emilykang's picture
Training in progress, epoch 0
c92f0ed verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.949579831932773,
"eval_steps": 500,
"global_step": 1480,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06722689075630252,
"grad_norm": 3.659412384033203,
"learning_rate": 0.00019997747161747695,
"loss": 1.5437,
"step": 10
},
{
"epoch": 0.13445378151260504,
"grad_norm": 1.5242640972137451,
"learning_rate": 0.00019990989662046818,
"loss": 1.09,
"step": 20
},
{
"epoch": 0.20168067226890757,
"grad_norm": 0.7281526923179626,
"learning_rate": 0.00019979730545608126,
"loss": 0.9849,
"step": 30
},
{
"epoch": 0.2689075630252101,
"grad_norm": 0.6494360566139221,
"learning_rate": 0.00019963974885425266,
"loss": 0.9444,
"step": 40
},
{
"epoch": 0.33613445378151263,
"grad_norm": 0.6406448483467102,
"learning_rate": 0.00019943729780489027,
"loss": 0.9413,
"step": 50
},
{
"epoch": 0.40336134453781514,
"grad_norm": 0.6042075157165527,
"learning_rate": 0.00019919004352588767,
"loss": 0.9238,
"step": 60
},
{
"epoch": 0.47058823529411764,
"grad_norm": 0.5904833674430847,
"learning_rate": 0.00019889809742202455,
"loss": 0.9071,
"step": 70
},
{
"epoch": 0.5378151260504201,
"grad_norm": 0.6063255667686462,
"learning_rate": 0.00019856159103477086,
"loss": 0.9101,
"step": 80
},
{
"epoch": 0.6050420168067226,
"grad_norm": 0.6029768586158752,
"learning_rate": 0.0001981806759830189,
"loss": 0.8926,
"step": 90
},
{
"epoch": 0.6722689075630253,
"grad_norm": 0.5855621695518494,
"learning_rate": 0.00019775552389476864,
"loss": 0.8943,
"step": 100
},
{
"epoch": 0.7394957983193278,
"grad_norm": 0.5790782570838928,
"learning_rate": 0.00019728632632979746,
"loss": 0.8661,
"step": 110
},
{
"epoch": 0.8067226890756303,
"grad_norm": 0.5598119497299194,
"learning_rate": 0.0001967732946933499,
"loss": 0.8572,
"step": 120
},
{
"epoch": 0.8739495798319328,
"grad_norm": 0.6340535283088684,
"learning_rate": 0.00019621666014088494,
"loss": 0.8419,
"step": 130
},
{
"epoch": 0.9411764705882353,
"grad_norm": 0.5767297148704529,
"learning_rate": 0.00019561667347392508,
"loss": 0.8369,
"step": 140
},
{
"epoch": 1.0084033613445378,
"grad_norm": 0.5530027151107788,
"learning_rate": 0.0001949736050270532,
"loss": 0.8337,
"step": 150
},
{
"epoch": 1.0756302521008403,
"grad_norm": 0.6440849900245667,
"learning_rate": 0.00019428774454610843,
"loss": 0.7649,
"step": 160
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.7260521650314331,
"learning_rate": 0.0001935594010576362,
"loss": 0.7262,
"step": 170
},
{
"epoch": 1.2100840336134453,
"grad_norm": 0.6408701539039612,
"learning_rate": 0.00019278890272965096,
"loss": 0.7619,
"step": 180
},
{
"epoch": 1.2773109243697478,
"grad_norm": 0.6750979423522949,
"learning_rate": 0.0001919765967237739,
"loss": 0.7609,
"step": 190
},
{
"epoch": 1.3445378151260505,
"grad_norm": 0.6665403246879578,
"learning_rate": 0.0001911228490388136,
"loss": 0.7638,
"step": 200
},
{
"epoch": 1.4117647058823528,
"grad_norm": 0.7674531936645508,
"learning_rate": 0.00019022804434585852,
"loss": 0.7607,
"step": 210
},
{
"epoch": 1.4789915966386555,
"grad_norm": 0.6566962003707886,
"learning_rate": 0.00018929258581495685,
"loss": 0.7438,
"step": 220
},
{
"epoch": 1.5462184873949578,
"grad_norm": 0.6066375970840454,
"learning_rate": 0.00018831689493346095,
"loss": 0.7801,
"step": 230
},
{
"epoch": 1.6134453781512605,
"grad_norm": 0.631864070892334,
"learning_rate": 0.00018730141131611882,
"loss": 0.7335,
"step": 240
},
{
"epoch": 1.680672268907563,
"grad_norm": 0.6826153993606567,
"learning_rate": 0.00018624659250699805,
"loss": 0.75,
"step": 250
},
{
"epoch": 1.7478991596638656,
"grad_norm": 0.6121156811714172,
"learning_rate": 0.00018515291377333112,
"loss": 0.7466,
"step": 260
},
{
"epoch": 1.815126050420168,
"grad_norm": 0.6482798457145691,
"learning_rate": 0.00018402086789137546,
"loss": 0.7552,
"step": 270
},
{
"epoch": 1.8823529411764706,
"grad_norm": 0.6285238265991211,
"learning_rate": 0.00018285096492438424,
"loss": 0.7428,
"step": 280
},
{
"epoch": 1.949579831932773,
"grad_norm": 0.7148864269256592,
"learning_rate": 0.00018164373199278856,
"loss": 0.7444,
"step": 290
},
{
"epoch": 2.0168067226890756,
"grad_norm": 0.6166530847549438,
"learning_rate": 0.00018039971303669407,
"loss": 0.7026,
"step": 300
},
{
"epoch": 2.0840336134453783,
"grad_norm": 0.7472362518310547,
"learning_rate": 0.00017911946857079888,
"loss": 0.6197,
"step": 310
},
{
"epoch": 2.1512605042016806,
"grad_norm": 0.8279550075531006,
"learning_rate": 0.00017780357543184397,
"loss": 0.6193,
"step": 320
},
{
"epoch": 2.2184873949579833,
"grad_norm": 0.7969969511032104,
"learning_rate": 0.00017645262651870926,
"loss": 0.6176,
"step": 330
},
{
"epoch": 2.2857142857142856,
"grad_norm": 0.7620482444763184,
"learning_rate": 0.00017506723052527242,
"loss": 0.6202,
"step": 340
},
{
"epoch": 2.3529411764705883,
"grad_norm": 0.790768563747406,
"learning_rate": 0.00017364801166615124,
"loss": 0.6183,
"step": 350
},
{
"epoch": 2.4201680672268906,
"grad_norm": 0.7445433139801025,
"learning_rate": 0.00017219560939545246,
"loss": 0.6053,
"step": 360
},
{
"epoch": 2.4873949579831933,
"grad_norm": 0.8667672276496887,
"learning_rate": 0.00017071067811865476,
"loss": 0.6273,
"step": 370
},
{
"epoch": 2.5546218487394956,
"grad_norm": 0.8110456466674805,
"learning_rate": 0.00016919388689775464,
"loss": 0.651,
"step": 380
},
{
"epoch": 2.6218487394957983,
"grad_norm": 0.804862380027771,
"learning_rate": 0.0001676459191498087,
"loss": 0.6385,
"step": 390
},
{
"epoch": 2.689075630252101,
"grad_norm": 0.7267991304397583,
"learning_rate": 0.00016606747233900815,
"loss": 0.6054,
"step": 400
},
{
"epoch": 2.7563025210084033,
"grad_norm": 0.788287878036499,
"learning_rate": 0.00016445925766242391,
"loss": 0.64,
"step": 410
},
{
"epoch": 2.8235294117647056,
"grad_norm": 0.7693036198616028,
"learning_rate": 0.00016282199972956425,
"loss": 0.6388,
"step": 420
},
{
"epoch": 2.8907563025210083,
"grad_norm": 0.8343464136123657,
"learning_rate": 0.00016115643623588915,
"loss": 0.6328,
"step": 430
},
{
"epoch": 2.957983193277311,
"grad_norm": 0.8166292905807495,
"learning_rate": 0.00015946331763042867,
"loss": 0.6153,
"step": 440
},
{
"epoch": 3.0252100840336134,
"grad_norm": 0.7756981253623962,
"learning_rate": 0.0001577434067776548,
"loss": 0.5833,
"step": 450
},
{
"epoch": 3.092436974789916,
"grad_norm": 0.8692726492881775,
"learning_rate": 0.00015599747861375955,
"loss": 0.4775,
"step": 460
},
{
"epoch": 3.1596638655462184,
"grad_norm": 0.9870768785476685,
"learning_rate": 0.00015422631979749354,
"loss": 0.4773,
"step": 470
},
{
"epoch": 3.226890756302521,
"grad_norm": 0.9229463934898376,
"learning_rate": 0.00015243072835572318,
"loss": 0.4712,
"step": 480
},
{
"epoch": 3.2941176470588234,
"grad_norm": 1.0052525997161865,
"learning_rate": 0.00015061151332386566,
"loss": 0.4753,
"step": 490
},
{
"epoch": 3.361344537815126,
"grad_norm": 0.9673507809638977,
"learning_rate": 0.00014876949438136347,
"loss": 0.5026,
"step": 500
},
{
"epoch": 3.4285714285714284,
"grad_norm": 0.9231823682785034,
"learning_rate": 0.0001469055014823637,
"loss": 0.483,
"step": 510
},
{
"epoch": 3.495798319327731,
"grad_norm": 0.8525064587593079,
"learning_rate": 0.00014502037448176734,
"loss": 0.5037,
"step": 520
},
{
"epoch": 3.5630252100840334,
"grad_norm": 0.9199729561805725,
"learning_rate": 0.00014311496275681783,
"loss": 0.4939,
"step": 530
},
{
"epoch": 3.630252100840336,
"grad_norm": 0.9707980155944824,
"learning_rate": 0.0001411901248243993,
"loss": 0.5023,
"step": 540
},
{
"epoch": 3.697478991596639,
"grad_norm": 0.9233918190002441,
"learning_rate": 0.00013924672795421637,
"loss": 0.4873,
"step": 550
},
{
"epoch": 3.764705882352941,
"grad_norm": 1.0375723838806152,
"learning_rate": 0.00013728564777803088,
"loss": 0.5025,
"step": 560
},
{
"epoch": 3.831932773109244,
"grad_norm": 0.9299758076667786,
"learning_rate": 0.0001353077678951301,
"loss": 0.5143,
"step": 570
},
{
"epoch": 3.899159663865546,
"grad_norm": 1.036216378211975,
"learning_rate": 0.00013331397947420576,
"loss": 0.51,
"step": 580
},
{
"epoch": 3.966386554621849,
"grad_norm": 0.8998732566833496,
"learning_rate": 0.00013130518085182225,
"loss": 0.5041,
"step": 590
},
{
"epoch": 4.033613445378151,
"grad_norm": 0.8797755241394043,
"learning_rate": 0.00012928227712765504,
"loss": 0.4424,
"step": 600
},
{
"epoch": 4.100840336134453,
"grad_norm": 0.9840869903564453,
"learning_rate": 0.0001272461797566823,
"loss": 0.3458,
"step": 610
},
{
"epoch": 4.168067226890757,
"grad_norm": 1.0934089422225952,
"learning_rate": 0.00012519780613851254,
"loss": 0.3392,
"step": 620
},
{
"epoch": 4.235294117647059,
"grad_norm": 1.1537727117538452,
"learning_rate": 0.00012313807920403419,
"loss": 0.3509,
"step": 630
},
{
"epoch": 4.302521008403361,
"grad_norm": 1.1627821922302246,
"learning_rate": 0.00012106792699957263,
"loss": 0.3602,
"step": 640
},
{
"epoch": 4.369747899159664,
"grad_norm": 1.0649752616882324,
"learning_rate": 0.00011898828226874284,
"loss": 0.3553,
"step": 650
},
{
"epoch": 4.436974789915967,
"grad_norm": 1.0529594421386719,
"learning_rate": 0.00011690008203218493,
"loss": 0.3549,
"step": 660
},
{
"epoch": 4.504201680672269,
"grad_norm": 1.1749626398086548,
"learning_rate": 0.00011480426716537315,
"loss": 0.3632,
"step": 670
},
{
"epoch": 4.571428571428571,
"grad_norm": 1.1761151552200317,
"learning_rate": 0.00011270178197468789,
"loss": 0.3616,
"step": 680
},
{
"epoch": 4.6386554621848735,
"grad_norm": 1.2466800212860107,
"learning_rate": 0.00011059357377194161,
"loss": 0.364,
"step": 690
},
{
"epoch": 4.705882352941177,
"grad_norm": 1.0312550067901611,
"learning_rate": 0.00010848059244755093,
"loss": 0.3701,
"step": 700
},
{
"epoch": 4.773109243697479,
"grad_norm": 1.054643154144287,
"learning_rate": 0.00010636379004254664,
"loss": 0.3734,
"step": 710
},
{
"epoch": 4.840336134453781,
"grad_norm": 1.0129141807556152,
"learning_rate": 0.00010424412031961484,
"loss": 0.3576,
"step": 720
},
{
"epoch": 4.907563025210084,
"grad_norm": 1.0076299905776978,
"learning_rate": 0.00010212253833336237,
"loss": 0.3661,
"step": 730
},
{
"epoch": 4.974789915966387,
"grad_norm": 1.115916132926941,
"learning_rate": 0.0001,
"loss": 0.3804,
"step": 740
},
{
"epoch": 5.042016806722689,
"grad_norm": 0.9718462824821472,
"learning_rate": 9.787746166663764e-05,
"loss": 0.3098,
"step": 750
},
{
"epoch": 5.109243697478991,
"grad_norm": 1.4013969898223877,
"learning_rate": 9.57558796803852e-05,
"loss": 0.255,
"step": 760
},
{
"epoch": 5.176470588235294,
"grad_norm": 1.0892488956451416,
"learning_rate": 9.363620995745337e-05,
"loss": 0.2527,
"step": 770
},
{
"epoch": 5.243697478991597,
"grad_norm": 1.0271626710891724,
"learning_rate": 9.151940755244912e-05,
"loss": 0.2519,
"step": 780
},
{
"epoch": 5.310924369747899,
"grad_norm": 1.227356195449829,
"learning_rate": 8.94064262280584e-05,
"loss": 0.2542,
"step": 790
},
{
"epoch": 5.378151260504202,
"grad_norm": 0.9420528411865234,
"learning_rate": 8.729821802531212e-05,
"loss": 0.2531,
"step": 800
},
{
"epoch": 5.445378151260504,
"grad_norm": 1.099165439605713,
"learning_rate": 8.519573283462687e-05,
"loss": 0.2567,
"step": 810
},
{
"epoch": 5.512605042016807,
"grad_norm": 0.891905665397644,
"learning_rate": 8.309991796781511e-05,
"loss": 0.2641,
"step": 820
},
{
"epoch": 5.579831932773109,
"grad_norm": 1.051827073097229,
"learning_rate": 8.101171773125716e-05,
"loss": 0.2582,
"step": 830
},
{
"epoch": 5.647058823529412,
"grad_norm": 1.180173397064209,
"learning_rate": 7.89320730004274e-05,
"loss": 0.2665,
"step": 840
},
{
"epoch": 5.714285714285714,
"grad_norm": 1.2048763036727905,
"learning_rate": 7.686192079596586e-05,
"loss": 0.2649,
"step": 850
},
{
"epoch": 5.781512605042017,
"grad_norm": 1.0822349786758423,
"learning_rate": 7.48021938614875e-05,
"loss": 0.2598,
"step": 860
},
{
"epoch": 5.848739495798319,
"grad_norm": 1.1536500453948975,
"learning_rate": 7.275382024331772e-05,
"loss": 0.2594,
"step": 870
},
{
"epoch": 5.915966386554622,
"grad_norm": 1.159244418144226,
"learning_rate": 7.071772287234497e-05,
"loss": 0.2669,
"step": 880
},
{
"epoch": 5.983193277310924,
"grad_norm": 1.0501562356948853,
"learning_rate": 6.869481914817779e-05,
"loss": 0.2662,
"step": 890
},
{
"epoch": 6.050420168067227,
"grad_norm": 0.7824720144271851,
"learning_rate": 6.668602052579424e-05,
"loss": 0.2091,
"step": 900
},
{
"epoch": 6.117647058823529,
"grad_norm": 1.0397021770477295,
"learning_rate": 6.469223210486992e-05,
"loss": 0.191,
"step": 910
},
{
"epoch": 6.184873949579832,
"grad_norm": 0.8494867086410522,
"learning_rate": 6.271435222196916e-05,
"loss": 0.1893,
"step": 920
},
{
"epoch": 6.2521008403361344,
"grad_norm": 0.8539510369300842,
"learning_rate": 6.0753272045783625e-05,
"loss": 0.1946,
"step": 930
},
{
"epoch": 6.319327731092437,
"grad_norm": 0.9266153573989868,
"learning_rate": 5.880987517560075e-05,
"loss": 0.1992,
"step": 940
},
{
"epoch": 6.38655462184874,
"grad_norm": 0.880462110042572,
"learning_rate": 5.688503724318217e-05,
"loss": 0.1973,
"step": 950
},
{
"epoch": 6.453781512605042,
"grad_norm": 1.0066040754318237,
"learning_rate": 5.497962551823266e-05,
"loss": 0.1956,
"step": 960
},
{
"epoch": 6.5210084033613445,
"grad_norm": 0.9597271680831909,
"learning_rate": 5.309449851763633e-05,
"loss": 0.1949,
"step": 970
},
{
"epoch": 6.588235294117647,
"grad_norm": 0.8810604214668274,
"learning_rate": 5.123050561863657e-05,
"loss": 0.1995,
"step": 980
},
{
"epoch": 6.65546218487395,
"grad_norm": 0.8872011303901672,
"learning_rate": 4.938848667613436e-05,
"loss": 0.2019,
"step": 990
},
{
"epoch": 6.722689075630252,
"grad_norm": 0.8763492107391357,
"learning_rate": 4.756927164427685e-05,
"loss": 0.2007,
"step": 1000
},
{
"epoch": 6.7899159663865545,
"grad_norm": 0.962574303150177,
"learning_rate": 4.57736802025065e-05,
"loss": 0.1992,
"step": 1010
},
{
"epoch": 6.857142857142857,
"grad_norm": 0.8366807103157043,
"learning_rate": 4.4002521386240466e-05,
"loss": 0.2012,
"step": 1020
},
{
"epoch": 6.92436974789916,
"grad_norm": 1.118316888809204,
"learning_rate": 4.2256593222345185e-05,
"loss": 0.2015,
"step": 1030
},
{
"epoch": 6.991596638655462,
"grad_norm": 0.8486827611923218,
"learning_rate": 4.053668236957134e-05,
"loss": 0.1992,
"step": 1040
},
{
"epoch": 7.0588235294117645,
"grad_norm": 0.6685436367988586,
"learning_rate": 3.884356376411089e-05,
"loss": 0.1697,
"step": 1050
},
{
"epoch": 7.126050420168067,
"grad_norm": 0.7779160737991333,
"learning_rate": 3.717800027043576e-05,
"loss": 0.1649,
"step": 1060
},
{
"epoch": 7.19327731092437,
"grad_norm": 0.7106925845146179,
"learning_rate": 3.554074233757608e-05,
"loss": 0.1652,
"step": 1070
},
{
"epoch": 7.260504201680672,
"grad_norm": 0.710456371307373,
"learning_rate": 3.393252766099187e-05,
"loss": 0.1603,
"step": 1080
},
{
"epoch": 7.3277310924369745,
"grad_norm": 0.8392521739006042,
"learning_rate": 3.2354080850191324e-05,
"loss": 0.1655,
"step": 1090
},
{
"epoch": 7.394957983193278,
"grad_norm": 0.7160742878913879,
"learning_rate": 3.080611310224539e-05,
"loss": 0.164,
"step": 1100
},
{
"epoch": 7.46218487394958,
"grad_norm": 0.8458212614059448,
"learning_rate": 2.9289321881345254e-05,
"loss": 0.164,
"step": 1110
},
{
"epoch": 7.529411764705882,
"grad_norm": 0.7505910396575928,
"learning_rate": 2.7804390604547557e-05,
"loss": 0.161,
"step": 1120
},
{
"epoch": 7.5966386554621845,
"grad_norm": 0.6830323338508606,
"learning_rate": 2.6351988333848788e-05,
"loss": 0.166,
"step": 1130
},
{
"epoch": 7.663865546218488,
"grad_norm": 0.6792168021202087,
"learning_rate": 2.493276947472756e-05,
"loss": 0.1598,
"step": 1140
},
{
"epoch": 7.73109243697479,
"grad_norm": 0.8226212859153748,
"learning_rate": 2.354737348129077e-05,
"loss": 0.1657,
"step": 1150
},
{
"epoch": 7.798319327731092,
"grad_norm": 0.7470860481262207,
"learning_rate": 2.2196424568156073e-05,
"loss": 0.1624,
"step": 1160
},
{
"epoch": 7.865546218487395,
"grad_norm": 0.746971070766449,
"learning_rate": 2.0880531429201145e-05,
"loss": 0.1647,
"step": 1170
},
{
"epoch": 7.932773109243698,
"grad_norm": 1.0174585580825806,
"learning_rate": 1.9600286963305957e-05,
"loss": 0.1613,
"step": 1180
},
{
"epoch": 8.0,
"grad_norm": 0.7260714173316956,
"learning_rate": 1.835626800721144e-05,
"loss": 0.164,
"step": 1190
},
{
"epoch": 8.067226890756302,
"grad_norm": 0.6740816831588745,
"learning_rate": 1.7149035075615794e-05,
"loss": 0.1442,
"step": 1200
},
{
"epoch": 8.134453781512605,
"grad_norm": 0.6308555006980896,
"learning_rate": 1.5979132108624574e-05,
"loss": 0.1475,
"step": 1210
},
{
"epoch": 8.201680672268907,
"grad_norm": 0.6884053349494934,
"learning_rate": 1.4847086226668872e-05,
"loss": 0.1457,
"step": 1220
},
{
"epoch": 8.268907563025211,
"grad_norm": 0.6926451921463013,
"learning_rate": 1.3753407493001968e-05,
"loss": 0.1472,
"step": 1230
},
{
"epoch": 8.336134453781513,
"grad_norm": 0.7861657738685608,
"learning_rate": 1.2698588683881186e-05,
"loss": 0.1454,
"step": 1240
},
{
"epoch": 8.403361344537815,
"grad_norm": 0.6917855739593506,
"learning_rate": 1.1683105066539068e-05,
"loss": 0.1469,
"step": 1250
},
{
"epoch": 8.470588235294118,
"grad_norm": 0.6251822113990784,
"learning_rate": 1.0707414185043163e-05,
"loss": 0.1434,
"step": 1260
},
{
"epoch": 8.53781512605042,
"grad_norm": 0.687460720539093,
"learning_rate": 9.771955654141496e-06,
"loss": 0.1489,
"step": 1270
},
{
"epoch": 8.605042016806722,
"grad_norm": 0.5865232348442078,
"learning_rate": 8.87715096118642e-06,
"loss": 0.1467,
"step": 1280
},
{
"epoch": 8.672268907563025,
"grad_norm": 0.6895480751991272,
"learning_rate": 8.023403276226126e-06,
"loss": 0.1498,
"step": 1290
},
{
"epoch": 8.739495798319329,
"grad_norm": 0.6769334077835083,
"learning_rate": 7.211097270349066e-06,
"loss": 0.1466,
"step": 1300
},
{
"epoch": 8.806722689075631,
"grad_norm": 0.677874743938446,
"learning_rate": 6.440598942363796e-06,
"loss": 0.1493,
"step": 1310
},
{
"epoch": 8.873949579831933,
"grad_norm": 0.6369357109069824,
"learning_rate": 5.71225545389158e-06,
"loss": 0.1462,
"step": 1320
},
{
"epoch": 8.941176470588236,
"grad_norm": 0.6327443718910217,
"learning_rate": 5.026394972946813e-06,
"loss": 0.1495,
"step": 1330
},
{
"epoch": 9.008403361344538,
"grad_norm": 0.5465492010116577,
"learning_rate": 4.383326526074916e-06,
"loss": 0.1441,
"step": 1340
},
{
"epoch": 9.07563025210084,
"grad_norm": 0.5892530679702759,
"learning_rate": 3.783339859115065e-06,
"loss": 0.1418,
"step": 1350
},
{
"epoch": 9.142857142857142,
"grad_norm": 0.5574983358383179,
"learning_rate": 3.226705306650113e-06,
"loss": 0.1418,
"step": 1360
},
{
"epoch": 9.210084033613445,
"grad_norm": 0.6200439929962158,
"learning_rate": 2.7136736702025433e-06,
"loss": 0.1418,
"step": 1370
},
{
"epoch": 9.277310924369749,
"grad_norm": 0.6464766263961792,
"learning_rate": 2.2444761052313856e-06,
"loss": 0.1407,
"step": 1380
},
{
"epoch": 9.344537815126051,
"grad_norm": 0.5886226296424866,
"learning_rate": 1.8193240169810943e-06,
"loss": 0.1392,
"step": 1390
},
{
"epoch": 9.411764705882353,
"grad_norm": 0.5666891932487488,
"learning_rate": 1.4384089652291543e-06,
"loss": 0.1404,
"step": 1400
},
{
"epoch": 9.478991596638656,
"grad_norm": 0.5538501739501953,
"learning_rate": 1.1019025779754666e-06,
"loss": 0.1386,
"step": 1410
},
{
"epoch": 9.546218487394958,
"grad_norm": 0.49777477979660034,
"learning_rate": 8.099564741123166e-07,
"loss": 0.1384,
"step": 1420
},
{
"epoch": 9.61344537815126,
"grad_norm": 0.6270516514778137,
"learning_rate": 5.627021951097545e-07,
"loss": 0.1383,
"step": 1430
},
{
"epoch": 9.680672268907562,
"grad_norm": 0.6225831508636475,
"learning_rate": 3.6025114574734785e-07,
"loss": 0.1379,
"step": 1440
},
{
"epoch": 9.747899159663866,
"grad_norm": 0.6717821359634399,
"learning_rate": 2.0269454391874666e-07,
"loss": 0.1412,
"step": 1450
},
{
"epoch": 9.815126050420169,
"grad_norm": 0.5855395197868347,
"learning_rate": 9.010337953185843e-08,
"loss": 0.1418,
"step": 1460
},
{
"epoch": 9.882352941176471,
"grad_norm": 0.63104647397995,
"learning_rate": 2.2528382523057113e-08,
"loss": 0.1408,
"step": 1470
},
{
"epoch": 9.949579831932773,
"grad_norm": 0.5754216909408569,
"learning_rate": 0.0,
"loss": 0.1426,
"step": 1480
},
{
"epoch": 9.949579831932773,
"step": 1480,
"total_flos": 7.279937555791872e+16,
"train_loss": 0.41058476212862377,
"train_runtime": 5774.901,
"train_samples_per_second": 1.03,
"train_steps_per_second": 0.256
}
],
"logging_steps": 10,
"max_steps": 1480,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 7.279937555791872e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}