{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 2930, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0034129692832764505, "grad_norm": 3.671875, "learning_rate": 6.825938566552902e-07, "loss": 3.0499, "step": 1 }, { "epoch": 0.017064846416382253, "grad_norm": 4.96875, "learning_rate": 3.4129692832764506e-06, "loss": 3.0421, "step": 5 }, { "epoch": 0.034129692832764506, "grad_norm": 4.34375, "learning_rate": 6.825938566552901e-06, "loss": 3.0559, "step": 10 }, { "epoch": 0.051194539249146756, "grad_norm": 3.09375, "learning_rate": 1.0238907849829352e-05, "loss": 2.9957, "step": 15 }, { "epoch": 0.06825938566552901, "grad_norm": 2.71875, "learning_rate": 1.3651877133105803e-05, "loss": 2.8653, "step": 20 }, { "epoch": 0.08532423208191127, "grad_norm": 3.3125, "learning_rate": 1.7064846416382256e-05, "loss": 2.7049, "step": 25 }, { "epoch": 0.10238907849829351, "grad_norm": 18.5, "learning_rate": 2.0477815699658705e-05, "loss": 2.5238, "step": 30 }, { "epoch": 0.11945392491467577, "grad_norm": 1.8828125, "learning_rate": 2.3890784982935157e-05, "loss": 2.3984, "step": 35 }, { "epoch": 0.13651877133105803, "grad_norm": 1.3671875, "learning_rate": 2.7303754266211605e-05, "loss": 2.3001, "step": 40 }, { "epoch": 0.15358361774744028, "grad_norm": 2.0625, "learning_rate": 3.071672354948806e-05, "loss": 2.1645, "step": 45 }, { "epoch": 0.17064846416382254, "grad_norm": 1.25, "learning_rate": 3.412969283276451e-05, "loss": 2.0453, "step": 50 }, { "epoch": 0.18771331058020477, "grad_norm": 0.8046875, "learning_rate": 3.754266211604096e-05, "loss": 1.8952, "step": 55 }, { "epoch": 0.20477815699658702, "grad_norm": 1.609375, "learning_rate": 4.095563139931741e-05, "loss": 1.7862, "step": 60 }, { "epoch": 0.22184300341296928, "grad_norm": 0.63671875, "learning_rate": 4.436860068259386e-05, "loss": 1.6922, "step": 65 }, { "epoch": 0.23890784982935154, "grad_norm": 0.400390625, "learning_rate": 4.778156996587031e-05, "loss": 1.6006, "step": 70 }, { "epoch": 0.25597269624573377, "grad_norm": 0.375, "learning_rate": 5.119453924914676e-05, "loss": 1.5335, "step": 75 }, { "epoch": 0.27303754266211605, "grad_norm": 0.43359375, "learning_rate": 5.460750853242321e-05, "loss": 1.4832, "step": 80 }, { "epoch": 0.2901023890784983, "grad_norm": 0.67578125, "learning_rate": 5.802047781569966e-05, "loss": 1.4393, "step": 85 }, { "epoch": 0.30716723549488056, "grad_norm": 0.337890625, "learning_rate": 6.143344709897612e-05, "loss": 1.3951, "step": 90 }, { "epoch": 0.3242320819112628, "grad_norm": 0.275390625, "learning_rate": 6.484641638225257e-05, "loss": 1.3594, "step": 95 }, { "epoch": 0.3412969283276451, "grad_norm": 0.267578125, "learning_rate": 6.825938566552902e-05, "loss": 1.3456, "step": 100 }, { "epoch": 0.3583617747440273, "grad_norm": 0.3671875, "learning_rate": 7.167235494880547e-05, "loss": 1.3174, "step": 105 }, { "epoch": 0.37542662116040953, "grad_norm": 0.328125, "learning_rate": 7.508532423208191e-05, "loss": 1.3087, "step": 110 }, { "epoch": 0.3924914675767918, "grad_norm": 0.5703125, "learning_rate": 7.849829351535837e-05, "loss": 1.3001, "step": 115 }, { "epoch": 0.40955631399317405, "grad_norm": 0.30078125, "learning_rate": 8.191126279863482e-05, "loss": 1.2871, "step": 120 }, { "epoch": 0.42662116040955633, "grad_norm": 0.65625, "learning_rate": 8.532423208191128e-05, "loss": 1.2567, "step": 125 }, { "epoch": 0.44368600682593856, "grad_norm": 0.458984375, "learning_rate": 8.873720136518772e-05, "loss": 1.2582, "step": 130 }, { "epoch": 0.46075085324232085, "grad_norm": 0.380859375, "learning_rate": 9.215017064846417e-05, "loss": 1.2471, "step": 135 }, { "epoch": 0.4778156996587031, "grad_norm": 0.298828125, "learning_rate": 9.556313993174063e-05, "loss": 1.2357, "step": 140 }, { "epoch": 0.4948805460750853, "grad_norm": 0.65625, "learning_rate": 9.897610921501707e-05, "loss": 1.2303, "step": 145 }, { "epoch": 0.5119453924914675, "grad_norm": 0.423828125, "learning_rate": 0.00010238907849829352, "loss": 1.226, "step": 150 }, { "epoch": 0.5290102389078498, "grad_norm": 0.5390625, "learning_rate": 0.00010580204778156998, "loss": 1.2251, "step": 155 }, { "epoch": 0.5460750853242321, "grad_norm": 0.416015625, "learning_rate": 0.00010921501706484642, "loss": 1.2135, "step": 160 }, { "epoch": 0.5631399317406144, "grad_norm": 0.3828125, "learning_rate": 0.00011262798634812288, "loss": 1.2069, "step": 165 }, { "epoch": 0.5802047781569966, "grad_norm": 0.6796875, "learning_rate": 0.00011604095563139932, "loss": 1.2005, "step": 170 }, { "epoch": 0.5972696245733788, "grad_norm": 0.41015625, "learning_rate": 0.00011945392491467577, "loss": 1.1944, "step": 175 }, { "epoch": 0.6143344709897611, "grad_norm": 0.50390625, "learning_rate": 0.00012286689419795224, "loss": 1.1775, "step": 180 }, { "epoch": 0.6313993174061433, "grad_norm": 0.38671875, "learning_rate": 0.00012627986348122866, "loss": 1.1844, "step": 185 }, { "epoch": 0.6484641638225256, "grad_norm": 0.46484375, "learning_rate": 0.00012969283276450513, "loss": 1.1711, "step": 190 }, { "epoch": 0.6655290102389079, "grad_norm": 0.72265625, "learning_rate": 0.00013310580204778158, "loss": 1.1824, "step": 195 }, { "epoch": 0.6825938566552902, "grad_norm": 1.0859375, "learning_rate": 0.00013651877133105805, "loss": 1.169, "step": 200 }, { "epoch": 0.6996587030716723, "grad_norm": 0.58203125, "learning_rate": 0.00013993174061433447, "loss": 1.1691, "step": 205 }, { "epoch": 0.7167235494880546, "grad_norm": 0.42578125, "learning_rate": 0.00014334470989761094, "loss": 1.1573, "step": 210 }, { "epoch": 0.7337883959044369, "grad_norm": 0.6328125, "learning_rate": 0.00014675767918088738, "loss": 1.1637, "step": 215 }, { "epoch": 0.7508532423208191, "grad_norm": 0.68359375, "learning_rate": 0.00015017064846416383, "loss": 1.1605, "step": 220 }, { "epoch": 0.7679180887372014, "grad_norm": 0.4140625, "learning_rate": 0.00015358361774744027, "loss": 1.1539, "step": 225 }, { "epoch": 0.7849829351535836, "grad_norm": 0.37109375, "learning_rate": 0.00015699658703071675, "loss": 1.1458, "step": 230 }, { "epoch": 0.8020477815699659, "grad_norm": 0.4140625, "learning_rate": 0.0001604095563139932, "loss": 1.1524, "step": 235 }, { "epoch": 0.8191126279863481, "grad_norm": 0.51171875, "learning_rate": 0.00016382252559726964, "loss": 1.1505, "step": 240 }, { "epoch": 0.8361774744027304, "grad_norm": 0.81640625, "learning_rate": 0.00016723549488054608, "loss": 1.1493, "step": 245 }, { "epoch": 0.8532423208191127, "grad_norm": 0.59765625, "learning_rate": 0.00017064846416382255, "loss": 1.1391, "step": 250 }, { "epoch": 0.8703071672354948, "grad_norm": 0.404296875, "learning_rate": 0.00017406143344709897, "loss": 1.1213, "step": 255 }, { "epoch": 0.8873720136518771, "grad_norm": 0.443359375, "learning_rate": 0.00017747440273037544, "loss": 1.1311, "step": 260 }, { "epoch": 0.9044368600682594, "grad_norm": 0.8046875, "learning_rate": 0.0001808873720136519, "loss": 1.1224, "step": 265 }, { "epoch": 0.9215017064846417, "grad_norm": 0.36328125, "learning_rate": 0.00018430034129692833, "loss": 1.1369, "step": 270 }, { "epoch": 0.9385665529010239, "grad_norm": 0.52734375, "learning_rate": 0.00018771331058020478, "loss": 1.1203, "step": 275 }, { "epoch": 0.9556313993174061, "grad_norm": 1.171875, "learning_rate": 0.00019112627986348125, "loss": 1.1281, "step": 280 }, { "epoch": 0.9726962457337884, "grad_norm": 0.8671875, "learning_rate": 0.0001945392491467577, "loss": 1.1231, "step": 285 }, { "epoch": 0.9897610921501706, "grad_norm": 0.466796875, "learning_rate": 0.00019795221843003414, "loss": 1.1249, "step": 290 }, { "epoch": 1.0, "eval_loss": 2.4640614986419678, "eval_runtime": 0.5515, "eval_samples_per_second": 18.133, "eval_steps_per_second": 1.813, "step": 293 }, { "epoch": 1.006825938566553, "grad_norm": 0.65625, "learning_rate": 0.00019999971613668125, "loss": 1.1028, "step": 295 }, { "epoch": 1.023890784982935, "grad_norm": 0.87890625, "learning_rate": 0.00019999652269285281, "loss": 1.0985, "step": 300 }, { "epoch": 1.0409556313993173, "grad_norm": 0.333984375, "learning_rate": 0.00019998978108973762, "loss": 1.0885, "step": 305 }, { "epoch": 1.0580204778156996, "grad_norm": 0.34375, "learning_rate": 0.00019997949156654686, "loss": 1.1064, "step": 310 }, { "epoch": 1.075085324232082, "grad_norm": 0.3828125, "learning_rate": 0.00019996565448838176, "loss": 1.0991, "step": 315 }, { "epoch": 1.0921501706484642, "grad_norm": 1.03125, "learning_rate": 0.0001999482703462211, "loss": 1.0947, "step": 320 }, { "epoch": 1.1092150170648465, "grad_norm": 0.478515625, "learning_rate": 0.00019992733975690333, "loss": 1.097, "step": 325 }, { "epoch": 1.1262798634812285, "grad_norm": 0.451171875, "learning_rate": 0.00019990286346310493, "loss": 1.0835, "step": 330 }, { "epoch": 1.1433447098976108, "grad_norm": 1.40625, "learning_rate": 0.00019987484233331394, "loss": 1.1033, "step": 335 }, { "epoch": 1.1604095563139931, "grad_norm": 1.8515625, "learning_rate": 0.00019984327736179936, "loss": 1.1011, "step": 340 }, { "epoch": 1.1774744027303754, "grad_norm": 1.6328125, "learning_rate": 0.0001998081696685755, "loss": 1.0986, "step": 345 }, { "epoch": 1.1945392491467577, "grad_norm": 0.72265625, "learning_rate": 0.0001997695204993626, "loss": 1.0859, "step": 350 }, { "epoch": 1.21160409556314, "grad_norm": 0.6875, "learning_rate": 0.00019972733122554246, "loss": 1.0867, "step": 355 }, { "epoch": 1.2286689419795223, "grad_norm": 0.62109375, "learning_rate": 0.00019968160334410975, "loss": 1.0949, "step": 360 }, { "epoch": 1.2457337883959045, "grad_norm": 0.376953125, "learning_rate": 0.00019963233847761894, "loss": 1.0683, "step": 365 }, { "epoch": 1.2627986348122868, "grad_norm": 0.5, "learning_rate": 0.00019957953837412677, "loss": 1.0829, "step": 370 }, { "epoch": 1.2798634812286689, "grad_norm": 0.306640625, "learning_rate": 0.0001995232049071302, "loss": 1.0878, "step": 375 }, { "epoch": 1.2969283276450512, "grad_norm": 0.458984375, "learning_rate": 0.00019946334007549978, "loss": 1.0697, "step": 380 }, { "epoch": 1.3139931740614335, "grad_norm": 0.54296875, "learning_rate": 0.00019939994600340905, "loss": 1.0765, "step": 385 }, { "epoch": 1.3310580204778157, "grad_norm": 0.310546875, "learning_rate": 0.00019933302494025884, "loss": 1.0772, "step": 390 }, { "epoch": 1.348122866894198, "grad_norm": 0.3515625, "learning_rate": 0.00019926257926059768, "loss": 1.0739, "step": 395 }, { "epoch": 1.36518771331058, "grad_norm": 0.271484375, "learning_rate": 0.00019918861146403733, "loss": 1.0816, "step": 400 }, { "epoch": 1.3822525597269624, "grad_norm": 0.30859375, "learning_rate": 0.0001991111241751644, "loss": 1.0711, "step": 405 }, { "epoch": 1.3993174061433447, "grad_norm": 0.27734375, "learning_rate": 0.00019903012014344686, "loss": 1.0616, "step": 410 }, { "epoch": 1.416382252559727, "grad_norm": 0.30859375, "learning_rate": 0.00019894560224313678, "loss": 1.0624, "step": 415 }, { "epoch": 1.4334470989761092, "grad_norm": 0.341796875, "learning_rate": 0.00019885757347316813, "loss": 1.0572, "step": 420 }, { "epoch": 1.4505119453924915, "grad_norm": 0.400390625, "learning_rate": 0.0001987660369570505, "loss": 1.0701, "step": 425 }, { "epoch": 1.4675767918088738, "grad_norm": 0.578125, "learning_rate": 0.00019867099594275827, "loss": 1.0669, "step": 430 }, { "epoch": 1.484641638225256, "grad_norm": 0.412109375, "learning_rate": 0.00019857245380261525, "loss": 1.0724, "step": 435 }, { "epoch": 1.5017064846416384, "grad_norm": 0.365234375, "learning_rate": 0.0001984704140331751, "loss": 1.0728, "step": 440 }, { "epoch": 1.5187713310580204, "grad_norm": 0.296875, "learning_rate": 0.00019836488025509736, "loss": 1.0712, "step": 445 }, { "epoch": 1.5358361774744027, "grad_norm": 0.3125, "learning_rate": 0.00019825585621301872, "loss": 1.0569, "step": 450 }, { "epoch": 1.552901023890785, "grad_norm": 0.486328125, "learning_rate": 0.00019814334577542038, "loss": 1.0638, "step": 455 }, { "epoch": 1.5699658703071673, "grad_norm": 0.30078125, "learning_rate": 0.0001980273529344907, "loss": 1.0638, "step": 460 }, { "epoch": 1.5870307167235493, "grad_norm": 0.310546875, "learning_rate": 0.00019790788180598358, "loss": 1.0556, "step": 465 }, { "epoch": 1.6040955631399316, "grad_norm": 0.265625, "learning_rate": 0.00019778493662907237, "loss": 1.056, "step": 470 }, { "epoch": 1.621160409556314, "grad_norm": 0.5390625, "learning_rate": 0.00019765852176619944, "loss": 1.0512, "step": 475 }, { "epoch": 1.6382252559726962, "grad_norm": 0.404296875, "learning_rate": 0.00019752864170292152, "loss": 1.0585, "step": 480 }, { "epoch": 1.6552901023890785, "grad_norm": 0.62890625, "learning_rate": 0.00019739530104775032, "loss": 1.0628, "step": 485 }, { "epoch": 1.6723549488054608, "grad_norm": 0.3125, "learning_rate": 0.00019725850453198925, "loss": 1.0612, "step": 490 }, { "epoch": 1.689419795221843, "grad_norm": 0.5234375, "learning_rate": 0.00019711825700956536, "loss": 1.0549, "step": 495 }, { "epoch": 1.7064846416382253, "grad_norm": 0.42578125, "learning_rate": 0.0001969745634568572, "loss": 1.0506, "step": 500 }, { "epoch": 1.7235494880546076, "grad_norm": 0.404296875, "learning_rate": 0.00019682742897251818, "loss": 1.0418, "step": 505 }, { "epoch": 1.74061433447099, "grad_norm": 0.400390625, "learning_rate": 0.0001966768587772957, "loss": 1.0508, "step": 510 }, { "epoch": 1.757679180887372, "grad_norm": 0.400390625, "learning_rate": 0.00019652285821384596, "loss": 1.0519, "step": 515 }, { "epoch": 1.7747440273037542, "grad_norm": 0.404296875, "learning_rate": 0.0001963654327465442, "loss": 1.0554, "step": 520 }, { "epoch": 1.7918088737201365, "grad_norm": 0.404296875, "learning_rate": 0.00019620458796129104, "loss": 1.0421, "step": 525 }, { "epoch": 1.8088737201365188, "grad_norm": 0.375, "learning_rate": 0.0001960403295653141, "loss": 1.0421, "step": 530 }, { "epoch": 1.8259385665529009, "grad_norm": 0.322265625, "learning_rate": 0.00019587266338696565, "loss": 1.046, "step": 535 }, { "epoch": 1.8430034129692832, "grad_norm": 0.279296875, "learning_rate": 0.00019570159537551552, "loss": 1.0528, "step": 540 }, { "epoch": 1.8600682593856654, "grad_norm": 0.31640625, "learning_rate": 0.00019552713160094038, "loss": 1.0481, "step": 545 }, { "epoch": 1.8771331058020477, "grad_norm": 0.314453125, "learning_rate": 0.00019534927825370815, "loss": 1.0477, "step": 550 }, { "epoch": 1.89419795221843, "grad_norm": 0.30078125, "learning_rate": 0.00019516804164455826, "loss": 1.0513, "step": 555 }, { "epoch": 1.9112627986348123, "grad_norm": 0.455078125, "learning_rate": 0.00019498342820427794, "loss": 1.0505, "step": 560 }, { "epoch": 1.9283276450511946, "grad_norm": 0.36328125, "learning_rate": 0.00019479544448347392, "loss": 1.0538, "step": 565 }, { "epoch": 1.9453924914675769, "grad_norm": 0.283203125, "learning_rate": 0.00019460409715233996, "loss": 1.0332, "step": 570 }, { "epoch": 1.9624573378839592, "grad_norm": 0.41796875, "learning_rate": 0.00019440939300042028, "loss": 1.047, "step": 575 }, { "epoch": 1.9795221843003414, "grad_norm": 0.365234375, "learning_rate": 0.00019421133893636854, "loss": 1.0321, "step": 580 }, { "epoch": 1.9965870307167235, "grad_norm": 0.298828125, "learning_rate": 0.00019400994198770274, "loss": 1.0415, "step": 585 }, { "epoch": 2.0, "eval_loss": 2.451392650604248, "eval_runtime": 0.5484, "eval_samples_per_second": 18.236, "eval_steps_per_second": 1.824, "step": 586 }, { "epoch": 2.013651877133106, "grad_norm": 0.287109375, "learning_rate": 0.00019380520930055602, "loss": 1.0194, "step": 590 }, { "epoch": 2.030716723549488, "grad_norm": 0.412109375, "learning_rate": 0.0001935971481394227, "loss": 0.9985, "step": 595 }, { "epoch": 2.04778156996587, "grad_norm": 0.28515625, "learning_rate": 0.00019338576588690104, "loss": 1.0026, "step": 600 }, { "epoch": 2.0648464163822524, "grad_norm": 0.34765625, "learning_rate": 0.00019317107004343078, "loss": 1.0018, "step": 605 }, { "epoch": 2.0819112627986347, "grad_norm": 0.310546875, "learning_rate": 0.0001929530682270274, "loss": 1.0096, "step": 610 }, { "epoch": 2.098976109215017, "grad_norm": 0.326171875, "learning_rate": 0.0001927317681730115, "loss": 1.0047, "step": 615 }, { "epoch": 2.1160409556313993, "grad_norm": 0.4609375, "learning_rate": 0.00019250717773373462, "loss": 0.9998, "step": 620 }, { "epoch": 2.1331058020477816, "grad_norm": 0.333984375, "learning_rate": 0.00019227930487830035, "loss": 1.0121, "step": 625 }, { "epoch": 2.150170648464164, "grad_norm": 0.326171875, "learning_rate": 0.00019204815769228176, "loss": 1.0064, "step": 630 }, { "epoch": 2.167235494880546, "grad_norm": 0.294921875, "learning_rate": 0.00019181374437743438, "loss": 0.9968, "step": 635 }, { "epoch": 2.1843003412969284, "grad_norm": 0.2890625, "learning_rate": 0.00019157607325140524, "loss": 1.0046, "step": 640 }, { "epoch": 2.2013651877133107, "grad_norm": 0.43359375, "learning_rate": 0.00019133515274743771, "loss": 1.0161, "step": 645 }, { "epoch": 2.218430034129693, "grad_norm": 0.3203125, "learning_rate": 0.00019109099141407233, "loss": 1.004, "step": 650 }, { "epoch": 2.2354948805460753, "grad_norm": 0.41015625, "learning_rate": 0.0001908435979148434, "loss": 1.0071, "step": 655 }, { "epoch": 2.252559726962457, "grad_norm": 0.318359375, "learning_rate": 0.00019059298102797146, "loss": 1.0117, "step": 660 }, { "epoch": 2.26962457337884, "grad_norm": 0.3671875, "learning_rate": 0.0001903391496460522, "loss": 0.9996, "step": 665 }, { "epoch": 2.2866894197952217, "grad_norm": 0.31640625, "learning_rate": 0.0001900821127757405, "loss": 1.0038, "step": 670 }, { "epoch": 2.303754266211604, "grad_norm": 0.5078125, "learning_rate": 0.0001898218795374311, "loss": 1.0105, "step": 675 }, { "epoch": 2.3208191126279862, "grad_norm": 0.451171875, "learning_rate": 0.0001895584591649349, "loss": 0.9929, "step": 680 }, { "epoch": 2.3378839590443685, "grad_norm": 0.333984375, "learning_rate": 0.00018929186100515136, "loss": 1.0018, "step": 685 }, { "epoch": 2.354948805460751, "grad_norm": 0.498046875, "learning_rate": 0.00018902209451773674, "loss": 0.9955, "step": 690 }, { "epoch": 2.372013651877133, "grad_norm": 0.4375, "learning_rate": 0.0001887491692747686, "loss": 0.9953, "step": 695 }, { "epoch": 2.3890784982935154, "grad_norm": 0.37890625, "learning_rate": 0.000188473094960406, "loss": 0.9833, "step": 700 }, { "epoch": 2.4061433447098977, "grad_norm": 0.291015625, "learning_rate": 0.00018819388137054604, "loss": 1.0089, "step": 705 }, { "epoch": 2.42320819112628, "grad_norm": 0.287109375, "learning_rate": 0.00018791153841247614, "loss": 1.0031, "step": 710 }, { "epoch": 2.4402730375426622, "grad_norm": 0.279296875, "learning_rate": 0.00018762607610452254, "loss": 1.002, "step": 715 }, { "epoch": 2.4573378839590445, "grad_norm": 0.333984375, "learning_rate": 0.00018733750457569485, "loss": 1.0003, "step": 720 }, { "epoch": 2.474402730375427, "grad_norm": 0.361328125, "learning_rate": 0.00018704583406532662, "loss": 1.004, "step": 725 }, { "epoch": 2.491467576791809, "grad_norm": 0.31640625, "learning_rate": 0.00018675107492271208, "loss": 1.0075, "step": 730 }, { "epoch": 2.508532423208191, "grad_norm": 0.2890625, "learning_rate": 0.0001864532376067387, "loss": 1.0035, "step": 735 }, { "epoch": 2.5255972696245736, "grad_norm": 0.33203125, "learning_rate": 0.00018615233268551643, "loss": 0.9968, "step": 740 }, { "epoch": 2.5426621160409555, "grad_norm": 0.294921875, "learning_rate": 0.00018584837083600244, "loss": 1.0124, "step": 745 }, { "epoch": 2.5597269624573378, "grad_norm": 0.302734375, "learning_rate": 0.00018554136284362237, "loss": 1.0012, "step": 750 }, { "epoch": 2.57679180887372, "grad_norm": 0.291015625, "learning_rate": 0.00018523131960188755, "loss": 0.9915, "step": 755 }, { "epoch": 2.5938566552901023, "grad_norm": 0.365234375, "learning_rate": 0.0001849182521120087, "loss": 0.9996, "step": 760 }, { "epoch": 2.6109215017064846, "grad_norm": 0.2890625, "learning_rate": 0.00018460217148250524, "loss": 0.9975, "step": 765 }, { "epoch": 2.627986348122867, "grad_norm": 0.33203125, "learning_rate": 0.0001842830889288114, "loss": 1.0008, "step": 770 }, { "epoch": 2.645051194539249, "grad_norm": 0.341796875, "learning_rate": 0.00018396101577287813, "loss": 1.0041, "step": 775 }, { "epoch": 2.6621160409556315, "grad_norm": 0.33984375, "learning_rate": 0.00018363596344277144, "loss": 0.9995, "step": 780 }, { "epoch": 2.6791808873720138, "grad_norm": 0.30078125, "learning_rate": 0.0001833079434722668, "loss": 1.002, "step": 785 }, { "epoch": 2.696245733788396, "grad_norm": 0.36328125, "learning_rate": 0.00018297696750044, "loss": 1.0057, "step": 790 }, { "epoch": 2.7133105802047783, "grad_norm": 0.30859375, "learning_rate": 0.00018264304727125407, "loss": 0.9966, "step": 795 }, { "epoch": 2.73037542662116, "grad_norm": 0.384765625, "learning_rate": 0.00018230619463314266, "loss": 0.9887, "step": 800 }, { "epoch": 2.747440273037543, "grad_norm": 0.373046875, "learning_rate": 0.00018196642153858958, "loss": 0.9993, "step": 805 }, { "epoch": 2.7645051194539247, "grad_norm": 0.408203125, "learning_rate": 0.00018162374004370463, "loss": 0.9953, "step": 810 }, { "epoch": 2.781569965870307, "grad_norm": 0.283203125, "learning_rate": 0.0001812781623077959, "loss": 0.9856, "step": 815 }, { "epoch": 2.7986348122866893, "grad_norm": 0.294921875, "learning_rate": 0.00018092970059293835, "loss": 1.0029, "step": 820 }, { "epoch": 2.8156996587030716, "grad_norm": 0.37109375, "learning_rate": 0.0001805783672635386, "loss": 0.991, "step": 825 }, { "epoch": 2.832764505119454, "grad_norm": 0.298828125, "learning_rate": 0.00018022417478589627, "loss": 1.0053, "step": 830 }, { "epoch": 2.849829351535836, "grad_norm": 0.3359375, "learning_rate": 0.00017986713572776174, "loss": 0.9865, "step": 835 }, { "epoch": 2.8668941979522184, "grad_norm": 0.271484375, "learning_rate": 0.00017950726275789, "loss": 0.9948, "step": 840 }, { "epoch": 2.8839590443686007, "grad_norm": 0.38671875, "learning_rate": 0.00017914456864559126, "loss": 0.9916, "step": 845 }, { "epoch": 2.901023890784983, "grad_norm": 0.345703125, "learning_rate": 0.0001787790662602779, "loss": 0.9985, "step": 850 }, { "epoch": 2.9180887372013653, "grad_norm": 0.34375, "learning_rate": 0.00017841076857100767, "loss": 0.994, "step": 855 }, { "epoch": 2.9351535836177476, "grad_norm": 0.265625, "learning_rate": 0.0001780396886460237, "loss": 0.9811, "step": 860 }, { "epoch": 2.9522184300341294, "grad_norm": 0.458984375, "learning_rate": 0.00017766583965229065, "loss": 0.9872, "step": 865 }, { "epoch": 2.969283276450512, "grad_norm": 0.37109375, "learning_rate": 0.00017728923485502759, "loss": 0.9951, "step": 870 }, { "epoch": 2.986348122866894, "grad_norm": 0.365234375, "learning_rate": 0.00017690988761723725, "loss": 0.9915, "step": 875 }, { "epoch": 3.0, "eval_loss": 2.4749691486358643, "eval_runtime": 0.5425, "eval_samples_per_second": 18.434, "eval_steps_per_second": 1.843, "step": 879 }, { "epoch": 3.0034129692832763, "grad_norm": 0.39453125, "learning_rate": 0.00017652781139923196, "loss": 0.9883, "step": 880 }, { "epoch": 3.0204778156996586, "grad_norm": 0.5078125, "learning_rate": 0.000176143019758156, "loss": 0.9611, "step": 885 }, { "epoch": 3.037542662116041, "grad_norm": 0.359375, "learning_rate": 0.0001757555263475044, "loss": 0.9542, "step": 890 }, { "epoch": 3.054607508532423, "grad_norm": 0.326171875, "learning_rate": 0.00017536534491663873, "loss": 0.9614, "step": 895 }, { "epoch": 3.0716723549488054, "grad_norm": 0.349609375, "learning_rate": 0.00017497248931029914, "loss": 0.9538, "step": 900 }, { "epoch": 3.0887372013651877, "grad_norm": 0.30859375, "learning_rate": 0.000174576973468113, "loss": 0.9581, "step": 905 }, { "epoch": 3.10580204778157, "grad_norm": 0.31640625, "learning_rate": 0.00017417881142410037, "loss": 0.9466, "step": 910 }, { "epoch": 3.1228668941979523, "grad_norm": 0.298828125, "learning_rate": 0.00017377801730617613, "loss": 0.9632, "step": 915 }, { "epoch": 3.1399317406143346, "grad_norm": 0.298828125, "learning_rate": 0.00017337460533564845, "loss": 0.948, "step": 920 }, { "epoch": 3.156996587030717, "grad_norm": 0.310546875, "learning_rate": 0.00017296858982671442, "loss": 0.9515, "step": 925 }, { "epoch": 3.174061433447099, "grad_norm": 0.29296875, "learning_rate": 0.00017255998518595194, "loss": 0.9625, "step": 930 }, { "epoch": 3.1911262798634814, "grad_norm": 0.28125, "learning_rate": 0.00017214880591180873, "loss": 0.9532, "step": 935 }, { "epoch": 3.2081911262798632, "grad_norm": 0.326171875, "learning_rate": 0.0001717350665940877, "loss": 0.9499, "step": 940 }, { "epoch": 3.2252559726962455, "grad_norm": 0.333984375, "learning_rate": 0.00017131878191342932, "loss": 0.9505, "step": 945 }, { "epoch": 3.242320819112628, "grad_norm": 0.376953125, "learning_rate": 0.00017089996664079084, "loss": 0.9489, "step": 950 }, { "epoch": 3.25938566552901, "grad_norm": 0.310546875, "learning_rate": 0.00017047863563692198, "loss": 0.9623, "step": 955 }, { "epoch": 3.2764505119453924, "grad_norm": 0.267578125, "learning_rate": 0.00017005480385183774, "loss": 0.9474, "step": 960 }, { "epoch": 3.2935153583617747, "grad_norm": 0.333984375, "learning_rate": 0.00016962848632428795, "loss": 0.9558, "step": 965 }, { "epoch": 3.310580204778157, "grad_norm": 0.34765625, "learning_rate": 0.00016919969818122345, "loss": 0.9538, "step": 970 }, { "epoch": 3.3276450511945392, "grad_norm": 0.5, "learning_rate": 0.00016876845463725975, "loss": 0.955, "step": 975 }, { "epoch": 3.3447098976109215, "grad_norm": 1.8203125, "learning_rate": 0.0001683347709941367, "loss": 0.9615, "step": 980 }, { "epoch": 3.361774744027304, "grad_norm": 0.44921875, "learning_rate": 0.0001678986626401759, "loss": 0.9591, "step": 985 }, { "epoch": 3.378839590443686, "grad_norm": 0.3671875, "learning_rate": 0.00016746014504973448, "loss": 0.9479, "step": 990 }, { "epoch": 3.3959044368600684, "grad_norm": 0.419921875, "learning_rate": 0.00016701923378265615, "loss": 0.9511, "step": 995 }, { "epoch": 3.4129692832764507, "grad_norm": 0.3203125, "learning_rate": 0.00016657594448371896, "loss": 0.962, "step": 1000 }, { "epoch": 3.430034129692833, "grad_norm": 0.4296875, "learning_rate": 0.0001661302928820803, "loss": 0.9612, "step": 1005 }, { "epoch": 3.4470989761092152, "grad_norm": 0.455078125, "learning_rate": 0.00016568229479071872, "loss": 0.9524, "step": 1010 }, { "epoch": 3.464163822525597, "grad_norm": 0.306640625, "learning_rate": 0.0001652319661058729, "loss": 0.9557, "step": 1015 }, { "epoch": 3.4812286689419794, "grad_norm": 0.26953125, "learning_rate": 0.00016477932280647747, "loss": 0.9635, "step": 1020 }, { "epoch": 3.4982935153583616, "grad_norm": 0.28515625, "learning_rate": 0.00016432438095359623, "loss": 0.9549, "step": 1025 }, { "epoch": 3.515358361774744, "grad_norm": 0.28515625, "learning_rate": 0.00016386715668985211, "loss": 0.9456, "step": 1030 }, { "epoch": 3.532423208191126, "grad_norm": 0.423828125, "learning_rate": 0.00016340766623885438, "loss": 0.945, "step": 1035 }, { "epoch": 3.5494880546075085, "grad_norm": 0.330078125, "learning_rate": 0.00016294592590462316, "loss": 0.95, "step": 1040 }, { "epoch": 3.5665529010238908, "grad_norm": 0.3359375, "learning_rate": 0.0001624819520710107, "loss": 0.9583, "step": 1045 }, { "epoch": 3.583617747440273, "grad_norm": 0.36328125, "learning_rate": 0.00016201576120112007, "loss": 0.9443, "step": 1050 }, { "epoch": 3.6006825938566553, "grad_norm": 0.345703125, "learning_rate": 0.0001615473698367212, "loss": 0.9635, "step": 1055 }, { "epoch": 3.6177474402730376, "grad_norm": 0.51953125, "learning_rate": 0.00016107679459766367, "loss": 0.9524, "step": 1060 }, { "epoch": 3.63481228668942, "grad_norm": 0.279296875, "learning_rate": 0.0001606040521812872, "loss": 0.9552, "step": 1065 }, { "epoch": 3.651877133105802, "grad_norm": 0.3125, "learning_rate": 0.00016012915936182892, "loss": 0.9502, "step": 1070 }, { "epoch": 3.6689419795221845, "grad_norm": 0.3125, "learning_rate": 0.00015965213298982855, "loss": 0.9629, "step": 1075 }, { "epoch": 3.6860068259385663, "grad_norm": 0.361328125, "learning_rate": 0.00015917298999153015, "loss": 0.9591, "step": 1080 }, { "epoch": 3.703071672354949, "grad_norm": 0.296875, "learning_rate": 0.00015869174736828168, "loss": 0.9699, "step": 1085 }, { "epoch": 3.720136518771331, "grad_norm": 0.30078125, "learning_rate": 0.00015820842219593182, "loss": 0.9478, "step": 1090 }, { "epoch": 3.737201365187713, "grad_norm": 0.33984375, "learning_rate": 0.00015772303162422385, "loss": 0.9646, "step": 1095 }, { "epoch": 3.7542662116040955, "grad_norm": 0.404296875, "learning_rate": 0.00015723559287618728, "loss": 0.9601, "step": 1100 }, { "epoch": 3.7713310580204777, "grad_norm": 0.421875, "learning_rate": 0.00015674612324752683, "loss": 0.9548, "step": 1105 }, { "epoch": 3.78839590443686, "grad_norm": 0.32421875, "learning_rate": 0.00015625464010600844, "loss": 0.9625, "step": 1110 }, { "epoch": 3.8054607508532423, "grad_norm": 0.287109375, "learning_rate": 0.00015576116089084327, "loss": 0.9448, "step": 1115 }, { "epoch": 3.8225255972696246, "grad_norm": 0.28125, "learning_rate": 0.00015526570311206884, "loss": 0.9547, "step": 1120 }, { "epoch": 3.839590443686007, "grad_norm": 0.275390625, "learning_rate": 0.00015476828434992762, "loss": 0.9527, "step": 1125 }, { "epoch": 3.856655290102389, "grad_norm": 0.326171875, "learning_rate": 0.00015426892225424337, "loss": 0.9499, "step": 1130 }, { "epoch": 3.8737201365187715, "grad_norm": 0.271484375, "learning_rate": 0.00015376763454379478, "loss": 0.9593, "step": 1135 }, { "epoch": 3.8907849829351537, "grad_norm": 0.314453125, "learning_rate": 0.0001532644390056868, "loss": 0.9457, "step": 1140 }, { "epoch": 3.9078498293515356, "grad_norm": 0.49609375, "learning_rate": 0.00015275935349471959, "loss": 0.9622, "step": 1145 }, { "epoch": 3.9249146757679183, "grad_norm": 0.3125, "learning_rate": 0.00015225239593275473, "loss": 0.9584, "step": 1150 }, { "epoch": 3.9419795221843, "grad_norm": 0.29296875, "learning_rate": 0.00015174358430807957, "loss": 0.9547, "step": 1155 }, { "epoch": 3.9590443686006824, "grad_norm": 0.28515625, "learning_rate": 0.00015123293667476887, "loss": 0.9546, "step": 1160 }, { "epoch": 3.9761092150170647, "grad_norm": 0.345703125, "learning_rate": 0.00015072047115204397, "loss": 0.945, "step": 1165 }, { "epoch": 3.993174061433447, "grad_norm": 0.3203125, "learning_rate": 0.00015020620592363034, "loss": 0.9551, "step": 1170 }, { "epoch": 4.0, "eval_loss": 2.529212474822998, "eval_runtime": 0.5437, "eval_samples_per_second": 18.394, "eval_steps_per_second": 1.839, "step": 1172 }, { "epoch": 4.010238907849829, "grad_norm": 0.31640625, "learning_rate": 0.00014969015923711195, "loss": 0.925, "step": 1175 }, { "epoch": 4.027303754266212, "grad_norm": 0.306640625, "learning_rate": 0.00014917234940328396, "loss": 0.9111, "step": 1180 }, { "epoch": 4.044368600682594, "grad_norm": 0.3203125, "learning_rate": 0.00014865279479550292, "loss": 0.9124, "step": 1185 }, { "epoch": 4.061433447098976, "grad_norm": 0.3125, "learning_rate": 0.00014813151384903493, "loss": 0.912, "step": 1190 }, { "epoch": 4.078498293515358, "grad_norm": 0.3125, "learning_rate": 0.00014760852506040162, "loss": 0.9113, "step": 1195 }, { "epoch": 4.09556313993174, "grad_norm": 0.298828125, "learning_rate": 0.0001470838469867234, "loss": 0.9168, "step": 1200 }, { "epoch": 4.112627986348123, "grad_norm": 0.310546875, "learning_rate": 0.00014655749824506151, "loss": 0.9152, "step": 1205 }, { "epoch": 4.129692832764505, "grad_norm": 0.3046875, "learning_rate": 0.00014602949751175713, "loss": 0.9098, "step": 1210 }, { "epoch": 4.146757679180888, "grad_norm": 0.333984375, "learning_rate": 0.00014549986352176882, "loss": 0.9213, "step": 1215 }, { "epoch": 4.163822525597269, "grad_norm": 0.341796875, "learning_rate": 0.00014496861506800758, "loss": 0.9128, "step": 1220 }, { "epoch": 4.180887372013652, "grad_norm": 0.29296875, "learning_rate": 0.0001444357710006703, "loss": 0.9102, "step": 1225 }, { "epoch": 4.197952218430034, "grad_norm": 0.330078125, "learning_rate": 0.0001439013502265707, "loss": 0.9058, "step": 1230 }, { "epoch": 4.215017064846417, "grad_norm": 0.380859375, "learning_rate": 0.00014336537170846848, "loss": 0.9233, "step": 1235 }, { "epoch": 4.2320819112627985, "grad_norm": 0.404296875, "learning_rate": 0.00014282785446439653, "loss": 0.9092, "step": 1240 }, { "epoch": 4.249146757679181, "grad_norm": 0.40234375, "learning_rate": 0.00014228881756698603, "loss": 0.9093, "step": 1245 }, { "epoch": 4.266211604095563, "grad_norm": 0.306640625, "learning_rate": 0.00014174828014278985, "loss": 0.9271, "step": 1250 }, { "epoch": 4.283276450511945, "grad_norm": 0.3203125, "learning_rate": 0.00014120626137160375, "loss": 0.9189, "step": 1255 }, { "epoch": 4.300341296928328, "grad_norm": 0.28125, "learning_rate": 0.00014066278048578584, "loss": 0.9078, "step": 1260 }, { "epoch": 4.3174061433447095, "grad_norm": 0.298828125, "learning_rate": 0.00014011785676957422, "loss": 0.9115, "step": 1265 }, { "epoch": 4.334470989761092, "grad_norm": 0.33203125, "learning_rate": 0.00013957150955840267, "loss": 0.9099, "step": 1270 }, { "epoch": 4.351535836177474, "grad_norm": 0.28125, "learning_rate": 0.0001390237582382147, "loss": 0.9208, "step": 1275 }, { "epoch": 4.368600682593857, "grad_norm": 0.3125, "learning_rate": 0.00013847462224477538, "loss": 0.9133, "step": 1280 }, { "epoch": 4.385665529010239, "grad_norm": 0.328125, "learning_rate": 0.00013792412106298198, "loss": 0.9088, "step": 1285 }, { "epoch": 4.402730375426621, "grad_norm": 0.328125, "learning_rate": 0.00013737227422617267, "loss": 0.9176, "step": 1290 }, { "epoch": 4.419795221843003, "grad_norm": 0.30078125, "learning_rate": 0.00013681910131543309, "loss": 0.9143, "step": 1295 }, { "epoch": 4.436860068259386, "grad_norm": 0.328125, "learning_rate": 0.00013626462195890168, "loss": 0.9148, "step": 1300 }, { "epoch": 4.453924914675768, "grad_norm": 0.29296875, "learning_rate": 0.00013570885583107347, "loss": 0.9165, "step": 1305 }, { "epoch": 4.4709897610921505, "grad_norm": 0.3203125, "learning_rate": 0.00013515182265210165, "loss": 0.9198, "step": 1310 }, { "epoch": 4.488054607508532, "grad_norm": 0.3046875, "learning_rate": 0.00013459354218709794, "loss": 0.9294, "step": 1315 }, { "epoch": 4.505119453924914, "grad_norm": 0.287109375, "learning_rate": 0.00013403403424543139, "loss": 0.9137, "step": 1320 }, { "epoch": 4.522184300341297, "grad_norm": 0.341796875, "learning_rate": 0.00013347331868002527, "loss": 0.9172, "step": 1325 }, { "epoch": 4.53924914675768, "grad_norm": 0.294921875, "learning_rate": 0.0001329114153866529, "loss": 0.9237, "step": 1330 }, { "epoch": 4.5563139931740615, "grad_norm": 0.32421875, "learning_rate": 0.00013234834430323145, "loss": 0.9144, "step": 1335 }, { "epoch": 4.573378839590443, "grad_norm": 0.326171875, "learning_rate": 0.00013178412540911457, "loss": 0.9193, "step": 1340 }, { "epoch": 4.590443686006826, "grad_norm": 0.322265625, "learning_rate": 0.00013121877872438354, "loss": 0.9217, "step": 1345 }, { "epoch": 4.607508532423208, "grad_norm": 0.3359375, "learning_rate": 0.00013065232430913676, "loss": 0.9252, "step": 1350 }, { "epoch": 4.624573378839591, "grad_norm": 0.294921875, "learning_rate": 0.00013008478226277816, "loss": 0.9265, "step": 1355 }, { "epoch": 4.6416382252559725, "grad_norm": 0.298828125, "learning_rate": 0.00012951617272330377, "loss": 0.9221, "step": 1360 }, { "epoch": 4.658703071672355, "grad_norm": 0.345703125, "learning_rate": 0.00012894651586658736, "loss": 0.9131, "step": 1365 }, { "epoch": 4.675767918088737, "grad_norm": 0.337890625, "learning_rate": 0.00012837583190566446, "loss": 0.9109, "step": 1370 }, { "epoch": 4.69283276450512, "grad_norm": 0.388671875, "learning_rate": 0.00012780414109001518, "loss": 0.9204, "step": 1375 }, { "epoch": 4.709897610921502, "grad_norm": 0.306640625, "learning_rate": 0.00012723146370484568, "loss": 0.9154, "step": 1380 }, { "epoch": 4.726962457337884, "grad_norm": 0.3515625, "learning_rate": 0.00012665782007036835, "loss": 0.9251, "step": 1385 }, { "epoch": 4.744027303754266, "grad_norm": 0.3984375, "learning_rate": 0.0001260832305410809, "loss": 0.926, "step": 1390 }, { "epoch": 4.761092150170649, "grad_norm": 0.369140625, "learning_rate": 0.00012550771550504396, "loss": 0.9137, "step": 1395 }, { "epoch": 4.778156996587031, "grad_norm": 0.34375, "learning_rate": 0.00012493129538315788, "loss": 0.9181, "step": 1400 }, { "epoch": 4.795221843003413, "grad_norm": 0.349609375, "learning_rate": 0.00012435399062843796, "loss": 0.9207, "step": 1405 }, { "epoch": 4.812286689419795, "grad_norm": 0.287109375, "learning_rate": 0.00012377582172528877, "loss": 0.9156, "step": 1410 }, { "epoch": 4.829351535836177, "grad_norm": 0.31640625, "learning_rate": 0.00012319680918877732, "loss": 0.9222, "step": 1415 }, { "epoch": 4.84641638225256, "grad_norm": 0.29296875, "learning_rate": 0.00012261697356390506, "loss": 0.9297, "step": 1420 }, { "epoch": 4.863481228668942, "grad_norm": 0.37109375, "learning_rate": 0.00012203633542487907, "loss": 0.9146, "step": 1425 }, { "epoch": 4.8805460750853245, "grad_norm": 0.453125, "learning_rate": 0.00012145491537438174, "loss": 0.917, "step": 1430 }, { "epoch": 4.897610921501706, "grad_norm": 0.33203125, "learning_rate": 0.00012087273404284002, "loss": 0.912, "step": 1435 }, { "epoch": 4.914675767918089, "grad_norm": 0.3359375, "learning_rate": 0.0001202898120876932, "loss": 0.9224, "step": 1440 }, { "epoch": 4.931740614334471, "grad_norm": 0.28515625, "learning_rate": 0.00011970617019266, "loss": 0.9167, "step": 1445 }, { "epoch": 4.948805460750854, "grad_norm": 0.33203125, "learning_rate": 0.00011912182906700466, "loss": 0.9166, "step": 1450 }, { "epoch": 4.965870307167235, "grad_norm": 0.294921875, "learning_rate": 0.00011853680944480206, "loss": 0.9243, "step": 1455 }, { "epoch": 4.982935153583618, "grad_norm": 0.310546875, "learning_rate": 0.00011795113208420208, "loss": 0.9128, "step": 1460 }, { "epoch": 5.0, "grad_norm": 0.373046875, "learning_rate": 0.00011736481776669306, "loss": 0.9287, "step": 1465 }, { "epoch": 5.0, "eval_loss": 2.5924570560455322, "eval_runtime": 0.5421, "eval_samples_per_second": 18.446, "eval_steps_per_second": 1.845, "step": 1465 }, { "epoch": 5.017064846416382, "grad_norm": 0.3203125, "learning_rate": 0.00011677788729636427, "loss": 0.8743, "step": 1470 }, { "epoch": 5.034129692832765, "grad_norm": 0.345703125, "learning_rate": 0.0001161903614991679, "loss": 0.8731, "step": 1475 }, { "epoch": 5.051194539249146, "grad_norm": 0.341796875, "learning_rate": 0.00011560226122218, "loss": 0.8735, "step": 1480 }, { "epoch": 5.068259385665529, "grad_norm": 0.3359375, "learning_rate": 0.00011501360733286085, "loss": 0.8808, "step": 1485 }, { "epoch": 5.085324232081911, "grad_norm": 0.314453125, "learning_rate": 0.00011442442071831434, "loss": 0.8776, "step": 1490 }, { "epoch": 5.102389078498294, "grad_norm": 0.333984375, "learning_rate": 0.00011383472228454699, "loss": 0.872, "step": 1495 }, { "epoch": 5.1194539249146755, "grad_norm": 0.314453125, "learning_rate": 0.00011324453295572618, "loss": 0.8801, "step": 1500 }, { "epoch": 5.136518771331058, "grad_norm": 0.310546875, "learning_rate": 0.00011265387367343763, "loss": 0.8767, "step": 1505 }, { "epoch": 5.15358361774744, "grad_norm": 0.337890625, "learning_rate": 0.00011206276539594221, "loss": 0.8764, "step": 1510 }, { "epoch": 5.170648464163823, "grad_norm": 0.333984375, "learning_rate": 0.00011147122909743257, "loss": 0.8768, "step": 1515 }, { "epoch": 5.187713310580205, "grad_norm": 0.32421875, "learning_rate": 0.00011087928576728865, "loss": 0.8848, "step": 1520 }, { "epoch": 5.204778156996587, "grad_norm": 0.337890625, "learning_rate": 0.00011028695640933309, "loss": 0.8905, "step": 1525 }, { "epoch": 5.221843003412969, "grad_norm": 0.318359375, "learning_rate": 0.00010969426204108583, "loss": 0.8872, "step": 1530 }, { "epoch": 5.238907849829351, "grad_norm": 0.310546875, "learning_rate": 0.00010910122369301842, "loss": 0.8749, "step": 1535 }, { "epoch": 5.255972696245734, "grad_norm": 0.34765625, "learning_rate": 0.00010850786240780786, "loss": 0.884, "step": 1540 }, { "epoch": 5.273037542662116, "grad_norm": 0.41015625, "learning_rate": 0.00010791419923958976, "loss": 0.8739, "step": 1545 }, { "epoch": 5.290102389078498, "grad_norm": 0.330078125, "learning_rate": 0.00010732025525321145, "loss": 0.8902, "step": 1550 }, { "epoch": 5.30716723549488, "grad_norm": 0.322265625, "learning_rate": 0.00010672605152348449, "loss": 0.8863, "step": 1555 }, { "epoch": 5.324232081911263, "grad_norm": 0.341796875, "learning_rate": 0.00010613160913443682, "loss": 0.8752, "step": 1560 }, { "epoch": 5.341296928327645, "grad_norm": 0.337890625, "learning_rate": 0.00010553694917856478, "loss": 0.8782, "step": 1565 }, { "epoch": 5.3583617747440275, "grad_norm": 0.326171875, "learning_rate": 0.00010494209275608455, "loss": 0.8804, "step": 1570 }, { "epoch": 5.375426621160409, "grad_norm": 0.32421875, "learning_rate": 0.00010434706097418338, "loss": 0.8889, "step": 1575 }, { "epoch": 5.392491467576792, "grad_norm": 0.373046875, "learning_rate": 0.00010375187494627098, "loss": 0.8861, "step": 1580 }, { "epoch": 5.409556313993174, "grad_norm": 0.3359375, "learning_rate": 0.00010315655579123, "loss": 0.878, "step": 1585 }, { "epoch": 5.426621160409557, "grad_norm": 0.388671875, "learning_rate": 0.00010256112463266687, "loss": 0.893, "step": 1590 }, { "epoch": 5.4436860068259385, "grad_norm": 0.3515625, "learning_rate": 0.00010196560259816221, "loss": 0.8913, "step": 1595 }, { "epoch": 5.460750853242321, "grad_norm": 0.345703125, "learning_rate": 0.00010137001081852113, "loss": 0.8848, "step": 1600 }, { "epoch": 5.477815699658703, "grad_norm": 0.353515625, "learning_rate": 0.00010077437042702362, "loss": 0.8867, "step": 1605 }, { "epoch": 5.494880546075085, "grad_norm": 0.328125, "learning_rate": 0.00010017870255867445, "loss": 0.8843, "step": 1610 }, { "epoch": 5.511945392491468, "grad_norm": 0.34375, "learning_rate": 9.958302834945332e-05, "loss": 0.8905, "step": 1615 }, { "epoch": 5.5290102389078495, "grad_norm": 0.38671875, "learning_rate": 9.898736893556502e-05, "loss": 0.8903, "step": 1620 }, { "epoch": 5.546075085324232, "grad_norm": 0.337890625, "learning_rate": 9.839174545268931e-05, "loss": 0.897, "step": 1625 }, { "epoch": 5.563139931740614, "grad_norm": 0.326171875, "learning_rate": 9.7796179035231e-05, "loss": 0.8925, "step": 1630 }, { "epoch": 5.580204778156997, "grad_norm": 0.310546875, "learning_rate": 9.720069081557009e-05, "loss": 0.8748, "step": 1635 }, { "epoch": 5.597269624573379, "grad_norm": 0.31640625, "learning_rate": 9.660530192331191e-05, "loss": 0.8829, "step": 1640 }, { "epoch": 5.614334470989761, "grad_norm": 0.30859375, "learning_rate": 9.601003348453734e-05, "loss": 0.8922, "step": 1645 }, { "epoch": 5.631399317406143, "grad_norm": 0.3203125, "learning_rate": 9.541490662105326e-05, "loss": 0.8936, "step": 1650 }, { "epoch": 5.648464163822526, "grad_norm": 0.337890625, "learning_rate": 9.481994244964297e-05, "loss": 0.8897, "step": 1655 }, { "epoch": 5.665529010238908, "grad_norm": 0.30078125, "learning_rate": 9.422516208131709e-05, "loss": 0.8762, "step": 1660 }, { "epoch": 5.6825938566552905, "grad_norm": 0.3046875, "learning_rate": 9.363058662056443e-05, "loss": 0.8842, "step": 1665 }, { "epoch": 5.699658703071672, "grad_norm": 0.341796875, "learning_rate": 9.303623716460297e-05, "loss": 0.8906, "step": 1670 }, { "epoch": 5.716723549488055, "grad_norm": 0.328125, "learning_rate": 9.244213480263148e-05, "loss": 0.8911, "step": 1675 }, { "epoch": 5.733788395904437, "grad_norm": 0.333984375, "learning_rate": 9.184830061508113e-05, "loss": 0.8893, "step": 1680 }, { "epoch": 5.750853242320819, "grad_norm": 0.3359375, "learning_rate": 9.125475567286744e-05, "loss": 0.8826, "step": 1685 }, { "epoch": 5.7679180887372015, "grad_norm": 0.341796875, "learning_rate": 9.066152103664283e-05, "loss": 0.8845, "step": 1690 }, { "epoch": 5.784982935153583, "grad_norm": 0.345703125, "learning_rate": 9.006861775604904e-05, "loss": 0.8808, "step": 1695 }, { "epoch": 5.802047781569966, "grad_norm": 0.328125, "learning_rate": 8.947606686897045e-05, "loss": 0.8829, "step": 1700 }, { "epoch": 5.819112627986348, "grad_norm": 0.31640625, "learning_rate": 8.88838894007875e-05, "loss": 0.8835, "step": 1705 }, { "epoch": 5.836177474402731, "grad_norm": 0.326171875, "learning_rate": 8.829210636363067e-05, "loss": 0.8894, "step": 1710 }, { "epoch": 5.853242320819112, "grad_norm": 0.318359375, "learning_rate": 8.770073875563493e-05, "loss": 0.8822, "step": 1715 }, { "epoch": 5.870307167235495, "grad_norm": 0.3203125, "learning_rate": 8.710980756019467e-05, "loss": 0.8811, "step": 1720 }, { "epoch": 5.887372013651877, "grad_norm": 0.32421875, "learning_rate": 8.651933374521907e-05, "loss": 0.8906, "step": 1725 }, { "epoch": 5.90443686006826, "grad_norm": 0.3125, "learning_rate": 8.592933826238818e-05, "loss": 0.8773, "step": 1730 }, { "epoch": 5.921501706484642, "grad_norm": 0.390625, "learning_rate": 8.533984204640941e-05, "loss": 0.8843, "step": 1735 }, { "epoch": 5.938566552901024, "grad_norm": 0.314453125, "learning_rate": 8.4750866014275e-05, "loss": 0.8907, "step": 1740 }, { "epoch": 5.955631399317406, "grad_norm": 0.353515625, "learning_rate": 8.416243106451934e-05, "loss": 0.8795, "step": 1745 }, { "epoch": 5.972696245733788, "grad_norm": 0.30859375, "learning_rate": 8.357455807647778e-05, "loss": 0.8767, "step": 1750 }, { "epoch": 5.989761092150171, "grad_norm": 0.34375, "learning_rate": 8.29872679095457e-05, "loss": 0.8733, "step": 1755 }, { "epoch": 6.0, "eval_loss": 2.6554951667785645, "eval_runtime": 0.5458, "eval_samples_per_second": 18.321, "eval_steps_per_second": 1.832, "step": 1758 }, { "epoch": 6.006825938566553, "grad_norm": 0.3203125, "learning_rate": 8.240058140243834e-05, "loss": 0.8646, "step": 1760 }, { "epoch": 6.023890784982935, "grad_norm": 0.34765625, "learning_rate": 8.181451937245131e-05, "loss": 0.8498, "step": 1765 }, { "epoch": 6.040955631399317, "grad_norm": 0.349609375, "learning_rate": 8.122910261472214e-05, "loss": 0.8455, "step": 1770 }, { "epoch": 6.0580204778157, "grad_norm": 0.365234375, "learning_rate": 8.064435190149218e-05, "loss": 0.8363, "step": 1775 }, { "epoch": 6.075085324232082, "grad_norm": 0.361328125, "learning_rate": 8.006028798136962e-05, "loss": 0.855, "step": 1780 }, { "epoch": 6.092150170648464, "grad_norm": 0.322265625, "learning_rate": 7.947693157859337e-05, "loss": 0.8556, "step": 1785 }, { "epoch": 6.109215017064846, "grad_norm": 0.3515625, "learning_rate": 7.889430339229754e-05, "loss": 0.8606, "step": 1790 }, { "epoch": 6.126279863481229, "grad_norm": 0.33203125, "learning_rate": 7.831242409577716e-05, "loss": 0.8535, "step": 1795 }, { "epoch": 6.143344709897611, "grad_norm": 0.34765625, "learning_rate": 7.773131433575444e-05, "loss": 0.851, "step": 1800 }, { "epoch": 6.160409556313994, "grad_norm": 0.369140625, "learning_rate": 7.715099473164632e-05, "loss": 0.8468, "step": 1805 }, { "epoch": 6.177474402730375, "grad_norm": 0.361328125, "learning_rate": 7.657148587483271e-05, "loss": 0.8518, "step": 1810 }, { "epoch": 6.194539249146757, "grad_norm": 0.330078125, "learning_rate": 7.599280832792596e-05, "loss": 0.8467, "step": 1815 }, { "epoch": 6.21160409556314, "grad_norm": 0.322265625, "learning_rate": 7.541498262404125e-05, "loss": 0.8549, "step": 1820 }, { "epoch": 6.228668941979522, "grad_norm": 0.32421875, "learning_rate": 7.483802926606787e-05, "loss": 0.8534, "step": 1825 }, { "epoch": 6.2457337883959045, "grad_norm": 0.326171875, "learning_rate": 7.426196872594182e-05, "loss": 0.8491, "step": 1830 }, { "epoch": 6.262798634812286, "grad_norm": 0.330078125, "learning_rate": 7.368682144391944e-05, "loss": 0.8503, "step": 1835 }, { "epoch": 6.279863481228669, "grad_norm": 0.361328125, "learning_rate": 7.311260782785207e-05, "loss": 0.8528, "step": 1840 }, { "epoch": 6.296928327645051, "grad_norm": 0.328125, "learning_rate": 7.253934825246193e-05, "loss": 0.8592, "step": 1845 }, { "epoch": 6.313993174061434, "grad_norm": 0.39453125, "learning_rate": 7.196706305861925e-05, "loss": 0.8528, "step": 1850 }, { "epoch": 6.3310580204778155, "grad_norm": 0.328125, "learning_rate": 7.139577255262034e-05, "loss": 0.8528, "step": 1855 }, { "epoch": 6.348122866894198, "grad_norm": 0.34375, "learning_rate": 7.082549700546726e-05, "loss": 0.8561, "step": 1860 }, { "epoch": 6.36518771331058, "grad_norm": 0.330078125, "learning_rate": 7.025625665214844e-05, "loss": 0.8562, "step": 1865 }, { "epoch": 6.382252559726963, "grad_norm": 0.3203125, "learning_rate": 6.968807169092059e-05, "loss": 0.8561, "step": 1870 }, { "epoch": 6.399317406143345, "grad_norm": 0.33203125, "learning_rate": 6.912096228259236e-05, "loss": 0.8598, "step": 1875 }, { "epoch": 6.4163822525597265, "grad_norm": 0.337890625, "learning_rate": 6.855494854980857e-05, "loss": 0.8573, "step": 1880 }, { "epoch": 6.433447098976109, "grad_norm": 0.359375, "learning_rate": 6.799005057633644e-05, "loss": 0.8576, "step": 1885 }, { "epoch": 6.450511945392491, "grad_norm": 0.32421875, "learning_rate": 6.742628840635284e-05, "loss": 0.855, "step": 1890 }, { "epoch": 6.467576791808874, "grad_norm": 0.33203125, "learning_rate": 6.68636820437331e-05, "loss": 0.8628, "step": 1895 }, { "epoch": 6.484641638225256, "grad_norm": 0.39453125, "learning_rate": 6.630225145134144e-05, "loss": 0.8489, "step": 1900 }, { "epoch": 6.501706484641638, "grad_norm": 0.34765625, "learning_rate": 6.574201655032216e-05, "loss": 0.8534, "step": 1905 }, { "epoch": 6.51877133105802, "grad_norm": 0.361328125, "learning_rate": 6.518299721939323e-05, "loss": 0.8582, "step": 1910 }, { "epoch": 6.535836177474403, "grad_norm": 0.34375, "learning_rate": 6.462521329414066e-05, "loss": 0.8561, "step": 1915 }, { "epoch": 6.552901023890785, "grad_norm": 0.326171875, "learning_rate": 6.406868456631483e-05, "loss": 0.8618, "step": 1920 }, { "epoch": 6.5699658703071675, "grad_norm": 0.36328125, "learning_rate": 6.351343078312819e-05, "loss": 0.8575, "step": 1925 }, { "epoch": 6.587030716723549, "grad_norm": 0.376953125, "learning_rate": 6.295947164655447e-05, "loss": 0.8504, "step": 1930 }, { "epoch": 6.604095563139932, "grad_norm": 0.3359375, "learning_rate": 6.240682681262971e-05, "loss": 0.8619, "step": 1935 }, { "epoch": 6.621160409556314, "grad_norm": 0.322265625, "learning_rate": 6.185551589075482e-05, "loss": 0.8536, "step": 1940 }, { "epoch": 6.638225255972696, "grad_norm": 0.33984375, "learning_rate": 6.130555844299973e-05, "loss": 0.8511, "step": 1945 }, { "epoch": 6.6552901023890785, "grad_norm": 0.322265625, "learning_rate": 6.075697398340913e-05, "loss": 0.859, "step": 1950 }, { "epoch": 6.672354948805461, "grad_norm": 0.330078125, "learning_rate": 6.0209781977310486e-05, "loss": 0.8617, "step": 1955 }, { "epoch": 6.689419795221843, "grad_norm": 0.314453125, "learning_rate": 5.9664001840622886e-05, "loss": 0.8478, "step": 1960 }, { "epoch": 6.706484641638225, "grad_norm": 0.314453125, "learning_rate": 5.91196529391683e-05, "loss": 0.8548, "step": 1965 }, { "epoch": 6.723549488054608, "grad_norm": 0.33984375, "learning_rate": 5.857675458798453e-05, "loss": 0.8623, "step": 1970 }, { "epoch": 6.7406143344709895, "grad_norm": 0.333984375, "learning_rate": 5.8035326050639615e-05, "loss": 0.853, "step": 1975 }, { "epoch": 6.757679180887372, "grad_norm": 0.3515625, "learning_rate": 5.749538653854861e-05, "loss": 0.8594, "step": 1980 }, { "epoch": 6.774744027303754, "grad_norm": 0.32421875, "learning_rate": 5.695695521029163e-05, "loss": 0.8528, "step": 1985 }, { "epoch": 6.791808873720137, "grad_norm": 0.328125, "learning_rate": 5.642005117093419e-05, "loss": 0.8485, "step": 1990 }, { "epoch": 6.808873720136519, "grad_norm": 0.333984375, "learning_rate": 5.5884693471349256e-05, "loss": 0.8578, "step": 1995 }, { "epoch": 6.825938566552901, "grad_norm": 0.330078125, "learning_rate": 5.535090110754131e-05, "loss": 0.8549, "step": 2000 }, { "epoch": 6.843003412969283, "grad_norm": 0.34375, "learning_rate": 5.481869301997236e-05, "loss": 0.8625, "step": 2005 }, { "epoch": 6.860068259385666, "grad_norm": 0.3125, "learning_rate": 5.428808809288975e-05, "loss": 0.8529, "step": 2010 }, { "epoch": 6.877133105802048, "grad_norm": 0.3359375, "learning_rate": 5.37591051536561e-05, "loss": 0.8505, "step": 2015 }, { "epoch": 6.8941979522184305, "grad_norm": 0.345703125, "learning_rate": 5.32317629720814e-05, "loss": 0.8585, "step": 2020 }, { "epoch": 6.911262798634812, "grad_norm": 0.341796875, "learning_rate": 5.270608025975686e-05, "loss": 0.8563, "step": 2025 }, { "epoch": 6.928327645051194, "grad_norm": 0.326171875, "learning_rate": 5.218207566939116e-05, "loss": 0.8534, "step": 2030 }, { "epoch": 6.945392491467577, "grad_norm": 0.330078125, "learning_rate": 5.1659767794148316e-05, "loss": 0.853, "step": 2035 }, { "epoch": 6.962457337883959, "grad_norm": 0.33984375, "learning_rate": 5.1139175166988187e-05, "loss": 0.8622, "step": 2040 }, { "epoch": 6.979522184300341, "grad_norm": 0.333984375, "learning_rate": 5.062031626000873e-05, "loss": 0.8602, "step": 2045 }, { "epoch": 6.996587030716723, "grad_norm": 0.33984375, "learning_rate": 5.0103209483790636e-05, "loss": 0.8577, "step": 2050 }, { "epoch": 7.0, "eval_loss": 2.731566905975342, "eval_runtime": 0.5528, "eval_samples_per_second": 18.088, "eval_steps_per_second": 1.809, "step": 2051 }, { "epoch": 7.013651877133106, "grad_norm": 0.322265625, "learning_rate": 4.9587873186744025e-05, "loss": 0.8366, "step": 2055 }, { "epoch": 7.030716723549488, "grad_norm": 0.326171875, "learning_rate": 4.9074325654457446e-05, "loss": 0.8237, "step": 2060 }, { "epoch": 7.047781569965871, "grad_norm": 0.333984375, "learning_rate": 4.856258510904899e-05, "loss": 0.8231, "step": 2065 }, { "epoch": 7.064846416382252, "grad_norm": 0.3359375, "learning_rate": 4.805266970851975e-05, "loss": 0.8253, "step": 2070 }, { "epoch": 7.081911262798635, "grad_norm": 0.333984375, "learning_rate": 4.7544597546109514e-05, "loss": 0.8313, "step": 2075 }, { "epoch": 7.098976109215017, "grad_norm": 0.337890625, "learning_rate": 4.7038386649654764e-05, "loss": 0.8322, "step": 2080 }, { "epoch": 7.1160409556314, "grad_norm": 0.33984375, "learning_rate": 4.6534054980949113e-05, "loss": 0.8317, "step": 2085 }, { "epoch": 7.1331058020477816, "grad_norm": 0.328125, "learning_rate": 4.603162043510566e-05, "loss": 0.8356, "step": 2090 }, { "epoch": 7.150170648464163, "grad_norm": 0.33984375, "learning_rate": 4.553110083992237e-05, "loss": 0.8289, "step": 2095 }, { "epoch": 7.167235494880546, "grad_norm": 0.359375, "learning_rate": 4.50325139552493e-05, "loss": 0.8382, "step": 2100 }, { "epoch": 7.184300341296928, "grad_norm": 0.35546875, "learning_rate": 4.4535877472358466e-05, "loss": 0.8363, "step": 2105 }, { "epoch": 7.201365187713311, "grad_norm": 0.32421875, "learning_rate": 4.404120901331618e-05, "loss": 0.8388, "step": 2110 }, { "epoch": 7.2184300341296925, "grad_norm": 0.34765625, "learning_rate": 4.354852613035763e-05, "loss": 0.8291, "step": 2115 }, { "epoch": 7.235494880546075, "grad_norm": 0.328125, "learning_rate": 4.305784630526416e-05, "loss": 0.8361, "step": 2120 }, { "epoch": 7.252559726962457, "grad_norm": 0.3359375, "learning_rate": 4.2569186948743e-05, "loss": 0.8416, "step": 2125 }, { "epoch": 7.26962457337884, "grad_norm": 0.345703125, "learning_rate": 4.2082565399809404e-05, "loss": 0.8281, "step": 2130 }, { "epoch": 7.286689419795222, "grad_norm": 0.326171875, "learning_rate": 4.159799892517148e-05, "loss": 0.8281, "step": 2135 }, { "epoch": 7.303754266211604, "grad_norm": 0.349609375, "learning_rate": 4.111550471861747e-05, "loss": 0.8352, "step": 2140 }, { "epoch": 7.320819112627986, "grad_norm": 0.359375, "learning_rate": 4.06350999004057e-05, "loss": 0.833, "step": 2145 }, { "epoch": 7.337883959044369, "grad_norm": 0.353515625, "learning_rate": 4.0156801516657095e-05, "loss": 0.825, "step": 2150 }, { "epoch": 7.354948805460751, "grad_norm": 0.3359375, "learning_rate": 3.968062653875031e-05, "loss": 0.8386, "step": 2155 }, { "epoch": 7.372013651877133, "grad_norm": 0.3359375, "learning_rate": 3.920659186271953e-05, "loss": 0.8454, "step": 2160 }, { "epoch": 7.389078498293515, "grad_norm": 0.349609375, "learning_rate": 3.873471430865515e-05, "loss": 0.8431, "step": 2165 }, { "epoch": 7.406143344709897, "grad_norm": 0.345703125, "learning_rate": 3.8265010620106533e-05, "loss": 0.8392, "step": 2170 }, { "epoch": 7.42320819112628, "grad_norm": 0.3359375, "learning_rate": 3.779749746348831e-05, "loss": 0.8362, "step": 2175 }, { "epoch": 7.440273037542662, "grad_norm": 0.35546875, "learning_rate": 3.7332191427488784e-05, "loss": 0.8348, "step": 2180 }, { "epoch": 7.4573378839590445, "grad_norm": 0.35546875, "learning_rate": 3.6869109022481386e-05, "loss": 0.831, "step": 2185 }, { "epoch": 7.474402730375426, "grad_norm": 0.357421875, "learning_rate": 3.640826667993891e-05, "loss": 0.8314, "step": 2190 }, { "epoch": 7.491467576791809, "grad_norm": 0.33203125, "learning_rate": 3.59496807518503e-05, "loss": 0.8258, "step": 2195 }, { "epoch": 7.508532423208191, "grad_norm": 0.3359375, "learning_rate": 3.549336751014057e-05, "loss": 0.8482, "step": 2200 }, { "epoch": 7.525597269624574, "grad_norm": 0.32421875, "learning_rate": 3.503934314609343e-05, "loss": 0.8387, "step": 2205 }, { "epoch": 7.5426621160409555, "grad_norm": 0.3515625, "learning_rate": 3.458762376977669e-05, "loss": 0.8344, "step": 2210 }, { "epoch": 7.559726962457338, "grad_norm": 0.353515625, "learning_rate": 3.41382254094707e-05, "loss": 0.8315, "step": 2215 }, { "epoch": 7.57679180887372, "grad_norm": 0.345703125, "learning_rate": 3.369116401109963e-05, "loss": 0.8331, "step": 2220 }, { "epoch": 7.593856655290102, "grad_norm": 0.34375, "learning_rate": 3.3246455437665594e-05, "loss": 0.8322, "step": 2225 }, { "epoch": 7.610921501706485, "grad_norm": 0.326171875, "learning_rate": 3.280411546868583e-05, "loss": 0.8281, "step": 2230 }, { "epoch": 7.627986348122867, "grad_norm": 0.34375, "learning_rate": 3.2364159799632786e-05, "loss": 0.8281, "step": 2235 }, { "epoch": 7.645051194539249, "grad_norm": 0.333984375, "learning_rate": 3.192660404137729e-05, "loss": 0.832, "step": 2240 }, { "epoch": 7.662116040955631, "grad_norm": 0.337890625, "learning_rate": 3.14914637196345e-05, "loss": 0.8361, "step": 2245 }, { "epoch": 7.679180887372014, "grad_norm": 0.328125, "learning_rate": 3.105875427441297e-05, "loss": 0.837, "step": 2250 }, { "epoch": 7.696245733788396, "grad_norm": 0.33984375, "learning_rate": 3.0628491059467014e-05, "loss": 0.8351, "step": 2255 }, { "epoch": 7.713310580204778, "grad_norm": 0.328125, "learning_rate": 3.020068934175171e-05, "loss": 0.838, "step": 2260 }, { "epoch": 7.73037542662116, "grad_norm": 0.333984375, "learning_rate": 2.977536430088125e-05, "loss": 0.8355, "step": 2265 }, { "epoch": 7.747440273037543, "grad_norm": 0.326171875, "learning_rate": 2.9352531028590424e-05, "loss": 0.8261, "step": 2270 }, { "epoch": 7.764505119453925, "grad_norm": 0.3359375, "learning_rate": 2.8932204528198926e-05, "loss": 0.8367, "step": 2275 }, { "epoch": 7.7815699658703075, "grad_norm": 0.333984375, "learning_rate": 2.8514399714079132e-05, "loss": 0.8405, "step": 2280 }, { "epoch": 7.798634812286689, "grad_norm": 0.328125, "learning_rate": 2.8099131411126867e-05, "loss": 0.8408, "step": 2285 }, { "epoch": 7.815699658703072, "grad_norm": 0.326171875, "learning_rate": 2.7686414354235356e-05, "loss": 0.8397, "step": 2290 }, { "epoch": 7.832764505119454, "grad_norm": 0.34375, "learning_rate": 2.7276263187772423e-05, "loss": 0.8385, "step": 2295 }, { "epoch": 7.849829351535837, "grad_norm": 0.333984375, "learning_rate": 2.6868692465060828e-05, "loss": 0.8309, "step": 2300 }, { "epoch": 7.8668941979522184, "grad_norm": 0.341796875, "learning_rate": 2.6463716647861904e-05, "loss": 0.8229, "step": 2305 }, { "epoch": 7.8839590443686, "grad_norm": 0.34765625, "learning_rate": 2.6061350105862382e-05, "loss": 0.8226, "step": 2310 }, { "epoch": 7.901023890784983, "grad_norm": 0.33203125, "learning_rate": 2.5661607116164532e-05, "loss": 0.8334, "step": 2315 }, { "epoch": 7.918088737201365, "grad_norm": 0.34765625, "learning_rate": 2.5264501862779667e-05, "loss": 0.8444, "step": 2320 }, { "epoch": 7.935153583617748, "grad_norm": 0.328125, "learning_rate": 2.4870048436124595e-05, "loss": 0.8403, "step": 2325 }, { "epoch": 7.952218430034129, "grad_norm": 0.32421875, "learning_rate": 2.4478260832521938e-05, "loss": 0.8302, "step": 2330 }, { "epoch": 7.969283276450512, "grad_norm": 0.33203125, "learning_rate": 2.4089152953703332e-05, "loss": 0.8265, "step": 2335 }, { "epoch": 7.986348122866894, "grad_norm": 0.3359375, "learning_rate": 2.37027386063162e-05, "loss": 0.8364, "step": 2340 }, { "epoch": 8.0, "eval_loss": 2.7742018699645996, "eval_runtime": 0.5517, "eval_samples_per_second": 18.125, "eval_steps_per_second": 1.813, "step": 2344 }, { "epoch": 8.003412969283277, "grad_norm": 0.33203125, "learning_rate": 2.331903150143391e-05, "loss": 0.83, "step": 2345 }, { "epoch": 8.020477815699659, "grad_norm": 0.330078125, "learning_rate": 2.293804525406915e-05, "loss": 0.8208, "step": 2350 }, { "epoch": 8.03754266211604, "grad_norm": 0.345703125, "learning_rate": 2.255979338269093e-05, "loss": 0.8288, "step": 2355 }, { "epoch": 8.054607508532424, "grad_norm": 0.3515625, "learning_rate": 2.2184289308744844e-05, "loss": 0.8251, "step": 2360 }, { "epoch": 8.071672354948806, "grad_norm": 0.33984375, "learning_rate": 2.1811546356176872e-05, "loss": 0.8202, "step": 2365 }, { "epoch": 8.088737201365188, "grad_norm": 0.341796875, "learning_rate": 2.144157775096063e-05, "loss": 0.8191, "step": 2370 }, { "epoch": 8.10580204778157, "grad_norm": 0.33984375, "learning_rate": 2.1074396620628e-05, "loss": 0.8161, "step": 2375 }, { "epoch": 8.122866894197951, "grad_norm": 0.330078125, "learning_rate": 2.0710015993803422e-05, "loss": 0.8259, "step": 2380 }, { "epoch": 8.139931740614335, "grad_norm": 0.34375, "learning_rate": 2.0348448799741537e-05, "loss": 0.8271, "step": 2385 }, { "epoch": 8.156996587030717, "grad_norm": 0.33984375, "learning_rate": 1.9989707867868425e-05, "loss": 0.8222, "step": 2390 }, { "epoch": 8.174061433447099, "grad_norm": 0.33984375, "learning_rate": 1.9633805927326387e-05, "loss": 0.8176, "step": 2395 }, { "epoch": 8.19112627986348, "grad_norm": 0.341796875, "learning_rate": 1.9280755606522384e-05, "loss": 0.8303, "step": 2400 }, { "epoch": 8.208191126279864, "grad_norm": 0.33984375, "learning_rate": 1.893056943267969e-05, "loss": 0.8179, "step": 2405 }, { "epoch": 8.225255972696246, "grad_norm": 0.341796875, "learning_rate": 1.8583259831393663e-05, "loss": 0.8219, "step": 2410 }, { "epoch": 8.242320819112628, "grad_norm": 0.337890625, "learning_rate": 1.8238839126190686e-05, "loss": 0.829, "step": 2415 }, { "epoch": 8.25938566552901, "grad_norm": 0.34765625, "learning_rate": 1.7897319538090962e-05, "loss": 0.8233, "step": 2420 }, { "epoch": 8.276450511945393, "grad_norm": 0.33203125, "learning_rate": 1.755871318517488e-05, "loss": 0.8224, "step": 2425 }, { "epoch": 8.293515358361775, "grad_norm": 0.328125, "learning_rate": 1.722303208215297e-05, "loss": 0.8239, "step": 2430 }, { "epoch": 8.310580204778157, "grad_norm": 0.33203125, "learning_rate": 1.6890288139939625e-05, "loss": 0.8324, "step": 2435 }, { "epoch": 8.327645051194539, "grad_norm": 0.33984375, "learning_rate": 1.6560493165230516e-05, "loss": 0.8216, "step": 2440 }, { "epoch": 8.344709897610922, "grad_norm": 0.337890625, "learning_rate": 1.623365886008357e-05, "loss": 0.8249, "step": 2445 }, { "epoch": 8.361774744027304, "grad_norm": 0.3359375, "learning_rate": 1.5909796821503785e-05, "loss": 0.8327, "step": 2450 }, { "epoch": 8.378839590443686, "grad_norm": 0.3359375, "learning_rate": 1.5588918541031783e-05, "loss": 0.8202, "step": 2455 }, { "epoch": 8.395904436860068, "grad_norm": 0.337890625, "learning_rate": 1.5271035404335954e-05, "loss": 0.8213, "step": 2460 }, { "epoch": 8.41296928327645, "grad_norm": 0.33203125, "learning_rate": 1.4956158690808585e-05, "loss": 0.8217, "step": 2465 }, { "epoch": 8.430034129692833, "grad_norm": 0.359375, "learning_rate": 1.464429957316552e-05, "loss": 0.8235, "step": 2470 }, { "epoch": 8.447098976109215, "grad_norm": 0.337890625, "learning_rate": 1.433546911704977e-05, "loss": 0.8257, "step": 2475 }, { "epoch": 8.464163822525597, "grad_norm": 0.3359375, "learning_rate": 1.402967828063897e-05, "loss": 0.8228, "step": 2480 }, { "epoch": 8.481228668941979, "grad_norm": 0.33203125, "learning_rate": 1.37269379142563e-05, "loss": 0.8155, "step": 2485 }, { "epoch": 8.498293515358363, "grad_norm": 0.337890625, "learning_rate": 1.3427258759985739e-05, "loss": 0.8329, "step": 2490 }, { "epoch": 8.515358361774744, "grad_norm": 0.337890625, "learning_rate": 1.3130651451290798e-05, "loss": 0.8224, "step": 2495 }, { "epoch": 8.532423208191126, "grad_norm": 0.353515625, "learning_rate": 1.2837126512637198e-05, "loss": 0.8219, "step": 2500 }, { "epoch": 8.549488054607508, "grad_norm": 0.330078125, "learning_rate": 1.2546694359119493e-05, "loss": 0.8151, "step": 2505 }, { "epoch": 8.56655290102389, "grad_norm": 0.33984375, "learning_rate": 1.2259365296091464e-05, "loss": 0.8237, "step": 2510 }, { "epoch": 8.583617747440274, "grad_norm": 0.34765625, "learning_rate": 1.1975149518800454e-05, "loss": 0.8207, "step": 2515 }, { "epoch": 8.600682593856655, "grad_norm": 0.341796875, "learning_rate": 1.1694057112025636e-05, "loss": 0.8221, "step": 2520 }, { "epoch": 8.617747440273037, "grad_norm": 0.33203125, "learning_rate": 1.141609804972017e-05, "loss": 0.828, "step": 2525 }, { "epoch": 8.634812286689419, "grad_norm": 0.345703125, "learning_rate": 1.1141282194657287e-05, "loss": 0.8232, "step": 2530 }, { "epoch": 8.651877133105803, "grad_norm": 0.353515625, "learning_rate": 1.086961929808038e-05, "loss": 0.8281, "step": 2535 }, { "epoch": 8.668941979522184, "grad_norm": 0.34375, "learning_rate": 1.0601118999356907e-05, "loss": 0.8252, "step": 2540 }, { "epoch": 8.686006825938566, "grad_norm": 0.333984375, "learning_rate": 1.0335790825636449e-05, "loss": 0.8225, "step": 2545 }, { "epoch": 8.703071672354948, "grad_norm": 0.341796875, "learning_rate": 1.00736441915126e-05, "loss": 0.8199, "step": 2550 }, { "epoch": 8.720136518771332, "grad_norm": 0.345703125, "learning_rate": 9.814688398688998e-06, "loss": 0.8146, "step": 2555 }, { "epoch": 8.737201365187714, "grad_norm": 0.34375, "learning_rate": 9.558932635649131e-06, "loss": 0.8303, "step": 2560 }, { "epoch": 8.754266211604095, "grad_norm": 0.328125, "learning_rate": 9.306385977330411e-06, "loss": 0.8224, "step": 2565 }, { "epoch": 8.771331058020477, "grad_norm": 0.333984375, "learning_rate": 9.057057384802181e-06, "loss": 0.8228, "step": 2570 }, { "epoch": 8.788395904436861, "grad_norm": 0.3359375, "learning_rate": 8.810955704947666e-06, "loss": 0.8231, "step": 2575 }, { "epoch": 8.805460750853243, "grad_norm": 0.330078125, "learning_rate": 8.568089670150115e-06, "loss": 0.8278, "step": 2580 }, { "epoch": 8.822525597269625, "grad_norm": 0.341796875, "learning_rate": 8.328467897982995e-06, "loss": 0.8248, "step": 2585 }, { "epoch": 8.839590443686006, "grad_norm": 0.333984375, "learning_rate": 8.092098890904098e-06, "loss": 0.8195, "step": 2590 }, { "epoch": 8.856655290102388, "grad_norm": 0.333984375, "learning_rate": 7.858991035953944e-06, "loss": 0.8203, "step": 2595 }, { "epoch": 8.873720136518772, "grad_norm": 0.328125, "learning_rate": 7.629152604458156e-06, "loss": 0.8257, "step": 2600 }, { "epoch": 8.890784982935154, "grad_norm": 0.34375, "learning_rate": 7.402591751733989e-06, "loss": 0.8128, "step": 2605 }, { "epoch": 8.907849829351536, "grad_norm": 0.3359375, "learning_rate": 7.179316516800894e-06, "loss": 0.8251, "step": 2610 }, { "epoch": 8.924914675767917, "grad_norm": 0.341796875, "learning_rate": 6.959334822095354e-06, "loss": 0.824, "step": 2615 }, { "epoch": 8.941979522184301, "grad_norm": 0.3515625, "learning_rate": 6.7426544731897245e-06, "loss": 0.8287, "step": 2620 }, { "epoch": 8.959044368600683, "grad_norm": 0.3359375, "learning_rate": 6.529283158515276e-06, "loss": 0.8264, "step": 2625 }, { "epoch": 8.976109215017065, "grad_norm": 0.337890625, "learning_rate": 6.319228449089376e-06, "loss": 0.8179, "step": 2630 }, { "epoch": 8.993174061433447, "grad_norm": 0.34375, "learning_rate": 6.11249779824693e-06, "loss": 0.8311, "step": 2635 }, { "epoch": 9.0, "eval_loss": 2.7970776557922363, "eval_runtime": 0.547, "eval_samples_per_second": 18.282, "eval_steps_per_second": 1.828, "step": 2637 }, { "epoch": 9.01023890784983, "grad_norm": 0.33984375, "learning_rate": 5.909098541375746e-06, "loss": 0.827, "step": 2640 }, { "epoch": 9.027303754266212, "grad_norm": 0.333984375, "learning_rate": 5.7090378956564216e-06, "loss": 0.8173, "step": 2645 }, { "epoch": 9.044368600682594, "grad_norm": 0.341796875, "learning_rate": 5.512322959806193e-06, "loss": 0.8315, "step": 2650 }, { "epoch": 9.061433447098976, "grad_norm": 0.345703125, "learning_rate": 5.3189607138270255e-06, "loss": 0.8278, "step": 2655 }, { "epoch": 9.078498293515358, "grad_norm": 0.328125, "learning_rate": 5.128958018758012e-06, "loss": 0.821, "step": 2660 }, { "epoch": 9.095563139931741, "grad_norm": 0.337890625, "learning_rate": 4.942321616431833e-06, "loss": 0.8261, "step": 2665 }, { "epoch": 9.112627986348123, "grad_norm": 0.341796875, "learning_rate": 4.7590581292356276e-06, "loss": 0.8267, "step": 2670 }, { "epoch": 9.129692832764505, "grad_norm": 0.3359375, "learning_rate": 4.579174059875946e-06, "loss": 0.8265, "step": 2675 }, { "epoch": 9.146757679180887, "grad_norm": 0.33203125, "learning_rate": 4.402675791148059e-06, "loss": 0.8217, "step": 2680 }, { "epoch": 9.16382252559727, "grad_norm": 0.330078125, "learning_rate": 4.229569585709425e-06, "loss": 0.8245, "step": 2685 }, { "epoch": 9.180887372013652, "grad_norm": 0.3359375, "learning_rate": 4.0598615858575605e-06, "loss": 0.8211, "step": 2690 }, { "epoch": 9.197952218430034, "grad_norm": 0.330078125, "learning_rate": 3.89355781331201e-06, "loss": 0.8162, "step": 2695 }, { "epoch": 9.215017064846416, "grad_norm": 0.33203125, "learning_rate": 3.730664169000708e-06, "loss": 0.8154, "step": 2700 }, { "epoch": 9.2320819112628, "grad_norm": 0.330078125, "learning_rate": 3.571186432850626e-06, "loss": 0.8245, "step": 2705 }, { "epoch": 9.249146757679181, "grad_norm": 0.333984375, "learning_rate": 3.415130263582611e-06, "loss": 0.8198, "step": 2710 }, { "epoch": 9.266211604095563, "grad_norm": 0.330078125, "learning_rate": 3.2625011985107257e-06, "loss": 0.8178, "step": 2715 }, { "epoch": 9.283276450511945, "grad_norm": 0.337890625, "learning_rate": 3.1133046533455947e-06, "loss": 0.825, "step": 2720 }, { "epoch": 9.300341296928327, "grad_norm": 0.3359375, "learning_rate": 2.967545922002379e-06, "loss": 0.8249, "step": 2725 }, { "epoch": 9.31740614334471, "grad_norm": 0.337890625, "learning_rate": 2.8252301764128962e-06, "loss": 0.8228, "step": 2730 }, { "epoch": 9.334470989761092, "grad_norm": 0.3359375, "learning_rate": 2.686362466342085e-06, "loss": 0.822, "step": 2735 }, { "epoch": 9.351535836177474, "grad_norm": 0.3359375, "learning_rate": 2.550947719208829e-06, "loss": 0.8224, "step": 2740 }, { "epoch": 9.368600682593856, "grad_norm": 0.34375, "learning_rate": 2.4189907399111534e-06, "loss": 0.8224, "step": 2745 }, { "epoch": 9.38566552901024, "grad_norm": 0.33984375, "learning_rate": 2.2904962106556793e-06, "loss": 0.82, "step": 2750 }, { "epoch": 9.402730375426621, "grad_norm": 0.337890625, "learning_rate": 2.1654686907915167e-06, "loss": 0.8183, "step": 2755 }, { "epoch": 9.419795221843003, "grad_norm": 0.33984375, "learning_rate": 2.0439126166485025e-06, "loss": 0.8189, "step": 2760 }, { "epoch": 9.436860068259385, "grad_norm": 0.333984375, "learning_rate": 1.925832301379726e-06, "loss": 0.8215, "step": 2765 }, { "epoch": 9.453924914675769, "grad_norm": 0.341796875, "learning_rate": 1.8112319348085771e-06, "loss": 0.8235, "step": 2770 }, { "epoch": 9.47098976109215, "grad_norm": 0.341796875, "learning_rate": 1.700115583279993e-06, "loss": 0.8157, "step": 2775 }, { "epoch": 9.488054607508532, "grad_norm": 0.337890625, "learning_rate": 1.592487189516212e-06, "loss": 0.8192, "step": 2780 }, { "epoch": 9.505119453924914, "grad_norm": 0.3359375, "learning_rate": 1.4883505724768932e-06, "loss": 0.8168, "step": 2785 }, { "epoch": 9.522184300341298, "grad_norm": 0.341796875, "learning_rate": 1.3877094272235712e-06, "loss": 0.8296, "step": 2790 }, { "epoch": 9.53924914675768, "grad_norm": 0.3359375, "learning_rate": 1.2905673247885718e-06, "loss": 0.8166, "step": 2795 }, { "epoch": 9.556313993174061, "grad_norm": 0.3359375, "learning_rate": 1.196927712048257e-06, "loss": 0.817, "step": 2800 }, { "epoch": 9.573378839590443, "grad_norm": 0.33984375, "learning_rate": 1.1067939116008009e-06, "loss": 0.813, "step": 2805 }, { "epoch": 9.590443686006825, "grad_norm": 0.33203125, "learning_rate": 1.020169121648218e-06, "loss": 0.8114, "step": 2810 }, { "epoch": 9.607508532423209, "grad_norm": 0.32421875, "learning_rate": 9.370564158829087e-07, "loss": 0.8146, "step": 2815 }, { "epoch": 9.62457337883959, "grad_norm": 0.333984375, "learning_rate": 8.574587433786363e-07, "loss": 0.8216, "step": 2820 }, { "epoch": 9.641638225255972, "grad_norm": 0.34375, "learning_rate": 7.813789284857986e-07, "loss": 0.8157, "step": 2825 }, { "epoch": 9.658703071672354, "grad_norm": 0.333984375, "learning_rate": 7.088196707312977e-07, "loss": 0.8283, "step": 2830 }, { "epoch": 9.675767918088738, "grad_norm": 0.330078125, "learning_rate": 6.39783544722694e-07, "loss": 0.8092, "step": 2835 }, { "epoch": 9.69283276450512, "grad_norm": 0.330078125, "learning_rate": 5.742730000568908e-07, "loss": 0.8242, "step": 2840 }, { "epoch": 9.709897610921502, "grad_norm": 0.341796875, "learning_rate": 5.12290361233192e-07, "loss": 0.8239, "step": 2845 }, { "epoch": 9.726962457337883, "grad_norm": 0.33984375, "learning_rate": 4.538378275708133e-07, "loss": 0.8145, "step": 2850 }, { "epoch": 9.744027303754265, "grad_norm": 0.3359375, "learning_rate": 3.989174731308998e-07, "loss": 0.8249, "step": 2855 }, { "epoch": 9.761092150170649, "grad_norm": 0.3359375, "learning_rate": 3.4753124664286265e-07, "loss": 0.817, "step": 2860 }, { "epoch": 9.77815699658703, "grad_norm": 0.33203125, "learning_rate": 2.9968097143526775e-07, "loss": 0.8115, "step": 2865 }, { "epoch": 9.795221843003413, "grad_norm": 0.35546875, "learning_rate": 2.5536834537114307e-07, "loss": 0.8192, "step": 2870 }, { "epoch": 9.812286689419794, "grad_norm": 0.328125, "learning_rate": 2.145949407877157e-07, "loss": 0.8181, "step": 2875 }, { "epoch": 9.829351535836178, "grad_norm": 0.3359375, "learning_rate": 1.7736220444064533e-07, "loss": 0.8203, "step": 2880 }, { "epoch": 9.84641638225256, "grad_norm": 0.333984375, "learning_rate": 1.436714574526543e-07, "loss": 0.826, "step": 2885 }, { "epoch": 9.863481228668942, "grad_norm": 0.337890625, "learning_rate": 1.1352389526668727e-07, "loss": 0.8241, "step": 2890 }, { "epoch": 9.880546075085324, "grad_norm": 0.3359375, "learning_rate": 8.692058760345622e-08, "loss": 0.8268, "step": 2895 }, { "epoch": 9.897610921501707, "grad_norm": 0.330078125, "learning_rate": 6.386247842353754e-08, "loss": 0.8106, "step": 2900 }, { "epoch": 9.914675767918089, "grad_norm": 0.330078125, "learning_rate": 4.435038589380991e-08, "loss": 0.8232, "step": 2905 }, { "epoch": 9.93174061433447, "grad_norm": 0.3359375, "learning_rate": 2.8385002358466418e-08, "loss": 0.8187, "step": 2910 }, { "epoch": 9.948805460750853, "grad_norm": 0.337890625, "learning_rate": 1.5966894314456415e-08, "loss": 0.8284, "step": 2915 }, { "epoch": 9.965870307167236, "grad_norm": 0.333984375, "learning_rate": 7.096502391346071e-09, "loss": 0.8275, "step": 2920 }, { "epoch": 9.982935153583618, "grad_norm": 0.33984375, "learning_rate": 1.7741413357197368e-09, "loss": 0.8271, "step": 2925 }, { "epoch": 10.0, "grad_norm": 0.333984375, "learning_rate": 0.0, "loss": 0.8243, "step": 2930 }, { "epoch": 10.0, "eval_loss": 2.7977683544158936, "eval_runtime": 0.5422, "eval_samples_per_second": 18.444, "eval_steps_per_second": 1.844, "step": 2930 }, { "epoch": 10.0, "step": 2930, "total_flos": 1.7464232891960525e+18, "train_loss": 0.9647074054125633, "train_runtime": 17674.2713, "train_samples_per_second": 7.945, "train_steps_per_second": 0.166 } ], "logging_steps": 5, "max_steps": 2930, "num_input_tokens_seen": 0, "num_train_epochs": 10, "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": 1.7464232891960525e+18, "train_batch_size": 8, "trial_name": null, "trial_params": null }