
| "learning_rate": 0.001, |
| "loss": 0.0663, |
| "step": 530 |
| }, |
| { |
| "epoch": 18.5, |
| "grad_norm": 0.1843532919883728, |
| "learning_rate": 0.001, |
| "loss": 0.0721, |
| "step": 532 |
| }, |
| { |
| "epoch": 18.57, |
| "grad_norm": 0.17645902931690216, |
| "learning_rate": 0.001, |
| "loss": 0.0746, |
| "step": 534 |
| }, |
| { |
| "epoch": 18.64, |
| "grad_norm": 0.16752366721630096, |
| "learning_rate": 0.001, |
| "loss": 0.0712, |
| "step": 536 |
| }, |
| { |
| "epoch": 18.71, |
| "grad_norm": 0.16078142821788788, |
| "learning_rate": 0.001, |
| "loss": 0.0729, |
| "step": 538 |
| }, |
| { |
| "epoch": 18.78, |
| "grad_norm": 0.1775059700012207, |
| "learning_rate": 0.001, |
| "loss": 0.0745, |
| "step": 540 |
| }, |
| { |
| "epoch": 18.85, |
| "grad_norm": 0.18710005283355713, |
| "learning_rate": 0.001, |
| "loss": 0.0743, |
| "step": 542 |
| }, |
| { |
| "epoch": 18.92, |
| "grad_norm": 0.20217396318912506, |
| "learning_rate": 0.001, |
| "loss": 0.0761, |
| "step": 544 |
| }, |
| { |
| "epoch": 18.99, |
| "grad_norm": 0.19417209923267365, |
| "learning_rate": 0.001, |
| "loss": 0.0799, |
| "step": 546 |
| }, |
| { |
| "epoch": 18.99, |
| "eval_loss": 4.538631916046143, |
| "eval_runtime": 14.2104, |
| "eval_samples_per_second": 23.785, |
| "eval_steps_per_second": 3.026, |
| "step": 546 |
| }, |
| { |
| "epoch": 19.06, |
| "grad_norm": 0.16049686074256897, |
| "learning_rate": 0.001, |
| "loss": 0.0633, |
| "step": 548 |
| }, |
| { |
| "epoch": 19.13, |
| "grad_norm": 0.15315844118595123, |
| "learning_rate": 0.001, |
| "loss": 0.0614, |
| "step": 550 |
| }, |
| { |
| "epoch": 19.2, |
| "grad_norm": 0.16441303491592407, |
| "learning_rate": 0.001, |
| "loss": 0.0658, |
| "step": 552 |
| }, |
| { |
| "epoch": 19.27, |
| "grad_norm": 0.16347071528434753, |
| "learning_rate": 0.001, |
| "loss": 0.0551, |
| "step": 554 |
| }, |
| { |
| "epoch": 19.34, |
| "grad_norm": 0.16774040460586548, |
| "learning_rate": 0.001, |
| "loss": 0.0698, |
| "step": 556 |
| }, |
| { |
| "epoch": 19.41, |
| "grad_norm": 0.15695886313915253, |
| "learning_rate": 0.001, |
| "loss": 0.063, |
| "step": 558 |
| }, |
| { |
| "epoch": 19.48, |
| "grad_norm": 0.1639881581068039, |
| "learning_rate": 0.001, |
| "loss": 0.0649, |
| "step": 560 |
| }, |
| { |
| "epoch": 19.55, |
| "grad_norm": 0.1653515100479126, |
| "learning_rate": 0.001, |
| "loss": 0.0592, |
| "step": 562 |
| }, |
| { |
| "epoch": 19.62, |
| "grad_norm": 0.1697942465543747, |
| "learning_rate": 0.001, |
| "loss": 0.0619, |
| "step": 564 |
| }, |
| { |
| "epoch": 19.69, |
| "grad_norm": 0.18345074355602264, |
| "learning_rate": 0.001, |
| "loss": 0.0674, |
| "step": 566 |
| }, |
| { |
| "epoch": 19.76, |
| "grad_norm": 0.17060339450836182, |
| "learning_rate": 0.001, |
| "loss": 0.0603, |
| "step": 568 |
| }, |
| { |
| "epoch": 19.83, |
| "grad_norm": 0.18731752038002014, |
| "learning_rate": 0.001, |
| "loss": 0.0668, |
| "step": 570 |
| }, |
| { |
| "epoch": 19.9, |
| "grad_norm": 0.1727019101381302, |
| "learning_rate": 0.001, |
| "loss": 0.0717, |
| "step": 572 |
| }, |
| { |
| "epoch": 19.97, |
| "grad_norm": 0.18209876120090485, |
| "learning_rate": 0.001, |
| "loss": 0.073, |
| "step": 574 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 4.588906764984131, |
| "eval_runtime": 14.2111, |
| "eval_samples_per_second": 23.784, |
| "eval_steps_per_second": 3.026, |
| "step": 575 |
| }, |
| { |
| "epoch": 20.03, |
| "grad_norm": 0.15836042165756226, |
| "learning_rate": 0.001, |
| "loss": 0.0655, |
| "step": 576 |
| }, |
| { |
| "epoch": 20.1, |
| "grad_norm": 0.1645493507385254, |
| "learning_rate": 0.001, |
| "loss": 0.0609, |
| "step": 578 |
| }, |
| { |
| "epoch": 20.17, |
| "grad_norm": 0.14691436290740967, |
| "learning_rate": 0.001, |
| "loss": 0.0533, |
| "step": 580 |
| }, |
| { |
| "epoch": 20.24, |
| "grad_norm": 0.15472760796546936, |
| "learning_rate": 0.001, |
| "loss": 0.0596, |
| "step": 582 |
| }, |
| { |
| "epoch": 20.31, |
| "grad_norm": 0.14597873389720917, |
| "learning_rate": 0.001, |
| "loss": 0.0548, |
| "step": 584 |
| }, |
| { |
| "epoch": 20.38, |
| "grad_norm": 0.14974112808704376, |
| "learning_rate": 0.001, |
| "loss": 0.057, |
| "step": 586 |
| }, |
| { |
| "epoch": 20.45, |
| "grad_norm": 0.16359882056713104, |
| "learning_rate": 0.001, |
| "loss": 0.0597, |
| "step": 588 |
| }, |
| { |
| "epoch": 20.52, |
| "grad_norm": 0.15623408555984497, |
| "learning_rate": 0.001, |
| "loss": 0.0581, |
| "step": 590 |
| }, |
| { |
| "epoch": 20.59, |
| "grad_norm": 0.16072715818881989, |
| "learning_rate": 0.001, |
| "loss": 0.0577, |
| "step": 592 |
| }, |
| { |
| "epoch": 20.66, |
| "grad_norm": 0.17041383683681488, |
| "learning_rate": 0.001, |
| "loss": 0.0601, |
| "step": 594 |
| }, |
| { |
| "epoch": 20.73, |
| "grad_norm": 0.182576522231102, |
| "learning_rate": 0.001, |
| "loss": 0.0614, |
| "step": 596 |
| }, |
| { |
| "epoch": 20.8, |
| "grad_norm": 0.17546887695789337, |
| "learning_rate": 0.001, |
| "loss": 0.0658, |
| "step": 598 |
| }, |
| { |
| "epoch": 20.87, |
| "grad_norm": 0.19615040719509125, |
| "learning_rate": 0.001, |
| "loss": 0.061, |
| "step": 600 |
| }, |
| { |
| "epoch": 20.94, |
| "grad_norm": 0.2895524799823761, |
| "learning_rate": 0.001, |
| "loss": 0.0825, |
| "step": 602 |
| }, |
| { |
| "epoch": 20.97, |
| "eval_loss": 4.681673049926758, |
| "eval_runtime": 14.2047, |
| "eval_samples_per_second": 23.795, |
| "eval_steps_per_second": 3.027, |
| "step": 603 |
| }, |
| { |
| "epoch": 21.01, |
| "grad_norm": 0.3042687177658081, |
| "learning_rate": 0.001, |
| "loss": 0.102, |
| "step": 604 |
| }, |
| { |
| "epoch": 21.08, |
| "grad_norm": 0.14991188049316406, |
| "learning_rate": 0.001, |
| "loss": 0.0585, |
| "step": 606 |
| }, |
| { |
| "epoch": 21.15, |
| "grad_norm": 0.13689693808555603, |
| "learning_rate": 0.001, |
| "loss": 0.0546, |
| "step": 608 |
| }, |
| { |
| "epoch": 21.22, |
| "grad_norm": 0.14480513334274292, |
| "learning_rate": 0.001, |
| "loss": 0.0533, |
| "step": 610 |
| }, |
| { |
| "epoch": 21.29, |
| "grad_norm": 0.148710235953331, |
| "learning_rate": 0.001, |
| "loss": 0.0543, |
| "step": 612 |
| }, |
| { |
| "epoch": 21.36, |
| "grad_norm": 0.14531894028186798, |
| "learning_rate": 0.001, |
| "loss": 0.0528, |
| "step": 614 |
| }, |
| { |
| "epoch": 21.43, |
| "grad_norm": 0.14758220314979553, |
| "learning_rate": 0.001, |
| "loss": 0.0536, |
| "step": 616 |
| }, |
| { |
| "epoch": 21.5, |
| "grad_norm": 0.1422356367111206, |
| "learning_rate": 0.001, |
| "loss": 0.0537, |
| "step": 618 |
| }, |
| { |
| "epoch": 21.57, |
| "grad_norm": 0.16927896440029144, |
| "learning_rate": 0.001, |
| "loss": 0.0551, |
| "step": 620 |
| }, |
| { |
| "epoch": 21.63, |
| "grad_norm": 0.18368251621723175, |
| "learning_rate": 0.001, |
| "loss": 0.0589, |
| "step": 622 |
| }, |
| { |
| "epoch": 21.7, |
| "grad_norm": 0.16162264347076416, |
| "learning_rate": 0.001, |
| "loss": 0.0639, |
| "step": 624 |
| }, |
| { |
| "epoch": 21.77, |
| "grad_norm": 0.1610013097524643, |
| "learning_rate": 0.001, |
| "loss": 0.0604, |
| "step": 626 |
| }, |
| { |
| "epoch": 21.84, |
| "grad_norm": 0.15656866133213043, |
| "learning_rate": 0.001, |
| "loss": 0.0603, |
| "step": 628 |
| }, |
| { |
| "epoch": 21.91, |
| "grad_norm": 0.15664397180080414, |
| "learning_rate": 0.001, |
| "loss": 0.0589, |
| "step": 630 |
| }, |
| { |
| "epoch": 21.98, |
| "grad_norm": 0.1484573483467102, |
| "learning_rate": 0.001, |
| "loss": 0.0616, |
| "step": 632 |
| }, |
| { |
| "epoch": 21.98, |
| "eval_loss": 5.026252746582031, |
| "eval_runtime": 14.2151, |
| "eval_samples_per_second": 23.778, |
| "eval_steps_per_second": 3.025, |
| "step": 632 |
| }, |
| { |
| "epoch": 22.05, |
| "grad_norm": 0.16003428399562836, |
| "learning_rate": 0.001, |
| "loss": 0.0579, |
| "step": 634 |
| }, |
| { |
| "epoch": 22.12, |
| "grad_norm": 0.14746786653995514, |
| "learning_rate": 0.001, |
| "loss": 0.0503, |
| "step": 636 |
| }, |
| { |
| "epoch": 22.19, |
| "grad_norm": 0.1616966724395752, |
| "learning_rate": 0.001, |
| "loss": 0.0518, |
| "step": 638 |
| }, |
| { |
| "epoch": 22.26, |
| "grad_norm": 0.14375324547290802, |
| "learning_rate": 0.001, |
| "loss": 0.0501, |
| "step": 640 |
| }, |
| { |
| "epoch": 22.33, |
| "grad_norm": 0.14273105561733246, |
| "learning_rate": 0.001, |
| "loss": 0.0543, |
| "step": 642 |
| }, |
| { |
| "epoch": 22.4, |
| "grad_norm": 0.14281895756721497, |
| "learning_rate": 0.001, |
| "loss": 0.0572, |
| "step": 644 |
| }, |
| { |
| "epoch": 22.47, |
| "grad_norm": 0.1508861482143402, |
| "learning_rate": 0.001, |
| "loss": 0.0538, |
| "step": 646 |
| }, |
| { |
| "epoch": 22.54, |
| "grad_norm": 0.1677195429801941, |
| "learning_rate": 0.001, |
| "loss": 0.052, |
| "step": 648 |
| }, |
| { |
| "epoch": 22.61, |
| "grad_norm": 0.16616381704807281, |
| "learning_rate": 0.001, |
| "loss": 0.0569, |
| "step": 650 |
| }, |
| { |
| "epoch": 22.68, |
| "grad_norm": 0.159612774848938, |
| "learning_rate": 0.001, |
| "loss": 0.0585, |
| "step": 652 |
| }, |
| { |
| "epoch": 22.75, |
| "grad_norm": 0.14692574739456177, |
| "learning_rate": 0.001, |
| "loss": 0.0559, |
| "step": 654 |
| }, |
| { |
| "epoch": 22.82, |
| "grad_norm": 0.14404280483722687, |
| "learning_rate": 0.001, |
| "loss": 0.0614, |
| "step": 656 |
| }, |
| { |
| "epoch": 22.89, |
| "grad_norm": 0.16935443878173828, |
| "learning_rate": 0.001, |
| "loss": 0.0531, |
| "step": 658 |
| }, |
| { |
| "epoch": 22.96, |
| "grad_norm": 0.16444338858127594, |
| "learning_rate": 0.001, |
| "loss": 0.0677, |
| "step": 660 |
| }, |
| { |
| "epoch": 22.99, |
| "eval_loss": 4.580361843109131, |
| "eval_runtime": 14.2193, |
| "eval_samples_per_second": 23.77, |
| "eval_steps_per_second": 3.024, |
| "step": 661 |
| }, |
| { |
| "epoch": 23.03, |
| "grad_norm": 0.1523355394601822, |
| "learning_rate": 0.001, |
| "loss": 0.056, |
| "step": 662 |
| }, |
| { |
| "epoch": 23.1, |
| "grad_norm": 0.13197599351406097, |
| "learning_rate": 0.001, |
| "loss": 0.0505, |
| "step": 664 |
| }, |
| { |
| "epoch": 23.17, |
| "grad_norm": 0.1436968594789505, |
| "learning_rate": 0.001, |
| "loss": 0.0459, |
| "step": 666 |
| }, |
| { |
| "epoch": 23.23, |
| "grad_norm": 0.15447324514389038, |
| "learning_rate": 0.001, |
| "loss": 0.0484, |
| "step": 668 |
| }, |
| { |
| "epoch": 23.3, |
| "grad_norm": 0.1536988466978073, |
| "learning_rate": 0.001, |
| "loss": 0.0523, |
| "step": 670 |
| }, |
| { |
| "epoch": 23.37, |
| "grad_norm": 0.14964550733566284, |
| "learning_rate": 0.001, |
| "loss": 0.0523, |
| "step": 672 |
| }, |
| { |
| "epoch": 23.44, |
| "grad_norm": 0.14874936640262604, |
| "learning_rate": 0.001, |
| "loss": 0.053, |
| "step": 674 |
| }, |
| { |
| "epoch": 23.51, |
| "grad_norm": 0.14731401205062866, |
| "learning_rate": 0.001, |
| "loss": 0.0534, |
| "step": 676 |
| }, |
| { |
| "epoch": 23.58, |
| "grad_norm": 0.15508398413658142, |
| "learning_rate": 0.001, |
| "loss": 0.0538, |
| "step": 678 |
| }, |
| { |
| "epoch": 23.65, |
| "grad_norm": 0.16380004584789276, |
| "learning_rate": 0.001, |
| "loss": 0.0539, |
| "step": 680 |
| }, |
| { |
| "epoch": 23.72, |
| "grad_norm": 0.38461077213287354, |
| "learning_rate": 0.001, |
| "loss": 0.0609, |
| "step": 682 |
| }, |
| { |
| "epoch": 23.79, |
| "grad_norm": 0.1609809696674347, |
| "learning_rate": 0.001, |
| "loss": 0.0553, |
| "step": 684 |
| }, |
| { |
| "epoch": 23.86, |
| "grad_norm": 0.1482686847448349, |
| "learning_rate": 0.001, |
| "loss": 0.0576, |
| "step": 686 |
| }, |
| { |
| "epoch": 23.93, |
| "grad_norm": 0.16069763898849487, |
| "learning_rate": 0.001, |
| "loss": 0.0569, |
| "step": 688 |
| }, |
| { |
| "epoch": 24.0, |
| "grad_norm": 0.16612602770328522, |
| "learning_rate": 0.001, |
| "loss": 0.0571, |
| "step": 690 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_loss": 4.839931488037109, |
| "eval_runtime": 14.2054, |
| "eval_samples_per_second": 23.794, |
| "eval_steps_per_second": 3.027, |
| "step": 690 |
| }, |
| { |
| "epoch": 24.07, |
| "grad_norm": 0.14117293059825897, |
| "learning_rate": 0.001, |
| "loss": 0.0473, |
| "step": 692 |
| }, |
| { |
| "epoch": 24.14, |
| "grad_norm": 0.13660480082035065, |
| "learning_rate": 0.001, |
| "loss": 0.0462, |
| "step": 694 |
| }, |
| { |
| "epoch": 24.21, |
| "grad_norm": 0.13649675250053406, |
| "learning_rate": 0.001, |
| "loss": 0.0436, |
| "step": 696 |
| }, |
| { |
| "epoch": 24.28, |
| "grad_norm": 0.13140219449996948, |
| "learning_rate": 0.001, |
| "loss": 0.0496, |
| "step": 698 |
| }, |
| { |
| "epoch": 24.35, |
| "grad_norm": 0.13666340708732605, |
| "learning_rate": 0.001, |
| "loss": 0.0453, |
| "step": 700 |
| }, |
| { |
| "epoch": 24.42, |
| "grad_norm": 0.14786505699157715, |
| "learning_rate": 0.001, |
| "loss": 0.0458, |
| "step": 702 |
| }, |
| { |
| "epoch": 24.49, |
| "grad_norm": 0.14177779853343964, |
| "learning_rate": 0.001, |
| "loss": 0.0454, |
| "step": 704 |
| }, |
| { |
| "epoch": 24.56, |
| "grad_norm": 0.15088017284870148, |
| "learning_rate": 0.001, |
| "loss": 0.0486, |
| "step": 706 |
| }, |
| { |
| "epoch": 24.63, |
| "grad_norm": 0.1343182623386383, |
| "learning_rate": 0.001, |
| "loss": 0.0466, |
| "step": 708 |
| }, |
| { |
| "epoch": 24.7, |
| "grad_norm": 0.14765577018260956, |
| "learning_rate": 0.001, |
| "loss": 0.051, |
| "step": 710 |
| }, |
| { |
| "epoch": 24.77, |
| "grad_norm": 0.1491304486989975, |
| "learning_rate": 0.001, |
| "loss": 0.0497, |
| "step": 712 |
| }, |
| { |
| "epoch": 24.83, |
| "grad_norm": 0.1482744961977005, |
| "learning_rate": 0.001, |
| "loss": 0.0525, |
| "step": 714 |
| }, |
| { |
| "epoch": 24.9, |
| "grad_norm": 0.15700866281986237, |
| "learning_rate": 0.001, |
| "loss": 0.0497, |
| "step": 716 |
| }, |
| { |
| "epoch": 24.97, |
| "grad_norm": 0.15650177001953125, |
| "learning_rate": 0.001, |
| "loss": 0.0525, |
| "step": 718 |
| }, |
| { |
| "epoch": 24.97, |
| "eval_loss": 4.934982776641846, |
| "eval_runtime": 14.2072, |
| "eval_samples_per_second": 23.791, |
| "eval_steps_per_second": 3.027, |
| "step": 718 |
| }, |
| { |
| "epoch": 25.04, |
| "grad_norm": 0.15254813432693481, |
| "learning_rate": 0.001, |
| "loss": 0.0501, |
| "step": 720 |
| }, |
| { |
| "epoch": 25.11, |
| "grad_norm": 0.1353287696838379, |
| "learning_rate": 0.001, |
| "loss": 0.0471, |
| "step": 722 |
| }, |
| { |
| "epoch": 25.18, |
| "grad_norm": 0.155950665473938, |
| "learning_rate": 0.001, |
| "loss": 0.0478, |
| "step": 724 |
| }, |
| { |
| "epoch": 25.25, |
| "grad_norm": 0.14119938015937805, |
| "learning_rate": 0.001, |
| "loss": 0.0484, |
| "step": 726 |
| }, |
| { |
| "epoch": 25.32, |
| "grad_norm": 0.14679110050201416, |
| "learning_rate": 0.001, |
| "loss": 0.0432, |
| "step": 728 |
| }, |
| { |
| "epoch": 25.39, |
| "grad_norm": 0.13392671942710876, |
| "learning_rate": 0.001, |
| "loss": 0.0486, |
| "step": 730 |
| }, |
| { |
| "epoch": 25.46, |
| "grad_norm": 0.13733159005641937, |
| "learning_rate": 0.001, |
| "loss": 0.0451, |
| "step": 732 |
| }, |
| { |
| "epoch": 25.53, |
| "grad_norm": 0.13778570294380188, |
| "learning_rate": 0.001, |
| "loss": 0.0452, |
| "step": 734 |
| }, |
| { |
| "epoch": 25.6, |
| "grad_norm": 0.15224093198776245, |
| "learning_rate": 0.001, |
| "loss": 0.0469, |
| "step": 736 |
| }, |
| { |
| "epoch": 25.67, |
| "grad_norm": 0.15857195854187012, |
| "learning_rate": 0.001, |
| "loss": 0.0489, |
| "step": 738 |
| }, |
| { |
| "epoch": 25.74, |
| "grad_norm": 0.15234865248203278, |
| "learning_rate": 0.001, |
| "loss": 0.0536, |
| "step": 740 |
| }, |
| { |
| "epoch": 25.81, |
| "grad_norm": 0.17310313880443573, |
| "learning_rate": 0.001, |
| "loss": 0.0518, |
| "step": 742 |
| }, |
| { |
| "epoch": 25.88, |
| "grad_norm": 0.23332546651363373, |
| "learning_rate": 0.001, |
| "loss": 0.0601, |
| "step": 744 |
| }, |
| { |
| "epoch": 25.95, |
| "grad_norm": 0.22406938672065735, |
| "learning_rate": 0.001, |
| "loss": 0.081, |
| "step": 746 |
| }, |
| { |
| "epoch": 25.98, |
| "eval_loss": 4.690272331237793, |
| "eval_runtime": 14.2141, |
| "eval_samples_per_second": 23.779, |
| "eval_steps_per_second": 3.025, |
| "step": 747 |
| }, |
| { |
| "epoch": 26.02, |
| "grad_norm": 0.14596611261367798, |
| "learning_rate": 0.001, |
| "loss": 0.0551, |
| "step": 748 |
| }, |
| { |
| "epoch": 26.09, |
| "grad_norm": 0.11857102066278458, |
| "learning_rate": 0.001, |
| "loss": 0.0398, |
| "step": 750 |
| }, |
| { |
| "epoch": 26.16, |
| "grad_norm": 0.13823005557060242, |
| "learning_rate": 0.001, |
| "loss": 0.0424, |
| "step": 752 |
| }, |
| { |
| "epoch": 26.23, |
| "grad_norm": 0.12586718797683716, |
| "learning_rate": 0.001, |
| "loss": 0.0422, |
| "step": 754 |
| }, |
| { |
| "epoch": 26.3, |
| "grad_norm": 0.12402280420064926, |
| "learning_rate": 0.001, |
| "loss": 0.04, |
| "step": 756 |
| }, |
| { |
| "epoch": 26.37, |
| "grad_norm": 0.1546175628900528, |
| "learning_rate": 0.001, |
| "loss": 0.0434, |
| "step": 758 |
| }, |
| { |
| "epoch": 26.43, |
| "grad_norm": 0.15831632912158966, |
| "learning_rate": 0.001, |
| "loss": 0.041, |
| "step": 760 |
| }, |
| { |
| "epoch": 26.5, |
| "grad_norm": 0.1380414068698883, |
| "learning_rate": 0.001, |
| "loss": 0.0411, |
| "step": 762 |
| }, |
| { |
| "epoch": 26.57, |
| "grad_norm": 0.13040709495544434, |
| "learning_rate": 0.001, |
| "loss": 0.0412, |
| "step": 764 |
| }, |
| { |
| "epoch": 26.64, |
| "grad_norm": 0.14285586774349213, |
| "learning_rate": 0.001, |
| "loss": 0.0426, |
| "step": 766 |
| }, |
| { |
| "epoch": 26.71, |
| "grad_norm": 0.14807988703250885, |
| "learning_rate": 0.001, |
| "loss": 0.045, |
| "step": 768 |
| }, |
| { |
| "epoch": 26.78, |
| "grad_norm": 0.14204862713813782, |
| "learning_rate": 0.001, |
| "loss": 0.0517, |
| "step": 770 |
| }, |
| { |
| "epoch": 26.85, |
| "grad_norm": 0.13837137818336487, |
| "learning_rate": 0.001, |
| "loss": 0.0452, |
| "step": 772 |
| }, |
| { |
| "epoch": 26.92, |
| "grad_norm": 0.14084497094154358, |
| "learning_rate": 0.001, |
| "loss": 0.0475, |
| "step": 774 |
| }, |
| { |
| "epoch": 26.99, |
| "grad_norm": 0.13428126275539398, |
| "learning_rate": 0.001, |
| "loss": 0.0505, |
| "step": 776 |
| }, |
| { |
| "epoch": 26.99, |
| "eval_loss": 5.000490665435791, |
| "eval_runtime": 14.2197, |
| "eval_samples_per_second": 23.77, |
| "eval_steps_per_second": 3.024, |
| "step": 776 |
| }, |
| { |
| "epoch": 27.06, |
| "grad_norm": 0.1252642720937729, |
| "learning_rate": 0.001, |
| "loss": 0.0372, |
| "step": 778 |
| }, |
| { |
| "epoch": 27.13, |
| "grad_norm": 0.1609179526567459, |
| "learning_rate": 0.001, |
| "loss": 0.0422, |
| "step": 780 |
| }, |
| { |
| "epoch": 27.2, |
| "grad_norm": 0.15185533463954926, |
| "learning_rate": 0.001, |
| "loss": 0.0427, |
| "step": 782 |
| }, |
| { |
| "epoch": 27.27, |
| "grad_norm": 0.1398567408323288, |
| "learning_rate": 0.001, |
| "loss": 0.0452, |
| "step": 784 |
| }, |
| { |
| "epoch": 27.34, |
| "grad_norm": 0.13516364991664886, |
| "learning_rate": 0.001, |
| "loss": 0.0431, |
| "step": 786 |
| }, |
| { |
| "epoch": 27.41, |
| "grad_norm": 0.1388152688741684, |
| "learning_rate": 0.001, |
| "loss": 0.0424, |
| "step": 788 |
| }, |
| { |
| "epoch": 27.48, |
| "grad_norm": 0.14043325185775757, |
| "learning_rate": 0.001, |
| "loss": 0.0428, |
| "step": 790 |
| }, |
| { |
| "epoch": 27.55, |
| "grad_norm": 0.14878694713115692, |
| "learning_rate": 0.001, |
| "loss": 0.0473, |
| "step": 792 |
| }, |
| { |
| "epoch": 27.62, |
| "grad_norm": 0.15647174417972565, |
| "learning_rate": 0.001, |
| "loss": 0.0448, |
| "step": 794 |
| }, |
| { |
| "epoch": 27.69, |
| "grad_norm": 0.1453557014465332, |
| "learning_rate": 0.001, |
| "loss": 0.0441, |
| "step": 796 |
| }, |
| { |
| "epoch": 27.76, |
| "grad_norm": 0.13821879029273987, |
| "learning_rate": 0.001, |
| "loss": 0.0473, |
| "step": 798 |
| }, |
| { |
| "epoch": 27.83, |
| "grad_norm": 0.1780141144990921, |
| "learning_rate": 0.001, |
| "loss": 0.048, |
| "step": 800 |
| }, |
| { |
| "epoch": 27.9, |
| "grad_norm": 0.16689875721931458, |
| "learning_rate": 0.001, |
| "loss": 0.0568, |
| "step": 802 |
| }, |
| { |
| "epoch": 27.97, |
| "grad_norm": 0.16479206085205078, |
| "learning_rate": 0.001, |
| "loss": 0.0576, |
| "step": 804 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_loss": 5.019590377807617, |
| "eval_runtime": 14.2181, |
| "eval_samples_per_second": 23.772, |
| "eval_steps_per_second": 3.024, |
| "step": 805 |
| }, |
| { |
| "epoch": 28.03, |
| "grad_norm": 0.17976313829421997, |
| "learning_rate": 0.001, |
| "loss": 0.0586, |
| "step": 806 |
| }, |
| { |
| "epoch": 28.1, |
| "grad_norm": 0.15373440086841583, |
| "learning_rate": 0.001, |
| "loss": 0.0479, |
| "step": 808 |
| }, |
| { |
| "epoch": 28.17, |
| "grad_norm": 0.13314908742904663, |
| "learning_rate": 0.001, |
| "loss": 0.044, |
| "step": 810 |
| }, |
| { |
| "epoch": 28.24, |
| "grad_norm": 0.12571971118450165, |
| "learning_rate": 0.001, |
| "loss": 0.0382, |
| "step": 812 |
| }, |
| { |
| "epoch": 28.31, |
| "grad_norm": 0.1362116038799286, |
| "learning_rate": 0.001, |
| "loss": 0.0412, |
| "step": 814 |
| }, |
| { |
| "epoch": 28.38, |
| "grad_norm": 0.1244189664721489, |
| "learning_rate": 0.001, |
| "loss": 0.0422, |
| "step": 816 |
| }, |
| { |
| "epoch": 28.45, |
| "grad_norm": 0.1321047842502594, |
| "learning_rate": 0.001, |
| "loss": 0.0419, |
| "step": 818 |
| }, |
| { |
| "epoch": 28.52, |
| "grad_norm": 0.14995931088924408, |
| "learning_rate": 0.001, |
| "loss": 0.0453, |
| "step": 820 |
| }, |
| { |
| "epoch": 28.59, |
| "grad_norm": 0.1319851577281952, |
| "learning_rate": 0.001, |
| "loss": 0.0428, |
| "step": 822 |
| }, |
| { |
| "epoch": 28.66, |
| "grad_norm": 0.14392071962356567, |
| "learning_rate": 0.001, |
| "loss": 0.0417, |
| "step": 824 |
| }, |
| { |
| "epoch": 28.73, |
| "grad_norm": 0.13848307728767395, |
| "learning_rate": 0.001, |
| "loss": 0.0445, |
| "step": 826 |
| }, |
| { |
| "epoch": 28.8, |
| "grad_norm": 0.1495485007762909, |
| "learning_rate": 0.001, |
| "loss": 0.0451, |
| "step": 828 |
| }, |
| { |
| "epoch": 28.87, |
| "grad_norm": 0.13798055052757263, |
| "learning_rate": 0.001, |
| "loss": 0.0456, |
| "step": 830 |
| }, |
| { |
| "epoch": 28.94, |
| "grad_norm": 0.1452612578868866, |
| "learning_rate": 0.001, |
| "loss": 0.0448, |
| "step": 832 |
| }, |
| { |
| "epoch": 28.97, |
| "eval_loss": 5.109987735748291, |
| "eval_runtime": 14.2104, |
| "eval_samples_per_second": 23.785, |
| "eval_steps_per_second": 3.026, |
| "step": 833 |
| }, |
| { |
| "epoch": 29.01, |
| "grad_norm": 0.17332157492637634, |
| "learning_rate": 0.001, |
| "loss": 0.0438, |
| "step": 834 |
| }, |
| { |
| "epoch": 29.08, |
| "grad_norm": 0.12759405374526978, |
| "learning_rate": 0.001, |
| "loss": 0.0391, |
| "step": 836 |
| }, |
| { |
| "epoch": 29.15, |
| "grad_norm": 0.13717012107372284, |
| "learning_rate": 0.001, |
| "loss": 0.0392, |
| "step": 838 |
| }, |
| { |
| "epoch": 29.22, |
| "grad_norm": 0.12544453144073486, |
| "learning_rate": 0.001, |
| "loss": 0.0373, |
| "step": 840 |
| }, |
| { |
| "epoch": 29.29, |
| "grad_norm": 0.12997865676879883, |
| "learning_rate": 0.001, |
| "loss": 0.0403, |
| "step": 842 |
| }, |
| { |
| "epoch": 29.36, |
| "grad_norm": 0.1252465397119522, |
| "learning_rate": 0.001, |
| "loss": 0.0355, |
| "step": 844 |
| }, |
| { |
| "epoch": 29.43, |
| "grad_norm": 0.13186001777648926, |
| "learning_rate": 0.001, |
| "loss": 0.046, |
| "step": 846 |
| }, |
| { |
| "epoch": 29.5, |
| "grad_norm": 0.1309279203414917, |
| "learning_rate": 0.001, |
| "loss": 0.0423, |
| "step": 848 |
| }, |
| { |
| "epoch": 29.57, |
| "grad_norm": 0.13001705706119537, |
| "learning_rate": 0.001, |
| "loss": 0.0401, |
| "step": 850 |
| }, |
| { |
| "epoch": 29.63, |
| "grad_norm": 0.13039255142211914, |
| "learning_rate": 0.001, |
| "loss": 0.0396, |
| "step": 852 |
| }, |
| { |
| "epoch": 29.7, |
| "grad_norm": 0.13635265827178955, |
| "learning_rate": 0.001, |
| "loss": 0.0426, |
| "step": 854 |
| }, |
| { |
| "epoch": 29.77, |
| "grad_norm": 0.16096022725105286, |
| "learning_rate": 0.001, |
| "loss": 0.0444, |
| "step": 856 |
| }, |
| { |
| "epoch": 29.84, |
| "grad_norm": 0.12575644254684448, |
| "learning_rate": 0.001, |
| "loss": 0.0427, |
| "step": 858 |
| }, |
| { |
| "epoch": 29.91, |
| "grad_norm": 0.13646484911441803, |
| "learning_rate": 0.001, |
| "loss": 0.0442, |
| "step": 860 |
| }, |
| { |
| "epoch": 29.98, |
| "grad_norm": 0.13415445387363434, |
| "learning_rate": 0.001, |
| "loss": 0.0457, |
| "step": 862 |
| }, |
| { |
| "epoch": 29.98, |
| "eval_loss": 5.0008440017700195, |
| "eval_runtime": 14.2056, |
| "eval_samples_per_second": 23.793, |
| "eval_steps_per_second": 3.027, |
| "step": 862 |
| }, |
| { |
| "epoch": 30.05, |
| "grad_norm": 0.12284772843122482, |
| "learning_rate": 0.001, |
| "loss": 0.0331, |
| "step": 864 |
| }, |
| { |
| "epoch": 30.12, |
| "grad_norm": 0.12438986450433731, |
| "learning_rate": 0.001, |
| "loss": 0.0372, |
| "step": 866 |
| }, |
| { |
| "epoch": 30.19, |
| "grad_norm": 0.12020161747932434, |
| "learning_rate": 0.001, |
| "loss": 0.0366, |
| "step": 868 |
| }, |
| { |
| "epoch": 30.26, |
| "grad_norm": 0.12868288159370422, |
| "learning_rate": 0.001, |
| "loss": 0.0384, |
| "step": 870 |
| }, |
| { |
| "epoch": 30.33, |
| "grad_norm": 0.1276613026857376, |
| "learning_rate": 0.001, |
| "loss": 0.0415, |
| "step": 872 |
| }, |
| { |
| "epoch": 30.4, |
| "grad_norm": 0.13801202178001404, |
| "learning_rate": 0.001, |
| "loss": 0.0403, |
| "step": 874 |
| }, |
| { |
| "epoch": 30.47, |
| "grad_norm": 0.1174420416355133, |
| "learning_rate": 0.001, |
| "loss": 0.0389, |
| "step": 876 |
| }, |
| { |
| "epoch": 30.54, |
| "grad_norm": 0.11008256673812866, |
| "learning_rate": 0.001, |
| "loss": 0.0342, |
| "step": 878 |
| }, |
| { |
| "epoch": 30.61, |
| "grad_norm": 0.12188894301652908, |
| "learning_rate": 0.001, |
| "loss": 0.0382, |
| "step": 880 |
| }, |
| { |
| "epoch": 30.68, |
| "grad_norm": 0.12297231703996658, |
| "learning_rate": 0.001, |
| "loss": 0.0382, |
| "step": 882 |
| }, |
| { |
| "epoch": 30.75, |
| "grad_norm": 0.12277786433696747, |
| "learning_rate": 0.001, |
| "loss": 0.0381, |
| "step": 884 |
| }, |
| { |
| "epoch": 30.82, |
| "grad_norm": 0.13909707963466644, |
| "learning_rate": 0.001, |
| "loss": 0.0385, |
| "step": 886 |
| }, |
| { |
| "epoch": 30.89, |
| "grad_norm": 0.13425001502037048, |
| "learning_rate": 0.001, |
| "loss": 0.0424, |
| "step": 888 |
| }, |
| { |
| "epoch": 30.96, |
| "grad_norm": 0.14270208775997162, |
| "learning_rate": 0.001, |
| "loss": 0.0442, |
| "step": 890 |
| }, |
| { |
| "epoch": 30.99, |
| "eval_loss": 5.50925874710083, |
| "eval_runtime": 14.2033, |
| "eval_samples_per_second": 23.797, |
| "eval_steps_per_second": 3.027, |
| "step": 891 |
| }, |
| { |
| "epoch": 31.03, |
| "grad_norm": 0.14988122880458832, |
| "learning_rate": 0.001, |
| "loss": 0.0391, |
| "step": 892 |
| }, |
| { |
| "epoch": 31.1, |
| "grad_norm": 0.12136206030845642, |
| "learning_rate": 0.001, |
| "loss": 0.0368, |
| "step": 894 |
| }, |
| { |
| "epoch": 31.17, |
| "grad_norm": 0.1474607139825821, |
| "learning_rate": 0.001, |
| "loss": 0.0366, |
| "step": 896 |
| }, |
| { |
| "epoch": 31.23, |
| "grad_norm": 0.1664348542690277, |
| "learning_rate": 0.001, |
| "loss": 0.0364, |
| "step": 898 |
| }, |
| { |
| "epoch": 31.3, |
| "grad_norm": 0.12352883070707321, |
| "learning_rate": 0.001, |
| "loss": 0.0368, |
| "step": 900 |
| }, |
| { |
| "epoch": 31.37, |
| "grad_norm": 0.1317415088415146, |
| "learning_rate": 0.001, |
| "loss": 0.0344, |
| "step": 902 |
| }, |
| { |
| "epoch": 31.44, |
| "grad_norm": 0.12790362536907196, |
| "learning_rate": 0.001, |
| "loss": 0.034, |
| "step": 904 |
| }, |
| { |
| "epoch": 31.51, |
| "grad_norm": 0.13639821112155914, |
| "learning_rate": 0.001, |
| "loss": 0.0385, |
| "step": 906 |
| }, |
| { |
| "epoch": 31.58, |
| "grad_norm": 0.14075782895088196, |
| "learning_rate": 0.001, |
| "loss": 0.0414, |
| "step": 908 |
| }, |
| { |
| "epoch": 31.65, |
| "grad_norm": 0.1388426125049591, |
| "learning_rate": 0.001, |
| "loss": 0.0423, |
| "step": 910 |
| }, |
| { |
| "epoch": 31.72, |
| "grad_norm": 0.1304369866847992, |
| "learning_rate": 0.001, |
| "loss": 0.0418, |
| "step": 912 |
| }, |
| { |
| "epoch": 31.79, |
| "grad_norm": 0.13760504126548767, |
| "learning_rate": 0.001, |
| "loss": 0.0438, |
| "step": 914 |
| }, |
| { |
| "epoch": 31.86, |
| "grad_norm": 0.13388106226921082, |
| "learning_rate": 0.001, |
| "loss": 0.0442, |
| "step": 916 |
| }, |
| { |
| "epoch": 31.93, |
| "grad_norm": 0.13234779238700867, |
| "learning_rate": 0.001, |
| "loss": 0.0403, |
| "step": 918 |
| }, |
| { |
| "epoch": 32.0, |
| "grad_norm": 0.12893211841583252, |
| "learning_rate": 0.001, |
| "loss": 0.0391, |
| "step": 920 |
| }, |
| { |
| "epoch": 32.0, |
| "eval_loss": 5.429612159729004, |
| "eval_runtime": 14.2128, |
| "eval_samples_per_second": 23.781, |
| "eval_steps_per_second": 3.025, |
| "step": 920 |
| }, |
| { |
| "epoch": 32.07, |
| "grad_norm": 0.12455160915851593, |
| "learning_rate": 0.001, |
| "loss": 0.0343, |
| "step": 922 |
| }, |
| { |
| "epoch": 32.14, |
| "grad_norm": 0.13458769023418427, |
| "learning_rate": 0.001, |
| "loss": 0.0358, |
| "step": 924 |
| }, |
| { |
| "epoch": 32.21, |
| "grad_norm": 0.11662837117910385, |
| "learning_rate": 0.001, |
| "loss": 0.0359, |
| "step": 926 |
| }, |
| { |
| "epoch": 32.28, |
| "grad_norm": 0.1250811070203781, |
| "learning_rate": 0.001, |
| "loss": 0.0366, |
| "step": 928 |
| }, |
| { |
| "epoch": 32.35, |
| "grad_norm": 0.1264219582080841, |
| "learning_rate": 0.001, |
| "loss": 0.0374, |
| "step": 930 |
| }, |
| { |
| "epoch": 32.42, |
| "grad_norm": 0.12272246927022934, |
| "learning_rate": 0.001, |
| "loss": 0.0378, |
| "step": 932 |
| }, |
| { |
| "epoch": 32.49, |
| "grad_norm": 0.12346846610307693, |
| "learning_rate": 0.001, |
| "loss": 0.0387, |
| "step": 934 |
| }, |
| { |
| "epoch": 32.56, |
| "grad_norm": 0.12550891935825348, |
| "learning_rate": 0.001, |
| "loss": 0.0355, |
| "step": 936 |
| }, |
| { |
| "epoch": 32.63, |
| "grad_norm": 0.13145896792411804, |
| "learning_rate": 0.001, |
| "loss": 0.0371, |
| "step": 938 |
| }, |
| { |
| "epoch": 32.7, |
| "grad_norm": 0.12549975514411926, |
| "learning_rate": 0.001, |
| "loss": 0.038, |
| "step": 940 |
| }, |
| { |
| "epoch": 32.77, |
| "grad_norm": 0.13180097937583923, |
| "learning_rate": 0.001, |
| "loss": 0.0361, |
| "step": 942 |
| }, |
| { |
| "epoch": 32.83, |
| "grad_norm": 0.1240687221288681, |
| "learning_rate": 0.001, |
| "loss": 0.0364, |
| "step": 944 |
| }, |
| { |
| "epoch": 32.9, |
| "grad_norm": 0.14110788702964783, |
| "learning_rate": 0.001, |
| "loss": 0.0421, |
| "step": 946 |
| }, |
| { |
| "epoch": 32.97, |
| "grad_norm": 0.14410488307476044, |
| "learning_rate": 0.001, |
| "loss": 0.0392, |
| "step": 948 |
| }, |
| { |
| "epoch": 32.97, |
| "eval_loss": 5.23565673828125, |
| "eval_runtime": 14.2111, |
| "eval_samples_per_second": 23.784, |
| "eval_steps_per_second": 3.026, |
| "step": 948 |
| }, |
| { |
| "epoch": 33.04, |
| "grad_norm": 0.12806980311870575, |
| "learning_rate": 0.001, |
| "loss": 0.041, |
| "step": 950 |
| }, |
| { |
| "epoch": 33.11, |
| "grad_norm": 0.12071588635444641, |
| "learning_rate": 0.001, |
| "loss": 0.0401, |
| "step": 952 |
| }, |
| { |
| "epoch": 33.18, |
| "grad_norm": 0.11720431596040726, |
| "learning_rate": 0.001, |
| "loss": 0.035, |
| "step": 954 |
| }, |
| { |
| "epoch": 33.25, |
| "grad_norm": 0.12089748680591583, |
| "learning_rate": 0.001, |
| "loss": 0.0389, |
| "step": 956 |
| }, |
| { |
| "epoch": 33.32, |
| "grad_norm": 0.1227785050868988, |
| "learning_rate": 0.001, |
| "loss": 0.0389, |
| "step": 958 |
| }, |
| { |
| "epoch": 33.39, |
| "grad_norm": 0.12859608232975006, |
| "learning_rate": 0.001, |
| "loss": 0.0342, |
| "step": 960 |
| }, |
| { |
| "epoch": 33.46, |
| "grad_norm": 0.2180158495903015, |
| "learning_rate": 0.001, |
| "loss": 0.041, |
| "step": 962 |
| }, |
| { |
| "epoch": 33.53, |
| "grad_norm": 0.2960141897201538, |
| "learning_rate": 0.001, |
| "loss": 0.0989, |
| "step": 964 |
| }, |
| { |
| "epoch": 33.6, |
| "grad_norm": 0.15140074491500854, |
| "learning_rate": 0.001, |
| "loss": 0.0503, |
| "step": 966 |
| }, |
| { |
| "epoch": 33.67, |
| "grad_norm": 0.13876180350780487, |
| "learning_rate": 0.001, |
| "loss": 0.0418, |
| "step": 968 |
| }, |
| { |
| "epoch": 33.74, |
| "grad_norm": 0.1290924996137619, |
| "learning_rate": 0.001, |
| "loss": 0.0413, |
| "step": 970 |
| }, |
| { |
| "epoch": 33.81, |
| "grad_norm": 0.13152842223644257, |
| "learning_rate": 0.001, |
| "loss": 0.0398, |
| "step": 972 |
| }, |
| { |
| "epoch": 33.88, |
| "grad_norm": 0.1308111995458603, |
| "learning_rate": 0.001, |
| "loss": 0.0384, |
| "step": 974 |
| }, |
| { |
| "epoch": 33.95, |
| "grad_norm": 0.12206979840993881, |
| "learning_rate": 0.001, |
| "loss": 0.0376, |
| "step": 976 |
| }, |
| { |
| "epoch": 33.98, |
| "eval_loss": 5.226629734039307, |
| "eval_runtime": 14.2113, |
| "eval_samples_per_second": 23.784, |
| "eval_steps_per_second": 3.026, |
| "step": 977 |
| }, |
| { |
| "epoch": 34.02, |
| "grad_norm": 0.15338914096355438, |
| "learning_rate": 0.001, |
| "loss": 0.036, |
| "step": 978 |
| }, |
| { |
| "epoch": 34.09, |
| "grad_norm": 0.12300385534763336, |
| "learning_rate": 0.001, |
| "loss": 0.0357, |
| "step": 980 |
| }, |
| { |
| "epoch": 34.16, |
| "grad_norm": 0.10930658131837845, |
| "learning_rate": 0.001, |
| "loss": 0.03, |
| "step": 982 |
| }, |
| { |
| "epoch": 34.23, |
| "grad_norm": 0.12387796491384506, |
| "learning_rate": 0.001, |
| "loss": 0.0393, |
| "step": 984 |
| }, |
| { |
| "epoch": 34.3, |
| "grad_norm": 0.1442791372537613, |
| "learning_rate": 0.001, |
| "loss": 0.0327, |
| "step": 986 |
| }, |
| { |
| "epoch": 34.37, |
| "grad_norm": 0.12000349164009094, |
| "learning_rate": 0.001, |
| "loss": 0.0356, |
| "step": 988 |
| }, |
| { |
| "epoch": 34.43, |
| "grad_norm": 0.12804967164993286, |
| "learning_rate": 0.001, |
| "loss": 0.0415, |
| "step": 990 |
| }, |
| { |
| "epoch": 34.5, |
| "grad_norm": 0.12344588339328766, |
| "learning_rate": 0.001, |
| "loss": 0.0348, |
| "step": 992 |
| }, |
| { |
| "epoch": 34.57, |
| "grad_norm": 0.12841206789016724, |
| "learning_rate": 0.001, |
| "loss": 0.036, |
| "step": 994 |
| }, |
| { |
| "epoch": 34.64, |
| "grad_norm": 0.11577708274126053, |
| "learning_rate": 0.001, |
| "loss": 0.0349, |
| "step": 996 |
| }, |
| { |
| "epoch": 34.71, |
| "grad_norm": 0.12154724448919296, |
| "learning_rate": 0.001, |
| "loss": 0.0384, |
| "step": 998 |
| }, |
| { |
| "epoch": 34.78, |
| "grad_norm": 0.12926706671714783, |
| "learning_rate": 0.001, |
| "loss": 0.0376, |
| "step": 1000 |
| }, |
| { |
| "epoch": 34.85, |
| "grad_norm": 0.11031629890203476, |
| "learning_rate": 0.001, |
| "loss": 0.0341, |
| "step": 1002 |
| }, |
| { |
| "epoch": 34.92, |
| "grad_norm": 0.13376009464263916, |
| "learning_rate": 0.001, |
| "loss": 0.0352, |
| "step": 1004 |
| }, |
| { |
| "epoch": 34.99, |
| "grad_norm": 0.1240614578127861, |
| "learning_rate": 0.001, |
| "loss": 0.0381, |
| "step": 1006 |
| }, |
| { |
| "epoch": 34.99, |
| "eval_loss": 5.263000965118408, |
| "eval_runtime": 14.2061, |
| "eval_samples_per_second": 23.793, |
| "eval_steps_per_second": 3.027, |
| "step": 1006 |
| }, |
| { |
| "epoch": 35.06, |
| "grad_norm": 0.12797795236110687, |
| "learning_rate": 0.001, |
| "loss": 0.0339, |
| "step": 1008 |
| }, |
| { |
| "epoch": 35.13, |
| "grad_norm": 0.13305290043354034, |
| "learning_rate": 0.001, |
| "loss": 0.0333, |
| "step": 1010 |
| }, |
| { |
| "epoch": 35.2, |
| "grad_norm": 0.12507498264312744, |
| "learning_rate": 0.001, |
| "loss": 0.0316, |
| "step": 1012 |
| }, |
| { |
| "epoch": 35.27, |
| "grad_norm": 0.1163344755768776, |
| "learning_rate": 0.001, |
| "loss": 0.0323, |
| "step": 1014 |
| }, |
| { |
| "epoch": 35.34, |
| "grad_norm": 0.11232735961675644, |
| "learning_rate": 0.001, |
| "loss": 0.035, |
| "step": 1016 |
| }, |
| { |
| "epoch": 35.41, |
| "grad_norm": 0.11937879770994186, |
| "learning_rate": 0.001, |
| "loss": 0.0343, |
| "step": 1018 |
| }, |
| { |
| "epoch": 35.48, |
| "grad_norm": 0.1227354183793068, |
| "learning_rate": 0.001, |
| "loss": 0.0316, |
| "step": 1020 |
| }, |
| { |
| "epoch": 35.55, |
| "grad_norm": 0.1201673150062561, |
| "learning_rate": 0.001, |
| "loss": 0.0345, |
| "step": 1022 |
| }, |
| { |
| "epoch": 35.62, |
| "grad_norm": 0.11625051498413086, |
| "learning_rate": 0.001, |
| "loss": 0.0305, |
| "step": 1024 |
| }, |
| { |
| "epoch": 35.69, |
| "grad_norm": 0.1144721657037735, |
| "learning_rate": 0.001, |
| "loss": 0.03, |
| "step": 1026 |
| }, |
| { |
| "epoch": 35.76, |
| "grad_norm": 0.12341687083244324, |
| "learning_rate": 0.001, |
| "loss": 0.0374, |
| "step": 1028 |
| }, |
| { |
| "epoch": 35.83, |
| "grad_norm": 0.12577305734157562, |
| "learning_rate": 0.001, |
| "loss": 0.0347, |
| "step": 1030 |
| }, |
| { |
| "epoch": 35.9, |
| "grad_norm": 0.11321111768484116, |
| "learning_rate": 0.001, |
| "loss": 0.0336, |
| "step": 1032 |
| }, |
| { |
| "epoch": 35.97, |
| "grad_norm": 0.11875444650650024, |
| "learning_rate": 0.001, |
| "loss": 0.0339, |
| "step": 1034 |
| }, |
| { |
| "epoch": 36.0, |
| "eval_loss": 5.353184700012207, |
| "eval_runtime": 14.1981, |
| "eval_samples_per_second": 23.806, |
| "eval_steps_per_second": 3.029, |
| "step": 1035 |
| }, |
| { |
| "epoch": 36.03, |
| "grad_norm": 0.122185118496418, |
| "learning_rate": 0.001, |
| "loss": 0.0285, |
| "step": 1036 |
| }, |
| { |
| "epoch": 36.1, |
| "grad_norm": 0.1075131967663765, |
| "learning_rate": 0.001, |
| "loss": 0.0312, |
| "step": 1038 |
| }, |
| { |
| "epoch": 36.17, |
| "grad_norm": 0.12375488132238388, |
| "learning_rate": 0.001, |
| "loss": 0.0291, |
| "step": 1040 |
| }, |
| { |
| "epoch": 36.24, |
| "grad_norm": 0.12728258967399597, |
| "learning_rate": 0.001, |
| "loss": 0.0333, |
| "step": 1042 |
| }, |
| { |
| "epoch": 36.31, |
| "grad_norm": 0.1169193834066391, |
| "learning_rate": 0.001, |
| "loss": 0.0309, |
| "step": 1044 |
| }, |
| { |
| "epoch": 36.38, |
| "grad_norm": 0.11048964411020279, |
| "learning_rate": 0.001, |
| "loss": 0.0299, |
| "step": 1046 |
| }, |
| { |
| "epoch": 36.45, |
| "grad_norm": 0.11923568695783615, |
| "learning_rate": 0.001, |
| "loss": 0.0301, |
| "step": 1048 |
| }, |
| { |
| "epoch": 36.52, |
| "grad_norm": 0.1160750761628151, |
| "learning_rate": 0.001, |
| "loss": 0.0287, |
| "step": 1050 |
| }, |
| { |
| "epoch": 36.59, |
| "grad_norm": 0.12535539269447327, |
| "learning_rate": 0.001, |
| "loss": 0.0335, |
| "step": 1052 |
| }, |
| { |
| "epoch": 36.66, |
| "grad_norm": 0.13712206482887268, |
| "learning_rate": 0.001, |
| "loss": 0.0358, |
| "step": 1054 |
| }, |
| { |
| "epoch": 36.73, |
| "grad_norm": 0.12085587531328201, |
| "learning_rate": 0.001, |
| "loss": 0.0362, |
| "step": 1056 |
| }, |
| { |
| "epoch": 36.8, |
| "grad_norm": 0.1010272428393364, |
| "learning_rate": 0.001, |
| "loss": 0.0324, |
| "step": 1058 |
| }, |
| { |
| "epoch": 36.87, |
| "grad_norm": 0.11820247769355774, |
| "learning_rate": 0.001, |
| "loss": 0.0315, |
| "step": 1060 |
| }, |
| { |
| "epoch": 36.94, |
| "grad_norm": 0.1259121298789978, |
| "learning_rate": 0.001, |
| "loss": 0.0377, |
| "step": 1062 |
| }, |
| { |
| "epoch": 36.97, |
| "eval_loss": 5.44431734085083, |
| "eval_runtime": 14.2065, |
| "eval_samples_per_second": 23.792, |
| "eval_steps_per_second": 3.027, |
| "step": 1063 |
| }, |
| { |
| "epoch": 37.01, |
| "grad_norm": 0.12725719809532166, |
| "learning_rate": 0.001, |
| "loss": 0.0277, |
| "step": 1064 |
| }, |
| { |
| "epoch": 37.08, |
| "grad_norm": 0.11410412192344666, |
| "learning_rate": 0.001, |
| "loss": 0.0282, |
| "step": 1066 |
| }, |
| { |
| "epoch": 37.15, |
| "grad_norm": 0.11205872148275375, |
| "learning_rate": 0.001, |
| "loss": 0.0302, |
| "step": 1068 |
| }, |
| { |
| "epoch": 37.22, |
| "grad_norm": 0.09593572467565536, |
| "learning_rate": 0.001, |
| "loss": 0.0263, |
| "step": 1070 |
| }, |
| { |
| "epoch": 37.29, |
| "grad_norm": 0.12462112307548523, |
| "learning_rate": 0.001, |
| "loss": 0.0328, |
| "step": 1072 |
| }, |
| { |
| "epoch": 37.36, |
| "grad_norm": 0.11873652786016464, |
| "learning_rate": 0.001, |
| "loss": 0.0328, |
| "step": 1074 |
| }, |
| { |
| "epoch": 37.43, |
| "grad_norm": 0.1105048656463623, |
| "learning_rate": 0.001, |
| "loss": 0.0298, |
| "step": 1076 |
| }, |
| { |
| "epoch": 37.5, |
| "grad_norm": 0.10692736506462097, |
| "learning_rate": 0.001, |
| "loss": 0.0328, |
| "step": 1078 |
| }, |
| { |
| "epoch": 37.57, |
| "grad_norm": 0.12755931913852692, |
| "learning_rate": 0.001, |
| "loss": 0.0321, |
| "step": 1080 |
| }, |
| { |
| "epoch": 37.63, |
| "grad_norm": 0.13307899236679077, |
| "learning_rate": 0.001, |
| "loss": 0.0329, |
| "step": 1082 |
| }, |
| { |
| "epoch": 37.7, |
| "grad_norm": 0.12125247716903687, |
| "learning_rate": 0.001, |
| "loss": 0.034, |
| "step": 1084 |
| }, |
| { |
| "epoch": 37.77, |
| "grad_norm": 0.12050389498472214, |
| "learning_rate": 0.001, |
| "loss": 0.031, |
| "step": 1086 |
| }, |
| { |
| "epoch": 37.84, |
| "grad_norm": 0.11437363177537918, |
| "learning_rate": 0.001, |
| "loss": 0.0308, |
| "step": 1088 |
| }, |
| { |
| "epoch": 37.91, |
| "grad_norm": 0.13162565231323242, |
| "learning_rate": 0.001, |
| "loss": 0.037, |
| "step": 1090 |
| }, |
| { |
| "epoch": 37.98, |
| "grad_norm": 0.13537472486495972, |
| "learning_rate": 0.001, |
| "loss": 0.0336, |
| "step": 1092 |
| }, |
| { |
| "epoch": 37.98, |
| "eval_loss": 5.080876350402832, |
| "eval_runtime": 14.2123, |
| "eval_samples_per_second": 23.782, |
| "eval_steps_per_second": 3.026, |
| "step": 1092 |
| }, |
| { |
| "epoch": 38.05, |
| "grad_norm": 0.10324922204017639, |
| "learning_rate": 0.001, |
| "loss": 0.0311, |
| "step": 1094 |
| }, |
| { |
| "epoch": 38.12, |
| "grad_norm": 0.10196162760257721, |
| "learning_rate": 0.001, |
| "loss": 0.0274, |
| "step": 1096 |
| }, |
| { |
| "epoch": 38.19, |
| "grad_norm": 0.10867214947938919, |
| "learning_rate": 0.001, |
| "loss": 0.0281, |
| "step": 1098 |
| }, |
| { |
| "epoch": 38.26, |
| "grad_norm": 0.10762563347816467, |
| "learning_rate": 0.001, |
| "loss": 0.0301, |
| "step": 1100 |
| }, |
| { |
| "epoch": 38.33, |
| "grad_norm": 0.10636897385120392, |
| "learning_rate": 0.001, |
| "loss": 0.0305, |
| "step": 1102 |
| }, |
| { |
| "epoch": 38.4, |
| "grad_norm": 0.10994244366884232, |
| "learning_rate": 0.001, |
| "loss": 0.0328, |
| "step": 1104 |
| }, |
| { |
| "epoch": 38.47, |
| "grad_norm": 0.11419042944908142, |
| "learning_rate": 0.001, |
| "loss": 0.0328, |
| "step": 1106 |
| }, |
| { |
| "epoch": 38.54, |
| "grad_norm": 0.10719581693410873, |
| "learning_rate": 0.001, |
| "loss": 0.0359, |
| "step": 1108 |
| }, |
| { |
| "epoch": 38.61, |
| "grad_norm": 0.13429002463817596, |
| "learning_rate": 0.001, |
| "loss": 0.0302, |
| "step": 1110 |
| }, |
| { |
| "epoch": 38.68, |
| "grad_norm": 0.11462274938821793, |
| "learning_rate": 0.001, |
| "loss": 0.0311, |
| "step": 1112 |
| }, |
| { |
| "epoch": 38.75, |
| "grad_norm": 0.12587036192417145, |
| "learning_rate": 0.001, |
| "loss": 0.0303, |
| "step": 1114 |
| }, |
| { |
| "epoch": 38.82, |
| "grad_norm": 0.11628645658493042, |
| "learning_rate": 0.001, |
| "loss": 0.0294, |
| "step": 1116 |
| }, |
| { |
| "epoch": 38.89, |
| "grad_norm": 0.1132420152425766, |
| "learning_rate": 0.001, |
| "loss": 0.0344, |
| "step": 1118 |
| }, |
| { |
| "epoch": 38.96, |
| "grad_norm": 0.12212924659252167, |
| "learning_rate": 0.001, |
| "loss": 0.0316, |
| "step": 1120 |
| }, |
| { |
| "epoch": 38.96, |
| "eval_loss": 5.267875671386719, |
| "eval_runtime": 14.2092, |
| "eval_samples_per_second": 23.787, |
| "eval_steps_per_second": 3.026, |
| "step": 1120 |
| }, |
| { |
| "epoch": 38.96, |
| "step": 1120, |
| "total_flos": 1.0970359673435505e+18, |
| "train_loss": 0.32971865670822026, |
| "train_runtime": 25027.7089, |
| "train_samples_per_second": 5.87, |
| "train_steps_per_second": 0.045 |
| } |
| ], |
| "logging_steps": 2, |
| "max_steps": 1120, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 40, |
| "save_steps": 500, |
| "total_flos": 1.0970359673435505e+18, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
