| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 1316, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.030395136778115502, |
| "grad_norm": 3.7902989768079007, |
| "learning_rate": 5e-06, |
| "loss": 0.9232, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.060790273556231005, |
| "grad_norm": 1.3254298624871779, |
| "learning_rate": 5e-06, |
| "loss": 0.8077, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0911854103343465, |
| "grad_norm": 1.3557713374081568, |
| "learning_rate": 5e-06, |
| "loss": 0.7712, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.12158054711246201, |
| "grad_norm": 0.852142730713199, |
| "learning_rate": 5e-06, |
| "loss": 0.7478, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1519756838905775, |
| "grad_norm": 1.1589303579731418, |
| "learning_rate": 5e-06, |
| "loss": 0.7319, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.182370820668693, |
| "grad_norm": 0.8100902744903822, |
| "learning_rate": 5e-06, |
| "loss": 0.7195, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2127659574468085, |
| "grad_norm": 0.8673008001709136, |
| "learning_rate": 5e-06, |
| "loss": 0.7081, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.24316109422492402, |
| "grad_norm": 0.7423688598113258, |
| "learning_rate": 5e-06, |
| "loss": 0.7003, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2735562310030395, |
| "grad_norm": 0.6335389419895006, |
| "learning_rate": 5e-06, |
| "loss": 0.6972, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.303951367781155, |
| "grad_norm": 0.7817561676931757, |
| "learning_rate": 5e-06, |
| "loss": 0.6846, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3343465045592705, |
| "grad_norm": 0.7502751260547881, |
| "learning_rate": 5e-06, |
| "loss": 0.6895, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.364741641337386, |
| "grad_norm": 0.7472084109089758, |
| "learning_rate": 5e-06, |
| "loss": 0.6807, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.3951367781155015, |
| "grad_norm": 0.7481089081787459, |
| "learning_rate": 5e-06, |
| "loss": 0.6864, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.425531914893617, |
| "grad_norm": 0.5755746859013778, |
| "learning_rate": 5e-06, |
| "loss": 0.6822, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.45592705167173253, |
| "grad_norm": 0.5619791086915955, |
| "learning_rate": 5e-06, |
| "loss": 0.6765, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.48632218844984804, |
| "grad_norm": 0.7084220069778482, |
| "learning_rate": 5e-06, |
| "loss": 0.6842, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.5167173252279635, |
| "grad_norm": 0.55077555413655, |
| "learning_rate": 5e-06, |
| "loss": 0.6765, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.547112462006079, |
| "grad_norm": 0.6554653563877829, |
| "learning_rate": 5e-06, |
| "loss": 0.6848, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.5775075987841946, |
| "grad_norm": 0.5649979229906555, |
| "learning_rate": 5e-06, |
| "loss": 0.671, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.60790273556231, |
| "grad_norm": 0.5095265209297971, |
| "learning_rate": 5e-06, |
| "loss": 0.6708, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6382978723404256, |
| "grad_norm": 0.6395559343113024, |
| "learning_rate": 5e-06, |
| "loss": 0.6724, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.668693009118541, |
| "grad_norm": 0.6091505668541892, |
| "learning_rate": 5e-06, |
| "loss": 0.672, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.6990881458966566, |
| "grad_norm": 0.5400604319742796, |
| "learning_rate": 5e-06, |
| "loss": 0.6689, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.729483282674772, |
| "grad_norm": 0.6227042628088405, |
| "learning_rate": 5e-06, |
| "loss": 0.6683, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.7598784194528876, |
| "grad_norm": 0.6561196138883073, |
| "learning_rate": 5e-06, |
| "loss": 0.6639, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.790273556231003, |
| "grad_norm": 0.5494056090536018, |
| "learning_rate": 5e-06, |
| "loss": 0.6687, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.8206686930091185, |
| "grad_norm": 0.6509251502203363, |
| "learning_rate": 5e-06, |
| "loss": 0.6628, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.851063829787234, |
| "grad_norm": 0.6562005533510465, |
| "learning_rate": 5e-06, |
| "loss": 0.6617, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.8814589665653495, |
| "grad_norm": 0.588457453543092, |
| "learning_rate": 5e-06, |
| "loss": 0.66, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.9118541033434651, |
| "grad_norm": 0.6838489054282243, |
| "learning_rate": 5e-06, |
| "loss": 0.6625, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9422492401215805, |
| "grad_norm": 0.6397607010295455, |
| "learning_rate": 5e-06, |
| "loss": 0.657, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.9726443768996961, |
| "grad_norm": 0.5485858261367895, |
| "learning_rate": 5e-06, |
| "loss": 0.658, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6595161557197571, |
| "eval_runtime": 177.2504, |
| "eval_samples_per_second": 49.991, |
| "eval_steps_per_second": 0.395, |
| "step": 329 |
| }, |
| { |
| "epoch": 1.0030395136778116, |
| "grad_norm": 0.7748104599618261, |
| "learning_rate": 5e-06, |
| "loss": 0.6586, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.033434650455927, |
| "grad_norm": 0.7796307948646688, |
| "learning_rate": 5e-06, |
| "loss": 0.621, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.0638297872340425, |
| "grad_norm": 0.5749293589407395, |
| "learning_rate": 5e-06, |
| "loss": 0.6134, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.094224924012158, |
| "grad_norm": 0.5746598182279792, |
| "learning_rate": 5e-06, |
| "loss": 0.6232, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.1246200607902737, |
| "grad_norm": 0.6407579223470411, |
| "learning_rate": 5e-06, |
| "loss": 0.6171, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.155015197568389, |
| "grad_norm": 0.5711034097494054, |
| "learning_rate": 5e-06, |
| "loss": 0.6182, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.1854103343465046, |
| "grad_norm": 0.5462611660716852, |
| "learning_rate": 5e-06, |
| "loss": 0.6121, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.21580547112462, |
| "grad_norm": 0.559220138591582, |
| "learning_rate": 5e-06, |
| "loss": 0.6118, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.2462006079027357, |
| "grad_norm": 0.6242230418554062, |
| "learning_rate": 5e-06, |
| "loss": 0.6111, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.2765957446808511, |
| "grad_norm": 0.758542684448963, |
| "learning_rate": 5e-06, |
| "loss": 0.6153, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.3069908814589666, |
| "grad_norm": 0.7000814442628917, |
| "learning_rate": 5e-06, |
| "loss": 0.6156, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.337386018237082, |
| "grad_norm": 0.5497316980656964, |
| "learning_rate": 5e-06, |
| "loss": 0.6152, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.3677811550151975, |
| "grad_norm": 0.5808146964585804, |
| "learning_rate": 5e-06, |
| "loss": 0.6163, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.3981762917933132, |
| "grad_norm": 0.7642249420211059, |
| "learning_rate": 5e-06, |
| "loss": 0.6122, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 0.830645214703665, |
| "learning_rate": 5e-06, |
| "loss": 0.615, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.458966565349544, |
| "grad_norm": 0.5443619869553693, |
| "learning_rate": 5e-06, |
| "loss": 0.6168, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.4893617021276595, |
| "grad_norm": 0.5381081344365592, |
| "learning_rate": 5e-06, |
| "loss": 0.6134, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.5197568389057752, |
| "grad_norm": 0.5854701007123095, |
| "learning_rate": 5e-06, |
| "loss": 0.6195, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.5501519756838906, |
| "grad_norm": 0.5202854235774086, |
| "learning_rate": 5e-06, |
| "loss": 0.6146, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.580547112462006, |
| "grad_norm": 0.5586275473819791, |
| "learning_rate": 5e-06, |
| "loss": 0.614, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.6109422492401215, |
| "grad_norm": 0.513644202200678, |
| "learning_rate": 5e-06, |
| "loss": 0.6121, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.641337386018237, |
| "grad_norm": 0.8058007149280308, |
| "learning_rate": 5e-06, |
| "loss": 0.606, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.6717325227963524, |
| "grad_norm": 0.5044382097307959, |
| "learning_rate": 5e-06, |
| "loss": 0.6122, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.702127659574468, |
| "grad_norm": 0.5443376424663797, |
| "learning_rate": 5e-06, |
| "loss": 0.6099, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.7325227963525835, |
| "grad_norm": 0.5734890227178636, |
| "learning_rate": 5e-06, |
| "loss": 0.6153, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.7629179331306992, |
| "grad_norm": 0.6406984921197459, |
| "learning_rate": 5e-06, |
| "loss": 0.6128, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.7933130699088147, |
| "grad_norm": 0.5572675755435519, |
| "learning_rate": 5e-06, |
| "loss": 0.6128, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.8237082066869301, |
| "grad_norm": 0.5350735032706304, |
| "learning_rate": 5e-06, |
| "loss": 0.6158, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.8541033434650456, |
| "grad_norm": 0.5448108006027796, |
| "learning_rate": 5e-06, |
| "loss": 0.6133, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.884498480243161, |
| "grad_norm": 0.5378299367383308, |
| "learning_rate": 5e-06, |
| "loss": 0.6107, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.9148936170212765, |
| "grad_norm": 0.4841663429658451, |
| "learning_rate": 5e-06, |
| "loss": 0.6043, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.9452887537993921, |
| "grad_norm": 0.6206310402363647, |
| "learning_rate": 5e-06, |
| "loss": 0.6098, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.9756838905775076, |
| "grad_norm": 0.5829965143789198, |
| "learning_rate": 5e-06, |
| "loss": 0.6098, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.6488195657730103, |
| "eval_runtime": 178.0481, |
| "eval_samples_per_second": 49.767, |
| "eval_steps_per_second": 0.393, |
| "step": 658 |
| }, |
| { |
| "epoch": 2.0060790273556233, |
| "grad_norm": 0.7508798660093038, |
| "learning_rate": 5e-06, |
| "loss": 0.5987, |
| "step": 660 |
| }, |
| { |
| "epoch": 2.0364741641337387, |
| "grad_norm": 0.6311828418273588, |
| "learning_rate": 5e-06, |
| "loss": 0.568, |
| "step": 670 |
| }, |
| { |
| "epoch": 2.066869300911854, |
| "grad_norm": 0.7692706573937823, |
| "learning_rate": 5e-06, |
| "loss": 0.5615, |
| "step": 680 |
| }, |
| { |
| "epoch": 2.0972644376899696, |
| "grad_norm": 0.5526369185975563, |
| "learning_rate": 5e-06, |
| "loss": 0.5647, |
| "step": 690 |
| }, |
| { |
| "epoch": 2.127659574468085, |
| "grad_norm": 0.5825813044009801, |
| "learning_rate": 5e-06, |
| "loss": 0.5658, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.1580547112462005, |
| "grad_norm": 0.6174482080267634, |
| "learning_rate": 5e-06, |
| "loss": 0.5666, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.188449848024316, |
| "grad_norm": 0.623613817254514, |
| "learning_rate": 5e-06, |
| "loss": 0.5613, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.2188449848024314, |
| "grad_norm": 0.524634593862084, |
| "learning_rate": 5e-06, |
| "loss": 0.5667, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.2492401215805473, |
| "grad_norm": 0.566645898660012, |
| "learning_rate": 5e-06, |
| "loss": 0.5628, |
| "step": 740 |
| }, |
| { |
| "epoch": 2.2796352583586628, |
| "grad_norm": 0.6365885057651556, |
| "learning_rate": 5e-06, |
| "loss": 0.5753, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.310030395136778, |
| "grad_norm": 0.801253703848877, |
| "learning_rate": 5e-06, |
| "loss": 0.571, |
| "step": 760 |
| }, |
| { |
| "epoch": 2.3404255319148937, |
| "grad_norm": 0.8023278828442812, |
| "learning_rate": 5e-06, |
| "loss": 0.5666, |
| "step": 770 |
| }, |
| { |
| "epoch": 2.370820668693009, |
| "grad_norm": 0.7164614671485612, |
| "learning_rate": 5e-06, |
| "loss": 0.57, |
| "step": 780 |
| }, |
| { |
| "epoch": 2.4012158054711246, |
| "grad_norm": 0.6976048317076531, |
| "learning_rate": 5e-06, |
| "loss": 0.5707, |
| "step": 790 |
| }, |
| { |
| "epoch": 2.43161094224924, |
| "grad_norm": 0.5859434491091309, |
| "learning_rate": 5e-06, |
| "loss": 0.5664, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.4620060790273555, |
| "grad_norm": 0.6013604895359559, |
| "learning_rate": 5e-06, |
| "loss": 0.5716, |
| "step": 810 |
| }, |
| { |
| "epoch": 2.4924012158054714, |
| "grad_norm": 0.5770646564525249, |
| "learning_rate": 5e-06, |
| "loss": 0.5698, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.522796352583587, |
| "grad_norm": 0.5743154460185586, |
| "learning_rate": 5e-06, |
| "loss": 0.5668, |
| "step": 830 |
| }, |
| { |
| "epoch": 2.5531914893617023, |
| "grad_norm": 0.5476583369006978, |
| "learning_rate": 5e-06, |
| "loss": 0.5683, |
| "step": 840 |
| }, |
| { |
| "epoch": 2.5835866261398177, |
| "grad_norm": 0.6274805119375185, |
| "learning_rate": 5e-06, |
| "loss": 0.5729, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.613981762917933, |
| "grad_norm": 0.5951521500106558, |
| "learning_rate": 5e-06, |
| "loss": 0.5725, |
| "step": 860 |
| }, |
| { |
| "epoch": 2.6443768996960486, |
| "grad_norm": 0.6316066213170742, |
| "learning_rate": 5e-06, |
| "loss": 0.577, |
| "step": 870 |
| }, |
| { |
| "epoch": 2.674772036474164, |
| "grad_norm": 0.7138887402031721, |
| "learning_rate": 5e-06, |
| "loss": 0.57, |
| "step": 880 |
| }, |
| { |
| "epoch": 2.7051671732522795, |
| "grad_norm": 0.52789291402505, |
| "learning_rate": 5e-06, |
| "loss": 0.5711, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.735562310030395, |
| "grad_norm": 0.5632737209576331, |
| "learning_rate": 5e-06, |
| "loss": 0.5631, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.7659574468085104, |
| "grad_norm": 0.5199894168279365, |
| "learning_rate": 5e-06, |
| "loss": 0.5684, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.7963525835866263, |
| "grad_norm": 0.5154434326609925, |
| "learning_rate": 5e-06, |
| "loss": 0.5712, |
| "step": 920 |
| }, |
| { |
| "epoch": 2.8267477203647418, |
| "grad_norm": 0.5568054139205092, |
| "learning_rate": 5e-06, |
| "loss": 0.5725, |
| "step": 930 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 0.5789874173104351, |
| "learning_rate": 5e-06, |
| "loss": 0.5671, |
| "step": 940 |
| }, |
| { |
| "epoch": 2.8875379939209727, |
| "grad_norm": 0.579332043481476, |
| "learning_rate": 5e-06, |
| "loss": 0.5681, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.917933130699088, |
| "grad_norm": 0.6770951766413347, |
| "learning_rate": 5e-06, |
| "loss": 0.5758, |
| "step": 960 |
| }, |
| { |
| "epoch": 2.9483282674772036, |
| "grad_norm": 0.507169174062393, |
| "learning_rate": 5e-06, |
| "loss": 0.5661, |
| "step": 970 |
| }, |
| { |
| "epoch": 2.978723404255319, |
| "grad_norm": 0.5498884808877578, |
| "learning_rate": 5e-06, |
| "loss": 0.5698, |
| "step": 980 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.6519307494163513, |
| "eval_runtime": 178.5178, |
| "eval_samples_per_second": 49.637, |
| "eval_steps_per_second": 0.392, |
| "step": 987 |
| }, |
| { |
| "epoch": 3.0091185410334345, |
| "grad_norm": 1.1362031957261596, |
| "learning_rate": 5e-06, |
| "loss": 0.5535, |
| "step": 990 |
| }, |
| { |
| "epoch": 3.0395136778115504, |
| "grad_norm": 0.8067510544416221, |
| "learning_rate": 5e-06, |
| "loss": 0.521, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.069908814589666, |
| "grad_norm": 0.6208037810435736, |
| "learning_rate": 5e-06, |
| "loss": 0.5236, |
| "step": 1010 |
| }, |
| { |
| "epoch": 3.1003039513677813, |
| "grad_norm": 0.7677671738970896, |
| "learning_rate": 5e-06, |
| "loss": 0.5199, |
| "step": 1020 |
| }, |
| { |
| "epoch": 3.1306990881458967, |
| "grad_norm": 0.6007177979811528, |
| "learning_rate": 5e-06, |
| "loss": 0.5247, |
| "step": 1030 |
| }, |
| { |
| "epoch": 3.161094224924012, |
| "grad_norm": 0.553114679192602, |
| "learning_rate": 5e-06, |
| "loss": 0.523, |
| "step": 1040 |
| }, |
| { |
| "epoch": 3.1914893617021276, |
| "grad_norm": 0.5486986330974329, |
| "learning_rate": 5e-06, |
| "loss": 0.5274, |
| "step": 1050 |
| }, |
| { |
| "epoch": 3.221884498480243, |
| "grad_norm": 0.6728734324135659, |
| "learning_rate": 5e-06, |
| "loss": 0.5196, |
| "step": 1060 |
| }, |
| { |
| "epoch": 3.2522796352583585, |
| "grad_norm": 0.5858866684023993, |
| "learning_rate": 5e-06, |
| "loss": 0.5281, |
| "step": 1070 |
| }, |
| { |
| "epoch": 3.282674772036474, |
| "grad_norm": 1.2273835417137062, |
| "learning_rate": 5e-06, |
| "loss": 0.525, |
| "step": 1080 |
| }, |
| { |
| "epoch": 3.31306990881459, |
| "grad_norm": 0.6823836072235112, |
| "learning_rate": 5e-06, |
| "loss": 0.5245, |
| "step": 1090 |
| }, |
| { |
| "epoch": 3.3434650455927053, |
| "grad_norm": 0.8267646820126024, |
| "learning_rate": 5e-06, |
| "loss": 0.5298, |
| "step": 1100 |
| }, |
| { |
| "epoch": 3.3738601823708207, |
| "grad_norm": 0.6061310756143279, |
| "learning_rate": 5e-06, |
| "loss": 0.521, |
| "step": 1110 |
| }, |
| { |
| "epoch": 3.404255319148936, |
| "grad_norm": 0.6277299404483033, |
| "learning_rate": 5e-06, |
| "loss": 0.5251, |
| "step": 1120 |
| }, |
| { |
| "epoch": 3.4346504559270516, |
| "grad_norm": 0.6944146885131118, |
| "learning_rate": 5e-06, |
| "loss": 0.5276, |
| "step": 1130 |
| }, |
| { |
| "epoch": 3.465045592705167, |
| "grad_norm": 0.6596324096264304, |
| "learning_rate": 5e-06, |
| "loss": 0.5271, |
| "step": 1140 |
| }, |
| { |
| "epoch": 3.4954407294832825, |
| "grad_norm": 0.5912481173983363, |
| "learning_rate": 5e-06, |
| "loss": 0.5298, |
| "step": 1150 |
| }, |
| { |
| "epoch": 3.5258358662613984, |
| "grad_norm": 0.5979661747536312, |
| "learning_rate": 5e-06, |
| "loss": 0.5268, |
| "step": 1160 |
| }, |
| { |
| "epoch": 3.556231003039514, |
| "grad_norm": 0.5714017426541542, |
| "learning_rate": 5e-06, |
| "loss": 0.5255, |
| "step": 1170 |
| }, |
| { |
| "epoch": 3.5866261398176293, |
| "grad_norm": 0.5773057743245565, |
| "learning_rate": 5e-06, |
| "loss": 0.528, |
| "step": 1180 |
| }, |
| { |
| "epoch": 3.617021276595745, |
| "grad_norm": 0.6774448242359234, |
| "learning_rate": 5e-06, |
| "loss": 0.5265, |
| "step": 1190 |
| }, |
| { |
| "epoch": 3.6474164133738602, |
| "grad_norm": 0.5305102122719293, |
| "learning_rate": 5e-06, |
| "loss": 0.5259, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.6778115501519757, |
| "grad_norm": 0.6165936573363839, |
| "learning_rate": 5e-06, |
| "loss": 0.5287, |
| "step": 1210 |
| }, |
| { |
| "epoch": 3.708206686930091, |
| "grad_norm": 0.8893565211407252, |
| "learning_rate": 5e-06, |
| "loss": 0.5272, |
| "step": 1220 |
| }, |
| { |
| "epoch": 3.7386018237082066, |
| "grad_norm": 0.5376687023985922, |
| "learning_rate": 5e-06, |
| "loss": 0.5272, |
| "step": 1230 |
| }, |
| { |
| "epoch": 3.768996960486322, |
| "grad_norm": 0.5976939651233717, |
| "learning_rate": 5e-06, |
| "loss": 0.5297, |
| "step": 1240 |
| }, |
| { |
| "epoch": 3.7993920972644375, |
| "grad_norm": 0.6169986716184761, |
| "learning_rate": 5e-06, |
| "loss": 0.5252, |
| "step": 1250 |
| }, |
| { |
| "epoch": 3.829787234042553, |
| "grad_norm": 0.6502385131800887, |
| "learning_rate": 5e-06, |
| "loss": 0.5291, |
| "step": 1260 |
| }, |
| { |
| "epoch": 3.860182370820669, |
| "grad_norm": 0.6127072490245848, |
| "learning_rate": 5e-06, |
| "loss": 0.5286, |
| "step": 1270 |
| }, |
| { |
| "epoch": 3.8905775075987843, |
| "grad_norm": 0.6567779052148662, |
| "learning_rate": 5e-06, |
| "loss": 0.5275, |
| "step": 1280 |
| }, |
| { |
| "epoch": 3.9209726443768997, |
| "grad_norm": 0.5588422551567276, |
| "learning_rate": 5e-06, |
| "loss": 0.5257, |
| "step": 1290 |
| }, |
| { |
| "epoch": 3.951367781155015, |
| "grad_norm": 0.5921220398068368, |
| "learning_rate": 5e-06, |
| "loss": 0.535, |
| "step": 1300 |
| }, |
| { |
| "epoch": 3.9817629179331306, |
| "grad_norm": 0.5516981057362507, |
| "learning_rate": 5e-06, |
| "loss": 0.5357, |
| "step": 1310 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.6647769808769226, |
| "eval_runtime": 177.56, |
| "eval_samples_per_second": 49.904, |
| "eval_steps_per_second": 0.394, |
| "step": 1316 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 1316, |
| "total_flos": 2203930255687680.0, |
| "train_loss": 0.6010652760604233, |
| "train_runtime": 39415.9831, |
| "train_samples_per_second": 17.085, |
| "train_steps_per_second": 0.033 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1316, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 2203930255687680.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
