| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.997084548104956, | |
| "eval_steps": 500, | |
| "global_step": 1542, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019436345966958212, | |
| "grad_norm": 3.5477320746078096, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0532, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.038872691933916424, | |
| "grad_norm": 2.8209235996953512, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9684, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05830903790087463, | |
| "grad_norm": 1.1257852692164845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9294, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07774538386783285, | |
| "grad_norm": 0.888481539231949, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9201, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09718172983479106, | |
| "grad_norm": 0.6469537614046023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8971, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11661807580174927, | |
| "grad_norm": 0.592544408615531, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8837, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 0.6433313667438364, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8749, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1554907677356657, | |
| "grad_norm": 1.344429915972531, | |
| "learning_rate": 5e-06, | |
| "loss": 0.867, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1749271137026239, | |
| "grad_norm": 0.8707935340603853, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8623, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19436345966958213, | |
| "grad_norm": 0.7828161719097383, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8624, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21379980563654033, | |
| "grad_norm": 0.682126021781355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8611, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23323615160349853, | |
| "grad_norm": 0.8081328723422389, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8551, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25267249757045673, | |
| "grad_norm": 0.6691994077909735, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8583, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 0.586140300081327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8523, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2915451895043732, | |
| "grad_norm": 0.8552001050583659, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8497, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3109815354713314, | |
| "grad_norm": 0.501523965918074, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8464, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3304178814382896, | |
| "grad_norm": 0.6785445153206255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.848, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3498542274052478, | |
| "grad_norm": 0.6494060293856031, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8459, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.369290573372206, | |
| "grad_norm": 0.6020737926390343, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8484, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.38872691933916426, | |
| "grad_norm": 0.48912875825316915, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8449, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.8781137047011839, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8395, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.42759961127308066, | |
| "grad_norm": 0.5879468826056136, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8387, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44703595724003886, | |
| "grad_norm": 0.6017675792916065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8363, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.46647230320699706, | |
| "grad_norm": 0.616647981494789, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8336, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4859086491739553, | |
| "grad_norm": 0.855268617382177, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8336, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5053449951409135, | |
| "grad_norm": 0.780188445457583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.831, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5247813411078717, | |
| "grad_norm": 0.5840816004625115, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8319, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "grad_norm": 0.6535257947752856, | |
| "learning_rate": 5e-06, | |
| "loss": 0.833, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5636540330417882, | |
| "grad_norm": 0.6710102563759031, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8354, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5830903790087464, | |
| "grad_norm": 0.5947252085113186, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8315, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6025267249757046, | |
| "grad_norm": 0.5902161171422673, | |
| "learning_rate": 5e-06, | |
| "loss": 0.83, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6219630709426628, | |
| "grad_norm": 0.5757165816873938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8299, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.641399416909621, | |
| "grad_norm": 0.6751753868245474, | |
| "learning_rate": 5e-06, | |
| "loss": 0.827, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6608357628765792, | |
| "grad_norm": 0.535560817394151, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8264, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "grad_norm": 0.6183377886108462, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8243, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6997084548104956, | |
| "grad_norm": 0.6200501825686097, | |
| "learning_rate": 5e-06, | |
| "loss": 0.828, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7191448007774538, | |
| "grad_norm": 0.5622254912052161, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8287, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.738581146744412, | |
| "grad_norm": 0.6720527159909909, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8234, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7580174927113703, | |
| "grad_norm": 0.5315560166276624, | |
| "learning_rate": 5e-06, | |
| "loss": 0.824, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7774538386783285, | |
| "grad_norm": 0.6413527148042328, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8194, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7968901846452867, | |
| "grad_norm": 0.6402327795437167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8243, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.6290935177044384, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8201, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8357628765792031, | |
| "grad_norm": 0.6137598310285064, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8187, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8551992225461613, | |
| "grad_norm": 0.6137894354862566, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8217, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8746355685131195, | |
| "grad_norm": 0.7376542092364302, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8191, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8940719144800777, | |
| "grad_norm": 0.5443940007812901, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8179, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9135082604470359, | |
| "grad_norm": 0.6778023088897194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8158, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9329446064139941, | |
| "grad_norm": 0.6040677193471313, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8176, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.5741967517130403, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8215, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9718172983479106, | |
| "grad_norm": 0.5184977635424605, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8218, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9912536443148688, | |
| "grad_norm": 0.5484601778792662, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8158, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.9990281827016521, | |
| "eval_loss": 0.8152287006378174, | |
| "eval_runtime": 547.9504, | |
| "eval_samples_per_second": 25.3, | |
| "eval_steps_per_second": 0.396, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.010689990281827, | |
| "grad_norm": 0.6821565020818955, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8355, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0301263362487851, | |
| "grad_norm": 0.6277981964271326, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7749, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0495626822157433, | |
| "grad_norm": 0.6114756472079457, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7751, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.0689990281827018, | |
| "grad_norm": 0.8259615966427586, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7756, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.08843537414966, | |
| "grad_norm": 0.6113352198439804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7789, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1078717201166182, | |
| "grad_norm": 0.5269512429419262, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7784, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1273080660835764, | |
| "grad_norm": 0.5792710933468033, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7757, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1467444120505346, | |
| "grad_norm": 0.5467198449481481, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7757, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.1661807580174928, | |
| "grad_norm": 0.6190447420364188, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7754, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.185617103984451, | |
| "grad_norm": 0.7074708178383962, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7738, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2050534499514092, | |
| "grad_norm": 0.5708793884696434, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7675, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": 0.5278424041049065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7724, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.2439261418853256, | |
| "grad_norm": 0.48269223376284837, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7678, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.2633624878522838, | |
| "grad_norm": 0.6628438951702088, | |
| "learning_rate": 5e-06, | |
| "loss": 0.772, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.282798833819242, | |
| "grad_norm": 0.49956285734450795, | |
| "learning_rate": 5e-06, | |
| "loss": 0.78, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3022351797862002, | |
| "grad_norm": 0.4482989241465936, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7712, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3216715257531584, | |
| "grad_norm": 0.515252608881534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7712, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.3411078717201166, | |
| "grad_norm": 0.5392787594093453, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7733, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.3605442176870748, | |
| "grad_norm": 0.5239288581769422, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7744, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.379980563654033, | |
| "grad_norm": 0.5368087860350439, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7721, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.3994169096209912, | |
| "grad_norm": 0.5331498843832938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7702, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4188532555879494, | |
| "grad_norm": 0.5840718481917428, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7755, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4382896015549078, | |
| "grad_norm": 0.537679455083028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7719, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.4577259475218658, | |
| "grad_norm": 0.7948828701245976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7717, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.4771622934888242, | |
| "grad_norm": 0.5813227807421696, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7763, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.4965986394557822, | |
| "grad_norm": 0.6049608273143411, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7719, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.5160349854227406, | |
| "grad_norm": 0.6057676712274179, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7742, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.5354713313896986, | |
| "grad_norm": 0.625042201984692, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7767, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.554907677356657, | |
| "grad_norm": 0.5502470811006085, | |
| "learning_rate": 5e-06, | |
| "loss": 0.769, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.574344023323615, | |
| "grad_norm": 0.5857965121292225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7709, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.5937803692905734, | |
| "grad_norm": 0.613513782295781, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7755, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.6132167152575316, | |
| "grad_norm": 0.583240417199926, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7738, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "grad_norm": 0.5231701163074167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7731, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.652089407191448, | |
| "grad_norm": 0.4914609295920534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7714, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.6715257531584062, | |
| "grad_norm": 0.5250445862469549, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7747, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.6909620991253644, | |
| "grad_norm": 0.5415316148110199, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7685, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7103984450923226, | |
| "grad_norm": 0.5426871063126633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7687, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.7298347910592808, | |
| "grad_norm": 0.5573890854917875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7732, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.749271137026239, | |
| "grad_norm": 0.5966240890058521, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7695, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.7687074829931972, | |
| "grad_norm": 0.48852508189672406, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7716, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.7881438289601554, | |
| "grad_norm": 0.510423049422432, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7695, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8075801749271136, | |
| "grad_norm": 0.5128362713697912, | |
| "learning_rate": 5e-06, | |
| "loss": 0.768, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.8270165208940718, | |
| "grad_norm": 0.5100892708497722, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7721, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.8464528668610303, | |
| "grad_norm": 0.5050841552954286, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7703, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.8658892128279883, | |
| "grad_norm": 0.5100122636839687, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7675, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.8853255587949467, | |
| "grad_norm": 0.5858103448907649, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7719, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.7186164442084766, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7704, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.924198250728863, | |
| "grad_norm": 0.49187325414902705, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7744, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.943634596695821, | |
| "grad_norm": 0.48132179189009133, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7666, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.9630709426627795, | |
| "grad_norm": 0.6042950330363083, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7682, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.9825072886297375, | |
| "grad_norm": 0.5107563561120851, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7688, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8017936944961548, | |
| "eval_runtime": 549.3546, | |
| "eval_samples_per_second": 25.235, | |
| "eval_steps_per_second": 0.395, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 2.001943634596696, | |
| "grad_norm": 0.8520236880105687, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8065, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.021379980563654, | |
| "grad_norm": 0.6759369335284802, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7247, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.0408163265306123, | |
| "grad_norm": 0.6810404313004184, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7257, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.0602526724975703, | |
| "grad_norm": 0.5976865962159595, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7266, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.0796890184645287, | |
| "grad_norm": 0.5170299538250477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7262, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.0991253644314867, | |
| "grad_norm": 0.636746039057963, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7271, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.118561710398445, | |
| "grad_norm": 0.7347207445428233, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7221, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.1379980563654035, | |
| "grad_norm": 0.6669755018146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7277, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.1574344023323615, | |
| "grad_norm": 0.5653238227925762, | |
| "learning_rate": 5e-06, | |
| "loss": 0.726, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.17687074829932, | |
| "grad_norm": 0.5720425000083328, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7271, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.196307094266278, | |
| "grad_norm": 0.5494809428119856, | |
| "learning_rate": 5e-06, | |
| "loss": 0.727, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.2157434402332363, | |
| "grad_norm": 0.6708852933316355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7286, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.2351797862001943, | |
| "grad_norm": 0.5649904350477953, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7253, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.2546161321671527, | |
| "grad_norm": 0.6681152322447659, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7227, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.2740524781341107, | |
| "grad_norm": 0.7452957502891413, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7271, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.293488824101069, | |
| "grad_norm": 0.730891816162587, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7297, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.312925170068027, | |
| "grad_norm": 0.5422066002537126, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7291, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.3323615160349855, | |
| "grad_norm": 0.5368279161848004, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7291, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.3517978620019435, | |
| "grad_norm": 0.5831776325357405, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7299, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.371234207968902, | |
| "grad_norm": 0.4988880812457934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7286, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.39067055393586, | |
| "grad_norm": 0.6745820300056689, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7246, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.4101068999028183, | |
| "grad_norm": 0.6502142374990822, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7274, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.4295432458697763, | |
| "grad_norm": 0.6686318012888572, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7273, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.4489795918367347, | |
| "grad_norm": 0.5959741098147713, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7296, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.4684159378036927, | |
| "grad_norm": 0.6933996442905096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7265, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.487852283770651, | |
| "grad_norm": 0.5220203781381132, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7279, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.5072886297376096, | |
| "grad_norm": 0.5382425321528858, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7305, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.5267249757045676, | |
| "grad_norm": 0.5181218910911854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7249, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.5461613216715255, | |
| "grad_norm": 0.6478067615615305, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7319, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.565597667638484, | |
| "grad_norm": 0.5078942293566884, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7288, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.5850340136054424, | |
| "grad_norm": 0.6268137880948265, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7299, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.6044703595724004, | |
| "grad_norm": 0.7996921164519973, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7332, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.6239067055393583, | |
| "grad_norm": 0.6835765316105765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7332, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.6433430515063168, | |
| "grad_norm": 0.6208677881375628, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7255, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.662779397473275, | |
| "grad_norm": 0.5685215567462071, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7311, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.682215743440233, | |
| "grad_norm": 0.502556515949076, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7288, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.7016520894071916, | |
| "grad_norm": 0.5557319329244653, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7252, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.7210884353741496, | |
| "grad_norm": 0.5681474343567127, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7324, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.740524781341108, | |
| "grad_norm": 0.5718856742663174, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7314, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.759961127308066, | |
| "grad_norm": 0.5207890225289823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7327, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.7793974732750244, | |
| "grad_norm": 0.5610775317663003, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7325, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.7988338192419824, | |
| "grad_norm": 0.49435740403271333, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7306, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.818270165208941, | |
| "grad_norm": 0.5548340643212172, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7248, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.837706511175899, | |
| "grad_norm": 0.8162943266425523, | |
| "learning_rate": 5e-06, | |
| "loss": 0.728, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.5605722072050826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7321, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.8765792031098156, | |
| "grad_norm": 0.5811312094740239, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7312, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.8960155490767736, | |
| "grad_norm": 0.581575144969956, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7321, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.9154518950437316, | |
| "grad_norm": 0.5099095695816087, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7334, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.93488824101069, | |
| "grad_norm": 0.5572721217938963, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7308, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.9543245869776484, | |
| "grad_norm": 0.522930114991094, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7295, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.9737609329446064, | |
| "grad_norm": 0.6436319992243297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7331, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.9931972789115644, | |
| "grad_norm": 0.6235339876579238, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7263, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.997084548104956, | |
| "eval_loss": 0.8005240559577942, | |
| "eval_runtime": 550.1116, | |
| "eval_samples_per_second": 25.2, | |
| "eval_steps_per_second": 0.394, | |
| "step": 1542 | |
| }, | |
| { | |
| "epoch": 2.997084548104956, | |
| "step": 1542, | |
| "total_flos": 2582698052812800.0, | |
| "train_loss": 0.7834810720498151, | |
| "train_runtime": 91136.0835, | |
| "train_samples_per_second": 8.67, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1542, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2582698052812800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |