| Training: N=256, B=16, lr=0.03, max_iters=1000000, ckpt_interval=50000 | |
| batch=4096, micro=1024, accum=4, params=112,384 | |
| output_dir=/mnt/task_runtime/sort-llm/1000k-checkpoints | |
| GPU: NVIDIA H100 80GB HBM3 | |
| itr 0/1000000 | loss 5.565604 | test 5.559675 | lr 1.49e-04 | 0 it/s | eta 220194m | 0.2m elapsed | |
| itr 1000/1000000 | loss 0.005900 | test 0.008111 | lr 3.00e-02 | 40 it/s | eta 420m | 0.4m elapsed | |
| itr 2000/1000000 | loss 0.003708 | test 0.001755 | lr 3.00e-02 | 54 it/s | eta 310m | 0.6m elapsed | |
| itr 3000/1000000 | loss 0.001833 | test 0.003504 | lr 3.00e-02 | 61 it/s | eta 272m | 0.8m elapsed | |
| itr 4000/1000000 | loss 0.002188 | test 0.003171 | lr 3.00e-02 | 65 it/s | eta 254m | 1.0m elapsed | |
| itr 5000/1000000 | loss 0.000615 | test 0.001090 | lr 3.00e-02 | 68 it/s | eta 242m | 1.2m elapsed | |
| itr 6000/1000000 | loss 0.002228 | test 0.000762 | lr 3.00e-02 | 71 it/s | eta 235m | 1.4m elapsed | |
| itr 7000/1000000 | loss 0.003039 | test 0.005727 | lr 3.00e-02 | 72 it/s | eta 229m | 1.6m elapsed | |
| itr 8000/1000000 | loss 0.000956 | test 0.003121 | lr 3.00e-02 | 73 it/s | eta 225m | 1.8m elapsed | |
| itr 9000/1000000 | loss 0.002028 | test 0.000132 | lr 3.00e-02 | 74 it/s | eta 222m | 2.0m elapsed | |
| itr 10000/1000000 | loss 0.002034 | test 0.001129 | lr 3.00e-02 | 75 it/s | eta 220m | 2.2m elapsed | |
| itr 11000/1000000 | loss 0.000286 | test 0.002584 | lr 3.00e-02 | 76 it/s | eta 217m | 2.4m elapsed | |
| itr 12000/1000000 | loss 0.005490 | test 0.004253 | lr 3.00e-02 | 76 it/s | eta 215m | 2.6m elapsed | |
| itr 13000/1000000 | loss 0.000449 | test 0.001502 | lr 3.00e-02 | 77 it/s | eta 214m | 2.8m elapsed | |
| itr 14000/1000000 | loss 0.002668 | test 0.001838 | lr 3.00e-02 | 77 it/s | eta 212m | 3.0m elapsed | |
| itr 15000/1000000 | loss 0.000664 | test 0.000487 | lr 3.00e-02 | 78 it/s | eta 211m | 3.2m elapsed | |
| itr 16000/1000000 | loss 0.001071 | test 0.000259 | lr 3.00e-02 | 78 it/s | eta 210m | 3.4m elapsed | |
| itr 17000/1000000 | loss 0.001660 | test 0.000212 | lr 3.00e-02 | 78 it/s | eta 209m | 3.6m elapsed | |
| itr 18000/1000000 | loss 0.000156 | test 0.000490 | lr 3.00e-02 | 79 it/s | eta 208m | 3.8m elapsed | |
| itr 19000/1000000 | loss 0.000414 | test 0.000054 | lr 3.00e-02 | 79 it/s | eta 208m | 4.0m elapsed | |
| itr 20000/1000000 | loss 0.000150 | test 0.000044 | lr 3.00e-02 | 79 it/s | eta 207m | 4.2m elapsed | |
| itr 21000/1000000 | loss 0.001983 | test 0.000687 | lr 3.00e-02 | 79 it/s | eta 207m | 4.4m elapsed | |
| itr 22000/1000000 | loss 0.000963 | test 0.002071 | lr 3.00e-02 | 79 it/s | eta 206m | 4.6m elapsed | |
| itr 23000/1000000 | loss 0.000899 | test 0.001556 | lr 3.00e-02 | 79 it/s | eta 205m | 4.8m elapsed | |
| itr 24000/1000000 | loss 0.001387 | test 0.000735 | lr 3.00e-02 | 79 it/s | eta 205m | 5.0m elapsed | |
| itr 25000/1000000 | loss 0.000461 | test 0.000493 | lr 3.00e-02 | 80 it/s | eta 204m | 5.2m elapsed | |
| itr 26000/1000000 | loss 0.000728 | test 0.000115 | lr 3.00e-02 | 80 it/s | eta 204m | 5.4m elapsed | |
| itr 27000/1000000 | loss 0.000322 | test 0.000717 | lr 2.99e-02 | 80 it/s | eta 203m | 5.6m elapsed | |
| itr 28000/1000000 | loss 0.000288 | test 0.000025 | lr 2.99e-02 | 80 it/s | eta 203m | 5.8m elapsed | |
| itr 29000/1000000 | loss 0.000180 | test 0.001061 | lr 2.99e-02 | 80 it/s | eta 202m | 6.0m elapsed | |
| itr 30000/1000000 | loss 0.001177 | test 0.001258 | lr 2.99e-02 | 80 it/s | eta 202m | 6.2m elapsed | |
| itr 31000/1000000 | loss 0.000255 | test 0.000069 | lr 2.99e-02 | 80 it/s | eta 201m | 6.4m elapsed | |
| itr 32000/1000000 | loss 0.003558 | test 0.000684 | lr 2.99e-02 | 80 it/s | eta 202m | 6.7m elapsed | |
| itr 33000/1000000 | loss 0.000991 | test 0.001067 | lr 2.99e-02 | 80 it/s | eta 202m | 6.9m elapsed | |
| itr 34000/1000000 | loss 0.000262 | test 0.000023 | lr 2.99e-02 | 80 it/s | eta 202m | 7.1m elapsed | |
| itr 35000/1000000 | loss 0.000170 | test 0.001583 | lr 2.99e-02 | 79 it/s | eta 203m | 7.4m elapsed | |
| itr 36000/1000000 | loss 0.003708 | test 0.003370 | lr 2.99e-02 | 79 it/s | eta 203m | 7.6m elapsed | |
| itr 37000/1000000 | loss 0.006338 | test 0.001830 | lr 2.99e-02 | 79 it/s | eta 204m | 7.8m elapsed | |
| itr 38000/1000000 | loss 0.000844 | test 0.001545 | lr 2.99e-02 | 79 it/s | eta 204m | 8.1m elapsed | |
| itr 39000/1000000 | loss 0.000186 | test 0.000051 | lr 2.99e-02 | 79 it/s | eta 204m | 8.3m elapsed | |
| itr 40000/1000000 | loss 0.003106 | test 0.000714 | lr 2.99e-02 | 78 it/s | eta 204m | 8.5m elapsed | |
| itr 41000/1000000 | loss 0.000038 | test 0.000015 | lr 2.99e-02 | 78 it/s | eta 204m | 8.7m elapsed | |
| itr 42000/1000000 | loss 0.000608 | test 0.000084 | lr 2.99e-02 | 78 it/s | eta 204m | 9.0m elapsed | |
| itr 43000/1000000 | loss 0.000155 | test 0.000392 | lr 2.99e-02 | 78 it/s | eta 204m | 9.2m elapsed | |
| itr 44000/1000000 | loss 0.000541 | test 0.000017 | lr 2.99e-02 | 78 it/s | eta 204m | 9.4m elapsed | |
| itr 45000/1000000 | loss 0.001366 | test 0.000216 | lr 2.99e-02 | 78 it/s | eta 204m | 9.6m elapsed | |
| itr 46000/1000000 | loss 0.000642 | test 0.001512 | lr 2.98e-02 | 78 it/s | eta 204m | 9.9m elapsed | |
| itr 47000/1000000 | loss 0.000305 | test 0.000364 | lr 2.98e-02 | 78 it/s | eta 204m | 10.1m elapsed | |
| itr 48000/1000000 | loss 0.000179 | test 0.000048 | lr 2.98e-02 | 78 it/s | eta 204m | 10.3m elapsed | |
| itr 49000/1000000 | loss 0.000264 | test 0.002732 | lr 2.98e-02 | 78 it/s | eta 204m | 10.5m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt50000.pt (10.7m) | |
| itr 50000/1000000 | loss 0.000044 | test 0.000046 | lr 2.98e-02 | 78 it/s | eta 203m | 10.7m elapsed | |
| itr 51000/1000000 | loss 0.004326 | test 0.001191 | lr 2.98e-02 | 78 it/s | eta 203m | 10.9m elapsed | |
| itr 52000/1000000 | loss 0.001498 | test 0.002715 | lr 2.98e-02 | 78 it/s | eta 202m | 11.1m elapsed | |
| itr 53000/1000000 | loss 0.000350 | test 0.000242 | lr 2.98e-02 | 78 it/s | eta 202m | 11.3m elapsed | |
| itr 54000/1000000 | loss 0.000089 | test 0.000063 | lr 2.98e-02 | 78 it/s | eta 202m | 11.5m elapsed | |
| itr 55000/1000000 | loss 0.000102 | test 0.001409 | lr 2.98e-02 | 78 it/s | eta 201m | 11.7m elapsed | |
| itr 56000/1000000 | loss 0.000082 | test 0.000156 | lr 2.98e-02 | 78 it/s | eta 201m | 11.9m elapsed | |
| itr 57000/1000000 | loss 0.001933 | test 0.001632 | lr 2.98e-02 | 79 it/s | eta 200m | 12.1m elapsed | |
| itr 58000/1000000 | loss 0.000241 | test 0.000026 | lr 2.98e-02 | 79 it/s | eta 200m | 12.3m elapsed | |
| itr 59000/1000000 | loss 0.000508 | test 0.001648 | lr 2.97e-02 | 79 it/s | eta 199m | 12.5m elapsed | |
| itr 60000/1000000 | loss 0.001071 | test 0.000752 | lr 2.97e-02 | 79 it/s | eta 199m | 12.7m elapsed | |
| itr 61000/1000000 | loss 0.001072 | test 0.000010 | lr 2.97e-02 | 79 it/s | eta 198m | 12.9m elapsed | |
| itr 62000/1000000 | loss 0.000090 | test 0.002160 | lr 2.97e-02 | 79 it/s | eta 198m | 13.1m elapsed | |
| itr 63000/1000000 | loss 0.000355 | test 0.000303 | lr 2.97e-02 | 79 it/s | eta 198m | 13.3m elapsed | |
| itr 64000/1000000 | loss 0.001284 | test 0.001136 | lr 2.97e-02 | 79 it/s | eta 197m | 13.5m elapsed | |
| itr 65000/1000000 | loss 0.000183 | test 0.000309 | lr 2.97e-02 | 79 it/s | eta 197m | 13.7m elapsed | |
| itr 66000/1000000 | loss 0.000730 | test 0.000023 | lr 2.97e-02 | 79 it/s | eta 197m | 13.9m elapsed | |
| itr 67000/1000000 | loss 0.000374 | test 0.000109 | lr 2.97e-02 | 79 it/s | eta 197m | 14.1m elapsed | |
| itr 68000/1000000 | loss 0.003656 | test 0.000200 | lr 2.97e-02 | 79 it/s | eta 196m | 14.3m elapsed | |
| itr 69000/1000000 | loss 0.001050 | test 0.000247 | lr 2.97e-02 | 79 it/s | eta 196m | 14.5m elapsed | |
| itr 70000/1000000 | loss 0.001332 | test 0.000879 | lr 2.96e-02 | 79 it/s | eta 196m | 14.7m elapsed | |
| itr 71000/1000000 | loss 0.000012 | test 0.000023 | lr 2.96e-02 | 79 it/s | eta 195m | 14.9m elapsed | |
| itr 72000/1000000 | loss 0.002846 | test 0.000880 | lr 2.96e-02 | 79 it/s | eta 195m | 15.1m elapsed | |
| itr 73000/1000000 | loss 0.000577 | test 0.000246 | lr 2.96e-02 | 79 it/s | eta 195m | 15.3m elapsed | |
| itr 74000/1000000 | loss 0.000341 | test 0.000132 | lr 2.96e-02 | 79 it/s | eta 194m | 15.5m elapsed | |
| itr 75000/1000000 | loss 0.000055 | test 0.000034 | lr 2.96e-02 | 79 it/s | eta 194m | 15.7m elapsed | |
| itr 76000/1000000 | loss 0.000984 | test 0.000558 | lr 2.96e-02 | 79 it/s | eta 194m | 15.9m elapsed | |
| itr 77000/1000000 | loss 0.000227 | test 0.001681 | lr 2.96e-02 | 79 it/s | eta 194m | 16.1m elapsed | |
| itr 78000/1000000 | loss 0.000009 | test 0.000124 | lr 2.96e-02 | 80 it/s | eta 193m | 16.3m elapsed | |
| itr 79000/1000000 | loss 0.003560 | test 0.021294 | lr 2.95e-02 | 80 it/s | eta 193m | 16.6m elapsed | |
| itr 80000/1000000 | loss 0.002076 | test 0.001117 | lr 2.95e-02 | 80 it/s | eta 193m | 16.7m elapsed | |
| itr 81000/1000000 | loss 0.000477 | test 0.000184 | lr 2.95e-02 | 80 it/s | eta 192m | 16.9m elapsed | |
| itr 82000/1000000 | loss 0.000948 | test 0.000348 | lr 2.95e-02 | 80 it/s | eta 192m | 17.1m elapsed | |
| itr 83000/1000000 | loss 0.001042 | test 0.000026 | lr 2.95e-02 | 80 it/s | eta 192m | 17.3m elapsed | |
| itr 84000/1000000 | loss 0.001943 | test 0.001897 | lr 2.95e-02 | 80 it/s | eta 191m | 17.5m elapsed | |
| itr 85000/1000000 | loss 0.000436 | test 0.000033 | lr 2.95e-02 | 80 it/s | eta 191m | 17.7m elapsed | |
| itr 86000/1000000 | loss 0.002676 | test 0.000231 | lr 2.95e-02 | 80 it/s | eta 191m | 17.9m elapsed | |
| itr 87000/1000000 | loss 0.000567 | test 0.001024 | lr 2.94e-02 | 80 it/s | eta 190m | 18.1m elapsed | |
| itr 88000/1000000 | loss 0.002299 | test 0.001491 | lr 2.94e-02 | 80 it/s | eta 190m | 18.3m elapsed | |
| itr 89000/1000000 | loss 0.000309 | test 0.001778 | lr 2.94e-02 | 80 it/s | eta 190m | 18.5m elapsed | |
| itr 90000/1000000 | loss 0.000860 | test 0.002158 | lr 2.94e-02 | 80 it/s | eta 189m | 18.7m elapsed | |
| itr 91000/1000000 | loss 0.002871 | test 0.001636 | lr 2.94e-02 | 80 it/s | eta 189m | 18.9m elapsed | |
| itr 92000/1000000 | loss 0.000362 | test 0.000171 | lr 2.94e-02 | 80 it/s | eta 189m | 19.1m elapsed | |
| itr 93000/1000000 | loss 0.001263 | test 0.000026 | lr 2.94e-02 | 80 it/s | eta 188m | 19.3m elapsed | |
| itr 94000/1000000 | loss 0.004303 | test 0.003471 | lr 2.94e-02 | 80 it/s | eta 188m | 19.5m elapsed | |
| itr 95000/1000000 | loss 0.000029 | test 0.000416 | lr 2.93e-02 | 80 it/s | eta 188m | 19.7m elapsed | |
| itr 96000/1000000 | loss 0.000166 | test 0.000059 | lr 2.93e-02 | 80 it/s | eta 187m | 19.9m elapsed | |
| itr 97000/1000000 | loss 0.001730 | test 0.002646 | lr 2.93e-02 | 80 it/s | eta 187m | 20.1m elapsed | |
| itr 98000/1000000 | loss 0.000939 | test 0.003036 | lr 2.93e-02 | 80 it/s | eta 187m | 20.3m elapsed | |
| itr 99000/1000000 | loss 0.000811 | test 0.000420 | lr 2.93e-02 | 80 it/s | eta 187m | 20.5m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt100000.pt (20.7m) | |
| itr 100000/1000000 | loss 0.000042 | test 0.000123 | lr 2.93e-02 | 81 it/s | eta 186m | 20.7m elapsed | |
| itr 101000/1000000 | loss 0.000997 | test 0.000413 | lr 2.93e-02 | 81 it/s | eta 186m | 20.9m elapsed | |
| itr 102000/1000000 | loss 0.000074 | test 0.000128 | lr 2.92e-02 | 81 it/s | eta 186m | 21.1m elapsed | |
| itr 103000/1000000 | loss 0.001461 | test 0.003949 | lr 2.92e-02 | 81 it/s | eta 185m | 21.3m elapsed | |
| itr 104000/1000000 | loss 0.000122 | test 0.000125 | lr 2.92e-02 | 81 it/s | eta 185m | 21.5m elapsed | |
| itr 105000/1000000 | loss 0.001126 | test 0.000429 | lr 2.92e-02 | 81 it/s | eta 185m | 21.7m elapsed | |
| itr 106000/1000000 | loss 0.000370 | test 0.006013 | lr 2.92e-02 | 81 it/s | eta 185m | 21.9m elapsed | |
| itr 107000/1000000 | loss 0.000967 | test 0.000677 | lr 2.92e-02 | 81 it/s | eta 184m | 22.1m elapsed | |
| itr 108000/1000000 | loss 0.004114 | test 0.010924 | lr 2.91e-02 | 81 it/s | eta 184m | 22.3m elapsed | |
| itr 109000/1000000 | loss 0.006451 | test 0.012045 | lr 2.91e-02 | 81 it/s | eta 184m | 22.5m elapsed | |
| itr 110000/1000000 | loss 0.003176 | test 0.001633 | lr 2.91e-02 | 81 it/s | eta 183m | 22.7m elapsed | |
| itr 111000/1000000 | loss 0.005331 | test 0.004955 | lr 2.91e-02 | 81 it/s | eta 183m | 22.9m elapsed | |
| itr 112000/1000000 | loss 0.001128 | test 0.000149 | lr 2.91e-02 | 81 it/s | eta 183m | 23.1m elapsed | |
| itr 113000/1000000 | loss 0.002038 | test 0.002655 | lr 2.91e-02 | 81 it/s | eta 183m | 23.3m elapsed | |
| itr 114000/1000000 | loss 0.003951 | test 0.000380 | lr 2.91e-02 | 81 it/s | eta 183m | 23.5m elapsed | |
| itr 115000/1000000 | loss 0.001294 | test 0.001591 | lr 2.90e-02 | 81 it/s | eta 182m | 23.7m elapsed | |
| itr 116000/1000000 | loss 0.008529 | test 0.008689 | lr 2.90e-02 | 81 it/s | eta 182m | 23.9m elapsed | |
| itr 117000/1000000 | loss 0.001240 | test 0.000646 | lr 2.90e-02 | 81 it/s | eta 182m | 24.1m elapsed | |
| itr 118000/1000000 | loss 0.038919 | test 0.057222 | lr 2.90e-02 | 81 it/s | eta 181m | 24.3m elapsed | |
| itr 119000/1000000 | loss 0.006452 | test 0.007227 | lr 2.90e-02 | 81 it/s | eta 181m | 24.5m elapsed | |
| itr 120000/1000000 | loss 0.003611 | test 0.000872 | lr 2.89e-02 | 81 it/s | eta 181m | 24.7m elapsed | |
| itr 121000/1000000 | loss 0.005444 | test 0.005751 | lr 2.89e-02 | 81 it/s | eta 181m | 24.9m elapsed | |
| itr 122000/1000000 | loss 0.010785 | test 0.008435 | lr 2.89e-02 | 81 it/s | eta 180m | 25.1m elapsed | |
| itr 123000/1000000 | loss 0.050315 | test 0.047582 | lr 2.89e-02 | 81 it/s | eta 180m | 25.3m elapsed | |
| itr 124000/1000000 | loss 0.005141 | test 0.002235 | lr 2.89e-02 | 81 it/s | eta 180m | 25.5m elapsed | |
| itr 125000/1000000 | loss 0.008586 | test 0.011863 | lr 2.89e-02 | 81 it/s | eta 180m | 25.6m elapsed | |
| itr 126000/1000000 | loss 0.023902 | test 0.017610 | lr 2.88e-02 | 81 it/s | eta 179m | 25.8m elapsed | |
| itr 127000/1000000 | loss 0.015655 | test 0.010482 | lr 2.88e-02 | 81 it/s | eta 179m | 26.0m elapsed | |
| itr 128000/1000000 | loss 0.029937 | test 0.035525 | lr 2.88e-02 | 81 it/s | eta 179m | 26.2m elapsed | |
| itr 129000/1000000 | loss 0.013300 | test 0.005939 | lr 2.88e-02 | 81 it/s | eta 178m | 26.4m elapsed | |
| itr 130000/1000000 | loss 0.011156 | test 0.017654 | lr 2.88e-02 | 81 it/s | eta 178m | 26.6m elapsed | |
| itr 131000/1000000 | loss 0.006514 | test 0.008975 | lr 2.88e-02 | 81 it/s | eta 178m | 26.8m elapsed | |
| itr 132000/1000000 | loss 0.023578 | test 0.026947 | lr 2.87e-02 | 81 it/s | eta 178m | 27.0m elapsed | |
| itr 133000/1000000 | loss 0.007581 | test 0.006107 | lr 2.87e-02 | 81 it/s | eta 178m | 27.2m elapsed | |
| itr 134000/1000000 | loss 0.016183 | test 0.013855 | lr 2.87e-02 | 81 it/s | eta 177m | 27.4m elapsed | |
| itr 135000/1000000 | loss 0.018960 | test 0.021221 | lr 2.87e-02 | 81 it/s | eta 177m | 27.6m elapsed | |
| itr 136000/1000000 | loss 0.020757 | test 0.013011 | lr 2.87e-02 | 81 it/s | eta 177m | 27.8m elapsed | |
| itr 137000/1000000 | loss 0.019165 | test 0.017986 | lr 2.86e-02 | 81 it/s | eta 177m | 28.0m elapsed | |
| itr 138000/1000000 | loss 0.008878 | test 0.025497 | lr 2.86e-02 | 81 it/s | eta 176m | 28.2m elapsed | |
| itr 139000/1000000 | loss 0.004245 | test 0.003108 | lr 2.86e-02 | 81 it/s | eta 176m | 28.4m elapsed | |
| itr 140000/1000000 | loss 0.016433 | test 0.009964 | lr 2.86e-02 | 82 it/s | eta 176m | 28.6m elapsed | |
| itr 141000/1000000 | loss 0.002839 | test 0.006362 | lr 2.86e-02 | 82 it/s | eta 176m | 28.8m elapsed | |
| itr 142000/1000000 | loss 0.004898 | test 0.003761 | lr 2.85e-02 | 82 it/s | eta 175m | 29.0m elapsed | |
| itr 143000/1000000 | loss 0.011203 | test 0.007850 | lr 2.85e-02 | 82 it/s | eta 175m | 29.2m elapsed | |
| itr 144000/1000000 | loss 0.003987 | test 0.005661 | lr 2.85e-02 | 82 it/s | eta 175m | 29.4m elapsed | |
| itr 145000/1000000 | loss 0.015595 | test 0.009820 | lr 2.85e-02 | 82 it/s | eta 175m | 29.6m elapsed | |
| itr 146000/1000000 | loss 0.006638 | test 0.008791 | lr 2.85e-02 | 82 it/s | eta 174m | 29.8m elapsed | |
| itr 147000/1000000 | loss 0.012278 | test 0.009385 | lr 2.84e-02 | 82 it/s | eta 174m | 30.0m elapsed | |
| itr 148000/1000000 | loss 0.029496 | test 0.032864 | lr 2.84e-02 | 82 it/s | eta 174m | 30.2m elapsed | |
| itr 149000/1000000 | loss 0.002081 | test 0.004195 | lr 2.84e-02 | 82 it/s | eta 174m | 30.4m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt150000.pt (30.6m) | |
| itr 150000/1000000 | loss 0.002631 | test 0.007714 | lr 2.84e-02 | 82 it/s | eta 173m | 30.6m elapsed | |
| itr 151000/1000000 | loss 0.003208 | test 0.002174 | lr 2.83e-02 | 82 it/s | eta 173m | 30.8m elapsed | |
| itr 152000/1000000 | loss 0.004880 | test 0.006382 | lr 2.83e-02 | 82 it/s | eta 173m | 31.0m elapsed | |
| itr 153000/1000000 | loss 0.005067 | test 0.003841 | lr 2.83e-02 | 82 it/s | eta 173m | 31.2m elapsed | |
| itr 154000/1000000 | loss 0.017109 | test 0.007622 | lr 2.83e-02 | 82 it/s | eta 172m | 31.4m elapsed | |
| itr 155000/1000000 | loss 0.004917 | test 0.003196 | lr 2.83e-02 | 82 it/s | eta 172m | 31.6m elapsed | |
| itr 156000/1000000 | loss 0.003128 | test 0.003431 | lr 2.82e-02 | 82 it/s | eta 172m | 31.8m elapsed | |
| itr 157000/1000000 | loss 0.003454 | test 0.003255 | lr 2.82e-02 | 82 it/s | eta 172m | 32.0m elapsed | |
| itr 158000/1000000 | loss 0.001873 | test 0.002244 | lr 2.82e-02 | 82 it/s | eta 172m | 32.2m elapsed | |
| itr 159000/1000000 | loss 0.007337 | test 0.007233 | lr 2.82e-02 | 82 it/s | eta 171m | 32.4m elapsed | |
| itr 160000/1000000 | loss 0.006816 | test 0.004005 | lr 2.81e-02 | 82 it/s | eta 171m | 32.6m elapsed | |
| itr 161000/1000000 | loss 0.028275 | test 0.009158 | lr 2.81e-02 | 82 it/s | eta 171m | 32.8m elapsed | |
| itr 162000/1000000 | loss 0.005242 | test 0.003933 | lr 2.81e-02 | 82 it/s | eta 171m | 33.0m elapsed | |
| itr 163000/1000000 | loss 0.003872 | test 0.002862 | lr 2.81e-02 | 82 it/s | eta 170m | 33.2m elapsed | |
| itr 164000/1000000 | loss 0.001210 | test 0.000838 | lr 2.81e-02 | 82 it/s | eta 170m | 33.4m elapsed | |
| itr 165000/1000000 | loss 0.002098 | test 0.002722 | lr 2.80e-02 | 82 it/s | eta 170m | 33.6m elapsed | |
| itr 166000/1000000 | loss 0.005085 | test 0.007191 | lr 2.80e-02 | 82 it/s | eta 170m | 33.8m elapsed | |
| itr 167000/1000000 | loss 0.002327 | test 0.000908 | lr 2.80e-02 | 82 it/s | eta 169m | 34.0m elapsed | |
| itr 168000/1000000 | loss 0.001695 | test 0.002770 | lr 2.80e-02 | 82 it/s | eta 169m | 34.2m elapsed | |
| itr 169000/1000000 | loss 0.003758 | test 0.008116 | lr 2.79e-02 | 82 it/s | eta 169m | 34.4m elapsed | |
| itr 170000/1000000 | loss 0.001615 | test 0.000453 | lr 2.79e-02 | 82 it/s | eta 169m | 34.6m elapsed | |
| itr 171000/1000000 | loss 0.001692 | test 0.001812 | lr 2.79e-02 | 82 it/s | eta 169m | 34.8m elapsed | |
| itr 172000/1000000 | loss 0.002641 | test 0.001640 | lr 2.79e-02 | 82 it/s | eta 168m | 35.0m elapsed | |
| itr 173000/1000000 | loss 0.004582 | test 0.003639 | lr 2.78e-02 | 82 it/s | eta 168m | 35.2m elapsed | |
| itr 174000/1000000 | loss 0.002548 | test 0.000796 | lr 2.78e-02 | 82 it/s | eta 168m | 35.4m elapsed | |
| itr 175000/1000000 | loss 0.001447 | test 0.000859 | lr 2.78e-02 | 82 it/s | eta 168m | 35.6m elapsed | |
| itr 176000/1000000 | loss 0.002242 | test 0.001543 | lr 2.78e-02 | 82 it/s | eta 167m | 35.8m elapsed | |
| itr 177000/1000000 | loss 0.003811 | test 0.003582 | lr 2.77e-02 | 82 it/s | eta 167m | 36.0m elapsed | |
| itr 178000/1000000 | loss 0.002979 | test 0.001270 | lr 2.77e-02 | 82 it/s | eta 167m | 36.2m elapsed | |
| itr 179000/1000000 | loss 0.001614 | test 0.002595 | lr 2.77e-02 | 82 it/s | eta 167m | 36.4m elapsed | |
| itr 180000/1000000 | loss 0.015684 | test 0.011610 | lr 2.77e-02 | 82 it/s | eta 167m | 36.6m elapsed | |
| itr 181000/1000000 | loss 0.004004 | test 0.003277 | lr 2.76e-02 | 82 it/s | eta 166m | 36.8m elapsed | |
| itr 182000/1000000 | loss 0.001806 | test 0.000656 | lr 2.76e-02 | 82 it/s | eta 166m | 37.0m elapsed | |
| itr 183000/1000000 | loss 0.001988 | test 0.001749 | lr 2.76e-02 | 82 it/s | eta 166m | 37.2m elapsed | |
| itr 184000/1000000 | loss 0.008320 | test 0.015587 | lr 2.76e-02 | 82 it/s | eta 166m | 37.4m elapsed | |
| itr 185000/1000000 | loss 0.000916 | test 0.000856 | lr 2.75e-02 | 82 it/s | eta 165m | 37.6m elapsed | |
| itr 186000/1000000 | loss 0.000665 | test 0.000248 | lr 2.75e-02 | 82 it/s | eta 165m | 37.8m elapsed | |
| itr 187000/1000000 | loss 0.003239 | test 0.003032 | lr 2.75e-02 | 82 it/s | eta 165m | 38.0m elapsed | |
| itr 188000/1000000 | loss 0.002974 | test 0.005697 | lr 2.75e-02 | 82 it/s | eta 165m | 38.2m elapsed | |
| itr 189000/1000000 | loss 0.002773 | test 0.004186 | lr 2.74e-02 | 82 it/s | eta 165m | 38.4m elapsed | |
| itr 190000/1000000 | loss 0.007559 | test 0.006253 | lr 2.74e-02 | 82 it/s | eta 164m | 38.6m elapsed | |
| itr 191000/1000000 | loss 0.008998 | test 0.008615 | lr 2.74e-02 | 82 it/s | eta 164m | 38.8m elapsed | |
| itr 192000/1000000 | loss 0.010976 | test 0.019136 | lr 2.74e-02 | 82 it/s | eta 164m | 39.0m elapsed | |
| itr 193000/1000000 | loss 0.010834 | test 0.008247 | lr 2.73e-02 | 82 it/s | eta 164m | 39.2m elapsed | |
| itr 194000/1000000 | loss 0.003224 | test 0.005925 | lr 2.73e-02 | 82 it/s | eta 164m | 39.4m elapsed | |
| itr 195000/1000000 | loss 0.006698 | test 0.004159 | lr 2.73e-02 | 82 it/s | eta 163m | 39.6m elapsed | |
| itr 196000/1000000 | loss 0.001029 | test 0.001724 | lr 2.72e-02 | 82 it/s | eta 163m | 39.8m elapsed | |
| itr 197000/1000000 | loss 0.003048 | test 0.002665 | lr 2.72e-02 | 82 it/s | eta 163m | 40.0m elapsed | |
| itr 198000/1000000 | loss 0.003253 | test 0.002176 | lr 2.72e-02 | 82 it/s | eta 163m | 40.2m elapsed | |
| itr 199000/1000000 | loss 0.003800 | test 0.001298 | lr 2.72e-02 | 82 it/s | eta 162m | 40.4m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt200000.pt (40.6m) | |
| itr 200000/1000000 | loss 0.001823 | test 0.001818 | lr 2.71e-02 | 82 it/s | eta 162m | 40.6m elapsed | |
| itr 201000/1000000 | loss 0.001621 | test 0.017514 | lr 2.71e-02 | 82 it/s | eta 162m | 40.8m elapsed | |
| itr 202000/1000000 | loss 0.003704 | test 0.003754 | lr 2.71e-02 | 82 it/s | eta 162m | 41.0m elapsed | |
| itr 203000/1000000 | loss 0.013148 | test 0.010167 | lr 2.71e-02 | 82 it/s | eta 162m | 41.2m elapsed | |
| itr 204000/1000000 | loss 0.003172 | test 0.001764 | lr 2.70e-02 | 82 it/s | eta 161m | 41.4m elapsed | |
| itr 205000/1000000 | loss 0.002997 | test 0.004906 | lr 2.70e-02 | 82 it/s | eta 161m | 41.6m elapsed | |
| itr 206000/1000000 | loss 0.002944 | test 0.003670 | lr 2.70e-02 | 82 it/s | eta 161m | 41.8m elapsed | |
| itr 207000/1000000 | loss 0.005225 | test 0.003702 | lr 2.69e-02 | 82 it/s | eta 161m | 42.0m elapsed | |
| itr 208000/1000000 | loss 0.011145 | test 0.010410 | lr 2.69e-02 | 82 it/s | eta 161m | 42.2m elapsed | |
| itr 209000/1000000 | loss 0.004208 | test 0.003291 | lr 2.69e-02 | 82 it/s | eta 160m | 42.4m elapsed | |
| itr 210000/1000000 | loss 0.001459 | test 0.001173 | lr 2.69e-02 | 82 it/s | eta 160m | 42.6m elapsed | |
| itr 211000/1000000 | loss 0.001348 | test 0.003247 | lr 2.68e-02 | 82 it/s | eta 160m | 42.8m elapsed | |
| itr 212000/1000000 | loss 0.012473 | test 0.015618 | lr 2.68e-02 | 82 it/s | eta 160m | 43.0m elapsed | |
| itr 213000/1000000 | loss 0.009718 | test 0.010204 | lr 2.68e-02 | 82 it/s | eta 159m | 43.2m elapsed | |
| itr 214000/1000000 | loss 0.003201 | test 0.004934 | lr 2.67e-02 | 82 it/s | eta 159m | 43.4m elapsed | |
| itr 215000/1000000 | loss 0.007161 | test 0.009942 | lr 2.67e-02 | 82 it/s | eta 159m | 43.6m elapsed | |
| itr 216000/1000000 | loss 0.003272 | test 0.004862 | lr 2.67e-02 | 82 it/s | eta 159m | 43.8m elapsed | |
| itr 217000/1000000 | loss 0.003876 | test 0.001456 | lr 2.67e-02 | 82 it/s | eta 159m | 44.0m elapsed | |
| itr 218000/1000000 | loss 0.009912 | test 0.014335 | lr 2.66e-02 | 82 it/s | eta 158m | 44.2m elapsed | |
| itr 219000/1000000 | loss 0.006082 | test 0.005790 | lr 2.66e-02 | 82 it/s | eta 158m | 44.4m elapsed | |
| itr 220000/1000000 | loss 0.002029 | test 0.005538 | lr 2.66e-02 | 82 it/s | eta 158m | 44.6m elapsed | |
| itr 221000/1000000 | loss 0.006171 | test 0.008454 | lr 2.65e-02 | 82 it/s | eta 158m | 44.8m elapsed | |
| itr 222000/1000000 | loss 0.002695 | test 0.001557 | lr 2.65e-02 | 82 it/s | eta 158m | 45.0m elapsed | |
| itr 223000/1000000 | loss 0.003136 | test 0.003158 | lr 2.65e-02 | 82 it/s | eta 157m | 45.2m elapsed | |
| itr 224000/1000000 | loss 0.003822 | test 0.003144 | lr 2.64e-02 | 82 it/s | eta 157m | 45.4m elapsed | |
| itr 225000/1000000 | loss 0.004907 | test 0.003249 | lr 2.64e-02 | 82 it/s | eta 157m | 45.6m elapsed | |
| itr 226000/1000000 | loss 0.001804 | test 0.003829 | lr 2.64e-02 | 82 it/s | eta 157m | 45.8m elapsed | |
| itr 227000/1000000 | loss 0.001066 | test 0.001487 | lr 2.63e-02 | 82 it/s | eta 157m | 46.0m elapsed | |
| itr 228000/1000000 | loss 0.003519 | test 0.003042 | lr 2.63e-02 | 82 it/s | eta 157m | 46.2m elapsed | |
| itr 229000/1000000 | loss 0.009115 | test 0.006111 | lr 2.63e-02 | 82 it/s | eta 156m | 46.4m elapsed | |
| itr 230000/1000000 | loss 0.003807 | test 0.011846 | lr 2.63e-02 | 82 it/s | eta 156m | 46.6m elapsed | |
| itr 231000/1000000 | loss 0.003453 | test 0.002707 | lr 2.62e-02 | 82 it/s | eta 156m | 46.8m elapsed | |
| itr 232000/1000000 | loss 0.005603 | test 0.005990 | lr 2.62e-02 | 82 it/s | eta 156m | 47.0m elapsed | |
| itr 233000/1000000 | loss 0.009672 | test 0.008974 | lr 2.62e-02 | 82 it/s | eta 156m | 47.2m elapsed | |
| itr 234000/1000000 | loss 0.024901 | test 0.024612 | lr 2.61e-02 | 82 it/s | eta 155m | 47.4m elapsed | |
| itr 235000/1000000 | loss 0.009276 | test 0.010469 | lr 2.61e-02 | 82 it/s | eta 155m | 47.6m elapsed | |
| itr 236000/1000000 | loss 0.008352 | test 0.009003 | lr 2.61e-02 | 82 it/s | eta 155m | 47.8m elapsed | |
| itr 237000/1000000 | loss 0.005251 | test 0.007232 | lr 2.60e-02 | 82 it/s | eta 155m | 48.0m elapsed | |
| itr 238000/1000000 | loss 0.003676 | test 0.003861 | lr 2.60e-02 | 82 it/s | eta 154m | 48.2m elapsed | |
| itr 239000/1000000 | loss 0.003811 | test 0.003159 | lr 2.60e-02 | 82 it/s | eta 154m | 48.4m elapsed | |
| itr 240000/1000000 | loss 0.003796 | test 0.007506 | lr 2.59e-02 | 82 it/s | eta 154m | 48.6m elapsed | |
| itr 241000/1000000 | loss 0.007820 | test 0.011314 | lr 2.59e-02 | 82 it/s | eta 154m | 48.8m elapsed | |
| itr 242000/1000000 | loss 0.009549 | test 0.015696 | lr 2.59e-02 | 82 it/s | eta 154m | 49.0m elapsed | |
| itr 243000/1000000 | loss 0.023500 | test 0.032679 | lr 2.58e-02 | 82 it/s | eta 153m | 49.2m elapsed | |
| itr 244000/1000000 | loss 0.011202 | test 0.011364 | lr 2.58e-02 | 82 it/s | eta 153m | 49.4m elapsed | |
| itr 245000/1000000 | loss 0.007761 | test 0.003998 | lr 2.58e-02 | 82 it/s | eta 153m | 49.6m elapsed | |
| itr 246000/1000000 | loss 0.008734 | test 0.003168 | lr 2.57e-02 | 82 it/s | eta 153m | 49.8m elapsed | |
| itr 247000/1000000 | loss 0.005033 | test 0.006757 | lr 2.57e-02 | 82 it/s | eta 153m | 50.0m elapsed | |
| itr 248000/1000000 | loss 0.004062 | test 0.002720 | lr 2.57e-02 | 82 it/s | eta 152m | 50.2m elapsed | |
| itr 249000/1000000 | loss 0.004180 | test 0.004302 | lr 2.56e-02 | 82 it/s | eta 152m | 50.5m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt250000.pt (50.7m) | |
| itr 250000/1000000 | loss 0.004622 | test 0.003972 | lr 2.56e-02 | 82 it/s | eta 152m | 50.7m elapsed | |
| itr 251000/1000000 | loss 0.002773 | test 0.002536 | lr 2.56e-02 | 82 it/s | eta 152m | 50.9m elapsed | |
| itr 252000/1000000 | loss 0.009182 | test 0.007900 | lr 2.55e-02 | 82 it/s | eta 152m | 51.1m elapsed | |
| itr 253000/1000000 | loss 0.012753 | test 0.012442 | lr 2.55e-02 | 82 it/s | eta 151m | 51.3m elapsed | |
| itr 254000/1000000 | loss 0.010537 | test 0.005049 | lr 2.55e-02 | 82 it/s | eta 151m | 51.5m elapsed | |
| itr 255000/1000000 | loss 0.003478 | test 0.002025 | lr 2.54e-02 | 82 it/s | eta 151m | 51.7m elapsed | |
| itr 256000/1000000 | loss 0.002485 | test 0.003211 | lr 2.54e-02 | 82 it/s | eta 151m | 51.8m elapsed | |
| itr 257000/1000000 | loss 0.001314 | test 0.001027 | lr 2.54e-02 | 82 it/s | eta 150m | 52.0m elapsed | |
| itr 258000/1000000 | loss 0.004131 | test 0.004499 | lr 2.53e-02 | 82 it/s | eta 150m | 52.2m elapsed | |
| itr 259000/1000000 | loss 0.004664 | test 0.003065 | lr 2.53e-02 | 82 it/s | eta 150m | 52.4m elapsed | |
| itr 260000/1000000 | loss 0.008717 | test 0.013530 | lr 2.53e-02 | 82 it/s | eta 150m | 52.6m elapsed | |
| itr 261000/1000000 | loss 0.009321 | test 0.016044 | lr 2.52e-02 | 82 it/s | eta 150m | 52.8m elapsed | |
| itr 262000/1000000 | loss 0.004047 | test 0.004220 | lr 2.52e-02 | 82 it/s | eta 149m | 53.0m elapsed | |
| itr 263000/1000000 | loss 0.005600 | test 0.009918 | lr 2.52e-02 | 82 it/s | eta 149m | 53.2m elapsed | |
| itr 264000/1000000 | loss 0.002371 | test 0.002102 | lr 2.51e-02 | 82 it/s | eta 149m | 53.4m elapsed | |
| itr 265000/1000000 | loss 0.012270 | test 0.009734 | lr 2.51e-02 | 82 it/s | eta 149m | 53.6m elapsed | |
| itr 266000/1000000 | loss 0.004520 | test 0.003119 | lr 2.51e-02 | 82 it/s | eta 149m | 53.8m elapsed | |
| itr 267000/1000000 | loss 0.013395 | test 0.014821 | lr 2.50e-02 | 82 it/s | eta 148m | 54.0m elapsed | |
| itr 268000/1000000 | loss 0.003759 | test 0.005636 | lr 2.50e-02 | 82 it/s | eta 148m | 54.2m elapsed | |
| itr 269000/1000000 | loss 0.001641 | test 0.004405 | lr 2.50e-02 | 82 it/s | eta 148m | 54.4m elapsed | |
| itr 270000/1000000 | loss 0.008738 | test 0.004861 | lr 2.49e-02 | 82 it/s | eta 148m | 54.6m elapsed | |
| itr 271000/1000000 | loss 0.004770 | test 0.005884 | lr 2.49e-02 | 82 it/s | eta 147m | 54.8m elapsed | |
| itr 272000/1000000 | loss 0.005810 | test 0.005220 | lr 2.49e-02 | 82 it/s | eta 147m | 55.0m elapsed | |
| itr 273000/1000000 | loss 0.003129 | test 0.003691 | lr 2.48e-02 | 82 it/s | eta 147m | 55.2m elapsed | |
| itr 274000/1000000 | loss 0.001099 | test 0.001402 | lr 2.48e-02 | 82 it/s | eta 147m | 55.4m elapsed | |
| itr 275000/1000000 | loss 0.004440 | test 0.004512 | lr 2.47e-02 | 82 it/s | eta 147m | 55.6m elapsed | |
| itr 276000/1000000 | loss 0.006433 | test 0.009516 | lr 2.47e-02 | 82 it/s | eta 147m | 55.8m elapsed | |
| itr 277000/1000000 | loss 0.003950 | test 0.001949 | lr 2.47e-02 | 82 it/s | eta 146m | 56.1m elapsed | |
| itr 278000/1000000 | loss 0.002606 | test 0.003372 | lr 2.46e-02 | 82 it/s | eta 146m | 56.3m elapsed | |
| itr 279000/1000000 | loss 0.004473 | test 0.002588 | lr 2.46e-02 | 82 it/s | eta 146m | 56.5m elapsed | |
| itr 280000/1000000 | loss 0.004403 | test 0.002590 | lr 2.46e-02 | 82 it/s | eta 146m | 56.7m elapsed | |
| itr 281000/1000000 | loss 0.007548 | test 0.006386 | lr 2.45e-02 | 82 it/s | eta 146m | 56.9m elapsed | |
| itr 282000/1000000 | loss 0.003142 | test 0.002407 | lr 2.45e-02 | 82 it/s | eta 145m | 57.1m elapsed | |
| itr 283000/1000000 | loss 0.006031 | test 0.004549 | lr 2.45e-02 | 82 it/s | eta 145m | 57.3m elapsed | |
| itr 284000/1000000 | loss 0.001923 | test 0.003924 | lr 2.44e-02 | 82 it/s | eta 145m | 57.5m elapsed | |
| itr 285000/1000000 | loss 0.005980 | test 0.005767 | lr 2.44e-02 | 82 it/s | eta 145m | 57.7m elapsed | |
| itr 286000/1000000 | loss 0.006389 | test 0.007830 | lr 2.43e-02 | 82 it/s | eta 144m | 57.9m elapsed | |
| itr 287000/1000000 | loss 0.007211 | test 0.012150 | lr 2.43e-02 | 82 it/s | eta 144m | 58.1m elapsed | |
| itr 288000/1000000 | loss 0.004674 | test 0.005390 | lr 2.43e-02 | 82 it/s | eta 144m | 58.3m elapsed | |
| itr 289000/1000000 | loss 0.006637 | test 0.004767 | lr 2.42e-02 | 82 it/s | eta 144m | 58.5m elapsed | |
| itr 290000/1000000 | loss 0.005097 | test 0.005723 | lr 2.42e-02 | 82 it/s | eta 144m | 58.7m elapsed | |
| itr 291000/1000000 | loss 0.004534 | test 0.008508 | lr 2.42e-02 | 82 it/s | eta 143m | 58.9m elapsed | |
| itr 292000/1000000 | loss 0.002413 | test 0.003464 | lr 2.41e-02 | 82 it/s | eta 143m | 59.1m elapsed | |
| itr 293000/1000000 | loss 0.003167 | test 0.003534 | lr 2.41e-02 | 82 it/s | eta 143m | 59.3m elapsed | |
| itr 294000/1000000 | loss 0.002332 | test 0.005762 | lr 2.40e-02 | 82 it/s | eta 143m | 59.5m elapsed | |
| itr 295000/1000000 | loss 0.003024 | test 0.003265 | lr 2.40e-02 | 82 it/s | eta 143m | 59.7m elapsed | |
| itr 296000/1000000 | loss 0.001427 | test 0.006907 | lr 2.40e-02 | 82 it/s | eta 142m | 59.9m elapsed | |
| itr 297000/1000000 | loss 0.001378 | test 0.002446 | lr 2.39e-02 | 82 it/s | eta 142m | 60.1m elapsed | |
| itr 298000/1000000 | loss 0.005329 | test 0.004246 | lr 2.39e-02 | 82 it/s | eta 142m | 60.3m elapsed | |
| itr 299000/1000000 | loss 0.001945 | test 0.001033 | lr 2.39e-02 | 82 it/s | eta 142m | 60.5m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt300000.pt (60.7m) | |
| itr 300000/1000000 | loss 0.008393 | test 0.005631 | lr 2.38e-02 | 82 it/s | eta 142m | 60.7m elapsed | |
| itr 301000/1000000 | loss 0.001491 | test 0.001708 | lr 2.38e-02 | 82 it/s | eta 141m | 60.9m elapsed | |
| itr 302000/1000000 | loss 0.017737 | test 0.021765 | lr 2.37e-02 | 82 it/s | eta 141m | 61.1m elapsed | |
| itr 303000/1000000 | loss 0.001970 | test 0.003681 | lr 2.37e-02 | 82 it/s | eta 141m | 61.3m elapsed | |
| itr 304000/1000000 | loss 0.006412 | test 0.011694 | lr 2.37e-02 | 82 it/s | eta 141m | 61.5m elapsed | |
| itr 305000/1000000 | loss 0.005008 | test 0.003764 | lr 2.36e-02 | 82 it/s | eta 141m | 61.7m elapsed | |
| itr 306000/1000000 | loss 0.002266 | test 0.002578 | lr 2.36e-02 | 82 it/s | eta 140m | 61.9m elapsed | |
| itr 307000/1000000 | loss 0.002737 | test 0.003259 | lr 2.36e-02 | 82 it/s | eta 140m | 62.1m elapsed | |
| itr 308000/1000000 | loss 0.002642 | test 0.001826 | lr 2.35e-02 | 82 it/s | eta 140m | 62.3m elapsed | |
| itr 309000/1000000 | loss 0.005028 | test 0.006778 | lr 2.35e-02 | 82 it/s | eta 140m | 62.5m elapsed | |
| itr 310000/1000000 | loss 0.002294 | test 0.003127 | lr 2.34e-02 | 82 it/s | eta 140m | 62.7m elapsed | |
| itr 311000/1000000 | loss 0.003965 | test 0.002364 | lr 2.34e-02 | 82 it/s | eta 139m | 62.9m elapsed | |
| itr 312000/1000000 | loss 0.005314 | test 0.005365 | lr 2.34e-02 | 82 it/s | eta 139m | 63.1m elapsed | |
| itr 313000/1000000 | loss 0.002483 | test 0.003410 | lr 2.33e-02 | 82 it/s | eta 139m | 63.3m elapsed | |
| itr 314000/1000000 | loss 0.002039 | test 0.004671 | lr 2.33e-02 | 82 it/s | eta 139m | 63.5m elapsed | |
| itr 315000/1000000 | loss 0.001961 | test 0.026695 | lr 2.32e-02 | 82 it/s | eta 139m | 63.7m elapsed | |
| itr 316000/1000000 | loss 0.001036 | test 0.001082 | lr 2.32e-02 | 82 it/s | eta 138m | 63.9m elapsed | |
| itr 317000/1000000 | loss 0.001760 | test 0.003842 | lr 2.32e-02 | 82 it/s | eta 138m | 64.1m elapsed | |
| itr 318000/1000000 | loss 0.001058 | test 0.001051 | lr 2.31e-02 | 82 it/s | eta 138m | 64.3m elapsed | |
| itr 319000/1000000 | loss 0.002107 | test 0.004607 | lr 2.31e-02 | 82 it/s | eta 138m | 64.5m elapsed | |
| itr 320000/1000000 | loss 0.004333 | test 0.000962 | lr 2.30e-02 | 82 it/s | eta 137m | 64.7m elapsed | |
| itr 321000/1000000 | loss 0.004252 | test 0.001845 | lr 2.30e-02 | 82 it/s | eta 137m | 64.9m elapsed | |
| itr 322000/1000000 | loss 0.002340 | test 0.002733 | lr 2.30e-02 | 82 it/s | eta 137m | 65.1m elapsed | |
| itr 323000/1000000 | loss 0.002213 | test 0.001930 | lr 2.29e-02 | 82 it/s | eta 137m | 65.3m elapsed | |
| itr 324000/1000000 | loss 0.012700 | test 0.008354 | lr 2.29e-02 | 82 it/s | eta 137m | 65.5m elapsed | |
| itr 325000/1000000 | loss 0.005515 | test 0.007601 | lr 2.28e-02 | 82 it/s | eta 136m | 65.7m elapsed | |
| itr 326000/1000000 | loss 0.004450 | test 0.005664 | lr 2.28e-02 | 82 it/s | eta 136m | 65.9m elapsed | |
| itr 327000/1000000 | loss 0.003337 | test 0.001621 | lr 2.28e-02 | 82 it/s | eta 136m | 66.1m elapsed | |
| itr 328000/1000000 | loss 0.002961 | test 0.004274 | lr 2.27e-02 | 82 it/s | eta 136m | 66.3m elapsed | |
| itr 329000/1000000 | loss 0.005740 | test 0.006325 | lr 2.27e-02 | 82 it/s | eta 136m | 66.5m elapsed | |
| itr 330000/1000000 | loss 0.003278 | test 0.002075 | lr 2.26e-02 | 82 it/s | eta 135m | 66.7m elapsed | |
| itr 331000/1000000 | loss 0.003894 | test 0.007131 | lr 2.26e-02 | 82 it/s | eta 135m | 66.9m elapsed | |
| itr 332000/1000000 | loss 0.004582 | test 0.001930 | lr 2.26e-02 | 82 it/s | eta 135m | 67.1m elapsed | |
| itr 333000/1000000 | loss 0.002449 | test 0.003576 | lr 2.25e-02 | 82 it/s | eta 135m | 67.3m elapsed | |
| itr 334000/1000000 | loss 0.002173 | test 0.001102 | lr 2.25e-02 | 82 it/s | eta 135m | 67.5m elapsed | |
| itr 335000/1000000 | loss 0.003154 | test 0.002047 | lr 2.24e-02 | 82 it/s | eta 134m | 67.7m elapsed | |
| itr 336000/1000000 | loss 0.003386 | test 0.002801 | lr 2.24e-02 | 82 it/s | eta 134m | 67.9m elapsed | |
| itr 337000/1000000 | loss 0.007896 | test 0.001383 | lr 2.24e-02 | 82 it/s | eta 134m | 68.1m elapsed | |
| itr 338000/1000000 | loss 0.005629 | test 0.005534 | lr 2.23e-02 | 82 it/s | eta 134m | 68.3m elapsed | |
| itr 339000/1000000 | loss 0.004258 | test 0.001614 | lr 2.23e-02 | 82 it/s | eta 134m | 68.5m elapsed | |
| itr 340000/1000000 | loss 0.004461 | test 0.001075 | lr 2.22e-02 | 82 it/s | eta 133m | 68.7m elapsed | |
| itr 341000/1000000 | loss 0.006842 | test 0.005425 | lr 2.22e-02 | 82 it/s | eta 133m | 68.9m elapsed | |
| itr 342000/1000000 | loss 0.003427 | test 0.004023 | lr 2.21e-02 | 82 it/s | eta 133m | 69.1m elapsed | |
| itr 343000/1000000 | loss 0.003179 | test 0.003171 | lr 2.21e-02 | 82 it/s | eta 133m | 69.3m elapsed | |
| itr 344000/1000000 | loss 0.003926 | test 0.003508 | lr 2.21e-02 | 82 it/s | eta 133m | 69.5m elapsed | |
| itr 345000/1000000 | loss 0.005034 | test 0.003905 | lr 2.20e-02 | 82 it/s | eta 132m | 69.7m elapsed | |
| itr 346000/1000000 | loss 0.005603 | test 0.002058 | lr 2.20e-02 | 82 it/s | eta 132m | 69.9m elapsed | |
| itr 347000/1000000 | loss 0.006487 | test 0.005847 | lr 2.19e-02 | 82 it/s | eta 132m | 70.1m elapsed | |
| itr 348000/1000000 | loss 0.005824 | test 0.003656 | lr 2.19e-02 | 82 it/s | eta 132m | 70.3m elapsed | |
| itr 349000/1000000 | loss 0.001822 | test 0.001324 | lr 2.19e-02 | 82 it/s | eta 132m | 70.5m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt350000.pt (70.7m) | |
| itr 350000/1000000 | loss 0.002943 | test 0.004247 | lr 2.18e-02 | 82 it/s | eta 131m | 70.7m elapsed | |
| itr 351000/1000000 | loss 0.004440 | test 0.002581 | lr 2.18e-02 | 82 it/s | eta 131m | 70.9m elapsed | |
| itr 352000/1000000 | loss 0.004287 | test 0.003299 | lr 2.17e-02 | 82 it/s | eta 131m | 71.2m elapsed | |
| itr 353000/1000000 | loss 0.003387 | test 0.004971 | lr 2.17e-02 | 82 it/s | eta 131m | 71.4m elapsed | |
| itr 354000/1000000 | loss 0.002081 | test 0.003832 | lr 2.16e-02 | 82 it/s | eta 131m | 71.6m elapsed | |
| itr 355000/1000000 | loss 0.002156 | test 0.001427 | lr 2.16e-02 | 82 it/s | eta 130m | 71.8m elapsed | |
| itr 356000/1000000 | loss 0.003054 | test 0.002901 | lr 2.16e-02 | 82 it/s | eta 130m | 72.0m elapsed | |
| itr 357000/1000000 | loss 0.003243 | test 0.004625 | lr 2.15e-02 | 82 it/s | eta 130m | 72.2m elapsed | |
| itr 358000/1000000 | loss 0.001294 | test 0.003649 | lr 2.15e-02 | 82 it/s | eta 130m | 72.4m elapsed | |
| itr 359000/1000000 | loss 0.001442 | test 0.001687 | lr 2.14e-02 | 82 it/s | eta 130m | 72.6m elapsed | |
| itr 360000/1000000 | loss 0.003954 | test 0.003179 | lr 2.14e-02 | 82 it/s | eta 129m | 72.8m elapsed | |
| itr 361000/1000000 | loss 0.000920 | test 0.002678 | lr 2.13e-02 | 82 it/s | eta 129m | 73.1m elapsed | |
| itr 362000/1000000 | loss 0.002287 | test 0.001438 | lr 2.13e-02 | 82 it/s | eta 129m | 73.3m elapsed | |
| itr 363000/1000000 | loss 0.002803 | test 0.003817 | lr 2.13e-02 | 82 it/s | eta 129m | 73.5m elapsed | |
| itr 364000/1000000 | loss 0.003315 | test 0.002531 | lr 2.12e-02 | 82 it/s | eta 129m | 73.7m elapsed | |
| itr 365000/1000000 | loss 0.002866 | test 0.005081 | lr 2.12e-02 | 82 it/s | eta 129m | 73.9m elapsed | |
| itr 366000/1000000 | loss 0.002767 | test 0.003085 | lr 2.11e-02 | 82 it/s | eta 128m | 74.1m elapsed | |
| itr 367000/1000000 | loss 0.002074 | test 0.001102 | lr 2.11e-02 | 82 it/s | eta 128m | 74.3m elapsed | |
| itr 368000/1000000 | loss 0.002023 | test 0.001736 | lr 2.10e-02 | 82 it/s | eta 128m | 74.5m elapsed | |
| itr 369000/1000000 | loss 0.009654 | test 0.007417 | lr 2.10e-02 | 82 it/s | eta 128m | 74.7m elapsed | |
| itr 370000/1000000 | loss 0.001866 | test 0.001661 | lr 2.10e-02 | 82 it/s | eta 128m | 74.9m elapsed | |
| itr 371000/1000000 | loss 0.001759 | test 0.001733 | lr 2.09e-02 | 82 it/s | eta 127m | 75.1m elapsed | |
| itr 372000/1000000 | loss 0.001348 | test 0.001445 | lr 2.09e-02 | 82 it/s | eta 127m | 75.4m elapsed | |
| itr 373000/1000000 | loss 0.001025 | test 0.001139 | lr 2.08e-02 | 82 it/s | eta 127m | 75.6m elapsed | |
| itr 374000/1000000 | loss 0.003717 | test 0.004814 | lr 2.08e-02 | 82 it/s | eta 127m | 75.8m elapsed | |
| itr 375000/1000000 | loss 0.001430 | test 0.002371 | lr 2.07e-02 | 82 it/s | eta 127m | 76.0m elapsed | |
| itr 376000/1000000 | loss 0.002895 | test 0.005415 | lr 2.07e-02 | 82 it/s | eta 126m | 76.2m elapsed | |
| itr 377000/1000000 | loss 0.001138 | test 0.000901 | lr 2.07e-02 | 82 it/s | eta 126m | 76.4m elapsed | |
| itr 378000/1000000 | loss 0.003841 | test 0.001460 | lr 2.06e-02 | 82 it/s | eta 126m | 76.6m elapsed | |
| itr 379000/1000000 | loss 0.002149 | test 0.001826 | lr 2.06e-02 | 82 it/s | eta 126m | 76.8m elapsed | |
| itr 380000/1000000 | loss 0.001728 | test 0.001090 | lr 2.05e-02 | 82 it/s | eta 126m | 77.0m elapsed | |
| itr 381000/1000000 | loss 0.000814 | test 0.001208 | lr 2.05e-02 | 82 it/s | eta 125m | 77.2m elapsed | |
| itr 382000/1000000 | loss 0.001328 | test 0.000395 | lr 2.04e-02 | 82 it/s | eta 125m | 77.4m elapsed | |
| itr 383000/1000000 | loss 0.001574 | test 0.001823 | lr 2.04e-02 | 82 it/s | eta 125m | 77.6m elapsed | |
| itr 384000/1000000 | loss 0.003327 | test 0.000766 | lr 2.04e-02 | 82 it/s | eta 125m | 77.8m elapsed | |
| itr 385000/1000000 | loss 0.001453 | test 0.000297 | lr 2.03e-02 | 82 it/s | eta 125m | 78.0m elapsed | |
| itr 386000/1000000 | loss 0.001908 | test 0.001323 | lr 2.03e-02 | 82 it/s | eta 124m | 78.2m elapsed | |
| itr 387000/1000000 | loss 0.001288 | test 0.002674 | lr 2.02e-02 | 82 it/s | eta 124m | 78.4m elapsed | |
| itr 388000/1000000 | loss 0.000865 | test 0.001158 | lr 2.02e-02 | 82 it/s | eta 124m | 78.6m elapsed | |
| itr 389000/1000000 | loss 0.001703 | test 0.001250 | lr 2.01e-02 | 82 it/s | eta 124m | 78.8m elapsed | |
| itr 390000/1000000 | loss 0.002844 | test 0.006893 | lr 2.01e-02 | 82 it/s | eta 124m | 79.0m elapsed | |
| itr 391000/1000000 | loss 0.002121 | test 0.003380 | lr 2.00e-02 | 82 it/s | eta 123m | 79.2m elapsed | |
| itr 392000/1000000 | loss 0.000529 | test 0.001308 | lr 2.00e-02 | 82 it/s | eta 123m | 79.4m elapsed | |
| itr 393000/1000000 | loss 0.001570 | test 0.001650 | lr 2.00e-02 | 82 it/s | eta 123m | 79.6m elapsed | |
| itr 394000/1000000 | loss 0.001720 | test 0.001071 | lr 1.99e-02 | 82 it/s | eta 123m | 79.8m elapsed | |
| itr 395000/1000000 | loss 0.002819 | test 0.001358 | lr 1.99e-02 | 82 it/s | eta 123m | 80.0m elapsed | |
| itr 396000/1000000 | loss 0.002082 | test 0.001268 | lr 1.98e-02 | 82 it/s | eta 122m | 80.2m elapsed | |
| itr 397000/1000000 | loss 0.004446 | test 0.005295 | lr 1.98e-02 | 82 it/s | eta 122m | 80.4m elapsed | |
| itr 398000/1000000 | loss 0.002277 | test 0.001181 | lr 1.97e-02 | 82 it/s | eta 122m | 80.6m elapsed | |
| itr 399000/1000000 | loss 0.001510 | test 0.000737 | lr 1.97e-02 | 82 it/s | eta 122m | 80.8m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt400000.pt (81.1m) | |
| itr 400000/1000000 | loss 0.001994 | test 0.000783 | lr 1.96e-02 | 82 it/s | eta 122m | 81.1m elapsed | |
| itr 401000/1000000 | loss 0.000946 | test 0.000425 | lr 1.96e-02 | 82 it/s | eta 121m | 81.3m elapsed | |
| itr 402000/1000000 | loss 0.001247 | test 0.000268 | lr 1.96e-02 | 82 it/s | eta 121m | 81.6m elapsed | |
| itr 403000/1000000 | loss 0.000218 | test 0.000423 | lr 1.95e-02 | 82 it/s | eta 121m | 81.8m elapsed | |
| itr 404000/1000000 | loss 0.000737 | test 0.002447 | lr 1.95e-02 | 82 it/s | eta 121m | 82.0m elapsed | |
| itr 405000/1000000 | loss 0.002025 | test 0.001079 | lr 1.94e-02 | 82 it/s | eta 121m | 82.3m elapsed | |
| itr 406000/1000000 | loss 0.001292 | test 0.003574 | lr 1.94e-02 | 82 it/s | eta 121m | 82.5m elapsed | |
| itr 407000/1000000 | loss 0.007450 | test 0.002135 | lr 1.93e-02 | 82 it/s | eta 121m | 82.8m elapsed | |
| itr 408000/1000000 | loss 0.001800 | test 0.000893 | lr 1.93e-02 | 82 it/s | eta 120m | 83.0m elapsed | |
| itr 409000/1000000 | loss 0.001514 | test 0.002052 | lr 1.92e-02 | 82 it/s | eta 120m | 83.2m elapsed | |
| itr 410000/1000000 | loss 0.000888 | test 0.000453 | lr 1.92e-02 | 82 it/s | eta 120m | 83.5m elapsed | |
| itr 411000/1000000 | loss 0.002151 | test 0.000888 | lr 1.91e-02 | 82 it/s | eta 120m | 83.7m elapsed | |
| itr 412000/1000000 | loss 0.002244 | test 0.004064 | lr 1.91e-02 | 82 it/s | eta 120m | 83.9m elapsed | |
| itr 413000/1000000 | loss 0.002123 | test 0.001336 | lr 1.91e-02 | 82 it/s | eta 120m | 84.2m elapsed | |
| itr 414000/1000000 | loss 0.001692 | test 0.002456 | lr 1.90e-02 | 82 it/s | eta 119m | 84.4m elapsed | |
| itr 415000/1000000 | loss 0.000447 | test 0.001131 | lr 1.90e-02 | 82 it/s | eta 119m | 84.6m elapsed | |
| itr 416000/1000000 | loss 0.001235 | test 0.000649 | lr 1.89e-02 | 82 it/s | eta 119m | 84.9m elapsed | |
| itr 417000/1000000 | loss 0.000872 | test 0.002683 | lr 1.89e-02 | 82 it/s | eta 119m | 85.1m elapsed | |
| itr 418000/1000000 | loss 0.000452 | test 0.001868 | lr 1.88e-02 | 82 it/s | eta 119m | 85.4m elapsed | |
| itr 419000/1000000 | loss 0.000650 | test 0.001383 | lr 1.88e-02 | 82 it/s | eta 119m | 85.6m elapsed | |
| itr 420000/1000000 | loss 0.001727 | test 0.001388 | lr 1.87e-02 | 82 it/s | eta 119m | 85.8m elapsed | |
| itr 421000/1000000 | loss 0.000855 | test 0.001414 | lr 1.87e-02 | 82 it/s | eta 118m | 86.1m elapsed | |
| itr 422000/1000000 | loss 0.001414 | test 0.001568 | lr 1.86e-02 | 81 it/s | eta 118m | 86.3m elapsed | |
| itr 423000/1000000 | loss 0.000784 | test 0.001099 | lr 1.86e-02 | 81 it/s | eta 118m | 86.5m elapsed | |
| itr 424000/1000000 | loss 0.000452 | test 0.000688 | lr 1.86e-02 | 81 it/s | eta 118m | 86.8m elapsed | |
| itr 425000/1000000 | loss 0.001131 | test 0.004156 | lr 1.85e-02 | 81 it/s | eta 118m | 87.0m elapsed | |
| itr 426000/1000000 | loss 0.001006 | test 0.000503 | lr 1.85e-02 | 81 it/s | eta 118m | 87.3m elapsed | |
| itr 427000/1000000 | loss 0.000715 | test 0.000196 | lr 1.84e-02 | 81 it/s | eta 117m | 87.5m elapsed | |
| itr 428000/1000000 | loss 0.001780 | test 0.001432 | lr 1.84e-02 | 81 it/s | eta 117m | 87.8m elapsed | |
| itr 429000/1000000 | loss 0.000568 | test 0.000459 | lr 1.83e-02 | 81 it/s | eta 117m | 88.0m elapsed | |
| itr 430000/1000000 | loss 0.002160 | test 0.001071 | lr 1.83e-02 | 81 it/s | eta 117m | 88.3m elapsed | |
| itr 431000/1000000 | loss 0.001142 | test 0.001103 | lr 1.82e-02 | 81 it/s | eta 117m | 88.5m elapsed | |
| itr 432000/1000000 | loss 0.001411 | test 0.000170 | lr 1.82e-02 | 81 it/s | eta 117m | 88.8m elapsed | |
| itr 433000/1000000 | loss 0.000884 | test 0.002708 | lr 1.81e-02 | 81 it/s | eta 117m | 89.0m elapsed | |
| itr 434000/1000000 | loss 0.000296 | test 0.001217 | lr 1.81e-02 | 81 it/s | eta 116m | 89.2m elapsed | |
| itr 435000/1000000 | loss 0.002236 | test 0.000242 | lr 1.80e-02 | 81 it/s | eta 116m | 89.5m elapsed | |
| itr 436000/1000000 | loss 0.001061 | test 0.001034 | lr 1.80e-02 | 81 it/s | eta 116m | 89.7m elapsed | |
| itr 437000/1000000 | loss 0.001255 | test 0.001206 | lr 1.80e-02 | 81 it/s | eta 116m | 89.9m elapsed | |
| itr 438000/1000000 | loss 0.001961 | test 0.000200 | lr 1.79e-02 | 81 it/s | eta 116m | 90.2m elapsed | |
| itr 439000/1000000 | loss 0.001840 | test 0.004009 | lr 1.79e-02 | 81 it/s | eta 116m | 90.4m elapsed | |
| itr 440000/1000000 | loss 0.006895 | test 0.003418 | lr 1.78e-02 | 81 it/s | eta 115m | 90.6m elapsed | |
| itr 441000/1000000 | loss 0.002611 | test 0.002545 | lr 1.78e-02 | 81 it/s | eta 115m | 90.9m elapsed | |
| itr 442000/1000000 | loss 0.001139 | test 0.004871 | lr 1.77e-02 | 81 it/s | eta 115m | 91.1m elapsed | |
| itr 443000/1000000 | loss 0.001616 | test 0.001309 | lr 1.77e-02 | 81 it/s | eta 115m | 91.4m elapsed | |
| itr 444000/1000000 | loss 0.000858 | test 0.000633 | lr 1.76e-02 | 81 it/s | eta 115m | 91.6m elapsed | |
| itr 445000/1000000 | loss 0.000600 | test 0.000687 | lr 1.76e-02 | 81 it/s | eta 115m | 91.9m elapsed | |
| itr 446000/1000000 | loss 0.000983 | test 0.000757 | lr 1.75e-02 | 81 it/s | eta 114m | 92.1m elapsed | |
| itr 447000/1000000 | loss 0.001356 | test 0.001997 | lr 1.75e-02 | 81 it/s | eta 114m | 92.4m elapsed | |
| itr 448000/1000000 | loss 0.000458 | test 0.001802 | lr 1.74e-02 | 81 it/s | eta 114m | 92.6m elapsed | |
| itr 449000/1000000 | loss 0.002622 | test 0.002531 | lr 1.74e-02 | 81 it/s | eta 114m | 92.8m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt450000.pt (93.1m) | |
| itr 450000/1000000 | loss 0.000394 | test 0.000679 | lr 1.74e-02 | 81 it/s | eta 114m | 93.1m elapsed | |
| itr 451000/1000000 | loss 0.001084 | test 0.001668 | lr 1.73e-02 | 81 it/s | eta 114m | 93.3m elapsed | |
| itr 452000/1000000 | loss 0.000904 | test 0.000887 | lr 1.73e-02 | 81 it/s | eta 113m | 93.5m elapsed | |
| itr 453000/1000000 | loss 0.000559 | test 0.001262 | lr 1.72e-02 | 81 it/s | eta 113m | 93.8m elapsed | |
| itr 454000/1000000 | loss 0.001658 | test 0.001047 | lr 1.72e-02 | 80 it/s | eta 113m | 94.0m elapsed | |
| itr 455000/1000000 | loss 0.001163 | test 0.000565 | lr 1.71e-02 | 80 it/s | eta 113m | 94.3m elapsed | |
| itr 456000/1000000 | loss 0.001217 | test 0.000588 | lr 1.71e-02 | 80 it/s | eta 113m | 94.5m elapsed | |
| itr 457000/1000000 | loss 0.001340 | test 0.000162 | lr 1.70e-02 | 80 it/s | eta 113m | 94.8m elapsed | |
| itr 458000/1000000 | loss 0.001003 | test 0.000660 | lr 1.70e-02 | 80 it/s | eta 112m | 95.0m elapsed | |
| itr 459000/1000000 | loss 0.000628 | test 0.000844 | lr 1.69e-02 | 80 it/s | eta 112m | 95.2m elapsed | |
| itr 460000/1000000 | loss 0.001609 | test 0.000969 | lr 1.69e-02 | 80 it/s | eta 112m | 95.5m elapsed | |
| itr 461000/1000000 | loss 0.000812 | test 0.000869 | lr 1.68e-02 | 80 it/s | eta 112m | 95.7m elapsed | |
| itr 462000/1000000 | loss 0.001097 | test 0.000646 | lr 1.68e-02 | 80 it/s | eta 112m | 96.0m elapsed | |
| itr 463000/1000000 | loss 0.001947 | test 0.002745 | lr 1.67e-02 | 80 it/s | eta 112m | 96.2m elapsed | |
| itr 464000/1000000 | loss 0.000358 | test 0.000239 | lr 1.67e-02 | 80 it/s | eta 111m | 96.4m elapsed | |
| itr 465000/1000000 | loss 0.000280 | test 0.000431 | lr 1.67e-02 | 80 it/s | eta 111m | 96.7m elapsed | |
| itr 466000/1000000 | loss 0.001872 | test 0.002631 | lr 1.66e-02 | 80 it/s | eta 111m | 96.9m elapsed | |
| itr 467000/1000000 | loss 0.000974 | test 0.001422 | lr 1.66e-02 | 80 it/s | eta 111m | 97.1m elapsed | |
| itr 468000/1000000 | loss 0.002256 | test 0.000342 | lr 1.65e-02 | 80 it/s | eta 111m | 97.4m elapsed | |
| itr 469000/1000000 | loss 0.001306 | test 0.000591 | lr 1.65e-02 | 80 it/s | eta 111m | 97.6m elapsed | |
| itr 470000/1000000 | loss 0.000744 | test 0.000749 | lr 1.64e-02 | 80 it/s | eta 110m | 97.9m elapsed | |
| itr 471000/1000000 | loss 0.001694 | test 0.000199 | lr 1.64e-02 | 80 it/s | eta 110m | 98.1m elapsed | |
| itr 472000/1000000 | loss 0.000957 | test 0.000876 | lr 1.63e-02 | 80 it/s | eta 110m | 98.4m elapsed | |
| itr 473000/1000000 | loss 0.000589 | test 0.000817 | lr 1.63e-02 | 80 it/s | eta 110m | 98.6m elapsed | |
| itr 474000/1000000 | loss 0.001815 | test 0.001019 | lr 1.62e-02 | 80 it/s | eta 110m | 98.9m elapsed | |
| itr 475000/1000000 | loss 0.001427 | test 0.000435 | lr 1.62e-02 | 80 it/s | eta 110m | 99.1m elapsed | |
| itr 476000/1000000 | loss 0.000278 | test 0.000804 | lr 1.61e-02 | 80 it/s | eta 109m | 99.4m elapsed | |
| itr 477000/1000000 | loss 0.001003 | test 0.000238 | lr 1.61e-02 | 80 it/s | eta 109m | 99.6m elapsed | |
| itr 478000/1000000 | loss 0.001878 | test 0.000767 | lr 1.60e-02 | 80 it/s | eta 109m | 99.8m elapsed | |
| itr 479000/1000000 | loss 0.000334 | test 0.000511 | lr 1.60e-02 | 80 it/s | eta 109m | 100.1m elapsed | |
| itr 480000/1000000 | loss 0.001118 | test 0.000247 | lr 1.59e-02 | 80 it/s | eta 109m | 100.3m elapsed | |
| itr 481000/1000000 | loss 0.001543 | test 0.003521 | lr 1.59e-02 | 80 it/s | eta 109m | 100.6m elapsed | |
| itr 482000/1000000 | loss 0.000814 | test 0.000069 | lr 1.59e-02 | 80 it/s | eta 108m | 100.8m elapsed | |
| itr 483000/1000000 | loss 0.000635 | test 0.000911 | lr 1.58e-02 | 80 it/s | eta 108m | 101.1m elapsed | |
| itr 484000/1000000 | loss 0.000328 | test 0.000193 | lr 1.58e-02 | 80 it/s | eta 108m | 101.3m elapsed | |
| itr 485000/1000000 | loss 0.002054 | test 0.000552 | lr 1.57e-02 | 80 it/s | eta 108m | 101.6m elapsed | |
| itr 486000/1000000 | loss 0.001282 | test 0.001324 | lr 1.57e-02 | 80 it/s | eta 108m | 101.8m elapsed | |
| itr 487000/1000000 | loss 0.000927 | test 0.000404 | lr 1.56e-02 | 80 it/s | eta 108m | 102.1m elapsed | |
| itr 488000/1000000 | loss 0.001547 | test 0.001409 | lr 1.56e-02 | 79 it/s | eta 107m | 102.3m elapsed | |
| itr 489000/1000000 | loss 0.001009 | test 0.000429 | lr 1.55e-02 | 79 it/s | eta 107m | 102.6m elapsed | |
| itr 490000/1000000 | loss 0.000391 | test 0.001136 | lr 1.55e-02 | 79 it/s | eta 107m | 102.8m elapsed | |
| itr 491000/1000000 | loss 0.001719 | test 0.000709 | lr 1.54e-02 | 79 it/s | eta 107m | 103.1m elapsed | |
| itr 492000/1000000 | loss 0.000929 | test 0.000274 | lr 1.54e-02 | 79 it/s | eta 107m | 103.3m elapsed | |
| itr 493000/1000000 | loss 0.000688 | test 0.000416 | lr 1.53e-02 | 79 it/s | eta 106m | 103.5m elapsed | |
| itr 494000/1000000 | loss 0.001212 | test 0.000492 | lr 1.53e-02 | 79 it/s | eta 106m | 103.8m elapsed | |
| itr 495000/1000000 | loss 0.000578 | test 0.000665 | lr 1.52e-02 | 79 it/s | eta 106m | 104.0m elapsed | |
| itr 496000/1000000 | loss 0.000660 | test 0.001143 | lr 1.52e-02 | 79 it/s | eta 106m | 104.3m elapsed | |
| itr 497000/1000000 | loss 0.000284 | test 0.002093 | lr 1.51e-02 | 79 it/s | eta 106m | 104.5m elapsed | |
| itr 498000/1000000 | loss 0.000990 | test 0.002114 | lr 1.51e-02 | 79 it/s | eta 106m | 104.8m elapsed | |
| itr 499000/1000000 | loss 0.000528 | test 0.002038 | lr 1.51e-02 | 79 it/s | eta 105m | 105.0m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt500000.pt (105.3m) | |
| itr 500000/1000000 | loss 0.001289 | test 0.000800 | lr 1.50e-02 | 79 it/s | eta 105m | 105.3m elapsed | |
| itr 501000/1000000 | loss 0.000646 | test 0.000287 | lr 1.50e-02 | 79 it/s | eta 105m | 105.5m elapsed | |
| itr 502000/1000000 | loss 0.001036 | test 0.000400 | lr 1.49e-02 | 79 it/s | eta 105m | 105.7m elapsed | |
| itr 503000/1000000 | loss 0.000451 | test 0.001039 | lr 1.49e-02 | 79 it/s | eta 105m | 106.0m elapsed | |
| itr 504000/1000000 | loss 0.000847 | test 0.002259 | lr 1.48e-02 | 79 it/s | eta 105m | 106.2m elapsed | |
| itr 505000/1000000 | loss 0.000371 | test 0.003567 | lr 1.48e-02 | 79 it/s | eta 104m | 106.5m elapsed | |
| itr 506000/1000000 | loss 0.000287 | test 0.000783 | lr 1.47e-02 | 79 it/s | eta 104m | 106.7m elapsed | |
| itr 507000/1000000 | loss 0.000687 | test 0.002631 | lr 1.47e-02 | 79 it/s | eta 104m | 107.0m elapsed | |
| itr 508000/1000000 | loss 0.000593 | test 0.000218 | lr 1.46e-02 | 79 it/s | eta 104m | 107.2m elapsed | |
| itr 509000/1000000 | loss 0.002741 | test 0.000698 | lr 1.46e-02 | 79 it/s | eta 104m | 107.5m elapsed | |
| itr 510000/1000000 | loss 0.001107 | test 0.000161 | lr 1.45e-02 | 79 it/s | eta 103m | 107.7m elapsed | |
| itr 511000/1000000 | loss 0.000504 | test 0.000285 | lr 1.45e-02 | 79 it/s | eta 103m | 108.0m elapsed | |
| itr 512000/1000000 | loss 0.001033 | test 0.000672 | lr 1.44e-02 | 79 it/s | eta 103m | 108.2m elapsed | |
| itr 513000/1000000 | loss 0.000751 | test 0.000351 | lr 1.44e-02 | 79 it/s | eta 103m | 108.4m elapsed | |
| itr 514000/1000000 | loss 0.000751 | test 0.000884 | lr 1.43e-02 | 79 it/s | eta 103m | 108.7m elapsed | |
| itr 515000/1000000 | loss 0.001823 | test 0.000271 | lr 1.43e-02 | 79 it/s | eta 103m | 108.9m elapsed | |
| itr 516000/1000000 | loss 0.000442 | test 0.002058 | lr 1.43e-02 | 79 it/s | eta 102m | 109.2m elapsed | |
| itr 517000/1000000 | loss 0.000415 | test 0.004220 | lr 1.42e-02 | 79 it/s | eta 102m | 109.4m elapsed | |
| itr 518000/1000000 | loss 0.000112 | test 0.000413 | lr 1.42e-02 | 79 it/s | eta 102m | 109.7m elapsed | |
| itr 519000/1000000 | loss 0.001832 | test 0.001179 | lr 1.41e-02 | 79 it/s | eta 102m | 109.9m elapsed | |
| itr 520000/1000000 | loss 0.001624 | test 0.000532 | lr 1.41e-02 | 79 it/s | eta 102m | 110.2m elapsed | |
| itr 521000/1000000 | loss 0.000550 | test 0.000107 | lr 1.40e-02 | 79 it/s | eta 102m | 110.4m elapsed | |
| itr 522000/1000000 | loss 0.000759 | test 0.000480 | lr 1.40e-02 | 79 it/s | eta 101m | 110.7m elapsed | |
| itr 523000/1000000 | loss 0.000576 | test 0.000082 | lr 1.39e-02 | 79 it/s | eta 101m | 110.9m elapsed | |
| itr 524000/1000000 | loss 0.000973 | test 0.000076 | lr 1.39e-02 | 79 it/s | eta 101m | 111.2m elapsed | |
| itr 525000/1000000 | loss 0.001313 | test 0.002751 | lr 1.38e-02 | 78 it/s | eta 101m | 111.5m elapsed | |
| itr 526000/1000000 | loss 0.001020 | test 0.000812 | lr 1.38e-02 | 78 it/s | eta 101m | 111.7m elapsed | |
| itr 527000/1000000 | loss 0.000432 | test 0.001053 | lr 1.37e-02 | 78 it/s | eta 101m | 112.0m elapsed | |
| itr 528000/1000000 | loss 0.000964 | test 0.001371 | lr 1.37e-02 | 78 it/s | eta 100m | 112.3m elapsed | |
| itr 529000/1000000 | loss 0.000604 | test 0.000537 | lr 1.36e-02 | 78 it/s | eta 100m | 112.6m elapsed | |
| itr 530000/1000000 | loss 0.001485 | test 0.000704 | lr 1.36e-02 | 78 it/s | eta 100m | 112.8m elapsed | |
| itr 531000/1000000 | loss 0.000378 | test 0.000817 | lr 1.35e-02 | 78 it/s | eta 100m | 113.1m elapsed | |
| itr 532000/1000000 | loss 0.002302 | test 0.000352 | lr 1.35e-02 | 78 it/s | eta 100m | 113.4m elapsed | |
| itr 533000/1000000 | loss 0.000332 | test 0.001617 | lr 1.35e-02 | 78 it/s | eta 100m | 113.6m elapsed | |
| itr 534000/1000000 | loss 0.000388 | test 0.001803 | lr 1.34e-02 | 78 it/s | eta 99m | 113.9m elapsed | |
| itr 535000/1000000 | loss 0.000488 | test 0.000095 | lr 1.34e-02 | 78 it/s | eta 99m | 114.2m elapsed | |
| itr 536000/1000000 | loss 0.001440 | test 0.001851 | lr 1.33e-02 | 78 it/s | eta 99m | 114.4m elapsed | |
| itr 537000/1000000 | loss 0.000474 | test 0.000094 | lr 1.33e-02 | 78 it/s | eta 99m | 114.7m elapsed | |
| itr 538000/1000000 | loss 0.001204 | test 0.000200 | lr 1.32e-02 | 78 it/s | eta 99m | 115.0m elapsed | |
| itr 539000/1000000 | loss 0.001045 | test 0.001166 | lr 1.32e-02 | 78 it/s | eta 99m | 115.2m elapsed | |
| itr 540000/1000000 | loss 0.002652 | test 0.001490 | lr 1.31e-02 | 78 it/s | eta 98m | 115.5m elapsed | |
| itr 541000/1000000 | loss 0.000687 | test 0.001076 | lr 1.31e-02 | 78 it/s | eta 98m | 115.7m elapsed | |
| itr 542000/1000000 | loss 0.001622 | test 0.000358 | lr 1.30e-02 | 78 it/s | eta 98m | 116.0m elapsed | |
| itr 543000/1000000 | loss 0.000340 | test 0.000547 | lr 1.30e-02 | 78 it/s | eta 98m | 116.2m elapsed | |
| itr 544000/1000000 | loss 0.001383 | test 0.000468 | lr 1.29e-02 | 78 it/s | eta 98m | 116.5m elapsed | |
| itr 545000/1000000 | loss 0.002046 | test 0.000591 | lr 1.29e-02 | 78 it/s | eta 97m | 116.8m elapsed | |
| itr 546000/1000000 | loss 0.001782 | test 0.000103 | lr 1.28e-02 | 78 it/s | eta 97m | 117.0m elapsed | |
| itr 547000/1000000 | loss 0.000538 | test 0.000441 | lr 1.28e-02 | 78 it/s | eta 97m | 117.3m elapsed | |
| itr 548000/1000000 | loss 0.000953 | test 0.000322 | lr 1.28e-02 | 78 it/s | eta 97m | 117.6m elapsed | |
| itr 549000/1000000 | loss 0.000613 | test 0.001711 | lr 1.27e-02 | 78 it/s | eta 97m | 117.8m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt550000.pt (118.1m) | |
| itr 550000/1000000 | loss 0.000916 | test 0.000286 | lr 1.27e-02 | 78 it/s | eta 97m | 118.1m elapsed | |
| itr 551000/1000000 | loss 0.000319 | test 0.000307 | lr 1.26e-02 | 78 it/s | eta 96m | 118.3m elapsed | |
| itr 552000/1000000 | loss 0.000660 | test 0.000476 | lr 1.26e-02 | 78 it/s | eta 96m | 118.6m elapsed | |
| itr 553000/1000000 | loss 0.000482 | test 0.001127 | lr 1.25e-02 | 78 it/s | eta 96m | 118.9m elapsed | |
| itr 554000/1000000 | loss 0.000807 | test 0.002527 | lr 1.25e-02 | 78 it/s | eta 96m | 119.1m elapsed | |
| itr 555000/1000000 | loss 0.003021 | test 0.000635 | lr 1.24e-02 | 77 it/s | eta 96m | 119.4m elapsed | |
| itr 556000/1000000 | loss 0.000457 | test 0.000065 | lr 1.24e-02 | 77 it/s | eta 96m | 119.6m elapsed | |
| itr 557000/1000000 | loss 0.000927 | test 0.000089 | lr 1.23e-02 | 77 it/s | eta 95m | 119.9m elapsed | |
| itr 558000/1000000 | loss 0.000837 | test 0.002987 | lr 1.23e-02 | 77 it/s | eta 95m | 120.1m elapsed | |
| itr 559000/1000000 | loss 0.000522 | test 0.003325 | lr 1.22e-02 | 77 it/s | eta 95m | 120.4m elapsed | |
| itr 560000/1000000 | loss 0.000689 | test 0.000723 | lr 1.22e-02 | 77 it/s | eta 95m | 120.7m elapsed | |
| itr 561000/1000000 | loss 0.000218 | test 0.000460 | lr 1.21e-02 | 77 it/s | eta 95m | 120.9m elapsed | |
| itr 562000/1000000 | loss 0.000607 | test 0.000090 | lr 1.21e-02 | 77 it/s | eta 94m | 121.2m elapsed | |
| itr 563000/1000000 | loss 0.000570 | test 0.000464 | lr 1.21e-02 | 77 it/s | eta 94m | 121.4m elapsed | |
| itr 564000/1000000 | loss 0.000395 | test 0.000428 | lr 1.20e-02 | 77 it/s | eta 94m | 121.7m elapsed | |
| itr 565000/1000000 | loss 0.000698 | test 0.000858 | lr 1.20e-02 | 77 it/s | eta 94m | 122.0m elapsed | |
| itr 566000/1000000 | loss 0.000252 | test 0.001223 | lr 1.19e-02 | 77 it/s | eta 94m | 122.2m elapsed | |
| itr 567000/1000000 | loss 0.001797 | test 0.000223 | lr 1.19e-02 | 77 it/s | eta 94m | 122.5m elapsed | |
| itr 568000/1000000 | loss 0.001313 | test 0.001167 | lr 1.18e-02 | 77 it/s | eta 93m | 122.7m elapsed | |
| itr 569000/1000000 | loss 0.001469 | test 0.000583 | lr 1.18e-02 | 77 it/s | eta 93m | 123.0m elapsed | |
| itr 570000/1000000 | loss 0.000327 | test 0.000896 | lr 1.17e-02 | 77 it/s | eta 93m | 123.3m elapsed | |
| itr 571000/1000000 | loss 0.000441 | test 0.002213 | lr 1.17e-02 | 77 it/s | eta 93m | 123.6m elapsed | |
| itr 572000/1000000 | loss 0.000308 | test 0.000151 | lr 1.16e-02 | 77 it/s | eta 93m | 123.8m elapsed | |
| itr 573000/1000000 | loss 0.000491 | test 0.001403 | lr 1.16e-02 | 77 it/s | eta 92m | 124.1m elapsed | |
| itr 574000/1000000 | loss 0.001935 | test 0.001634 | lr 1.15e-02 | 77 it/s | eta 92m | 124.3m elapsed | |
| itr 575000/1000000 | loss 0.000316 | test 0.000311 | lr 1.15e-02 | 77 it/s | eta 92m | 124.6m elapsed | |
| itr 576000/1000000 | loss 0.000319 | test 0.001583 | lr 1.15e-02 | 77 it/s | eta 92m | 124.9m elapsed | |
| itr 577000/1000000 | loss 0.001068 | test 0.000553 | lr 1.14e-02 | 77 it/s | eta 92m | 125.1m elapsed | |
| itr 578000/1000000 | loss 0.000309 | test 0.001567 | lr 1.14e-02 | 77 it/s | eta 92m | 125.4m elapsed | |
| itr 579000/1000000 | loss 0.000702 | test 0.000341 | lr 1.13e-02 | 77 it/s | eta 91m | 125.6m elapsed | |
| itr 580000/1000000 | loss 0.000472 | test 0.002253 | lr 1.13e-02 | 77 it/s | eta 91m | 125.9m elapsed | |
| itr 581000/1000000 | loss 0.004853 | test 0.000864 | lr 1.12e-02 | 77 it/s | eta 91m | 126.1m elapsed | |
| itr 582000/1000000 | loss 0.000948 | test 0.000316 | lr 1.12e-02 | 77 it/s | eta 91m | 126.4m elapsed | |
| itr 583000/1000000 | loss 0.000806 | test 0.000349 | lr 1.11e-02 | 77 it/s | eta 91m | 126.7m elapsed | |
| itr 584000/1000000 | loss 0.000344 | test 0.000147 | lr 1.11e-02 | 77 it/s | eta 90m | 126.9m elapsed | |
| itr 585000/1000000 | loss 0.000508 | test 0.000179 | lr 1.10e-02 | 77 it/s | eta 90m | 127.2m elapsed | |
| itr 586000/1000000 | loss 0.000906 | test 0.000017 | lr 1.10e-02 | 77 it/s | eta 90m | 127.4m elapsed | |
| itr 587000/1000000 | loss 0.000390 | test 0.000422 | lr 1.10e-02 | 77 it/s | eta 90m | 127.7m elapsed | |
| itr 588000/1000000 | loss 0.000410 | test 0.000424 | lr 1.09e-02 | 77 it/s | eta 90m | 127.9m elapsed | |
| itr 589000/1000000 | loss 0.000668 | test 0.000325 | lr 1.09e-02 | 77 it/s | eta 89m | 128.2m elapsed | |
| itr 590000/1000000 | loss 0.000224 | test 0.000525 | lr 1.08e-02 | 77 it/s | eta 89m | 128.5m elapsed | |
| itr 591000/1000000 | loss 0.001199 | test 0.001293 | lr 1.08e-02 | 77 it/s | eta 89m | 128.7m elapsed | |
| itr 592000/1000000 | loss 0.000753 | test 0.000574 | lr 1.07e-02 | 76 it/s | eta 89m | 129.0m elapsed | |
| itr 593000/1000000 | loss 0.001366 | test 0.000133 | lr 1.07e-02 | 76 it/s | eta 89m | 129.2m elapsed | |
| itr 594000/1000000 | loss 0.000720 | test 0.000382 | lr 1.06e-02 | 76 it/s | eta 89m | 129.5m elapsed | |
| itr 595000/1000000 | loss 0.000109 | test 0.000918 | lr 1.06e-02 | 76 it/s | eta 88m | 129.8m elapsed | |
| itr 596000/1000000 | loss 0.001055 | test 0.000862 | lr 1.05e-02 | 76 it/s | eta 88m | 130.0m elapsed | |
| itr 597000/1000000 | loss 0.000222 | test 0.000738 | lr 1.05e-02 | 76 it/s | eta 88m | 130.3m elapsed | |
| itr 598000/1000000 | loss 0.000939 | test 0.001116 | lr 1.05e-02 | 76 it/s | eta 88m | 130.6m elapsed | |
| itr 599000/1000000 | loss 0.000900 | test 0.001805 | lr 1.04e-02 | 76 it/s | eta 88m | 130.8m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt600000.pt (131.1m) | |
| itr 600000/1000000 | loss 0.002757 | test 0.006506 | lr 1.04e-02 | 76 it/s | eta 87m | 131.1m elapsed | |
| itr 601000/1000000 | loss 0.000133 | test 0.000274 | lr 1.03e-02 | 76 it/s | eta 87m | 131.3m elapsed | |
| itr 602000/1000000 | loss 0.000523 | test 0.001719 | lr 1.03e-02 | 76 it/s | eta 87m | 131.6m elapsed | |
| itr 603000/1000000 | loss 0.000236 | test 0.000978 | lr 1.02e-02 | 76 it/s | eta 87m | 131.9m elapsed | |
| itr 604000/1000000 | loss 0.000523 | test 0.001594 | lr 1.02e-02 | 76 it/s | eta 87m | 132.1m elapsed | |
| itr 605000/1000000 | loss 0.000924 | test 0.000402 | lr 1.01e-02 | 76 it/s | eta 86m | 132.4m elapsed | |
| itr 606000/1000000 | loss 0.000702 | test 0.000262 | lr 1.01e-02 | 76 it/s | eta 86m | 132.6m elapsed | |
| itr 607000/1000000 | loss 0.000341 | test 0.001212 | lr 1.01e-02 | 76 it/s | eta 86m | 132.9m elapsed | |
| itr 608000/1000000 | loss 0.001332 | test 0.000854 | lr 1.00e-02 | 76 it/s | eta 86m | 133.1m elapsed | |
| itr 609000/1000000 | loss 0.000069 | test 0.000991 | lr 9.97e-03 | 76 it/s | eta 86m | 133.4m elapsed | |
| itr 610000/1000000 | loss 0.000534 | test 0.000031 | lr 9.92e-03 | 76 it/s | eta 85m | 133.7m elapsed | |
| itr 611000/1000000 | loss 0.000123 | test 0.000111 | lr 9.88e-03 | 76 it/s | eta 85m | 133.9m elapsed | |
| itr 612000/1000000 | loss 0.001303 | test 0.000226 | lr 9.83e-03 | 76 it/s | eta 85m | 134.2m elapsed | |
| itr 613000/1000000 | loss 0.000656 | test 0.000158 | lr 9.79e-03 | 76 it/s | eta 85m | 134.4m elapsed | |
| itr 614000/1000000 | loss 0.000125 | test 0.000943 | lr 9.75e-03 | 76 it/s | eta 85m | 134.7m elapsed | |
| itr 615000/1000000 | loss 0.000474 | test 0.000673 | lr 9.70e-03 | 76 it/s | eta 84m | 135.0m elapsed | |
| itr 616000/1000000 | loss 0.000383 | test 0.000548 | lr 9.66e-03 | 76 it/s | eta 84m | 135.2m elapsed | |
| itr 617000/1000000 | loss 0.000066 | test 0.000147 | lr 9.61e-03 | 76 it/s | eta 84m | 135.5m elapsed | |
| itr 618000/1000000 | loss 0.000372 | test 0.000964 | lr 9.57e-03 | 76 it/s | eta 84m | 135.7m elapsed | |
| itr 619000/1000000 | loss 0.000254 | test 0.000593 | lr 9.53e-03 | 76 it/s | eta 84m | 136.0m elapsed | |
| itr 620000/1000000 | loss 0.000684 | test 0.000052 | lr 9.48e-03 | 76 it/s | eta 84m | 136.3m elapsed | |
| itr 621000/1000000 | loss 0.000477 | test 0.000119 | lr 9.44e-03 | 76 it/s | eta 83m | 136.5m elapsed | |
| itr 622000/1000000 | loss 0.000136 | test 0.000865 | lr 9.39e-03 | 76 it/s | eta 83m | 136.8m elapsed | |
| itr 623000/1000000 | loss 0.000241 | test 0.000992 | lr 9.35e-03 | 76 it/s | eta 83m | 137.0m elapsed | |
| itr 624000/1000000 | loss 0.000387 | test 0.000383 | lr 9.31e-03 | 76 it/s | eta 83m | 137.3m elapsed | |
| itr 625000/1000000 | loss 0.000173 | test 0.000589 | lr 9.26e-03 | 76 it/s | eta 83m | 137.5m elapsed | |
| itr 626000/1000000 | loss 0.000303 | test 0.000554 | lr 9.22e-03 | 76 it/s | eta 82m | 137.8m elapsed | |
| itr 627000/1000000 | loss 0.000181 | test 0.000045 | lr 9.18e-03 | 76 it/s | eta 82m | 138.0m elapsed | |
| itr 628000/1000000 | loss 0.000472 | test 0.000181 | lr 9.13e-03 | 76 it/s | eta 82m | 138.3m elapsed | |
| itr 629000/1000000 | loss 0.000236 | test 0.000077 | lr 9.09e-03 | 76 it/s | eta 82m | 138.6m elapsed | |
| itr 630000/1000000 | loss 0.001096 | test 0.000428 | lr 9.05e-03 | 76 it/s | eta 82m | 138.8m elapsed | |
| itr 631000/1000000 | loss 0.000329 | test 0.000356 | lr 9.00e-03 | 76 it/s | eta 81m | 139.1m elapsed | |
| itr 632000/1000000 | loss 0.000230 | test 0.000693 | lr 8.96e-03 | 76 it/s | eta 81m | 139.3m elapsed | |
| itr 633000/1000000 | loss 0.000175 | test 0.000704 | lr 8.92e-03 | 76 it/s | eta 81m | 139.6m elapsed | |
| itr 634000/1000000 | loss 0.000138 | test 0.000305 | lr 8.87e-03 | 76 it/s | eta 81m | 139.8m elapsed | |
| itr 635000/1000000 | loss 0.000952 | test 0.000354 | lr 8.83e-03 | 76 it/s | eta 81m | 140.1m elapsed | |
| itr 636000/1000000 | loss 0.000304 | test 0.000071 | lr 8.79e-03 | 76 it/s | eta 80m | 140.3m elapsed | |
| itr 637000/1000000 | loss 0.000953 | test 0.000091 | lr 8.75e-03 | 76 it/s | eta 80m | 140.6m elapsed | |
| itr 638000/1000000 | loss 0.000094 | test 0.000409 | lr 8.70e-03 | 75 it/s | eta 80m | 140.8m elapsed | |
| itr 639000/1000000 | loss 0.000619 | test 0.001174 | lr 8.66e-03 | 75 it/s | eta 80m | 141.1m elapsed | |
| itr 640000/1000000 | loss 0.000466 | test 0.000069 | lr 8.62e-03 | 75 it/s | eta 80m | 141.4m elapsed | |
| itr 641000/1000000 | loss 0.000234 | test 0.000187 | lr 8.57e-03 | 75 it/s | eta 79m | 141.6m elapsed | |
| itr 642000/1000000 | loss 0.000075 | test 0.001485 | lr 8.53e-03 | 75 it/s | eta 79m | 141.9m elapsed | |
| itr 643000/1000000 | loss 0.000226 | test 0.000865 | lr 8.49e-03 | 75 it/s | eta 79m | 142.1m elapsed | |
| itr 644000/1000000 | loss 0.000457 | test 0.000237 | lr 8.45e-03 | 75 it/s | eta 79m | 142.4m elapsed | |
| itr 645000/1000000 | loss 0.000168 | test 0.000438 | lr 8.40e-03 | 75 it/s | eta 79m | 142.6m elapsed | |
| itr 646000/1000000 | loss 0.000077 | test 0.000153 | lr 8.36e-03 | 75 it/s | eta 78m | 142.9m elapsed | |
| itr 647000/1000000 | loss 0.000508 | test 0.000107 | lr 8.32e-03 | 75 it/s | eta 78m | 143.2m elapsed | |
| itr 648000/1000000 | loss 0.001218 | test 0.000172 | lr 8.28e-03 | 75 it/s | eta 78m | 143.4m elapsed | |
| itr 649000/1000000 | loss 0.000786 | test 0.001057 | lr 8.24e-03 | 75 it/s | eta 78m | 143.7m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt650000.pt (143.9m) | |
| itr 650000/1000000 | loss 0.000416 | test 0.000102 | lr 8.19e-03 | 75 it/s | eta 77m | 143.9m elapsed | |
| itr 651000/1000000 | loss 0.000130 | test 0.000008 | lr 8.15e-03 | 75 it/s | eta 77m | 144.2m elapsed | |
| itr 652000/1000000 | loss 0.000476 | test 0.000248 | lr 8.11e-03 | 75 it/s | eta 77m | 144.4m elapsed | |
| itr 653000/1000000 | loss 0.000097 | test 0.000812 | lr 8.07e-03 | 75 it/s | eta 77m | 144.7m elapsed | |
| itr 654000/1000000 | loss 0.000288 | test 0.001048 | lr 8.03e-03 | 75 it/s | eta 77m | 145.0m elapsed | |
| itr 655000/1000000 | loss 0.000713 | test 0.000137 | lr 7.98e-03 | 75 it/s | eta 76m | 145.2m elapsed | |
| itr 656000/1000000 | loss 0.002329 | test 0.002157 | lr 7.94e-03 | 75 it/s | eta 76m | 145.5m elapsed | |
| itr 657000/1000000 | loss 0.000142 | test 0.000208 | lr 7.90e-03 | 75 it/s | eta 76m | 145.7m elapsed | |
| itr 658000/1000000 | loss 0.000637 | test 0.000066 | lr 7.86e-03 | 75 it/s | eta 76m | 146.0m elapsed | |
| itr 659000/1000000 | loss 0.018877 | test 0.018993 | lr 7.82e-03 | 75 it/s | eta 76m | 146.3m elapsed | |
| itr 660000/1000000 | loss 0.000155 | test 0.000085 | lr 7.78e-03 | 75 it/s | eta 75m | 146.5m elapsed | |
| itr 661000/1000000 | loss 0.001094 | test 0.000150 | lr 7.74e-03 | 75 it/s | eta 75m | 146.8m elapsed | |
| itr 662000/1000000 | loss 0.000055 | test 0.002017 | lr 7.69e-03 | 75 it/s | eta 75m | 147.0m elapsed | |
| itr 663000/1000000 | loss 0.000589 | test 0.000083 | lr 7.65e-03 | 75 it/s | eta 75m | 147.3m elapsed | |
| itr 664000/1000000 | loss 0.000488 | test 0.000298 | lr 7.61e-03 | 75 it/s | eta 75m | 147.5m elapsed | |
| itr 665000/1000000 | loss 0.001199 | test 0.000074 | lr 7.57e-03 | 75 it/s | eta 74m | 147.8m elapsed | |
| itr 666000/1000000 | loss 0.002395 | test 0.001162 | lr 7.53e-03 | 75 it/s | eta 74m | 148.1m elapsed | |
| itr 667000/1000000 | loss 0.000599 | test 0.000385 | lr 7.49e-03 | 75 it/s | eta 74m | 148.3m elapsed | |
| itr 668000/1000000 | loss 0.013578 | test 0.013052 | lr 7.45e-03 | 75 it/s | eta 74m | 148.6m elapsed | |
| itr 669000/1000000 | loss 0.001007 | test 0.001454 | lr 7.41e-03 | 75 it/s | eta 74m | 148.9m elapsed | |
| itr 670000/1000000 | loss 0.002008 | test 0.001295 | lr 7.37e-03 | 75 it/s | eta 73m | 149.1m elapsed | |
| itr 671000/1000000 | loss 0.001732 | test 0.000467 | lr 7.33e-03 | 75 it/s | eta 73m | 149.4m elapsed | |
| itr 672000/1000000 | loss 0.000755 | test 0.000449 | lr 7.29e-03 | 75 it/s | eta 73m | 149.7m elapsed | |
| itr 673000/1000000 | loss 0.001142 | test 0.000328 | lr 7.25e-03 | 75 it/s | eta 73m | 150.0m elapsed | |
| itr 674000/1000000 | loss 0.000554 | test 0.001864 | lr 7.21e-03 | 75 it/s | eta 73m | 150.2m elapsed | |
| itr 675000/1000000 | loss 0.000543 | test 0.000658 | lr 7.17e-03 | 75 it/s | eta 72m | 150.5m elapsed | |
| itr 676000/1000000 | loss 0.000306 | test 0.000805 | lr 7.13e-03 | 75 it/s | eta 72m | 150.7m elapsed | |
| itr 677000/1000000 | loss 0.000448 | test 0.001523 | lr 7.09e-03 | 75 it/s | eta 72m | 151.0m elapsed | |
| itr 678000/1000000 | loss 0.000579 | test 0.001930 | lr 7.05e-03 | 75 it/s | eta 72m | 151.3m elapsed | |
| itr 679000/1000000 | loss 0.000549 | test 0.000654 | lr 7.01e-03 | 75 it/s | eta 72m | 151.5m elapsed | |
| itr 680000/1000000 | loss 0.000359 | test 0.000412 | lr 6.97e-03 | 75 it/s | eta 71m | 151.8m elapsed | |
| itr 681000/1000000 | loss 0.000367 | test 0.000680 | lr 6.93e-03 | 75 it/s | eta 71m | 152.1m elapsed | |
| itr 682000/1000000 | loss 0.000320 | test 0.000174 | lr 6.89e-03 | 75 it/s | eta 71m | 152.3m elapsed | |
| itr 683000/1000000 | loss 0.000809 | test 0.000107 | lr 6.85e-03 | 75 it/s | eta 71m | 152.6m elapsed | |
| itr 684000/1000000 | loss 0.000677 | test 0.000299 | lr 6.81e-03 | 75 it/s | eta 71m | 152.8m elapsed | |
| itr 685000/1000000 | loss 0.000999 | test 0.002609 | lr 6.77e-03 | 75 it/s | eta 70m | 153.1m elapsed | |
| itr 686000/1000000 | loss 0.000148 | test 0.000860 | lr 6.73e-03 | 75 it/s | eta 70m | 153.4m elapsed | |
| itr 687000/1000000 | loss 0.002500 | test 0.000090 | lr 6.69e-03 | 75 it/s | eta 70m | 153.6m elapsed | |
| itr 688000/1000000 | loss 0.000671 | test 0.000946 | lr 6.65e-03 | 75 it/s | eta 70m | 153.9m elapsed | |
| itr 689000/1000000 | loss 0.000200 | test 0.000315 | lr 6.61e-03 | 74 it/s | eta 70m | 154.2m elapsed | |
| itr 690000/1000000 | loss 0.000276 | test 0.000042 | lr 6.57e-03 | 74 it/s | eta 69m | 154.4m elapsed | |
| itr 691000/1000000 | loss 0.000270 | test 0.000395 | lr 6.53e-03 | 74 it/s | eta 69m | 154.7m elapsed | |
| itr 692000/1000000 | loss 0.000306 | test 0.000316 | lr 6.49e-03 | 74 it/s | eta 69m | 154.9m elapsed | |
| itr 693000/1000000 | loss 0.000897 | test 0.000040 | lr 6.46e-03 | 74 it/s | eta 69m | 155.2m elapsed | |
| itr 694000/1000000 | loss 0.000682 | test 0.005001 | lr 6.42e-03 | 74 it/s | eta 69m | 155.4m elapsed | |
| itr 695000/1000000 | loss 0.000768 | test 0.000424 | lr 6.38e-03 | 74 it/s | eta 68m | 155.7m elapsed | |
| itr 696000/1000000 | loss 0.000208 | test 0.000176 | lr 6.34e-03 | 74 it/s | eta 68m | 156.0m elapsed | |
| itr 697000/1000000 | loss 0.000355 | test 0.000196 | lr 6.30e-03 | 74 it/s | eta 68m | 156.2m elapsed | |
| itr 698000/1000000 | loss 0.000468 | test 0.000517 | lr 6.26e-03 | 74 it/s | eta 68m | 156.5m elapsed | |
| itr 699000/1000000 | loss 0.000746 | test 0.001236 | lr 6.22e-03 | 74 it/s | eta 67m | 156.8m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt700000.pt (157.0m) | |
| itr 700000/1000000 | loss 0.000303 | test 0.000428 | lr 6.19e-03 | 74 it/s | eta 67m | 157.0m elapsed | |
| itr 701000/1000000 | loss 0.000047 | test 0.002215 | lr 6.15e-03 | 74 it/s | eta 67m | 157.3m elapsed | |
| itr 702000/1000000 | loss 0.000414 | test 0.000298 | lr 6.11e-03 | 74 it/s | eta 67m | 157.5m elapsed | |
| itr 703000/1000000 | loss 0.000133 | test 0.000529 | lr 6.07e-03 | 74 it/s | eta 67m | 157.8m elapsed | |
| itr 704000/1000000 | loss 0.001255 | test 0.000090 | lr 6.03e-03 | 74 it/s | eta 66m | 158.1m elapsed | |
| itr 705000/1000000 | loss 0.000343 | test 0.000111 | lr 6.00e-03 | 74 it/s | eta 66m | 158.3m elapsed | |
| itr 706000/1000000 | loss 0.000877 | test 0.000086 | lr 5.96e-03 | 74 it/s | eta 66m | 158.6m elapsed | |
| itr 707000/1000000 | loss 0.000282 | test 0.000913 | lr 5.92e-03 | 74 it/s | eta 66m | 158.8m elapsed | |
| itr 708000/1000000 | loss 0.000316 | test 0.000074 | lr 5.88e-03 | 74 it/s | eta 66m | 159.1m elapsed | |
| itr 709000/1000000 | loss 0.000436 | test 0.000941 | lr 5.85e-03 | 74 it/s | eta 65m | 159.4m elapsed | |
| itr 710000/1000000 | loss 0.000530 | test 0.002516 | lr 5.81e-03 | 74 it/s | eta 65m | 159.6m elapsed | |
| itr 711000/1000000 | loss 0.000910 | test 0.000828 | lr 5.77e-03 | 74 it/s | eta 65m | 159.9m elapsed | |
| itr 712000/1000000 | loss 0.001277 | test 0.000279 | lr 5.74e-03 | 74 it/s | eta 65m | 160.1m elapsed | |
| itr 713000/1000000 | loss 0.000335 | test 0.000944 | lr 5.70e-03 | 74 it/s | eta 65m | 160.4m elapsed | |
| itr 714000/1000000 | loss 0.000306 | test 0.000669 | lr 5.66e-03 | 74 it/s | eta 64m | 160.7m elapsed | |
| itr 715000/1000000 | loss 0.000153 | test 0.000403 | lr 5.62e-03 | 74 it/s | eta 64m | 160.9m elapsed | |
| itr 716000/1000000 | loss 0.000095 | test 0.000782 | lr 5.59e-03 | 74 it/s | eta 64m | 161.2m elapsed | |
| itr 717000/1000000 | loss 0.001323 | test 0.000435 | lr 5.55e-03 | 74 it/s | eta 64m | 161.4m elapsed | |
| itr 718000/1000000 | loss 0.000480 | test 0.000404 | lr 5.51e-03 | 74 it/s | eta 64m | 161.7m elapsed | |
| itr 719000/1000000 | loss 0.000659 | test 0.001304 | lr 5.48e-03 | 74 it/s | eta 63m | 162.0m elapsed | |
| itr 720000/1000000 | loss 0.000112 | test 0.003684 | lr 5.44e-03 | 74 it/s | eta 63m | 162.2m elapsed | |
| itr 721000/1000000 | loss 0.001143 | test 0.001784 | lr 5.41e-03 | 74 it/s | eta 63m | 162.5m elapsed | |
| itr 722000/1000000 | loss 0.000684 | test 0.000059 | lr 5.37e-03 | 74 it/s | eta 63m | 162.7m elapsed | |
| itr 723000/1000000 | loss 0.000290 | test 0.000591 | lr 5.33e-03 | 74 it/s | eta 62m | 163.0m elapsed | |
| itr 724000/1000000 | loss 0.000192 | test 0.000254 | lr 5.30e-03 | 74 it/s | eta 62m | 163.2m elapsed | |
| itr 725000/1000000 | loss 0.000321 | test 0.000392 | lr 5.26e-03 | 74 it/s | eta 62m | 163.5m elapsed | |
| itr 726000/1000000 | loss 0.000232 | test 0.001012 | lr 5.23e-03 | 74 it/s | eta 62m | 163.8m elapsed | |
| itr 727000/1000000 | loss 0.000279 | test 0.000133 | lr 5.19e-03 | 74 it/s | eta 62m | 164.0m elapsed | |
| itr 728000/1000000 | loss 0.000235 | test 0.000271 | lr 5.15e-03 | 74 it/s | eta 61m | 164.3m elapsed | |
| itr 729000/1000000 | loss 0.000719 | test 0.000082 | lr 5.12e-03 | 74 it/s | eta 61m | 164.5m elapsed | |
| itr 730000/1000000 | loss 0.000034 | test 0.000292 | lr 5.08e-03 | 74 it/s | eta 61m | 164.8m elapsed | |
| itr 731000/1000000 | loss 0.000294 | test 0.000136 | lr 5.05e-03 | 74 it/s | eta 61m | 165.0m elapsed | |
| itr 732000/1000000 | loss 0.000307 | test 0.000327 | lr 5.01e-03 | 74 it/s | eta 61m | 165.3m elapsed | |
| itr 733000/1000000 | loss 0.000095 | test 0.000125 | lr 4.98e-03 | 74 it/s | eta 60m | 165.6m elapsed | |
| itr 734000/1000000 | loss 0.000035 | test 0.000570 | lr 4.94e-03 | 74 it/s | eta 60m | 165.8m elapsed | |
| itr 735000/1000000 | loss 0.000328 | test 0.000291 | lr 4.91e-03 | 74 it/s | eta 60m | 166.1m elapsed | |
| itr 736000/1000000 | loss 0.001335 | test 0.000173 | lr 4.87e-03 | 74 it/s | eta 60m | 166.3m elapsed | |
| itr 737000/1000000 | loss 0.000211 | test 0.000361 | lr 4.84e-03 | 74 it/s | eta 59m | 166.6m elapsed | |
| itr 738000/1000000 | loss 0.000302 | test 0.000100 | lr 4.80e-03 | 74 it/s | eta 59m | 166.8m elapsed | |
| itr 739000/1000000 | loss 0.000235 | test 0.000017 | lr 4.77e-03 | 74 it/s | eta 59m | 167.1m elapsed | |
| itr 740000/1000000 | loss 0.000636 | test 0.000685 | lr 4.73e-03 | 74 it/s | eta 59m | 167.4m elapsed | |
| itr 741000/1000000 | loss 0.000421 | test 0.000090 | lr 4.70e-03 | 74 it/s | eta 59m | 167.6m elapsed | |
| itr 742000/1000000 | loss 0.000031 | test 0.000307 | lr 4.67e-03 | 74 it/s | eta 58m | 167.9m elapsed | |
| itr 743000/1000000 | loss 0.000247 | test 0.000127 | lr 4.63e-03 | 74 it/s | eta 58m | 168.1m elapsed | |
| itr 744000/1000000 | loss 0.000326 | test 0.000081 | lr 4.60e-03 | 74 it/s | eta 58m | 168.4m elapsed | |
| itr 745000/1000000 | loss 0.000088 | test 0.001619 | lr 4.56e-03 | 74 it/s | eta 58m | 168.6m elapsed | |
| itr 746000/1000000 | loss 0.000242 | test 0.000573 | lr 4.53e-03 | 74 it/s | eta 58m | 168.9m elapsed | |
| itr 747000/1000000 | loss 0.001604 | test 0.000060 | lr 4.50e-03 | 74 it/s | eta 57m | 169.2m elapsed | |
| itr 748000/1000000 | loss 0.000383 | test 0.000033 | lr 4.46e-03 | 74 it/s | eta 57m | 169.4m elapsed | |
| itr 749000/1000000 | loss 0.001297 | test 0.000089 | lr 4.43e-03 | 74 it/s | eta 57m | 169.7m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt750000.pt (169.9m) | |
| itr 750000/1000000 | loss 0.000129 | test 0.000049 | lr 4.40e-03 | 74 it/s | eta 57m | 169.9m elapsed | |
| itr 751000/1000000 | loss 0.000137 | test 0.000031 | lr 4.36e-03 | 74 it/s | eta 56m | 170.2m elapsed | |
| itr 752000/1000000 | loss 0.000945 | test 0.000648 | lr 4.33e-03 | 74 it/s | eta 56m | 170.5m elapsed | |
| itr 753000/1000000 | loss 0.000221 | test 0.000132 | lr 4.30e-03 | 74 it/s | eta 56m | 170.7m elapsed | |
| itr 754000/1000000 | loss 0.000337 | test 0.000049 | lr 4.26e-03 | 74 it/s | eta 56m | 171.0m elapsed | |
| itr 755000/1000000 | loss 0.000366 | test 0.003119 | lr 4.23e-03 | 73 it/s | eta 56m | 171.2m elapsed | |
| itr 756000/1000000 | loss 0.000200 | test 0.000321 | lr 4.20e-03 | 73 it/s | eta 55m | 171.5m elapsed | |
| itr 757000/1000000 | loss 0.001409 | test 0.000259 | lr 4.17e-03 | 73 it/s | eta 55m | 171.7m elapsed | |
| itr 758000/1000000 | loss 0.000396 | test 0.000360 | lr 4.13e-03 | 73 it/s | eta 55m | 172.0m elapsed | |
| itr 759000/1000000 | loss 0.000162 | test 0.000884 | lr 4.10e-03 | 73 it/s | eta 55m | 172.2m elapsed | |
| itr 760000/1000000 | loss 0.000375 | test 0.000433 | lr 4.07e-03 | 73 it/s | eta 54m | 172.5m elapsed | |
| itr 761000/1000000 | loss 0.000069 | test 0.000141 | lr 4.04e-03 | 73 it/s | eta 54m | 172.7m elapsed | |
| itr 762000/1000000 | loss 0.001472 | test 0.000008 | lr 4.00e-03 | 73 it/s | eta 54m | 173.0m elapsed | |
| itr 763000/1000000 | loss 0.000585 | test 0.000122 | lr 3.97e-03 | 73 it/s | eta 54m | 173.3m elapsed | |
| itr 764000/1000000 | loss 0.000313 | test 0.000168 | lr 3.94e-03 | 73 it/s | eta 54m | 173.5m elapsed | |
| itr 765000/1000000 | loss 0.001126 | test 0.000080 | lr 3.91e-03 | 73 it/s | eta 53m | 173.8m elapsed | |
| itr 766000/1000000 | loss 0.000217 | test 0.000030 | lr 3.88e-03 | 73 it/s | eta 53m | 174.0m elapsed | |
| itr 767000/1000000 | loss 0.000559 | test 0.000630 | lr 3.84e-03 | 73 it/s | eta 53m | 174.3m elapsed | |
| itr 768000/1000000 | loss 0.000233 | test 0.000492 | lr 3.81e-03 | 73 it/s | eta 53m | 174.5m elapsed | |
| itr 769000/1000000 | loss 0.000383 | test 0.001678 | lr 3.78e-03 | 73 it/s | eta 53m | 174.8m elapsed | |
| itr 770000/1000000 | loss 0.000341 | test 0.000098 | lr 3.75e-03 | 73 it/s | eta 52m | 175.1m elapsed | |
| itr 771000/1000000 | loss 0.000048 | test 0.000067 | lr 3.72e-03 | 73 it/s | eta 52m | 175.3m elapsed | |
| itr 772000/1000000 | loss 0.000051 | test 0.000046 | lr 3.69e-03 | 73 it/s | eta 52m | 175.6m elapsed | |
| itr 773000/1000000 | loss 0.000165 | test 0.000400 | lr 3.66e-03 | 73 it/s | eta 52m | 175.8m elapsed | |
| itr 774000/1000000 | loss 0.000165 | test 0.000476 | lr 3.63e-03 | 73 it/s | eta 51m | 176.1m elapsed | |
| itr 775000/1000000 | loss 0.000134 | test 0.000047 | lr 3.60e-03 | 73 it/s | eta 51m | 176.4m elapsed | |
| itr 776000/1000000 | loss 0.000672 | test 0.000176 | lr 3.57e-03 | 73 it/s | eta 51m | 176.6m elapsed | |
| itr 777000/1000000 | loss 0.000237 | test 0.000039 | lr 3.54e-03 | 73 it/s | eta 51m | 176.9m elapsed | |
| itr 778000/1000000 | loss 0.000296 | test 0.000597 | lr 3.50e-03 | 73 it/s | eta 51m | 177.1m elapsed | |
| itr 779000/1000000 | loss 0.000120 | test 0.000062 | lr 3.47e-03 | 73 it/s | eta 50m | 177.4m elapsed | |
| itr 780000/1000000 | loss 0.000040 | test 0.000043 | lr 3.44e-03 | 73 it/s | eta 50m | 177.6m elapsed | |
| itr 781000/1000000 | loss 0.000053 | test 0.000273 | lr 3.41e-03 | 73 it/s | eta 50m | 177.9m elapsed | |
| itr 782000/1000000 | loss 0.000105 | test 0.000018 | lr 3.38e-03 | 73 it/s | eta 50m | 178.2m elapsed | |
| itr 783000/1000000 | loss 0.000214 | test 0.000465 | lr 3.35e-03 | 73 it/s | eta 49m | 178.4m elapsed | |
| itr 784000/1000000 | loss 0.000309 | test 0.000084 | lr 3.33e-03 | 73 it/s | eta 49m | 178.7m elapsed | |
| itr 785000/1000000 | loss 0.000387 | test 0.000189 | lr 3.30e-03 | 73 it/s | eta 49m | 178.9m elapsed | |
| itr 786000/1000000 | loss 0.000559 | test 0.000043 | lr 3.27e-03 | 73 it/s | eta 49m | 179.2m elapsed | |
| itr 787000/1000000 | loss 0.000355 | test 0.000465 | lr 3.24e-03 | 73 it/s | eta 49m | 179.4m elapsed | |
| itr 788000/1000000 | loss 0.000037 | test 0.000024 | lr 3.21e-03 | 73 it/s | eta 48m | 179.7m elapsed | |
| itr 789000/1000000 | loss 0.001314 | test 0.000023 | lr 3.18e-03 | 73 it/s | eta 48m | 180.0m elapsed | |
| itr 790000/1000000 | loss 0.000754 | test 0.000550 | lr 3.15e-03 | 73 it/s | eta 48m | 180.2m elapsed | |
| itr 791000/1000000 | loss 0.000177 | test 0.000368 | lr 3.12e-03 | 73 it/s | eta 48m | 180.5m elapsed | |
| itr 792000/1000000 | loss 0.000209 | test 0.000991 | lr 3.09e-03 | 73 it/s | eta 47m | 180.7m elapsed | |
| itr 793000/1000000 | loss 0.000059 | test 0.001190 | lr 3.06e-03 | 73 it/s | eta 47m | 181.0m elapsed | |
| itr 794000/1000000 | loss 0.000049 | test 0.000524 | lr 3.04e-03 | 73 it/s | eta 47m | 181.2m elapsed | |
| itr 795000/1000000 | loss 0.001850 | test 0.000189 | lr 3.01e-03 | 73 it/s | eta 47m | 181.5m elapsed | |
| itr 796000/1000000 | loss 0.000039 | test 0.000254 | lr 2.98e-03 | 73 it/s | eta 47m | 181.8m elapsed | |
| itr 797000/1000000 | loss 0.000053 | test 0.000070 | lr 2.95e-03 | 73 it/s | eta 46m | 182.0m elapsed | |
| itr 798000/1000000 | loss 0.000463 | test 0.000031 | lr 2.92e-03 | 73 it/s | eta 46m | 182.3m elapsed | |
| itr 799000/1000000 | loss 0.000086 | test 0.000022 | lr 2.89e-03 | 73 it/s | eta 46m | 182.5m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt800000.pt (182.8m) | |
| itr 800000/1000000 | loss 0.000274 | test 0.000110 | lr 2.87e-03 | 73 it/s | eta 46m | 182.8m elapsed | |
| itr 801000/1000000 | loss 0.000021 | test 0.000050 | lr 2.84e-03 | 73 it/s | eta 45m | 183.0m elapsed | |
| itr 802000/1000000 | loss 0.000076 | test 0.000073 | lr 2.81e-03 | 73 it/s | eta 45m | 183.3m elapsed | |
| itr 803000/1000000 | loss 0.000609 | test 0.000927 | lr 2.78e-03 | 73 it/s | eta 45m | 183.6m elapsed | |
| itr 804000/1000000 | loss 0.000023 | test 0.000024 | lr 2.76e-03 | 73 it/s | eta 45m | 183.8m elapsed | |
| itr 805000/1000000 | loss 0.000359 | test 0.000201 | lr 2.73e-03 | 73 it/s | eta 45m | 184.1m elapsed | |
| itr 806000/1000000 | loss 0.009193 | test 0.000694 | lr 2.70e-03 | 73 it/s | eta 44m | 184.3m elapsed | |
| itr 807000/1000000 | loss 0.000251 | test 0.000180 | lr 2.68e-03 | 73 it/s | eta 44m | 184.6m elapsed | |
| itr 808000/1000000 | loss 0.000081 | test 0.000016 | lr 2.65e-03 | 73 it/s | eta 44m | 184.8m elapsed | |
| itr 809000/1000000 | loss 0.000135 | test 0.001522 | lr 2.62e-03 | 73 it/s | eta 44m | 185.1m elapsed | |
| itr 810000/1000000 | loss 0.000571 | test 0.000199 | lr 2.60e-03 | 73 it/s | eta 43m | 185.3m elapsed | |
| itr 811000/1000000 | loss 0.000239 | test 0.000047 | lr 2.57e-03 | 73 it/s | eta 43m | 185.6m elapsed | |
| itr 812000/1000000 | loss 0.000284 | test 0.000083 | lr 2.54e-03 | 73 it/s | eta 43m | 185.9m elapsed | |
| itr 813000/1000000 | loss 0.000509 | test 0.000075 | lr 2.52e-03 | 73 it/s | eta 43m | 186.1m elapsed | |
| itr 814000/1000000 | loss 0.000032 | test 0.000020 | lr 2.49e-03 | 73 it/s | eta 43m | 186.4m elapsed | |
| itr 815000/1000000 | loss 0.000078 | test 0.000024 | lr 2.46e-03 | 73 it/s | eta 42m | 186.6m elapsed | |
| itr 816000/1000000 | loss 0.000026 | test 0.000010 | lr 2.44e-03 | 73 it/s | eta 42m | 186.9m elapsed | |
| itr 817000/1000000 | loss 0.000099 | test 0.001045 | lr 2.41e-03 | 73 it/s | eta 42m | 187.1m elapsed | |
| itr 818000/1000000 | loss 0.000385 | test 0.000341 | lr 2.39e-03 | 73 it/s | eta 42m | 187.4m elapsed | |
| itr 819000/1000000 | loss 0.000827 | test 0.000080 | lr 2.36e-03 | 73 it/s | eta 41m | 187.7m elapsed | |
| itr 820000/1000000 | loss 0.000449 | test 0.000880 | lr 2.34e-03 | 73 it/s | eta 41m | 187.9m elapsed | |
| itr 821000/1000000 | loss 0.000200 | test 0.000137 | lr 2.31e-03 | 73 it/s | eta 41m | 188.2m elapsed | |
| itr 822000/1000000 | loss 0.000019 | test 0.000074 | lr 2.29e-03 | 73 it/s | eta 41m | 188.4m elapsed | |
| itr 823000/1000000 | loss 0.000135 | test 0.000290 | lr 2.26e-03 | 73 it/s | eta 41m | 188.7m elapsed | |
| itr 824000/1000000 | loss 0.000428 | test 0.000066 | lr 2.24e-03 | 73 it/s | eta 40m | 188.9m elapsed | |
| itr 825000/1000000 | loss 0.000011 | test 0.000311 | lr 2.21e-03 | 73 it/s | eta 40m | 189.2m elapsed | |
| itr 826000/1000000 | loss 0.000373 | test 0.000006 | lr 2.19e-03 | 73 it/s | eta 40m | 189.5m elapsed | |
| itr 827000/1000000 | loss 0.000327 | test 0.000019 | lr 2.16e-03 | 73 it/s | eta 40m | 189.7m elapsed | |
| itr 828000/1000000 | loss 0.000553 | test 0.000853 | lr 2.14e-03 | 73 it/s | eta 39m | 190.0m elapsed | |
| itr 829000/1000000 | loss 0.000303 | test 0.000004 | lr 2.11e-03 | 73 it/s | eta 39m | 190.2m elapsed | |
| itr 830000/1000000 | loss 0.000148 | test 0.000291 | lr 2.09e-03 | 73 it/s | eta 39m | 190.5m elapsed | |
| itr 831000/1000000 | loss 0.000291 | test 0.000038 | lr 2.07e-03 | 73 it/s | eta 39m | 190.7m elapsed | |
| itr 832000/1000000 | loss 0.000060 | test 0.000038 | lr 2.04e-03 | 73 it/s | eta 39m | 191.0m elapsed | |
| itr 833000/1000000 | loss 0.000175 | test 0.000448 | lr 2.02e-03 | 73 it/s | eta 38m | 191.3m elapsed | |
| itr 834000/1000000 | loss 0.000057 | test 0.000155 | lr 2.00e-03 | 73 it/s | eta 38m | 191.5m elapsed | |
| itr 835000/1000000 | loss 0.000043 | test 0.000129 | lr 1.97e-03 | 73 it/s | eta 38m | 191.8m elapsed | |
| itr 836000/1000000 | loss 0.000600 | test 0.000251 | lr 1.95e-03 | 73 it/s | eta 38m | 192.0m elapsed | |
| itr 837000/1000000 | loss 0.000285 | test 0.000047 | lr 1.93e-03 | 73 it/s | eta 37m | 192.3m elapsed | |
| itr 838000/1000000 | loss 0.000140 | test 0.000295 | lr 1.90e-03 | 73 it/s | eta 37m | 192.5m elapsed | |
| itr 839000/1000000 | loss 0.000034 | test 0.000045 | lr 1.88e-03 | 73 it/s | eta 37m | 192.8m elapsed | |
| itr 840000/1000000 | loss 0.000032 | test 0.000029 | lr 1.86e-03 | 73 it/s | eta 37m | 193.0m elapsed | |
| itr 841000/1000000 | loss 0.000033 | test 0.000007 | lr 1.83e-03 | 73 it/s | eta 37m | 193.3m elapsed | |
| itr 842000/1000000 | loss 0.000275 | test 0.000011 | lr 1.81e-03 | 73 it/s | eta 36m | 193.6m elapsed | |
| itr 843000/1000000 | loss 0.000035 | test 0.000029 | lr 1.79e-03 | 72 it/s | eta 36m | 193.8m elapsed | |
| itr 844000/1000000 | loss 0.000524 | test 0.000018 | lr 1.77e-03 | 72 it/s | eta 36m | 194.1m elapsed | |
| itr 845000/1000000 | loss 0.000265 | test 0.000203 | lr 1.75e-03 | 72 it/s | eta 36m | 194.3m elapsed | |
| itr 846000/1000000 | loss 0.000011 | test 0.000064 | lr 1.72e-03 | 72 it/s | eta 35m | 194.6m elapsed | |
| itr 847000/1000000 | loss 0.000006 | test 0.000007 | lr 1.70e-03 | 72 it/s | eta 35m | 194.9m elapsed | |
| itr 848000/1000000 | loss 0.000087 | test 0.000688 | lr 1.68e-03 | 72 it/s | eta 35m | 195.1m elapsed | |
| itr 849000/1000000 | loss 0.000016 | test 0.000090 | lr 1.66e-03 | 72 it/s | eta 35m | 195.4m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt850000.pt (195.6m) | |
| itr 850000/1000000 | loss 0.000358 | test 0.000005 | lr 1.64e-03 | 72 it/s | eta 35m | 195.6m elapsed | |
| itr 851000/1000000 | loss 0.000471 | test 0.000106 | lr 1.62e-03 | 72 it/s | eta 34m | 195.9m elapsed | |
| itr 852000/1000000 | loss 0.000022 | test 0.000009 | lr 1.59e-03 | 72 it/s | eta 34m | 196.2m elapsed | |
| itr 853000/1000000 | loss 0.001130 | test 0.000005 | lr 1.57e-03 | 72 it/s | eta 34m | 196.4m elapsed | |
| itr 854000/1000000 | loss 0.000082 | test 0.000024 | lr 1.55e-03 | 72 it/s | eta 34m | 196.7m elapsed | |
| itr 855000/1000000 | loss 0.000069 | test 0.000051 | lr 1.53e-03 | 72 it/s | eta 33m | 196.9m elapsed | |
| itr 856000/1000000 | loss 0.000086 | test 0.000071 | lr 1.51e-03 | 72 it/s | eta 33m | 197.2m elapsed | |
| itr 857000/1000000 | loss 0.000183 | test 0.000211 | lr 1.49e-03 | 72 it/s | eta 33m | 197.5m elapsed | |
| itr 858000/1000000 | loss 0.000022 | test 0.000005 | lr 1.47e-03 | 72 it/s | eta 33m | 197.7m elapsed | |
| itr 859000/1000000 | loss 0.000045 | test 0.000004 | lr 1.45e-03 | 72 it/s | eta 32m | 198.0m elapsed | |
| itr 860000/1000000 | loss 0.000126 | test 0.000013 | lr 1.43e-03 | 72 it/s | eta 32m | 198.2m elapsed | |
| itr 861000/1000000 | loss 0.000015 | test 0.000017 | lr 1.41e-03 | 72 it/s | eta 32m | 198.5m elapsed | |
| itr 862000/1000000 | loss 0.000279 | test 0.000454 | lr 1.39e-03 | 72 it/s | eta 32m | 198.8m elapsed | |
| itr 863000/1000000 | loss 0.000050 | test 0.000007 | lr 1.37e-03 | 72 it/s | eta 32m | 199.0m elapsed | |
| itr 864000/1000000 | loss 0.000127 | test 0.000240 | lr 1.35e-03 | 72 it/s | eta 31m | 199.3m elapsed | |
| itr 865000/1000000 | loss 0.000013 | test 0.000284 | lr 1.33e-03 | 72 it/s | eta 31m | 199.6m elapsed | |
| itr 866000/1000000 | loss 0.000021 | test 0.000013 | lr 1.31e-03 | 72 it/s | eta 31m | 199.8m elapsed | |
| itr 867000/1000000 | loss 0.000030 | test 0.000015 | lr 1.29e-03 | 72 it/s | eta 31m | 200.1m elapsed | |
| itr 868000/1000000 | loss 0.000336 | test 0.000011 | lr 1.27e-03 | 72 it/s | eta 30m | 200.3m elapsed | |
| itr 869000/1000000 | loss 0.000023 | test 0.000031 | lr 1.25e-03 | 72 it/s | eta 30m | 200.6m elapsed | |
| itr 870000/1000000 | loss 0.000042 | test 0.000053 | lr 1.24e-03 | 72 it/s | eta 30m | 200.9m elapsed | |
| itr 871000/1000000 | loss 0.000123 | test 0.000005 | lr 1.22e-03 | 72 it/s | eta 30m | 201.1m elapsed | |
| itr 872000/1000000 | loss 0.000014 | test 0.000892 | lr 1.20e-03 | 72 it/s | eta 30m | 201.4m elapsed | |
| itr 873000/1000000 | loss 0.000009 | test 0.000016 | lr 1.18e-03 | 72 it/s | eta 29m | 201.7m elapsed | |
| itr 874000/1000000 | loss 0.000016 | test 0.000007 | lr 1.16e-03 | 72 it/s | eta 29m | 201.9m elapsed | |
| itr 875000/1000000 | loss 0.000563 | test 0.000005 | lr 1.14e-03 | 72 it/s | eta 29m | 202.2m elapsed | |
| itr 876000/1000000 | loss 0.000119 | test 0.000016 | lr 1.13e-03 | 72 it/s | eta 29m | 202.4m elapsed | |
| itr 877000/1000000 | loss 0.000080 | test 0.000015 | lr 1.11e-03 | 72 it/s | eta 28m | 202.7m elapsed | |
| itr 878000/1000000 | loss 0.000006 | test 0.000025 | lr 1.09e-03 | 72 it/s | eta 28m | 203.0m elapsed | |
| itr 879000/1000000 | loss 0.000052 | test 0.000011 | lr 1.07e-03 | 72 it/s | eta 28m | 203.2m elapsed | |
| itr 880000/1000000 | loss 0.000069 | test 0.000486 | lr 1.05e-03 | 72 it/s | eta 28m | 203.5m elapsed | |
| itr 881000/1000000 | loss 0.000054 | test 0.000518 | lr 1.04e-03 | 72 it/s | eta 28m | 203.7m elapsed | |
| itr 882000/1000000 | loss 0.000010 | test 0.000035 | lr 1.02e-03 | 72 it/s | eta 27m | 204.0m elapsed | |
| itr 883000/1000000 | loss 0.000066 | test 0.000190 | lr 1.00e-03 | 72 it/s | eta 27m | 204.2m elapsed | |
| itr 884000/1000000 | loss 0.000050 | test 0.000014 | lr 9.86e-04 | 72 it/s | eta 27m | 204.5m elapsed | |
| itr 885000/1000000 | loss 0.000005 | test 0.000016 | lr 9.70e-04 | 72 it/s | eta 27m | 204.8m elapsed | |
| itr 886000/1000000 | loss 0.000036 | test 0.000143 | lr 9.53e-04 | 72 it/s | eta 26m | 205.0m elapsed | |
| itr 887000/1000000 | loss 0.000184 | test 0.000020 | lr 9.37e-04 | 72 it/s | eta 26m | 205.3m elapsed | |
| itr 888000/1000000 | loss 0.000676 | test 0.000003 | lr 9.20e-04 | 72 it/s | eta 26m | 205.5m elapsed | |
| itr 889000/1000000 | loss 0.000420 | test 0.000061 | lr 9.04e-04 | 72 it/s | eta 26m | 205.8m elapsed | |
| itr 890000/1000000 | loss 0.000528 | test 0.000067 | lr 8.88e-04 | 72 it/s | eta 25m | 206.0m elapsed | |
| itr 891000/1000000 | loss 0.000023 | test 0.000046 | lr 8.72e-04 | 72 it/s | eta 25m | 206.3m elapsed | |
| itr 892000/1000000 | loss 0.000012 | test 0.000513 | lr 8.56e-04 | 72 it/s | eta 25m | 206.6m elapsed | |
| itr 893000/1000000 | loss 0.000006 | test 0.000040 | lr 8.41e-04 | 72 it/s | eta 25m | 206.8m elapsed | |
| itr 894000/1000000 | loss 0.000303 | test 0.000017 | lr 8.25e-04 | 72 it/s | eta 25m | 207.1m elapsed | |
| itr 895000/1000000 | loss 0.000016 | test 0.000016 | lr 8.10e-04 | 72 it/s | eta 24m | 207.3m elapsed | |
| itr 896000/1000000 | loss 0.000527 | test 0.000166 | lr 7.95e-04 | 72 it/s | eta 24m | 207.6m elapsed | |
| itr 897000/1000000 | loss 0.000283 | test 0.000003 | lr 7.80e-04 | 72 it/s | eta 24m | 207.9m elapsed | |
| itr 898000/1000000 | loss 0.000084 | test 0.000036 | lr 7.65e-04 | 72 it/s | eta 24m | 208.1m elapsed | |
| itr 899000/1000000 | loss 0.000095 | test 0.000172 | lr 7.50e-04 | 72 it/s | eta 23m | 208.4m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt900000.pt (208.6m) | |
| itr 900000/1000000 | loss 0.000011 | test 0.000802 | lr 7.35e-04 | 72 it/s | eta 23m | 208.6m elapsed | |
| itr 901000/1000000 | loss 0.000046 | test 0.000004 | lr 7.21e-04 | 72 it/s | eta 23m | 208.9m elapsed | |
| itr 902000/1000000 | loss 0.000007 | test 0.000083 | lr 7.07e-04 | 72 it/s | eta 23m | 209.2m elapsed | |
| itr 903000/1000000 | loss 0.000347 | test 0.000003 | lr 6.92e-04 | 72 it/s | eta 22m | 209.4m elapsed | |
| itr 904000/1000000 | loss 0.000007 | test 0.000002 | lr 6.78e-04 | 72 it/s | eta 22m | 209.7m elapsed | |
| itr 905000/1000000 | loss 0.000041 | test 0.000106 | lr 6.64e-04 | 72 it/s | eta 22m | 209.9m elapsed | |
| itr 906000/1000000 | loss 0.000256 | test 0.000012 | lr 6.51e-04 | 72 it/s | eta 22m | 210.2m elapsed | |
| itr 907000/1000000 | loss 0.000010 | test 0.000235 | lr 6.37e-04 | 72 it/s | eta 22m | 210.5m elapsed | |
| itr 908000/1000000 | loss 0.000157 | test 0.000005 | lr 6.23e-04 | 72 it/s | eta 21m | 210.7m elapsed | |
| itr 909000/1000000 | loss 0.000335 | test 0.000003 | lr 6.10e-04 | 72 it/s | eta 21m | 211.0m elapsed | |
| itr 910000/1000000 | loss 0.000020 | test 0.000002 | lr 5.97e-04 | 72 it/s | eta 21m | 211.2m elapsed | |
| itr 911000/1000000 | loss 0.000004 | test 0.000041 | lr 5.84e-04 | 72 it/s | eta 21m | 211.5m elapsed | |
| itr 912000/1000000 | loss 0.000343 | test 0.000081 | lr 5.71e-04 | 72 it/s | eta 20m | 211.7m elapsed | |
| itr 913000/1000000 | loss 0.000005 | test 0.000685 | lr 5.58e-04 | 72 it/s | eta 20m | 212.0m elapsed | |
| itr 914000/1000000 | loss 0.000009 | test 0.000013 | lr 5.45e-04 | 72 it/s | eta 20m | 212.3m elapsed | |
| itr 915000/1000000 | loss 0.000018 | test 0.000772 | lr 5.33e-04 | 72 it/s | eta 20m | 212.5m elapsed | |
| itr 916000/1000000 | loss 0.000006 | test 0.000005 | lr 5.20e-04 | 72 it/s | eta 20m | 212.8m elapsed | |
| itr 917000/1000000 | loss 0.000060 | test 0.000005 | lr 5.08e-04 | 72 it/s | eta 19m | 213.0m elapsed | |
| itr 918000/1000000 | loss 0.000083 | test 0.000011 | lr 4.96e-04 | 72 it/s | eta 19m | 213.3m elapsed | |
| itr 919000/1000000 | loss 0.000319 | test 0.000009 | lr 4.84e-04 | 72 it/s | eta 19m | 213.5m elapsed | |
| itr 920000/1000000 | loss 0.000228 | test 0.000020 | lr 4.72e-04 | 72 it/s | eta 19m | 213.8m elapsed | |
| itr 921000/1000000 | loss 0.000332 | test 0.000004 | lr 4.61e-04 | 72 it/s | eta 18m | 214.1m elapsed | |
| itr 922000/1000000 | loss 0.000085 | test 0.001390 | lr 4.49e-04 | 72 it/s | eta 18m | 214.3m elapsed | |
| itr 923000/1000000 | loss 0.000020 | test 0.000004 | lr 4.38e-04 | 72 it/s | eta 18m | 214.6m elapsed | |
| itr 924000/1000000 | loss 0.000056 | test 0.000016 | lr 4.27e-04 | 72 it/s | eta 18m | 214.8m elapsed | |
| itr 925000/1000000 | loss 0.000006 | test 0.000336 | lr 4.16e-04 | 72 it/s | eta 17m | 215.1m elapsed | |
| itr 926000/1000000 | loss 0.000007 | test 0.000023 | lr 4.05e-04 | 72 it/s | eta 17m | 215.3m elapsed | |
| itr 927000/1000000 | loss 0.000315 | test 0.000003 | lr 3.94e-04 | 72 it/s | eta 17m | 215.6m elapsed | |
| itr 928000/1000000 | loss 0.000393 | test 0.000005 | lr 3.83e-04 | 72 it/s | eta 17m | 215.9m elapsed | |
| itr 929000/1000000 | loss 0.000008 | test 0.000013 | lr 3.73e-04 | 72 it/s | eta 17m | 216.1m elapsed | |
| itr 930000/1000000 | loss 0.000005 | test 0.000003 | lr 3.62e-04 | 72 it/s | eta 16m | 216.4m elapsed | |
| itr 931000/1000000 | loss 0.000061 | test 0.000002 | lr 3.52e-04 | 72 it/s | eta 16m | 216.6m elapsed | |
| itr 932000/1000000 | loss 0.000003 | test 0.000006 | lr 3.42e-04 | 72 it/s | eta 16m | 216.9m elapsed | |
| itr 933000/1000000 | loss 0.000009 | test 0.000003 | lr 3.32e-04 | 72 it/s | eta 16m | 217.1m elapsed | |
| itr 934000/1000000 | loss 0.000011 | test 0.000003 | lr 3.22e-04 | 72 it/s | eta 15m | 217.4m elapsed | |
| itr 935000/1000000 | loss 0.000019 | test 0.000016 | lr 3.13e-04 | 72 it/s | eta 15m | 217.6m elapsed | |
| itr 936000/1000000 | loss 0.000049 | test 0.000038 | lr 3.03e-04 | 72 it/s | eta 15m | 217.9m elapsed | |
| itr 937000/1000000 | loss 0.000008 | test 0.000079 | lr 2.94e-04 | 72 it/s | eta 15m | 218.2m elapsed | |
| itr 938000/1000000 | loss 0.000016 | test 0.000005 | lr 2.85e-04 | 72 it/s | eta 14m | 218.4m elapsed | |
| itr 939000/1000000 | loss 0.000005 | test 0.000027 | lr 2.76e-04 | 72 it/s | eta 14m | 218.7m elapsed | |
| itr 940000/1000000 | loss 0.000175 | test 0.000100 | lr 2.67e-04 | 72 it/s | eta 14m | 218.9m elapsed | |
| itr 941000/1000000 | loss 0.000017 | test 0.000025 | lr 2.58e-04 | 72 it/s | eta 14m | 219.2m elapsed | |
| itr 942000/1000000 | loss 0.000007 | test 0.000022 | lr 2.49e-04 | 72 it/s | eta 14m | 219.4m elapsed | |
| itr 943000/1000000 | loss 0.000004 | test 0.000003 | lr 2.41e-04 | 72 it/s | eta 13m | 219.7m elapsed | |
| itr 944000/1000000 | loss 0.000008 | test 0.000004 | lr 2.33e-04 | 72 it/s | eta 13m | 220.0m elapsed | |
| itr 945000/1000000 | loss 0.000029 | test 0.000142 | lr 2.24e-04 | 72 it/s | eta 13m | 220.2m elapsed | |
| itr 946000/1000000 | loss 0.000019 | test 0.000783 | lr 2.16e-04 | 72 it/s | eta 13m | 220.5m elapsed | |
| itr 947000/1000000 | loss 0.000038 | test 0.000014 | lr 2.09e-04 | 71 it/s | eta 12m | 220.7m elapsed | |
| itr 948000/1000000 | loss 0.000223 | test 0.000052 | lr 2.01e-04 | 71 it/s | eta 12m | 221.0m elapsed | |
| itr 949000/1000000 | loss 0.000006 | test 0.000042 | lr 1.93e-04 | 71 it/s | eta 12m | 221.3m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt950000.pt (221.5m) | |
| itr 950000/1000000 | loss 0.000010 | test 0.000004 | lr 1.86e-04 | 71 it/s | eta 12m | 221.5m elapsed | |
| itr 951000/1000000 | loss 0.000052 | test 0.000010 | lr 1.78e-04 | 71 it/s | eta 11m | 221.8m elapsed | |
| itr 952000/1000000 | loss 0.000006 | test 0.000003 | lr 1.71e-04 | 71 it/s | eta 11m | 222.0m elapsed | |
| itr 953000/1000000 | loss 0.000003 | test 0.000034 | lr 1.64e-04 | 71 it/s | eta 11m | 222.3m elapsed | |
| itr 954000/1000000 | loss 0.000066 | test 0.000029 | lr 1.57e-04 | 71 it/s | eta 11m | 222.6m elapsed | |
| itr 955000/1000000 | loss 0.000028 | test 0.000016 | lr 1.51e-04 | 71 it/s | eta 10m | 222.8m elapsed | |
| itr 956000/1000000 | loss 0.000004 | test 0.000041 | lr 1.44e-04 | 71 it/s | eta 10m | 223.1m elapsed | |
| itr 957000/1000000 | loss 0.000027 | test 0.000003 | lr 1.38e-04 | 71 it/s | eta 10m | 223.3m elapsed | |
| itr 958000/1000000 | loss 0.000102 | test 0.000303 | lr 1.31e-04 | 71 it/s | eta 10m | 223.6m elapsed | |
| itr 959000/1000000 | loss 0.000031 | test 0.000007 | lr 1.25e-04 | 71 it/s | eta 10m | 223.8m elapsed | |
| itr 960000/1000000 | loss 0.000007 | test 0.000060 | lr 1.19e-04 | 71 it/s | eta 9m | 224.1m elapsed | |
| itr 961000/1000000 | loss 0.000101 | test 0.000005 | lr 1.13e-04 | 71 it/s | eta 9m | 224.4m elapsed | |
| itr 962000/1000000 | loss 0.000009 | test 0.000003 | lr 1.08e-04 | 71 it/s | eta 9m | 224.6m elapsed | |
| itr 963000/1000000 | loss 0.000004 | test 0.000023 | lr 1.02e-04 | 71 it/s | eta 9m | 224.9m elapsed | |
| itr 964000/1000000 | loss 0.000007 | test 0.000005 | lr 9.69e-05 | 71 it/s | eta 8m | 225.1m elapsed | |
| itr 965000/1000000 | loss 0.000012 | test 0.000150 | lr 9.16e-05 | 71 it/s | eta 8m | 225.4m elapsed | |
| itr 966000/1000000 | loss 0.000099 | test 0.000002 | lr 8.65e-05 | 71 it/s | eta 8m | 225.7m elapsed | |
| itr 967000/1000000 | loss 0.000135 | test 0.000002 | lr 8.16e-05 | 71 it/s | eta 8m | 225.9m elapsed | |
| itr 968000/1000000 | loss 0.000017 | test 0.000012 | lr 7.68e-05 | 71 it/s | eta 7m | 226.2m elapsed | |
| itr 969000/1000000 | loss 0.000057 | test 0.000004 | lr 7.21e-05 | 71 it/s | eta 7m | 226.4m elapsed | |
| itr 970000/1000000 | loss 0.000203 | test 0.000066 | lr 6.76e-05 | 71 it/s | eta 7m | 226.7m elapsed | |
| itr 971000/1000000 | loss 0.000156 | test 0.000016 | lr 6.32e-05 | 71 it/s | eta 7m | 226.9m elapsed | |
| itr 972000/1000000 | loss 0.000279 | test 0.000001 | lr 5.90e-05 | 71 it/s | eta 7m | 227.2m elapsed | |
| itr 973000/1000000 | loss 0.002399 | test 0.000005 | lr 5.49e-05 | 71 it/s | eta 6m | 227.4m elapsed | |
| itr 974000/1000000 | loss 0.000100 | test 0.000003 | lr 5.10e-05 | 71 it/s | eta 6m | 227.7m elapsed | |
| itr 975000/1000000 | loss 0.000110 | test 0.000004 | lr 4.73e-05 | 71 it/s | eta 6m | 228.0m elapsed | |
| itr 976000/1000000 | loss 0.000087 | test 0.000001 | lr 4.36e-05 | 71 it/s | eta 6m | 228.2m elapsed | |
| itr 977000/1000000 | loss 0.000002 | test 0.000002 | lr 4.02e-05 | 71 it/s | eta 5m | 228.5m elapsed | |
| itr 978000/1000000 | loss 0.000002 | test 0.000002 | lr 3.68e-05 | 71 it/s | eta 5m | 228.7m elapsed | |
| itr 979000/1000000 | loss 0.000015 | test 0.000051 | lr 3.36e-05 | 71 it/s | eta 5m | 229.0m elapsed | |
| itr 980000/1000000 | loss 0.000238 | test 0.000004 | lr 3.06e-05 | 71 it/s | eta 5m | 229.3m elapsed | |
| itr 981000/1000000 | loss 0.000280 | test 0.000291 | lr 2.77e-05 | 71 it/s | eta 4m | 229.5m elapsed | |
| itr 982000/1000000 | loss 0.000012 | test 0.000006 | lr 2.50e-05 | 71 it/s | eta 4m | 229.8m elapsed | |
| itr 983000/1000000 | loss 0.000007 | test 0.000014 | lr 2.24e-05 | 71 it/s | eta 4m | 230.0m elapsed | |
| itr 984000/1000000 | loss 0.000253 | test 0.000184 | lr 2.00e-05 | 71 it/s | eta 4m | 230.3m elapsed | |
| itr 985000/1000000 | loss 0.000007 | test 0.000005 | lr 1.77e-05 | 71 it/s | eta 4m | 230.5m elapsed | |
| itr 986000/1000000 | loss 0.000161 | test 0.000002 | lr 1.55e-05 | 71 it/s | eta 3m | 230.8m elapsed | |
| itr 987000/1000000 | loss 0.000007 | test 0.000008 | lr 1.35e-05 | 71 it/s | eta 3m | 231.1m elapsed | |
| itr 988000/1000000 | loss 0.000029 | test 0.000013 | lr 1.17e-05 | 71 it/s | eta 3m | 231.3m elapsed | |
| itr 989000/1000000 | loss 0.000049 | test 0.000004 | lr 9.96e-06 | 71 it/s | eta 3m | 231.6m elapsed | |
| itr 990000/1000000 | loss 0.000046 | test 0.000028 | lr 8.40e-06 | 71 it/s | eta 2m | 231.8m elapsed | |
| itr 991000/1000000 | loss 0.000128 | test 0.000019 | lr 7.00e-06 | 71 it/s | eta 2m | 232.1m elapsed | |
| itr 992000/1000000 | loss 0.000009 | test 0.000002 | lr 5.74e-06 | 71 it/s | eta 2m | 232.3m elapsed | |
| itr 993000/1000000 | loss 0.000042 | test 0.000004 | lr 4.63e-06 | 71 it/s | eta 2m | 232.6m elapsed | |
| itr 994000/1000000 | loss 0.000041 | test 0.000003 | lr 3.67e-06 | 71 it/s | eta 1m | 232.9m elapsed | |
| itr 995000/1000000 | loss 0.000006 | test 0.000002 | lr 2.85e-06 | 71 it/s | eta 1m | 233.1m elapsed | |
| itr 996000/1000000 | loss 0.000030 | test 0.000025 | lr 2.18e-06 | 71 it/s | eta 1m | 233.4m elapsed | |
| itr 997000/1000000 | loss 0.000084 | test 0.000003 | lr 1.67e-06 | 71 it/s | eta 1m | 233.6m elapsed | |
| itr 998000/1000000 | loss 0.000064 | test 0.000086 | lr 1.30e-06 | 71 it/s | eta 0m | 233.9m elapsed | |
| itr 999000/1000000 | loss 0.000005 | test 0.000014 | lr 1.07e-06 | 71 it/s | eta 0m | 234.2m elapsed | |
| [CKPT] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__ckpt1000000.pt (234.4m) | |
| [FINAL] Saved sortgpt_k16_methfixed_mlp1_L2_N256_E64_pos0_fln1_wd0p0_lr0p03_dseed1337_iseed1337__final.pt | |
| Finished 1000000 iterations in 234.4m (3.91h) | |
| History saved to /mnt/task_runtime/sort-llm/1000k-checkpoints/training_history.json | |