| { |
| "best_global_step": 900, |
| "best_metric": 0.05392824113368988, |
| "best_model_checkpoint": "/kaggle/working/billstructai_qwen_lora/checkpoint-900", |
| "epoch": 1.9163558870538093, |
| "eval_steps": 100, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.021310602024507193, |
| "grad_norm": 0.5570411682128906, |
| "learning_rate": 6.206896551724138e-05, |
| "loss": 0.48706421852111814, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.042621204049014386, |
| "grad_norm": 0.5630005598068237, |
| "learning_rate": 0.00013103448275862068, |
| "loss": 0.223022723197937, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06393180607352157, |
| "grad_norm": 0.2142772376537323, |
| "learning_rate": 0.0002, |
| "loss": 0.11430357694625855, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08524240809802877, |
| "grad_norm": 0.1824568212032318, |
| "learning_rate": 0.00019994054478472144, |
| "loss": 0.10234310626983642, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.10655301012253596, |
| "grad_norm": 0.1363372802734375, |
| "learning_rate": 0.00019976224983733816, |
| "loss": 0.09078772068023681, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.12786361214704314, |
| "grad_norm": 0.22561518847942352, |
| "learning_rate": 0.0001994653271691398, |
| "loss": 0.08356261253356934, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.14917421417155036, |
| "grad_norm": 0.234844371676445, |
| "learning_rate": 0.00019905012985214953, |
| "loss": 0.08094308376312256, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.17048481619605754, |
| "grad_norm": 0.21515238285064697, |
| "learning_rate": 0.00019851715159928466, |
| "loss": 0.07718738913536072, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.19179541822056473, |
| "grad_norm": 0.13278549909591675, |
| "learning_rate": 0.0001978670261772804, |
| "loss": 0.08123236298561096, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.21310602024507191, |
| "grad_norm": 0.17123660445213318, |
| "learning_rate": 0.00019710052665307523, |
| "loss": 0.0745608925819397, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.21310602024507191, |
| "eval_loss": 0.07421404123306274, |
| "eval_runtime": 248.5477, |
| "eval_samples_per_second": 1.891, |
| "eval_steps_per_second": 1.891, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.23441662226957913, |
| "grad_norm": 0.16013474762439728, |
| "learning_rate": 0.00019621856447455364, |
| "loss": 0.07106327414512634, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.2557272242940863, |
| "grad_norm": 0.13360778987407684, |
| "learning_rate": 0.00019522218838673944, |
| "loss": 0.0767333984375, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2770378263185935, |
| "grad_norm": 0.16006118059158325, |
| "learning_rate": 0.00019411258318472862, |
| "loss": 0.06799736022949218, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.2983484283431007, |
| "grad_norm": 0.17742912471294403, |
| "learning_rate": 0.00019289106830484436, |
| "loss": 0.06742151379585266, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.3196590303676079, |
| "grad_norm": 0.19604063034057617, |
| "learning_rate": 0.00019155909625568967, |
| "loss": 0.06300732493400574, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3409696323921151, |
| "grad_norm": 0.23139697313308716, |
| "learning_rate": 0.0001901182508909631, |
| "loss": 0.0801832914352417, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.36228023441662227, |
| "grad_norm": 0.15756270289421082, |
| "learning_rate": 0.00018857024552609145, |
| "loss": 0.06489556431770324, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.38359083644112946, |
| "grad_norm": 0.16894873976707458, |
| "learning_rate": 0.00018691692090091927, |
| "loss": 0.06612523198127747, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.40490143846563664, |
| "grad_norm": 0.17246082425117493, |
| "learning_rate": 0.0001851602429908767, |
| "loss": 0.0627750039100647, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.42621204049014383, |
| "grad_norm": 0.15236839652061462, |
| "learning_rate": 0.00018330230066923022, |
| "loss": 0.06336764097213746, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.42621204049014383, |
| "eval_loss": 0.0664505884051323, |
| "eval_runtime": 249.4364, |
| "eval_samples_per_second": 1.884, |
| "eval_steps_per_second": 1.884, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.447522642514651, |
| "grad_norm": 0.1786014884710312, |
| "learning_rate": 0.0001813453032231939, |
| "loss": 0.0747511088848114, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.46883324453915826, |
| "grad_norm": 0.12548740208148956, |
| "learning_rate": 0.00017929157772685685, |
| "loss": 0.06296217441558838, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.49014384656366544, |
| "grad_norm": 0.12285338342189789, |
| "learning_rate": 0.00017714356627404924, |
| "loss": 0.05755079984664917, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5114544485881726, |
| "grad_norm": 0.12364857643842697, |
| "learning_rate": 0.000174903823074438, |
| "loss": 0.07338430285453797, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5327650506126798, |
| "grad_norm": 0.14315958321094513, |
| "learning_rate": 0.00017257501141630516, |
| "loss": 0.06376387476921082, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.554075652637187, |
| "grad_norm": 0.17841553688049316, |
| "learning_rate": 0.0001701599004996203, |
| "loss": 0.07746977806091308, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.5753862546616942, |
| "grad_norm": 0.18484671413898468, |
| "learning_rate": 0.00016766136214317286, |
| "loss": 0.0655578076839447, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.5966968566862014, |
| "grad_norm": 0.15894602239131927, |
| "learning_rate": 0.00016508236736968016, |
| "loss": 0.059864658117294314, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.6180074587107086, |
| "grad_norm": 0.14981523156166077, |
| "learning_rate": 0.00016242598287293135, |
| "loss": 0.06459205150604248, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.6393180607352158, |
| "grad_norm": 0.19262194633483887, |
| "learning_rate": 0.00015969536737116879, |
| "loss": 0.05724593997001648, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6393180607352158, |
| "eval_loss": 0.06404831260442734, |
| "eval_runtime": 248.8778, |
| "eval_samples_per_second": 1.888, |
| "eval_steps_per_second": 1.888, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.660628662759723, |
| "grad_norm": 0.16405339539051056, |
| "learning_rate": 0.0001568937678510425, |
| "loss": 0.06382941007614136, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.6819392647842302, |
| "grad_norm": 0.13134469091892242, |
| "learning_rate": 0.00015402451570660437, |
| "loss": 0.06093383431434631, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.7032498668087374, |
| "grad_norm": 0.19201718270778656, |
| "learning_rate": 0.00015109102277793306, |
| "loss": 0.0615972101688385, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7245604688332445, |
| "grad_norm": 0.11001285165548325, |
| "learning_rate": 0.00014809677729410046, |
| "loss": 0.05652051568031311, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.7458710708577517, |
| "grad_norm": 0.1298859715461731, |
| "learning_rate": 0.0001450453397253033, |
| "loss": 0.05437501072883606, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.7671816728822589, |
| "grad_norm": 0.1667214184999466, |
| "learning_rate": 0.0001419403385490929, |
| "loss": 0.05537524223327637, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.7884922749067661, |
| "grad_norm": 0.160597026348114, |
| "learning_rate": 0.00013878546593573663, |
| "loss": 0.06058817505836487, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.8098028769312733, |
| "grad_norm": 0.11980368942022324, |
| "learning_rate": 0.00013558447335784254, |
| "loss": 0.056959474086761476, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.8311134789557805, |
| "grad_norm": 0.10598862916231155, |
| "learning_rate": 0.00013234116712946715, |
| "loss": 0.062009012699127196, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.8524240809802877, |
| "grad_norm": 0.1465042680501938, |
| "learning_rate": 0.00012905940388001092, |
| "loss": 0.06569045186042785, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8524240809802877, |
| "eval_loss": 0.05861470475792885, |
| "eval_runtime": 248.8019, |
| "eval_samples_per_second": 1.889, |
| "eval_steps_per_second": 1.889, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8737346830047948, |
| "grad_norm": 0.13985313475131989, |
| "learning_rate": 0.00012574308596828364, |
| "loss": 0.059485018253326416, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.895045285029302, |
| "grad_norm": 0.09439831972122192, |
| "learning_rate": 0.00012239615684219273, |
| "loss": 0.04954729676246643, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9163558870538092, |
| "grad_norm": 0.13079901039600372, |
| "learning_rate": 0.0001190225963495725, |
| "loss": 0.06261422634124755, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.9376664890783165, |
| "grad_norm": 0.17101094126701355, |
| "learning_rate": 0.00011562641600572993, |
| "loss": 0.05220479965209961, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.9589770911028237, |
| "grad_norm": 0.18949410319328308, |
| "learning_rate": 0.0001122116542233342, |
| "loss": 0.05655173659324646, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.9802876931273309, |
| "grad_norm": 0.16985633969306946, |
| "learning_rate": 0.0001087823715103234, |
| "loss": 0.05631093382835388, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.21016985177993774, |
| "learning_rate": 0.00010534264564153651, |
| "loss": 0.0492259293794632, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.0213106020245073, |
| "grad_norm": 0.10946141928434372, |
| "learning_rate": 0.00010189656680981415, |
| "loss": 0.045346027612686156, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.0426212040490144, |
| "grad_norm": 0.18159270286560059, |
| "learning_rate": 9.844823276233243e-05, |
| "loss": 0.04748743176460266, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.0639318060735217, |
| "grad_norm": 0.1416451632976532, |
| "learning_rate": 9.500174392795431e-05, |
| "loss": 0.04537383615970612, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0639318060735217, |
| "eval_loss": 0.05737318471074104, |
| "eval_runtime": 249.9023, |
| "eval_samples_per_second": 1.881, |
| "eval_steps_per_second": 1.881, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0852424080980287, |
| "grad_norm": 0.1302674263715744, |
| "learning_rate": 9.156119854139173e-05, |
| "loss": 0.042424333095550534, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.106553010122536, |
| "grad_norm": 0.15241168439388275, |
| "learning_rate": 8.813068776997747e-05, |
| "loss": 0.037749645113945005, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.1278636121470431, |
| "grad_norm": 0.189493790268898, |
| "learning_rate": 8.471429084884012e-05, |
| "loss": 0.04497165381908417, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.1491742141715504, |
| "grad_norm": 0.1870124340057373, |
| "learning_rate": 8.131607023026814e-05, |
| "loss": 0.04265827238559723, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.1704848161960575, |
| "grad_norm": 0.1087406650185585, |
| "learning_rate": 7.794006675303031e-05, |
| "loss": 0.035568210482597354, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.1917954182205648, |
| "grad_norm": 0.1936003565788269, |
| "learning_rate": 7.459029483739711e-05, |
| "loss": 0.038499835133552554, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.2131060202450719, |
| "grad_norm": 0.1559380143880844, |
| "learning_rate": 7.127073771157606e-05, |
| "loss": 0.04679949283599853, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.2344166222695792, |
| "grad_norm": 0.1537848860025406, |
| "learning_rate": 6.798534267523806e-05, |
| "loss": 0.04622254967689514, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.2557272242940862, |
| "grad_norm": 0.17289568483829498, |
| "learning_rate": 6.473801640576633e-05, |
| "loss": 0.040285307168960574, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.2770378263185935, |
| "grad_norm": 0.14587342739105225, |
| "learning_rate": 6.153262031280951e-05, |
| "loss": 0.03852958083152771, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.2770378263185935, |
| "eval_loss": 0.056128598749637604, |
| "eval_runtime": 248.6964, |
| "eval_samples_per_second": 1.89, |
| "eval_steps_per_second": 1.89, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.2983484283431008, |
| "grad_norm": 0.15503859519958496, |
| "learning_rate": 5.8372965946662815e-05, |
| "loss": 0.03877540528774261, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.319659030367608, |
| "grad_norm": 0.10821698606014252, |
| "learning_rate": 5.5262810465937045e-05, |
| "loss": 0.04052968025207519, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.340969632392115, |
| "grad_norm": 0.18947947025299072, |
| "learning_rate": 5.2205852169905434e-05, |
| "loss": 0.05081030130386353, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.3622802344166223, |
| "grad_norm": 0.2615494132041931, |
| "learning_rate": 4.920572610083977e-05, |
| "loss": 0.04443525373935699, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.3835908364411296, |
| "grad_norm": 0.1606501042842865, |
| "learning_rate": 4.626599972156593e-05, |
| "loss": 0.04287891089916229, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.4049014384656366, |
| "grad_norm": 0.14430288970470428, |
| "learning_rate": 4.3390168673378775e-05, |
| "loss": 0.04097432494163513, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.4262120404901437, |
| "grad_norm": 0.14559805393218994, |
| "learning_rate": 4.0581652619359775e-05, |
| "loss": 0.034264594316482544, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.447522642514651, |
| "grad_norm": 0.15087302029132843, |
| "learning_rate": 3.7843791178041054e-05, |
| "loss": 0.038701537251472476, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.4688332445391583, |
| "grad_norm": 0.18511506915092468, |
| "learning_rate": 3.5179839952250524e-05, |
| "loss": 0.039507734775543216, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.4901438465636654, |
| "grad_norm": 0.1208174079656601, |
| "learning_rate": 3.2592966657860625e-05, |
| "loss": 0.037732216715812686, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.4901438465636654, |
| "eval_loss": 0.05517593026161194, |
| "eval_runtime": 248.5187, |
| "eval_samples_per_second": 1.891, |
| "eval_steps_per_second": 1.891, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.5114544485881725, |
| "grad_norm": 0.14407405257225037, |
| "learning_rate": 3.0086247357043705e-05, |
| "loss": 0.04141993820667267, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.5327650506126798, |
| "grad_norm": 0.1950131356716156, |
| "learning_rate": 2.766266280051316e-05, |
| "loss": 0.042274028062820435, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.554075652637187, |
| "grad_norm": 0.1330132633447647, |
| "learning_rate": 2.5325094883100108e-05, |
| "loss": 0.039421483874320984, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.5753862546616944, |
| "grad_norm": 0.16335627436637878, |
| "learning_rate": 2.3076323216879714e-05, |
| "loss": 0.03970510959625244, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.5966968566862014, |
| "grad_norm": 0.1316670924425125, |
| "learning_rate": 2.0919021825922536e-05, |
| "loss": 0.04199607074260712, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.6180074587107085, |
| "grad_norm": 0.132982537150383, |
| "learning_rate": 1.8855755966600962e-05, |
| "loss": 0.04375255405902863, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.6393180607352158, |
| "grad_norm": 0.15142162144184113, |
| "learning_rate": 1.688897907723186e-05, |
| "loss": 0.03803563416004181, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.660628662759723, |
| "grad_norm": 0.15250155329704285, |
| "learning_rate": 1.50210298606825e-05, |
| "loss": 0.03791479468345642, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.6819392647842302, |
| "grad_norm": 0.11432624608278275, |
| "learning_rate": 1.325412950340882e-05, |
| "loss": 0.0383548378944397, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.7032498668087372, |
| "grad_norm": 0.15887320041656494, |
| "learning_rate": 1.159037903423319e-05, |
| "loss": 0.04067508578300476, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.7032498668087372, |
| "eval_loss": 0.054582156240940094, |
| "eval_runtime": 248.4421, |
| "eval_samples_per_second": 1.892, |
| "eval_steps_per_second": 1.892, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.7245604688332445, |
| "grad_norm": 0.2519368827342987, |
| "learning_rate": 1.0031756826001914e-05, |
| "loss": 0.0420225739479065, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.7458710708577518, |
| "grad_norm": 0.13151676952838898, |
| "learning_rate": 8.580116243093562e-06, |
| "loss": 0.041281819343566895, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.767181672882259, |
| "grad_norm": 0.11074542254209518, |
| "learning_rate": 7.23718343757539e-06, |
| "loss": 0.03622758090496063, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.788492274906766, |
| "grad_norm": 0.17330627143383026, |
| "learning_rate": 6.004555296628556e-06, |
| "loss": 0.0376776397228241, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.8098028769312733, |
| "grad_norm": 0.1254781186580658, |
| "learning_rate": 4.88369754368263e-06, |
| "loss": 0.03871485292911529, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.8311134789557806, |
| "grad_norm": 0.15773062407970428, |
| "learning_rate": 3.8759429955175564e-06, |
| "loss": 0.041798022389411923, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.8524240809802877, |
| "grad_norm": 0.12225436419248581, |
| "learning_rate": 2.9824899774055113e-06, |
| "loss": 0.036775484681129456, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.8737346830047947, |
| "grad_norm": 0.14229069650173187, |
| "learning_rate": 2.2044008981771947e-06, |
| "loss": 0.03825798928737641, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.895045285029302, |
| "grad_norm": 0.12034007161855698, |
| "learning_rate": 1.5426009869067948e-06, |
| "loss": 0.03620096147060394, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.9163558870538093, |
| "grad_norm": 0.16056819260120392, |
| "learning_rate": 9.97877192718255e-07, |
| "loss": 0.037316632270812986, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.9163558870538093, |
| "eval_loss": 0.05392824113368988, |
| "eval_runtime": 248.0734, |
| "eval_samples_per_second": 1.895, |
| "eval_steps_per_second": 1.895, |
| "step": 900 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 940, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.290876726467379e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
