| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00444780500822844, | |
| "eval_steps": 10, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.447805008228439e-05, | |
| "grad_norm": 0.5683791637420654, | |
| "learning_rate": 9.99995774416091e-07, | |
| "loss": 2.5379, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.447805008228439e-05, | |
| "eval_loss": 2.2479803562164307, | |
| "eval_runtime": 228.3596, | |
| "eval_samples_per_second": 0.28, | |
| "eval_steps_per_second": 0.07, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.895610016456878e-05, | |
| "grad_norm": 0.48047935962677, | |
| "learning_rate": 9.999915484938526e-07, | |
| "loss": 2.7954, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001334341502468532, | |
| "grad_norm": 0.41253846883773804, | |
| "learning_rate": 9.999873222332442e-07, | |
| "loss": 2.5331, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00017791220032913757, | |
| "grad_norm": 0.5433268547058105, | |
| "learning_rate": 9.999830956342252e-07, | |
| "loss": 2.6313, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00022239025041142198, | |
| "grad_norm": 0.4853809177875519, | |
| "learning_rate": 9.999788686967546e-07, | |
| "loss": 3.0209, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002668683004937064, | |
| "grad_norm": 0.41539642214775085, | |
| "learning_rate": 9.999746414207922e-07, | |
| "loss": 2.1449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00031134635057599076, | |
| "grad_norm": 0.38092610239982605, | |
| "learning_rate": 9.999704138062971e-07, | |
| "loss": 2.7408, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00035582440065827514, | |
| "grad_norm": 0.42732885479927063, | |
| "learning_rate": 9.999661858532288e-07, | |
| "loss": 2.6069, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004003024507405595, | |
| "grad_norm": 0.385442852973938, | |
| "learning_rate": 9.999619575615465e-07, | |
| "loss": 2.4027, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00044478050082284395, | |
| "grad_norm": 0.5769224762916565, | |
| "learning_rate": 9.999577289312093e-07, | |
| "loss": 2.7377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00044478050082284395, | |
| "eval_loss": 2.127828598022461, | |
| "eval_runtime": 240.4406, | |
| "eval_samples_per_second": 0.266, | |
| "eval_steps_per_second": 0.067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004892585509051283, | |
| "grad_norm": 0.3700040578842163, | |
| "learning_rate": 9.999534999621769e-07, | |
| "loss": 2.4942, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005337366009874128, | |
| "grad_norm": 0.564141571521759, | |
| "learning_rate": 9.999492706544085e-07, | |
| "loss": 2.199, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005782146510696971, | |
| "grad_norm": 0.38583478331565857, | |
| "learning_rate": 9.999450410078634e-07, | |
| "loss": 2.5461, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006226927011519815, | |
| "grad_norm": 0.28498372435569763, | |
| "learning_rate": 9.999408110225007e-07, | |
| "loss": 2.1158, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006671707512342659, | |
| "grad_norm": 0.3804119825363159, | |
| "learning_rate": 9.999365806982799e-07, | |
| "loss": 2.2961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007116488013165503, | |
| "grad_norm": 0.3127712607383728, | |
| "learning_rate": 9.999323500351601e-07, | |
| "loss": 2.1634, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007561268513988347, | |
| "grad_norm": 0.3194904625415802, | |
| "learning_rate": 9.999281190331008e-07, | |
| "loss": 2.323, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.000800604901481119, | |
| "grad_norm": 0.3155025541782379, | |
| "learning_rate": 9.999238876920612e-07, | |
| "loss": 2.198, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008450829515634034, | |
| "grad_norm": 0.5667710304260254, | |
| "learning_rate": 9.999196560120004e-07, | |
| "loss": 2.2118, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008895610016456879, | |
| "grad_norm": 0.5151445269584656, | |
| "learning_rate": 9.999154239928777e-07, | |
| "loss": 2.3158, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008895610016456879, | |
| "eval_loss": 2.0555460453033447, | |
| "eval_runtime": 242.0578, | |
| "eval_samples_per_second": 0.264, | |
| "eval_steps_per_second": 0.066, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009340390517279723, | |
| "grad_norm": 0.39977356791496277, | |
| "learning_rate": 9.999111916346526e-07, | |
| "loss": 2.0448, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009785171018102566, | |
| "grad_norm": 0.3716548979282379, | |
| "learning_rate": 9.99906958937284e-07, | |
| "loss": 2.1979, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001022995151892541, | |
| "grad_norm": 0.48981648683547974, | |
| "learning_rate": 9.999027259007314e-07, | |
| "loss": 1.9194, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0010674732019748255, | |
| "grad_norm": 0.38807594776153564, | |
| "learning_rate": 9.99898492524954e-07, | |
| "loss": 1.9887, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00111195125205711, | |
| "grad_norm": 0.9124931693077087, | |
| "learning_rate": 9.998942588099108e-07, | |
| "loss": 2.2736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011564293021393943, | |
| "grad_norm": 0.3414762020111084, | |
| "learning_rate": 9.99890024755561e-07, | |
| "loss": 2.0791, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0012009073522216787, | |
| "grad_norm": 0.5927892327308655, | |
| "learning_rate": 9.998857903618642e-07, | |
| "loss": 2.4562, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001245385402303963, | |
| "grad_norm": 0.31966015696525574, | |
| "learning_rate": 9.998815556287793e-07, | |
| "loss": 1.9254, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0012898634523862474, | |
| "grad_norm": 0.444794237613678, | |
| "learning_rate": 9.998773205562656e-07, | |
| "loss": 2.1384, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0013343415024685318, | |
| "grad_norm": 0.5257573127746582, | |
| "learning_rate": 9.998730851442821e-07, | |
| "loss": 2.2903, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013343415024685318, | |
| "eval_loss": 2.0174190998077393, | |
| "eval_runtime": 244.9536, | |
| "eval_samples_per_second": 0.261, | |
| "eval_steps_per_second": 0.065, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013788195525508162, | |
| "grad_norm": 0.2638561427593231, | |
| "learning_rate": 9.998688493927882e-07, | |
| "loss": 2.0546, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0014232976026331006, | |
| "grad_norm": 0.45275381207466125, | |
| "learning_rate": 9.99864613301743e-07, | |
| "loss": 2.064, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.001467775652715385, | |
| "grad_norm": 0.45670074224472046, | |
| "learning_rate": 9.998603768711058e-07, | |
| "loss": 2.2222, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0015122537027976693, | |
| "grad_norm": 0.7620413303375244, | |
| "learning_rate": 9.998561401008355e-07, | |
| "loss": 2.0651, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0015567317528799537, | |
| "grad_norm": 0.42548975348472595, | |
| "learning_rate": 9.998519029908915e-07, | |
| "loss": 2.2957, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001601209802962238, | |
| "grad_norm": 0.31207627058029175, | |
| "learning_rate": 9.998476655412328e-07, | |
| "loss": 2.2575, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0016456878530445225, | |
| "grad_norm": 0.2575569450855255, | |
| "learning_rate": 9.998434277518184e-07, | |
| "loss": 2.1558, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0016901659031268068, | |
| "grad_norm": 0.5504156947135925, | |
| "learning_rate": 9.998391896226079e-07, | |
| "loss": 2.4939, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0017346439532090912, | |
| "grad_norm": 0.36677634716033936, | |
| "learning_rate": 9.998349511535599e-07, | |
| "loss": 1.8096, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0017791220032913758, | |
| "grad_norm": 0.45712989568710327, | |
| "learning_rate": 9.99830712344634e-07, | |
| "loss": 1.8726, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017791220032913758, | |
| "eval_loss": 1.9996732473373413, | |
| "eval_runtime": 234.0331, | |
| "eval_samples_per_second": 0.273, | |
| "eval_steps_per_second": 0.068, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018236000533736602, | |
| "grad_norm": 0.45847609639167786, | |
| "learning_rate": 9.998264731957889e-07, | |
| "loss": 1.8686, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0018680781034559446, | |
| "grad_norm": 0.33932119607925415, | |
| "learning_rate": 9.998222337069841e-07, | |
| "loss": 2.2302, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.001912556153538229, | |
| "grad_norm": 1.3315902948379517, | |
| "learning_rate": 9.998179938781784e-07, | |
| "loss": 1.8721, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.001957034203620513, | |
| "grad_norm": 1.2163060903549194, | |
| "learning_rate": 9.99813753709331e-07, | |
| "loss": 2.1642, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0020015122537027975, | |
| "grad_norm": 0.4775317907333374, | |
| "learning_rate": 9.99809513200401e-07, | |
| "loss": 2.4106, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002045990303785082, | |
| "grad_norm": 0.28207871317863464, | |
| "learning_rate": 9.998052723513476e-07, | |
| "loss": 2.058, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0020904683538673662, | |
| "grad_norm": 0.5639588236808777, | |
| "learning_rate": 9.998010311621295e-07, | |
| "loss": 2.2522, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.002134946403949651, | |
| "grad_norm": 0.45129290223121643, | |
| "learning_rate": 9.997967896327061e-07, | |
| "loss": 2.3281, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0021794244540319354, | |
| "grad_norm": 0.4590243101119995, | |
| "learning_rate": 9.997925477630364e-07, | |
| "loss": 2.1991, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00222390250411422, | |
| "grad_norm": 0.3881557881832123, | |
| "learning_rate": 9.997883055530797e-07, | |
| "loss": 2.2259, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00222390250411422, | |
| "eval_loss": 1.9868642091751099, | |
| "eval_runtime": 233.6732, | |
| "eval_samples_per_second": 0.274, | |
| "eval_steps_per_second": 0.068, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002268380554196504, | |
| "grad_norm": 0.4352044463157654, | |
| "learning_rate": 9.997840630027944e-07, | |
| "loss": 2.2623, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0023128586042787886, | |
| "grad_norm": 0.43397316336631775, | |
| "learning_rate": 9.997798201121402e-07, | |
| "loss": 1.8368, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.002357336654361073, | |
| "grad_norm": 0.38807961344718933, | |
| "learning_rate": 9.99775576881076e-07, | |
| "loss": 2.0101, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0024018147044433573, | |
| "grad_norm": 0.6237647533416748, | |
| "learning_rate": 9.997713333095603e-07, | |
| "loss": 2.0238, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0024462927545256417, | |
| "grad_norm": 0.34039369225502014, | |
| "learning_rate": 9.997670893975529e-07, | |
| "loss": 2.1, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.002490770804607926, | |
| "grad_norm": 0.4221118986606598, | |
| "learning_rate": 9.997628451450122e-07, | |
| "loss": 2.1649, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0025352488546902105, | |
| "grad_norm": 0.38328638672828674, | |
| "learning_rate": 9.997586005518976e-07, | |
| "loss": 2.1151, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.002579726904772495, | |
| "grad_norm": 0.3308090567588806, | |
| "learning_rate": 9.997543556181679e-07, | |
| "loss": 2.1499, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0026242049548547792, | |
| "grad_norm": 0.3598516881465912, | |
| "learning_rate": 9.99750110343782e-07, | |
| "loss": 2.1146, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0026686830049370636, | |
| "grad_norm": 0.38582974672317505, | |
| "learning_rate": 9.997458647286993e-07, | |
| "loss": 1.8236, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0026686830049370636, | |
| "eval_loss": 1.9794503450393677, | |
| "eval_runtime": 312.5608, | |
| "eval_samples_per_second": 0.205, | |
| "eval_steps_per_second": 0.051, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002713161055019348, | |
| "grad_norm": 0.5031485557556152, | |
| "learning_rate": 9.997416187728787e-07, | |
| "loss": 2.3825, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0027576391051016324, | |
| "grad_norm": 0.40436115860939026, | |
| "learning_rate": 9.997373724762788e-07, | |
| "loss": 1.9051, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0028021171551839167, | |
| "grad_norm": 0.3216610252857208, | |
| "learning_rate": 9.997331258388588e-07, | |
| "loss": 1.7655, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.002846595205266201, | |
| "grad_norm": 0.30226317048072815, | |
| "learning_rate": 9.997288788605777e-07, | |
| "loss": 2.215, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0028910732553484855, | |
| "grad_norm": 0.34857413172721863, | |
| "learning_rate": 9.997246315413945e-07, | |
| "loss": 2.1704, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.00293555130543077, | |
| "grad_norm": 0.4939625859260559, | |
| "learning_rate": 9.99720383881268e-07, | |
| "loss": 2.1591, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0029800293555130542, | |
| "grad_norm": 0.6396478414535522, | |
| "learning_rate": 9.997161358801571e-07, | |
| "loss": 2.4183, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0030245074055953386, | |
| "grad_norm": 0.3547438681125641, | |
| "learning_rate": 9.99711887538021e-07, | |
| "loss": 2.3338, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.003068985455677623, | |
| "grad_norm": 0.455522745847702, | |
| "learning_rate": 9.997076388548186e-07, | |
| "loss": 2.2559, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0031134635057599074, | |
| "grad_norm": 0.5139729976654053, | |
| "learning_rate": 9.997033898305084e-07, | |
| "loss": 2.4271, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0031134635057599074, | |
| "eval_loss": 1.974100947380066, | |
| "eval_runtime": 231.1208, | |
| "eval_samples_per_second": 0.277, | |
| "eval_steps_per_second": 0.069, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0031579415558421918, | |
| "grad_norm": 0.3868389427661896, | |
| "learning_rate": 9.996991404650499e-07, | |
| "loss": 1.8754, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.003202419605924476, | |
| "grad_norm": 0.4664241373538971, | |
| "learning_rate": 9.996948907584016e-07, | |
| "loss": 1.9934, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0032468976560067605, | |
| "grad_norm": 0.3952767848968506, | |
| "learning_rate": 9.996906407105226e-07, | |
| "loss": 2.0883, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.003291375706089045, | |
| "grad_norm": 0.4785691797733307, | |
| "learning_rate": 9.996863903213718e-07, | |
| "loss": 2.3203, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0033358537561713293, | |
| "grad_norm": 0.4103385806083679, | |
| "learning_rate": 9.99682139590908e-07, | |
| "loss": 2.0406, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0033803318062536137, | |
| "grad_norm": 0.45813262462615967, | |
| "learning_rate": 9.996778885190904e-07, | |
| "loss": 2.1745, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.003424809856335898, | |
| "grad_norm": 0.34197866916656494, | |
| "learning_rate": 9.996736371058771e-07, | |
| "loss": 2.0839, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0034692879064181824, | |
| "grad_norm": 0.4917107820510864, | |
| "learning_rate": 9.996693853512279e-07, | |
| "loss": 1.9646, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0035137659565004672, | |
| "grad_norm": 0.570755124092102, | |
| "learning_rate": 9.99665133255101e-07, | |
| "loss": 2.4128, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0035582440065827516, | |
| "grad_norm": 0.6334550380706787, | |
| "learning_rate": 9.996608808174557e-07, | |
| "loss": 2.3972, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0035582440065827516, | |
| "eval_loss": 1.9703996181488037, | |
| "eval_runtime": 236.153, | |
| "eval_samples_per_second": 0.271, | |
| "eval_steps_per_second": 0.068, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.003602722056665036, | |
| "grad_norm": 0.44049328565597534, | |
| "learning_rate": 9.996566280382507e-07, | |
| "loss": 2.389, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0036472001067473204, | |
| "grad_norm": 0.5198694467544556, | |
| "learning_rate": 9.996523749174444e-07, | |
| "loss": 1.8092, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0036916781568296047, | |
| "grad_norm": 0.4297351837158203, | |
| "learning_rate": 9.996481214549966e-07, | |
| "loss": 1.9158, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.003736156206911889, | |
| "grad_norm": 0.5207564234733582, | |
| "learning_rate": 9.996438676508653e-07, | |
| "loss": 2.3368, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0037806342569941735, | |
| "grad_norm": 3.4639275074005127, | |
| "learning_rate": 9.996396135050097e-07, | |
| "loss": 2.0157, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.003825112307076458, | |
| "grad_norm": 0.5132240056991577, | |
| "learning_rate": 9.996353590173885e-07, | |
| "loss": 2.1738, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0038695903571587423, | |
| "grad_norm": 0.559355616569519, | |
| "learning_rate": 9.996311041879605e-07, | |
| "loss": 2.2668, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.003914068407241026, | |
| "grad_norm": 0.40078872442245483, | |
| "learning_rate": 9.996268490166847e-07, | |
| "loss": 2.0339, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.003958546457323311, | |
| "grad_norm": 0.43362948298454285, | |
| "learning_rate": 9.996225935035196e-07, | |
| "loss": 2.3476, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.004003024507405595, | |
| "grad_norm": 0.6087605953216553, | |
| "learning_rate": 9.99618337648424e-07, | |
| "loss": 2.3268, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004003024507405595, | |
| "eval_loss": 1.9674957990646362, | |
| "eval_runtime": 241.976, | |
| "eval_samples_per_second": 0.264, | |
| "eval_steps_per_second": 0.066, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004047502557487879, | |
| "grad_norm": 3.6922800540924072, | |
| "learning_rate": 9.996140814513573e-07, | |
| "loss": 2.2244, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.004091980607570164, | |
| "grad_norm": 0.6901090145111084, | |
| "learning_rate": 9.996098249122776e-07, | |
| "loss": 2.127, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.004136458657652448, | |
| "grad_norm": 0.42567893862724304, | |
| "learning_rate": 9.99605568031144e-07, | |
| "loss": 1.99, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0041809367077347325, | |
| "grad_norm": 0.37529805302619934, | |
| "learning_rate": 9.996013108079149e-07, | |
| "loss": 2.1369, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.004225414757817018, | |
| "grad_norm": 0.5616635084152222, | |
| "learning_rate": 9.995970532425493e-07, | |
| "loss": 1.8421, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.004269892807899302, | |
| "grad_norm": 0.3917858898639679, | |
| "learning_rate": 9.995927953350061e-07, | |
| "loss": 2.0905, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0043143708579815865, | |
| "grad_norm": 0.3693113923072815, | |
| "learning_rate": 9.99588537085244e-07, | |
| "loss": 2.326, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.004358848908063871, | |
| "grad_norm": 0.4595705270767212, | |
| "learning_rate": 9.995842784932216e-07, | |
| "loss": 1.8433, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.004403326958146155, | |
| "grad_norm": 0.46681633591651917, | |
| "learning_rate": 9.995800195588977e-07, | |
| "loss": 2.21, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.00444780500822844, | |
| "grad_norm": 0.5430231690406799, | |
| "learning_rate": 9.99575760282231e-07, | |
| "loss": 2.4849, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00444780500822844, | |
| "eval_loss": 1.964964509010315, | |
| "eval_runtime": 231.4209, | |
| "eval_samples_per_second": 0.277, | |
| "eval_steps_per_second": 0.069, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 22483, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.248725545091072e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |