| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9946777054997042, | |
| "eval_steps": 500, | |
| "global_step": 1266, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02365464222353637, | |
| "grad_norm": 39.04922181795541, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9233, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04730928444707274, | |
| "grad_norm": 8.275301054500245, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8198, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0709639266706091, | |
| "grad_norm": 16.91349063149131, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8094, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09461856889414548, | |
| "grad_norm": 14.148988171179118, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7679, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11827321111768184, | |
| "grad_norm": 1.026404466612184, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7523, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1419278533412182, | |
| "grad_norm": 0.8542225183892468, | |
| "learning_rate": 5e-06, | |
| "loss": 0.725, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16558249556475457, | |
| "grad_norm": 0.7426518873227826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7185, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18923713778829096, | |
| "grad_norm": 0.6764382829611749, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6999, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21289178001182732, | |
| "grad_norm": 0.5663920137594394, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23654642223536368, | |
| "grad_norm": 0.6218835377066562, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6968, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26020106445890007, | |
| "grad_norm": 0.601497886261039, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6885, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2838557066824364, | |
| "grad_norm": 0.8786039473525534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6863, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3075103489059728, | |
| "grad_norm": 0.5373447312315734, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6792, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33116499112950915, | |
| "grad_norm": 0.5195473153997355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6746, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35481963335304556, | |
| "grad_norm": 0.5999120946052041, | |
| "learning_rate": 5e-06, | |
| "loss": 0.68, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3784742755765819, | |
| "grad_norm": 0.5351205582865509, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6766, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4021289178001183, | |
| "grad_norm": 0.5425010920017291, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6839, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42578356002365464, | |
| "grad_norm": 0.702582958286065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6711, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 1.2564450479675764, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6776, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47309284447072736, | |
| "grad_norm": 0.6226292820244915, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6695, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4967474866942638, | |
| "grad_norm": 0.6729451633589562, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6656, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5204021289178001, | |
| "grad_norm": 0.72360498041814, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6699, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5440567711413364, | |
| "grad_norm": 0.5730443009789895, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6693, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5677114133648729, | |
| "grad_norm": 0.6304204873609028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6564, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5913660555884093, | |
| "grad_norm": 0.6327686473365169, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6707, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6150206978119456, | |
| "grad_norm": 0.5640335014419563, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6617, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.638675340035482, | |
| "grad_norm": 0.6026872513783592, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6711, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6623299822590183, | |
| "grad_norm": 0.5194797310260643, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6561, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6859846244825547, | |
| "grad_norm": 0.6658270095766984, | |
| "learning_rate": 5e-06, | |
| "loss": 0.663, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7096392667060911, | |
| "grad_norm": 0.5259962549449988, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6511, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7332939089296274, | |
| "grad_norm": 0.5776532705758929, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6649, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7569485511531638, | |
| "grad_norm": 0.5249892835904177, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6648, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7806031933767001, | |
| "grad_norm": 0.5092145613062358, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6614, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8042578356002366, | |
| "grad_norm": 0.5273167065626364, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6468, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8279124778237729, | |
| "grad_norm": 0.5666036582386984, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6562, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8515671200473093, | |
| "grad_norm": 0.6164474600239763, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6544, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8752217622708457, | |
| "grad_norm": 0.5854672267431167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6547, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 0.5313196039449892, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6584, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9225310467179184, | |
| "grad_norm": 0.5598019500152581, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6533, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9461856889414547, | |
| "grad_norm": 0.6003027055491813, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6458, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9698403311649911, | |
| "grad_norm": 0.6341763962447327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.656, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9934949733885275, | |
| "grad_norm": 0.6083507877729101, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6538, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9982259018332348, | |
| "eval_loss": 0.6558582186698914, | |
| "eval_runtime": 224.885, | |
| "eval_samples_per_second": 50.635, | |
| "eval_steps_per_second": 0.396, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.0171496156120639, | |
| "grad_norm": 0.9361782463296332, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6157, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0408042578356003, | |
| "grad_norm": 0.6204113010596938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6065, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0644589000591367, | |
| "grad_norm": 0.6564336264095381, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6048, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0881135422826729, | |
| "grad_norm": 0.5555833545533679, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6072, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1117681845062093, | |
| "grad_norm": 0.568736434370096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6026, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1354228267297457, | |
| "grad_norm": 0.5963174527245159, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6041, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1590774689532821, | |
| "grad_norm": 0.6296624775692966, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6036, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1827321111768185, | |
| "grad_norm": 0.7667349314546962, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6068, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2063867534003547, | |
| "grad_norm": 0.6034621980970892, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2300413956238911, | |
| "grad_norm": 0.5825117431703367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6026, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2536960378474276, | |
| "grad_norm": 0.5671081402783421, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.277350680070964, | |
| "grad_norm": 0.5309591912112671, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6132, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3010053222945004, | |
| "grad_norm": 0.5636046858771947, | |
| "learning_rate": 5e-06, | |
| "loss": 0.605, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3246599645180366, | |
| "grad_norm": 0.6623955102141809, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6082, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.348314606741573, | |
| "grad_norm": 0.5742305096790601, | |
| "learning_rate": 5e-06, | |
| "loss": 0.605, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3719692489651094, | |
| "grad_norm": 0.5167065988140831, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6091, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3956238911886458, | |
| "grad_norm": 0.5112713876137833, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6049, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4192785334121822, | |
| "grad_norm": 0.515536375353522, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6079, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4429331756357184, | |
| "grad_norm": 0.5943800369847494, | |
| "learning_rate": 5e-06, | |
| "loss": 0.602, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4665878178592548, | |
| "grad_norm": 0.5570413849081146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6074, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4902424600827913, | |
| "grad_norm": 0.5383074416990815, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6055, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5138971023063275, | |
| "grad_norm": 0.6221748842819845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6048, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.537551744529864, | |
| "grad_norm": 0.623130737085543, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6124, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5612063867534003, | |
| "grad_norm": 0.7728758992657894, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6073, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5848610289769367, | |
| "grad_norm": 0.5531126954202661, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6023, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.6085156712004731, | |
| "grad_norm": 0.8207249388527519, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6041, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6321703134240093, | |
| "grad_norm": 0.7382668830128054, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6027, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.655824955647546, | |
| "grad_norm": 0.8181634349883082, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6077, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6794795978710821, | |
| "grad_norm": 0.5715750112816181, | |
| "learning_rate": 5e-06, | |
| "loss": 0.603, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.7031342400946186, | |
| "grad_norm": 0.564060422032355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6137, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.726788882318155, | |
| "grad_norm": 0.5112934215435977, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6041, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7504435245416912, | |
| "grad_norm": 0.6498040890743698, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6038, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7740981667652278, | |
| "grad_norm": 0.6625174306160165, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.797752808988764, | |
| "grad_norm": 0.5200239654238437, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8214074512123004, | |
| "grad_norm": 0.5056250667365105, | |
| "learning_rate": 5e-06, | |
| "loss": 0.601, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8450620934358368, | |
| "grad_norm": 0.5465224841554837, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6043, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.868716735659373, | |
| "grad_norm": 0.5173445168820222, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6051, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8923713778829097, | |
| "grad_norm": 0.5037163086029489, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6071, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9160260201064458, | |
| "grad_norm": 0.5032092904194995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6097, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.9396806623299823, | |
| "grad_norm": 0.5153373413177225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6017, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.9633353045535187, | |
| "grad_norm": 0.48445434626456924, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6097, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9869899467770549, | |
| "grad_norm": 0.5493690840998718, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5996, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.9988172678888232, | |
| "eval_loss": 0.6458428502082825, | |
| "eval_runtime": 226.2611, | |
| "eval_samples_per_second": 50.327, | |
| "eval_steps_per_second": 0.393, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 2.0106445890005915, | |
| "grad_norm": 0.6225484532666892, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5795, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.0342992312241277, | |
| "grad_norm": 0.5819857678964343, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5553, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.057953873447664, | |
| "grad_norm": 0.7185360534865078, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5506, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.0816085156712005, | |
| "grad_norm": 0.5134284842767335, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5539, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.5986326239884353, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5609, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.1289178001182734, | |
| "grad_norm": 0.579714763513885, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5546, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1525724423418096, | |
| "grad_norm": 0.570292196409214, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5586, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.1762270845653457, | |
| "grad_norm": 0.5811117001743673, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5585, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1998817267888824, | |
| "grad_norm": 0.554144816987719, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5562, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2235363690124186, | |
| "grad_norm": 0.6493826388527278, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5565, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.247191011235955, | |
| "grad_norm": 0.5220557856218626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.2708456534594914, | |
| "grad_norm": 0.6378102281048501, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5602, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.2945002956830276, | |
| "grad_norm": 0.5497371876386185, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5628, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.3181549379065642, | |
| "grad_norm": 0.6521682175920844, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5565, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3418095801301004, | |
| "grad_norm": 0.5734936169662879, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5674, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.365464222353637, | |
| "grad_norm": 0.5394258314592499, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5569, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3891188645771733, | |
| "grad_norm": 0.5306593171364488, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5502, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4127735068007095, | |
| "grad_norm": 0.5344199954837688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5549, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.436428149024246, | |
| "grad_norm": 0.5892751227456119, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5533, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4600827912477823, | |
| "grad_norm": 0.6529042003930223, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5613, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.483737433471319, | |
| "grad_norm": 0.5765438425321338, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5646, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.507392075694855, | |
| "grad_norm": 0.6764490044193554, | |
| "learning_rate": 5e-06, | |
| "loss": 0.567, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5310467179183913, | |
| "grad_norm": 0.5365218264481744, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5532, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.554701360141928, | |
| "grad_norm": 0.6033785399498255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5622, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.578356002365464, | |
| "grad_norm": 0.8004909937255467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5661, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.6020106445890008, | |
| "grad_norm": 0.5819582134735406, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5616, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.625665286812537, | |
| "grad_norm": 0.5537773395049099, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5628, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.649319929036073, | |
| "grad_norm": 0.5539615560141525, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5648, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.67297457125961, | |
| "grad_norm": 0.6206027218523953, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5643, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.696629213483146, | |
| "grad_norm": 0.5108322877934205, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5586, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7202838557066826, | |
| "grad_norm": 0.48797735494965916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5563, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.743938497930219, | |
| "grad_norm": 0.5823974142352172, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.767593140153755, | |
| "grad_norm": 0.8599218035136146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5723, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.7912477823772917, | |
| "grad_norm": 0.6555716714163583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5633, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.814902424600828, | |
| "grad_norm": 0.49879910164951613, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5581, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.8385570668243645, | |
| "grad_norm": 0.5241725506783274, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5623, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.8622117090479007, | |
| "grad_norm": 0.6173811070502804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.885866351271437, | |
| "grad_norm": 0.5397292738316359, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5642, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.9095209934949735, | |
| "grad_norm": 0.7053290870019903, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5593, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.9331756357185097, | |
| "grad_norm": 0.5500348460578961, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5591, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.9568302779420463, | |
| "grad_norm": 0.5833114667049699, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5649, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.9804849201655825, | |
| "grad_norm": 0.569413301750619, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5577, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.9946777054997042, | |
| "eval_loss": 0.648719847202301, | |
| "eval_runtime": 225.8886, | |
| "eval_samples_per_second": 50.41, | |
| "eval_steps_per_second": 0.394, | |
| "step": 1266 | |
| }, | |
| { | |
| "epoch": 2.9946777054997042, | |
| "step": 1266, | |
| "total_flos": 2120178393415680.0, | |
| "train_loss": 0.6180764295478568, | |
| "train_runtime": 37891.5513, | |
| "train_samples_per_second": 17.129, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1266, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2120178393415680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |