TinyDNABERT
/
Finetuned Models
/finetuning_outputs
/tfbs
/TinyDNABERT_base_model
/checkpoint-3000
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 12.0, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.6611918807029724, | |
| "learning_rate": 5.319148936170213e-05, | |
| "loss": 0.6932, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.9467485547065735, | |
| "learning_rate": 0.00010638297872340425, | |
| "loss": 0.6912, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.9465051889419556, | |
| "learning_rate": 0.00015957446808510637, | |
| "loss": 0.6893, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.5430934429168701, | |
| "learning_rate": 0.0002127659574468085, | |
| "loss": 0.6804, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.6103107929229736, | |
| "learning_rate": 0.00026595744680851064, | |
| "loss": 0.6806, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.3773200511932373, | |
| "learning_rate": 0.00031914893617021275, | |
| "loss": 0.6801, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.8832203149795532, | |
| "learning_rate": 0.0003723404255319149, | |
| "loss": 0.6791, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.3350876569747925, | |
| "learning_rate": 0.0003992081821181128, | |
| "loss": 0.6746, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.5796219110488892, | |
| "learning_rate": 0.0003975585615308479, | |
| "loss": 0.6771, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.884006381034851, | |
| "learning_rate": 0.00039590894094358297, | |
| "loss": 0.6649, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 3.286440372467041, | |
| "learning_rate": 0.0003942593203563181, | |
| "loss": 0.6388, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 8.244946479797363, | |
| "learning_rate": 0.0003926096997690532, | |
| "loss": 0.6238, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 4.265683650970459, | |
| "learning_rate": 0.00039096007918178817, | |
| "loss": 0.6383, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 4.115826606750488, | |
| "learning_rate": 0.0003893104585945233, | |
| "loss": 0.6194, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 5.694250583648682, | |
| "learning_rate": 0.0003876608380072583, | |
| "loss": 0.6324, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 3.463121175765991, | |
| "learning_rate": 0.00038601121741999343, | |
| "loss": 0.621, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 4.582865238189697, | |
| "learning_rate": 0.0003843615968327285, | |
| "loss": 0.6116, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 11.996281623840332, | |
| "learning_rate": 0.0003827119762454636, | |
| "loss": 0.6393, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 3.0407373905181885, | |
| "learning_rate": 0.00038106235565819863, | |
| "loss": 0.628, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.917588233947754, | |
| "learning_rate": 0.0003794127350709337, | |
| "loss": 0.6078, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 4.748379707336426, | |
| "learning_rate": 0.0003777631144836688, | |
| "loss": 0.4899, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 3.8076977729797363, | |
| "learning_rate": 0.00037611349389640383, | |
| "loss": 0.5086, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 5.2440714836120605, | |
| "learning_rate": 0.00037446387330913894, | |
| "loss": 0.5327, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 7.110438346862793, | |
| "learning_rate": 0.000372814252721874, | |
| "loss": 0.5436, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 5.46150541305542, | |
| "learning_rate": 0.00037116463213460903, | |
| "loss": 0.5294, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 5.136163234710693, | |
| "learning_rate": 0.00036951501154734414, | |
| "loss": 0.5245, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 8.735346794128418, | |
| "learning_rate": 0.0003678653909600792, | |
| "loss": 0.5449, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 2.922825574874878, | |
| "learning_rate": 0.0003662157703728143, | |
| "loss": 0.5406, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 7.744819641113281, | |
| "learning_rate": 0.00036456614978554934, | |
| "loss": 0.5447, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 11.6185884475708, | |
| "learning_rate": 0.00036291652919828444, | |
| "loss": 0.5195, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 3.73836088180542, | |
| "learning_rate": 0.00036126690861101944, | |
| "loss": 0.3824, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 14.850343704223633, | |
| "learning_rate": 0.00035961728802375454, | |
| "loss": 0.4071, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "grad_norm": 5.7157440185546875, | |
| "learning_rate": 0.0003579676674364896, | |
| "loss": 0.3986, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "grad_norm": 12.418399810791016, | |
| "learning_rate": 0.0003563180468492247, | |
| "loss": 0.4282, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 12.793001174926758, | |
| "learning_rate": 0.0003546684262619598, | |
| "loss": 0.4822, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 6.489450931549072, | |
| "learning_rate": 0.00035301880567469485, | |
| "loss": 0.4239, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "grad_norm": 5.365822792053223, | |
| "learning_rate": 0.0003513691850874299, | |
| "loss": 0.421, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "grad_norm": 12.643745422363281, | |
| "learning_rate": 0.00034971956450016495, | |
| "loss": 0.3964, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "grad_norm": 14.334024429321289, | |
| "learning_rate": 0.00034806994391290005, | |
| "loss": 0.4634, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 6.819091320037842, | |
| "learning_rate": 0.0003464203233256351, | |
| "loss": 0.4139, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "grad_norm": 8.29238224029541, | |
| "learning_rate": 0.0003447707027383702, | |
| "loss": 0.2695, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "grad_norm": 5.984206676483154, | |
| "learning_rate": 0.00034312108215110525, | |
| "loss": 0.2653, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "grad_norm": 5.9425435066223145, | |
| "learning_rate": 0.0003414714615638403, | |
| "loss": 0.2982, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "grad_norm": 7.1877593994140625, | |
| "learning_rate": 0.0003398218409765754, | |
| "loss": 0.3309, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 17.83046531677246, | |
| "learning_rate": 0.00033817222038931045, | |
| "loss": 0.3467, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "grad_norm": 4.865128517150879, | |
| "learning_rate": 0.00033652259980204556, | |
| "loss": 0.3117, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "grad_norm": 31.427154541015625, | |
| "learning_rate": 0.0003348729792147806, | |
| "loss": 0.3273, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 26.77984619140625, | |
| "learning_rate": 0.0003332233586275157, | |
| "loss": 0.3504, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "grad_norm": 9.389993667602539, | |
| "learning_rate": 0.00033157373804025076, | |
| "loss": 0.3339, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 25.70441246032715, | |
| "learning_rate": 0.0003299241174529858, | |
| "loss": 0.3336, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "grad_norm": 13.482085227966309, | |
| "learning_rate": 0.0003282744968657209, | |
| "loss": 0.2156, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "grad_norm": 8.725810050964355, | |
| "learning_rate": 0.00032662487627845596, | |
| "loss": 0.1811, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "grad_norm": 9.313215255737305, | |
| "learning_rate": 0.00032497525569119106, | |
| "loss": 0.2807, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "grad_norm": 11.026411056518555, | |
| "learning_rate": 0.0003233256351039261, | |
| "loss": 0.2757, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 11.038985252380371, | |
| "learning_rate": 0.00032167601451666116, | |
| "loss": 0.2177, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 4.008651256561279, | |
| "learning_rate": 0.00032002639392939627, | |
| "loss": 0.2163, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "grad_norm": 12.480770111083984, | |
| "learning_rate": 0.0003183767733421313, | |
| "loss": 0.2173, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "grad_norm": 8.751969337463379, | |
| "learning_rate": 0.0003167271527548664, | |
| "loss": 0.2299, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "grad_norm": 7.701971530914307, | |
| "learning_rate": 0.00031507753216760147, | |
| "loss": 0.1949, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 8.48027515411377, | |
| "learning_rate": 0.00031342791158033657, | |
| "loss": 0.2599, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "grad_norm": 9.29404067993164, | |
| "learning_rate": 0.00031177829099307157, | |
| "loss": 0.1376, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "grad_norm": 20.137714385986328, | |
| "learning_rate": 0.00031012867040580667, | |
| "loss": 0.1647, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "grad_norm": 11.394575119018555, | |
| "learning_rate": 0.0003084790498185417, | |
| "loss": 0.1565, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 8.214287757873535, | |
| "learning_rate": 0.0003068294292312768, | |
| "loss": 0.1739, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "grad_norm": 7.779988765716553, | |
| "learning_rate": 0.0003051798086440119, | |
| "loss": 0.1403, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "grad_norm": 9.421648025512695, | |
| "learning_rate": 0.000303530188056747, | |
| "loss": 0.1545, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "grad_norm": 5.751734256744385, | |
| "learning_rate": 0.000301880567469482, | |
| "loss": 0.1971, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "grad_norm": 23.861705780029297, | |
| "learning_rate": 0.0003002309468822171, | |
| "loss": 0.1681, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "grad_norm": 18.944721221923828, | |
| "learning_rate": 0.0002985813262949522, | |
| "loss": 0.1703, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 14.045795440673828, | |
| "learning_rate": 0.00029693170570768723, | |
| "loss": 0.1801, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "grad_norm": 6.4620137214660645, | |
| "learning_rate": 0.00029528208512042233, | |
| "loss": 0.1253, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "grad_norm": 4.318169593811035, | |
| "learning_rate": 0.0002936324645331574, | |
| "loss": 0.1397, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "grad_norm": 24.91462516784668, | |
| "learning_rate": 0.00029198284394589243, | |
| "loss": 0.1259, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "grad_norm": 23.614572525024414, | |
| "learning_rate": 0.00029033322335862753, | |
| "loss": 0.1293, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 3.60048508644104, | |
| "learning_rate": 0.0002886836027713626, | |
| "loss": 0.138, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "grad_norm": 16.62705421447754, | |
| "learning_rate": 0.0002870339821840977, | |
| "loss": 0.1733, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "grad_norm": 33.79671859741211, | |
| "learning_rate": 0.00028538436159683273, | |
| "loss": 0.217, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "grad_norm": 9.69206428527832, | |
| "learning_rate": 0.00028373474100956784, | |
| "loss": 0.1289, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "grad_norm": 18.655046463012695, | |
| "learning_rate": 0.0002820851204223029, | |
| "loss": 0.1168, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 8.4110746383667, | |
| "learning_rate": 0.00028043549983503794, | |
| "loss": 0.1471, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "grad_norm": 14.473428726196289, | |
| "learning_rate": 0.00027878587924777304, | |
| "loss": 0.0774, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "grad_norm": 1.2464979887008667, | |
| "learning_rate": 0.0002771362586605081, | |
| "loss": 0.0715, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "grad_norm": 26.74981689453125, | |
| "learning_rate": 0.0002754866380732432, | |
| "loss": 0.1289, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "grad_norm": 13.958703994750977, | |
| "learning_rate": 0.00027383701748597824, | |
| "loss": 0.1294, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "grad_norm": 10.394835472106934, | |
| "learning_rate": 0.0002721873968987133, | |
| "loss": 0.0987, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "grad_norm": 9.387774467468262, | |
| "learning_rate": 0.00027053777631144834, | |
| "loss": 0.1269, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "grad_norm": 4.988718509674072, | |
| "learning_rate": 0.00026888815572418344, | |
| "loss": 0.1374, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "grad_norm": 12.66832447052002, | |
| "learning_rate": 0.00026723853513691855, | |
| "loss": 0.0997, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "grad_norm": 19.10486602783203, | |
| "learning_rate": 0.0002655889145496536, | |
| "loss": 0.1325, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 3.2943971157073975, | |
| "learning_rate": 0.0002639392939623887, | |
| "loss": 0.1385, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "grad_norm": 11.490874290466309, | |
| "learning_rate": 0.0002622896733751237, | |
| "loss": 0.0573, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "grad_norm": 11.961288452148438, | |
| "learning_rate": 0.0002606400527878588, | |
| "loss": 0.1128, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "grad_norm": 0.7256277203559875, | |
| "learning_rate": 0.00025899043220059385, | |
| "loss": 0.0673, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "grad_norm": 9.857927322387695, | |
| "learning_rate": 0.00025734081161332895, | |
| "loss": 0.2072, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "grad_norm": 34.927734375, | |
| "learning_rate": 0.000255691191026064, | |
| "loss": 0.221, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 28.461849212646484, | |
| "learning_rate": 0.0002540415704387991, | |
| "loss": 0.1263, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "grad_norm": 9.591217041015625, | |
| "learning_rate": 0.00025239194985153415, | |
| "loss": 0.099, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "grad_norm": 9.780253410339355, | |
| "learning_rate": 0.0002507423292642692, | |
| "loss": 0.0754, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "grad_norm": 14.394485473632812, | |
| "learning_rate": 0.0002490927086770043, | |
| "loss": 0.0909, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 4.217277526855469, | |
| "learning_rate": 0.00024744308808973936, | |
| "loss": 0.1495, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "grad_norm": 0.08438724279403687, | |
| "learning_rate": 0.00024579346750247446, | |
| "loss": 0.0662, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "grad_norm": 0.9595862030982971, | |
| "learning_rate": 0.0002441438469152095, | |
| "loss": 0.084, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "grad_norm": 42.32374954223633, | |
| "learning_rate": 0.00024249422632794456, | |
| "loss": 0.0541, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "grad_norm": 24.792821884155273, | |
| "learning_rate": 0.00024084460574067963, | |
| "loss": 0.121, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "grad_norm": 2.7049331665039062, | |
| "learning_rate": 0.0002391949851534147, | |
| "loss": 0.1551, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "grad_norm": 2.788362741470337, | |
| "learning_rate": 0.0002375453645661498, | |
| "loss": 0.0877, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "grad_norm": 0.4999215006828308, | |
| "learning_rate": 0.00023589574397888486, | |
| "loss": 0.1263, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "grad_norm": 16.476675033569336, | |
| "learning_rate": 0.00023424612339161997, | |
| "loss": 0.0883, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "grad_norm": 38.192726135253906, | |
| "learning_rate": 0.000232596502804355, | |
| "loss": 0.0843, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 18.09952735900879, | |
| "learning_rate": 0.00023094688221709007, | |
| "loss": 0.0957, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "grad_norm": 34.254417419433594, | |
| "learning_rate": 0.00022929726162982514, | |
| "loss": 0.0856, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "grad_norm": 11.744216918945312, | |
| "learning_rate": 0.00022764764104256022, | |
| "loss": 0.0654, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "grad_norm": 0.1285558044910431, | |
| "learning_rate": 0.0002259980204552953, | |
| "loss": 0.0638, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "grad_norm": 20.57583999633789, | |
| "learning_rate": 0.00022434839986803037, | |
| "loss": 0.079, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "grad_norm": 0.7192332148551941, | |
| "learning_rate": 0.00022269877928076542, | |
| "loss": 0.0854, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "grad_norm": 31.341829299926758, | |
| "learning_rate": 0.0002210491586935005, | |
| "loss": 0.063, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "grad_norm": 13.460247039794922, | |
| "learning_rate": 0.00021939953810623557, | |
| "loss": 0.1358, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "grad_norm": 1.671036720275879, | |
| "learning_rate": 0.00021774991751897065, | |
| "loss": 0.0806, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "grad_norm": 22.026491165161133, | |
| "learning_rate": 0.00021610029693170573, | |
| "loss": 0.0912, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 46.78192138671875, | |
| "learning_rate": 0.0002144506763444408, | |
| "loss": 0.0763, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 6250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 152458444800000.0, | |
| "train_batch_size": 20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |