tasky / checkpoint-2000-new /trainer_state.json
jordiclive's picture
Upload folder using huggingface_hub
cc0637c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.195546950629235,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.030977734753146177,
"grad_norm": 99.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.9661,
"step": 10
},
{
"epoch": 0.061955469506292354,
"grad_norm": 374.0,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.2124,
"step": 20
},
{
"epoch": 0.09293320425943853,
"grad_norm": 1392640.0,
"learning_rate": 3e-06,
"loss": 2.2122,
"step": 30
},
{
"epoch": 0.12391093901258471,
"grad_norm": 78.5,
"learning_rate": 4.000000000000001e-06,
"loss": 1.9339,
"step": 40
},
{
"epoch": 0.15488867376573087,
"grad_norm": 13500416.0,
"learning_rate": 5e-06,
"loss": 1.8448,
"step": 50
},
{
"epoch": 0.18586640851887706,
"grad_norm": 98.0,
"learning_rate": 6e-06,
"loss": 1.9577,
"step": 60
},
{
"epoch": 0.21684414327202323,
"grad_norm": 11337728.0,
"learning_rate": 7.000000000000001e-06,
"loss": 2.089,
"step": 70
},
{
"epoch": 0.24782187802516942,
"grad_norm": 20736.0,
"learning_rate": 8.000000000000001e-06,
"loss": 1.8571,
"step": 80
},
{
"epoch": 0.2787996127783156,
"grad_norm": 8512.0,
"learning_rate": 9e-06,
"loss": 2.0639,
"step": 90
},
{
"epoch": 0.30977734753146174,
"grad_norm": 1004.0,
"learning_rate": 1e-05,
"loss": 1.978,
"step": 100
},
{
"epoch": 0.34075508228460794,
"grad_norm": 470.0,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.9845,
"step": 110
},
{
"epoch": 0.3717328170377541,
"grad_norm": 268435456.0,
"learning_rate": 1.2e-05,
"loss": 1.9825,
"step": 120
},
{
"epoch": 0.4027105517909003,
"grad_norm": 50593792.0,
"learning_rate": 1.3000000000000001e-05,
"loss": 2.0309,
"step": 130
},
{
"epoch": 0.43368828654404645,
"grad_norm": 942080.0,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.804,
"step": 140
},
{
"epoch": 0.46466602129719264,
"grad_norm": 93.5,
"learning_rate": 1.5e-05,
"loss": 1.9188,
"step": 150
},
{
"epoch": 0.49564375605033884,
"grad_norm": 138.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.7755,
"step": 160
},
{
"epoch": 0.526621490803485,
"grad_norm": 2310144.0,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.9404,
"step": 170
},
{
"epoch": 0.5575992255566312,
"grad_norm": 252928.0,
"learning_rate": 1.8e-05,
"loss": 1.9115,
"step": 180
},
{
"epoch": 0.5885769603097774,
"grad_norm": 36096.0,
"learning_rate": 1.9e-05,
"loss": 2.0781,
"step": 190
},
{
"epoch": 0.6195546950629235,
"grad_norm": 143.0,
"learning_rate": 2e-05,
"loss": 1.8338,
"step": 200
},
{
"epoch": 0.6505324298160697,
"grad_norm": 222208.0,
"learning_rate": 2.1e-05,
"loss": 1.9065,
"step": 210
},
{
"epoch": 0.6815101645692159,
"grad_norm": 11599872.0,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.8142,
"step": 220
},
{
"epoch": 0.712487899322362,
"grad_norm": 3568.0,
"learning_rate": 2.3000000000000003e-05,
"loss": 1.7811,
"step": 230
},
{
"epoch": 0.7434656340755083,
"grad_norm": 81.5,
"learning_rate": 2.4e-05,
"loss": 1.7512,
"step": 240
},
{
"epoch": 0.7744433688286544,
"grad_norm": 3696.0,
"learning_rate": 2.5e-05,
"loss": 1.8697,
"step": 250
},
{
"epoch": 0.8054211035818006,
"grad_norm": 63744.0,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.7677,
"step": 260
},
{
"epoch": 0.8363988383349468,
"grad_norm": 55.5,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.7307,
"step": 270
},
{
"epoch": 0.8673765730880929,
"grad_norm": 202.0,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.9074,
"step": 280
},
{
"epoch": 0.8983543078412392,
"grad_norm": 348.0,
"learning_rate": 2.9e-05,
"loss": 1.7037,
"step": 290
},
{
"epoch": 0.9293320425943853,
"grad_norm": 342.0,
"learning_rate": 3e-05,
"loss": 1.5886,
"step": 300
},
{
"epoch": 0.9603097773475314,
"grad_norm": 62.5,
"learning_rate": 3.1e-05,
"loss": 1.6942,
"step": 310
},
{
"epoch": 0.9912875121006777,
"grad_norm": 91.5,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.5326,
"step": 320
},
{
"epoch": 1.0222652468538238,
"grad_norm": 6560.0,
"learning_rate": 3.3e-05,
"loss": 1.6642,
"step": 330
},
{
"epoch": 1.05324298160697,
"grad_norm": 51.5,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.5624,
"step": 340
},
{
"epoch": 1.084220716360116,
"grad_norm": 1752.0,
"learning_rate": 3.5e-05,
"loss": 1.447,
"step": 350
},
{
"epoch": 1.1151984511132624,
"grad_norm": 48.25,
"learning_rate": 3.6e-05,
"loss": 1.6133,
"step": 360
},
{
"epoch": 1.1461761858664086,
"grad_norm": 52.25,
"learning_rate": 3.7e-05,
"loss": 1.4596,
"step": 370
},
{
"epoch": 1.1771539206195547,
"grad_norm": 12032.0,
"learning_rate": 3.8e-05,
"loss": 1.5244,
"step": 380
},
{
"epoch": 1.2081316553727008,
"grad_norm": 49.0,
"learning_rate": 3.9000000000000006e-05,
"loss": 1.5972,
"step": 390
},
{
"epoch": 1.239109390125847,
"grad_norm": 39.25,
"learning_rate": 4e-05,
"loss": 1.2712,
"step": 400
},
{
"epoch": 1.2700871248789931,
"grad_norm": 1120.0,
"learning_rate": 4.1e-05,
"loss": 1.4318,
"step": 410
},
{
"epoch": 1.3010648596321395,
"grad_norm": 28160.0,
"learning_rate": 4.2e-05,
"loss": 1.3211,
"step": 420
},
{
"epoch": 1.3320425943852856,
"grad_norm": 12845056.0,
"learning_rate": 4.3e-05,
"loss": 1.4051,
"step": 430
},
{
"epoch": 1.3630203291384317,
"grad_norm": 6979584.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.2505,
"step": 440
},
{
"epoch": 1.3939980638915779,
"grad_norm": 27.75,
"learning_rate": 4.5e-05,
"loss": 1.1342,
"step": 450
},
{
"epoch": 1.424975798644724,
"grad_norm": 73.0,
"learning_rate": 4.600000000000001e-05,
"loss": 1.2342,
"step": 460
},
{
"epoch": 1.4559535333978704,
"grad_norm": 19.75,
"learning_rate": 4.7e-05,
"loss": 1.0688,
"step": 470
},
{
"epoch": 1.4869312681510165,
"grad_norm": 604.0,
"learning_rate": 4.8e-05,
"loss": 1.0641,
"step": 480
},
{
"epoch": 1.5179090029041626,
"grad_norm": 79.5,
"learning_rate": 4.9e-05,
"loss": 1.0869,
"step": 490
},
{
"epoch": 1.5488867376573088,
"grad_norm": 2144.0,
"learning_rate": 5e-05,
"loss": 1.0356,
"step": 500
},
{
"epoch": 1.5488867376573088,
"eval_loss": 0.21533620357513428,
"eval_runtime": 145.9664,
"eval_samples_per_second": 10.276,
"eval_steps_per_second": 2.569,
"step": 500
},
{
"epoch": 1.579864472410455,
"grad_norm": 125.0,
"learning_rate": 5.1000000000000006e-05,
"loss": 1.0417,
"step": 510
},
{
"epoch": 1.6108422071636013,
"grad_norm": 17.875,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.0518,
"step": 520
},
{
"epoch": 1.6418199419167472,
"grad_norm": 68.0,
"learning_rate": 5.300000000000001e-05,
"loss": 1.1404,
"step": 530
},
{
"epoch": 1.6727976766698935,
"grad_norm": 19.5,
"learning_rate": 5.4000000000000005e-05,
"loss": 0.9938,
"step": 540
},
{
"epoch": 1.7037754114230397,
"grad_norm": 290.0,
"learning_rate": 5.500000000000001e-05,
"loss": 0.9374,
"step": 550
},
{
"epoch": 1.7347531461761858,
"grad_norm": 58.5,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.0777,
"step": 560
},
{
"epoch": 1.7657308809293322,
"grad_norm": 422.0,
"learning_rate": 5.6999999999999996e-05,
"loss": 1.059,
"step": 570
},
{
"epoch": 1.796708615682478,
"grad_norm": 28.625,
"learning_rate": 5.8e-05,
"loss": 0.965,
"step": 580
},
{
"epoch": 1.8276863504356244,
"grad_norm": 43.75,
"learning_rate": 5.9e-05,
"loss": 0.9527,
"step": 590
},
{
"epoch": 1.8586640851887706,
"grad_norm": 12.75,
"learning_rate": 6e-05,
"loss": 0.8296,
"step": 600
},
{
"epoch": 1.8896418199419167,
"grad_norm": 16.0,
"learning_rate": 6.1e-05,
"loss": 0.933,
"step": 610
},
{
"epoch": 1.920619554695063,
"grad_norm": 11.875,
"learning_rate": 6.2e-05,
"loss": 0.8117,
"step": 620
},
{
"epoch": 1.951597289448209,
"grad_norm": 50.0,
"learning_rate": 6.3e-05,
"loss": 0.9475,
"step": 630
},
{
"epoch": 1.9825750242013553,
"grad_norm": 143.0,
"learning_rate": 6.400000000000001e-05,
"loss": 0.8241,
"step": 640
},
{
"epoch": 2.0135527589545013,
"grad_norm": 108.5,
"learning_rate": 6.500000000000001e-05,
"loss": 0.7861,
"step": 650
},
{
"epoch": 2.0445304937076476,
"grad_norm": 13184.0,
"learning_rate": 6.6e-05,
"loss": 0.8384,
"step": 660
},
{
"epoch": 2.075508228460794,
"grad_norm": 1736704.0,
"learning_rate": 6.7e-05,
"loss": 0.8896,
"step": 670
},
{
"epoch": 2.10648596321394,
"grad_norm": 48.75,
"learning_rate": 6.800000000000001e-05,
"loss": 0.9377,
"step": 680
},
{
"epoch": 2.1374636979670862,
"grad_norm": 2816.0,
"learning_rate": 6.9e-05,
"loss": 0.8322,
"step": 690
},
{
"epoch": 2.168441432720232,
"grad_norm": 3.125,
"learning_rate": 7e-05,
"loss": 0.8397,
"step": 700
},
{
"epoch": 2.1994191674733785,
"grad_norm": 8.6875,
"learning_rate": 7.1e-05,
"loss": 0.9265,
"step": 710
},
{
"epoch": 2.230396902226525,
"grad_norm": 9.875,
"learning_rate": 7.2e-05,
"loss": 0.8141,
"step": 720
},
{
"epoch": 2.261374636979671,
"grad_norm": 14.8125,
"learning_rate": 7.3e-05,
"loss": 0.7629,
"step": 730
},
{
"epoch": 2.292352371732817,
"grad_norm": 6.4375,
"learning_rate": 7.4e-05,
"loss": 0.85,
"step": 740
},
{
"epoch": 2.323330106485963,
"grad_norm": 3.796875,
"learning_rate": 7.500000000000001e-05,
"loss": 0.9116,
"step": 750
},
{
"epoch": 2.3543078412391094,
"grad_norm": 544768.0,
"learning_rate": 7.6e-05,
"loss": 0.8437,
"step": 760
},
{
"epoch": 2.3852855759922553,
"grad_norm": 117760.0,
"learning_rate": 7.7e-05,
"loss": 0.9072,
"step": 770
},
{
"epoch": 2.4162633107454017,
"grad_norm": 22.75,
"learning_rate": 7.800000000000001e-05,
"loss": 1.0168,
"step": 780
},
{
"epoch": 2.447241045498548,
"grad_norm": 2211840.0,
"learning_rate": 7.900000000000001e-05,
"loss": 1.1433,
"step": 790
},
{
"epoch": 2.478218780251694,
"grad_norm": 41.5,
"learning_rate": 8e-05,
"loss": 0.7485,
"step": 800
},
{
"epoch": 2.5091965150048403,
"grad_norm": 1810432.0,
"learning_rate": 8.1e-05,
"loss": 0.9516,
"step": 810
},
{
"epoch": 2.5401742497579862,
"grad_norm": 1081344.0,
"learning_rate": 8.2e-05,
"loss": 1.0742,
"step": 820
},
{
"epoch": 2.5711519845111326,
"grad_norm": 337641472.0,
"learning_rate": 8.3e-05,
"loss": 1.023,
"step": 830
},
{
"epoch": 2.602129719264279,
"grad_norm": 14548992.0,
"learning_rate": 8.4e-05,
"loss": 1.185,
"step": 840
},
{
"epoch": 2.633107454017425,
"grad_norm": 4.71875,
"learning_rate": 8.5e-05,
"loss": 1.3584,
"step": 850
},
{
"epoch": 2.664085188770571,
"grad_norm": 618496.0,
"learning_rate": 8.6e-05,
"loss": 0.9947,
"step": 860
},
{
"epoch": 2.695062923523717,
"grad_norm": 22151168.0,
"learning_rate": 8.7e-05,
"loss": 1.0296,
"step": 870
},
{
"epoch": 2.7260406582768635,
"grad_norm": 77824.0,
"learning_rate": 8.800000000000001e-05,
"loss": 0.8889,
"step": 880
},
{
"epoch": 2.75701839303001,
"grad_norm": 2.640625,
"learning_rate": 8.900000000000001e-05,
"loss": 0.733,
"step": 890
},
{
"epoch": 2.7879961277831558,
"grad_norm": 18.625,
"learning_rate": 9e-05,
"loss": 0.7786,
"step": 900
},
{
"epoch": 2.818973862536302,
"grad_norm": 9.0625,
"learning_rate": 9.1e-05,
"loss": 0.7221,
"step": 910
},
{
"epoch": 2.849951597289448,
"grad_norm": 10.4375,
"learning_rate": 9.200000000000001e-05,
"loss": 0.6316,
"step": 920
},
{
"epoch": 2.8809293320425944,
"grad_norm": 4.84375,
"learning_rate": 9.300000000000001e-05,
"loss": 0.7015,
"step": 930
},
{
"epoch": 2.9119070667957407,
"grad_norm": 4.1875,
"learning_rate": 9.4e-05,
"loss": 0.7161,
"step": 940
},
{
"epoch": 2.9428848015488867,
"grad_norm": 2.8125,
"learning_rate": 9.5e-05,
"loss": 0.7325,
"step": 950
},
{
"epoch": 2.973862536302033,
"grad_norm": 5.90625,
"learning_rate": 9.6e-05,
"loss": 0.6447,
"step": 960
},
{
"epoch": 3.004840271055179,
"grad_norm": 1.6015625,
"learning_rate": 9.7e-05,
"loss": 0.7079,
"step": 970
},
{
"epoch": 3.0358180058083253,
"grad_norm": 3.8125,
"learning_rate": 9.8e-05,
"loss": 0.6075,
"step": 980
},
{
"epoch": 3.0667957405614716,
"grad_norm": 1.9140625,
"learning_rate": 9.900000000000001e-05,
"loss": 0.697,
"step": 990
},
{
"epoch": 3.0977734753146176,
"grad_norm": 1.140625,
"learning_rate": 0.0001,
"loss": 0.7175,
"step": 1000
},
{
"epoch": 3.0977734753146176,
"eval_loss": 0.1426076889038086,
"eval_runtime": 146.0018,
"eval_samples_per_second": 10.274,
"eval_steps_per_second": 2.568,
"step": 1000
},
{
"epoch": 3.128751210067764,
"grad_norm": 1.6328125,
"learning_rate": 9.988452655889145e-05,
"loss": 0.5774,
"step": 1010
},
{
"epoch": 3.15972894482091,
"grad_norm": 24.125,
"learning_rate": 9.976905311778292e-05,
"loss": 0.5575,
"step": 1020
},
{
"epoch": 3.190706679574056,
"grad_norm": 1.8046875,
"learning_rate": 9.965357967667437e-05,
"loss": 0.5609,
"step": 1030
},
{
"epoch": 3.2216844143272025,
"grad_norm": 0.6015625,
"learning_rate": 9.953810623556582e-05,
"loss": 0.5562,
"step": 1040
},
{
"epoch": 3.2526621490803485,
"grad_norm": 37748736.0,
"learning_rate": 9.942263279445728e-05,
"loss": 0.6574,
"step": 1050
},
{
"epoch": 3.283639883833495,
"grad_norm": 0.66015625,
"learning_rate": 9.930715935334873e-05,
"loss": 0.5348,
"step": 1060
},
{
"epoch": 3.3146176185866407,
"grad_norm": 2.0625,
"learning_rate": 9.919168591224018e-05,
"loss": 0.5574,
"step": 1070
},
{
"epoch": 3.345595353339787,
"grad_norm": 0.9453125,
"learning_rate": 9.907621247113164e-05,
"loss": 0.5546,
"step": 1080
},
{
"epoch": 3.3765730880929334,
"grad_norm": 0.49609375,
"learning_rate": 9.896073903002309e-05,
"loss": 0.4716,
"step": 1090
},
{
"epoch": 3.4075508228460794,
"grad_norm": 1.1015625,
"learning_rate": 9.884526558891456e-05,
"loss": 0.4992,
"step": 1100
},
{
"epoch": 3.4385285575992257,
"grad_norm": 1.9609375,
"learning_rate": 9.8729792147806e-05,
"loss": 0.4814,
"step": 1110
},
{
"epoch": 3.4695062923523716,
"grad_norm": 0.81640625,
"learning_rate": 9.861431870669747e-05,
"loss": 0.5451,
"step": 1120
},
{
"epoch": 3.500484027105518,
"grad_norm": 1.3046875,
"learning_rate": 9.849884526558892e-05,
"loss": 0.5436,
"step": 1130
},
{
"epoch": 3.5314617618586643,
"grad_norm": 0.91015625,
"learning_rate": 9.838337182448038e-05,
"loss": 0.5237,
"step": 1140
},
{
"epoch": 3.5624394966118103,
"grad_norm": 1.5078125,
"learning_rate": 9.826789838337183e-05,
"loss": 0.4595,
"step": 1150
},
{
"epoch": 3.593417231364956,
"grad_norm": 3.015625,
"learning_rate": 9.81524249422633e-05,
"loss": 0.5892,
"step": 1160
},
{
"epoch": 3.6243949661181025,
"grad_norm": 1.703125,
"learning_rate": 9.803695150115474e-05,
"loss": 0.4804,
"step": 1170
},
{
"epoch": 3.655372700871249,
"grad_norm": 0.484375,
"learning_rate": 9.79214780600462e-05,
"loss": 0.471,
"step": 1180
},
{
"epoch": 3.6863504356243952,
"grad_norm": 0.6171875,
"learning_rate": 9.780600461893766e-05,
"loss": 0.5353,
"step": 1190
},
{
"epoch": 3.717328170377541,
"grad_norm": 1.6015625,
"learning_rate": 9.76905311778291e-05,
"loss": 0.5112,
"step": 1200
},
{
"epoch": 3.748305905130687,
"grad_norm": 28.25,
"learning_rate": 9.757505773672056e-05,
"loss": 0.5225,
"step": 1210
},
{
"epoch": 3.7792836398838334,
"grad_norm": 0.98828125,
"learning_rate": 9.745958429561202e-05,
"loss": 0.4663,
"step": 1220
},
{
"epoch": 3.81026137463698,
"grad_norm": 0.6640625,
"learning_rate": 9.734411085450347e-05,
"loss": 0.5263,
"step": 1230
},
{
"epoch": 3.8412391093901257,
"grad_norm": 1.0703125,
"learning_rate": 9.722863741339492e-05,
"loss": 0.5353,
"step": 1240
},
{
"epoch": 3.872216844143272,
"grad_norm": 0.28515625,
"learning_rate": 9.711316397228638e-05,
"loss": 0.4615,
"step": 1250
},
{
"epoch": 3.903194578896418,
"grad_norm": 0.515625,
"learning_rate": 9.699769053117783e-05,
"loss": 0.4887,
"step": 1260
},
{
"epoch": 3.9341723136495643,
"grad_norm": 0.70703125,
"learning_rate": 9.68822170900693e-05,
"loss": 0.4658,
"step": 1270
},
{
"epoch": 3.9651500484027107,
"grad_norm": 0.455078125,
"learning_rate": 9.676674364896074e-05,
"loss": 0.4914,
"step": 1280
},
{
"epoch": 3.9961277831558566,
"grad_norm": 0.67578125,
"learning_rate": 9.66512702078522e-05,
"loss": 0.5355,
"step": 1290
},
{
"epoch": 4.0271055179090025,
"grad_norm": 0.5390625,
"learning_rate": 9.653579676674366e-05,
"loss": 0.5068,
"step": 1300
},
{
"epoch": 4.058083252662149,
"grad_norm": 0.71875,
"learning_rate": 9.64203233256351e-05,
"loss": 0.4409,
"step": 1310
},
{
"epoch": 4.089060987415295,
"grad_norm": 0.7421875,
"learning_rate": 9.630484988452656e-05,
"loss": 0.4788,
"step": 1320
},
{
"epoch": 4.120038722168442,
"grad_norm": 0.443359375,
"learning_rate": 9.618937644341802e-05,
"loss": 0.4901,
"step": 1330
},
{
"epoch": 4.151016456921588,
"grad_norm": 0.33203125,
"learning_rate": 9.607390300230947e-05,
"loss": 0.4119,
"step": 1340
},
{
"epoch": 4.181994191674733,
"grad_norm": 1.421875,
"learning_rate": 9.595842956120092e-05,
"loss": 0.4597,
"step": 1350
},
{
"epoch": 4.21297192642788,
"grad_norm": 0.953125,
"learning_rate": 9.584295612009238e-05,
"loss": 0.5134,
"step": 1360
},
{
"epoch": 4.243949661181026,
"grad_norm": 0.73046875,
"learning_rate": 9.572748267898383e-05,
"loss": 0.4222,
"step": 1370
},
{
"epoch": 4.2749273959341725,
"grad_norm": 0.412109375,
"learning_rate": 9.56120092378753e-05,
"loss": 0.4851,
"step": 1380
},
{
"epoch": 4.305905130687319,
"grad_norm": 0.7578125,
"learning_rate": 9.549653579676674e-05,
"loss": 0.505,
"step": 1390
},
{
"epoch": 4.336882865440464,
"grad_norm": 0.453125,
"learning_rate": 9.538106235565821e-05,
"loss": 0.4439,
"step": 1400
},
{
"epoch": 4.367860600193611,
"grad_norm": 0.609375,
"learning_rate": 9.526558891454966e-05,
"loss": 0.4311,
"step": 1410
},
{
"epoch": 4.398838334946757,
"grad_norm": 0.302734375,
"learning_rate": 9.515011547344112e-05,
"loss": 0.4369,
"step": 1420
},
{
"epoch": 4.429816069699903,
"grad_norm": 0.30859375,
"learning_rate": 9.503464203233257e-05,
"loss": 0.4863,
"step": 1430
},
{
"epoch": 4.46079380445305,
"grad_norm": 0.43359375,
"learning_rate": 9.491916859122403e-05,
"loss": 0.4471,
"step": 1440
},
{
"epoch": 4.491771539206195,
"grad_norm": 0.345703125,
"learning_rate": 9.480369515011548e-05,
"loss": 0.4816,
"step": 1450
},
{
"epoch": 4.522749273959342,
"grad_norm": 0.28125,
"learning_rate": 9.468822170900693e-05,
"loss": 0.4363,
"step": 1460
},
{
"epoch": 4.553727008712488,
"grad_norm": 0.5390625,
"learning_rate": 9.45727482678984e-05,
"loss": 0.414,
"step": 1470
},
{
"epoch": 4.584704743465634,
"grad_norm": 0.29296875,
"learning_rate": 9.445727482678985e-05,
"loss": 0.4318,
"step": 1480
},
{
"epoch": 4.615682478218781,
"grad_norm": 0.298828125,
"learning_rate": 9.43418013856813e-05,
"loss": 0.456,
"step": 1490
},
{
"epoch": 4.646660212971926,
"grad_norm": 0.4375,
"learning_rate": 9.422632794457276e-05,
"loss": 0.4453,
"step": 1500
},
{
"epoch": 4.646660212971926,
"eval_loss": 0.10397772490978241,
"eval_runtime": 145.9588,
"eval_samples_per_second": 10.277,
"eval_steps_per_second": 2.569,
"step": 1500
},
{
"epoch": 4.6776379477250725,
"grad_norm": 0.365234375,
"learning_rate": 9.411085450346421e-05,
"loss": 0.4319,
"step": 1510
},
{
"epoch": 4.708615682478219,
"grad_norm": 0.578125,
"learning_rate": 9.399538106235566e-05,
"loss": 0.4488,
"step": 1520
},
{
"epoch": 4.739593417231365,
"grad_norm": 0.2373046875,
"learning_rate": 9.387990762124712e-05,
"loss": 0.4171,
"step": 1530
},
{
"epoch": 4.770571151984511,
"grad_norm": 0.4296875,
"learning_rate": 9.376443418013857e-05,
"loss": 0.4042,
"step": 1540
},
{
"epoch": 4.801548886737657,
"grad_norm": 0.578125,
"learning_rate": 9.364896073903002e-05,
"loss": 0.4238,
"step": 1550
},
{
"epoch": 4.832526621490803,
"grad_norm": 0.515625,
"learning_rate": 9.353348729792148e-05,
"loss": 0.4288,
"step": 1560
},
{
"epoch": 4.86350435624395,
"grad_norm": 1.7265625,
"learning_rate": 9.341801385681293e-05,
"loss": 0.46,
"step": 1570
},
{
"epoch": 4.894482090997096,
"grad_norm": 0.287109375,
"learning_rate": 9.330254041570438e-05,
"loss": 0.4821,
"step": 1580
},
{
"epoch": 4.9254598257502415,
"grad_norm": 0.228515625,
"learning_rate": 9.318706697459585e-05,
"loss": 0.3854,
"step": 1590
},
{
"epoch": 4.956437560503388,
"grad_norm": 0.41796875,
"learning_rate": 9.30715935334873e-05,
"loss": 0.3778,
"step": 1600
},
{
"epoch": 4.987415295256534,
"grad_norm": 0.2333984375,
"learning_rate": 9.295612009237876e-05,
"loss": 0.425,
"step": 1610
},
{
"epoch": 5.018393030009681,
"grad_norm": 0.41796875,
"learning_rate": 9.284064665127021e-05,
"loss": 0.3792,
"step": 1620
},
{
"epoch": 5.049370764762827,
"grad_norm": 0.6171875,
"learning_rate": 9.272517321016166e-05,
"loss": 0.4225,
"step": 1630
},
{
"epoch": 5.0803484995159724,
"grad_norm": 0.28125,
"learning_rate": 9.260969976905312e-05,
"loss": 0.3942,
"step": 1640
},
{
"epoch": 5.111326234269119,
"grad_norm": 0.412109375,
"learning_rate": 9.249422632794457e-05,
"loss": 0.3928,
"step": 1650
},
{
"epoch": 5.142303969022265,
"grad_norm": 0.185546875,
"learning_rate": 9.237875288683603e-05,
"loss": 0.4357,
"step": 1660
},
{
"epoch": 5.1732817037754115,
"grad_norm": 0.47265625,
"learning_rate": 9.226327944572748e-05,
"loss": 0.4773,
"step": 1670
},
{
"epoch": 5.204259438528558,
"grad_norm": 0.470703125,
"learning_rate": 9.214780600461895e-05,
"loss": 0.4383,
"step": 1680
},
{
"epoch": 5.235237173281703,
"grad_norm": 0.31640625,
"learning_rate": 9.20323325635104e-05,
"loss": 0.4585,
"step": 1690
},
{
"epoch": 5.26621490803485,
"grad_norm": 2.078125,
"learning_rate": 9.191685912240186e-05,
"loss": 0.4713,
"step": 1700
},
{
"epoch": 5.297192642787996,
"grad_norm": 0.275390625,
"learning_rate": 9.180138568129331e-05,
"loss": 0.4222,
"step": 1710
},
{
"epoch": 5.328170377541142,
"grad_norm": 0.30859375,
"learning_rate": 9.168591224018476e-05,
"loss": 0.3981,
"step": 1720
},
{
"epoch": 5.359148112294289,
"grad_norm": 0.244140625,
"learning_rate": 9.157043879907622e-05,
"loss": 0.4118,
"step": 1730
},
{
"epoch": 5.390125847047434,
"grad_norm": 0.357421875,
"learning_rate": 9.145496535796767e-05,
"loss": 0.4211,
"step": 1740
},
{
"epoch": 5.421103581800581,
"grad_norm": 0.3671875,
"learning_rate": 9.133949191685914e-05,
"loss": 0.3755,
"step": 1750
},
{
"epoch": 5.452081316553727,
"grad_norm": 0.5390625,
"learning_rate": 9.122401847575059e-05,
"loss": 0.4243,
"step": 1760
},
{
"epoch": 5.483059051306873,
"grad_norm": 0.2109375,
"learning_rate": 9.110854503464203e-05,
"loss": 0.4099,
"step": 1770
},
{
"epoch": 5.51403678606002,
"grad_norm": 0.408203125,
"learning_rate": 9.09930715935335e-05,
"loss": 0.4153,
"step": 1780
},
{
"epoch": 5.545014520813165,
"grad_norm": 0.345703125,
"learning_rate": 9.087759815242495e-05,
"loss": 0.3927,
"step": 1790
},
{
"epoch": 5.5759922555663115,
"grad_norm": 0.578125,
"learning_rate": 9.07621247113164e-05,
"loss": 0.3794,
"step": 1800
},
{
"epoch": 5.606969990319458,
"grad_norm": 0.43359375,
"learning_rate": 9.064665127020786e-05,
"loss": 0.4094,
"step": 1810
},
{
"epoch": 5.637947725072604,
"grad_norm": 0.259765625,
"learning_rate": 9.053117782909931e-05,
"loss": 0.4592,
"step": 1820
},
{
"epoch": 5.668925459825751,
"grad_norm": 0.458984375,
"learning_rate": 9.041570438799076e-05,
"loss": 0.4026,
"step": 1830
},
{
"epoch": 5.699903194578896,
"grad_norm": 0.376953125,
"learning_rate": 9.030023094688222e-05,
"loss": 0.4556,
"step": 1840
},
{
"epoch": 5.730880929332042,
"grad_norm": 0.30859375,
"learning_rate": 9.018475750577367e-05,
"loss": 0.4606,
"step": 1850
},
{
"epoch": 5.761858664085189,
"grad_norm": 0.458984375,
"learning_rate": 9.006928406466512e-05,
"loss": 0.4363,
"step": 1860
},
{
"epoch": 5.792836398838335,
"grad_norm": 0.228515625,
"learning_rate": 8.995381062355659e-05,
"loss": 0.3631,
"step": 1870
},
{
"epoch": 5.8238141335914815,
"grad_norm": 0.58203125,
"learning_rate": 8.983833718244804e-05,
"loss": 0.4075,
"step": 1880
},
{
"epoch": 5.854791868344627,
"grad_norm": 0.59375,
"learning_rate": 8.972286374133948e-05,
"loss": 0.4456,
"step": 1890
},
{
"epoch": 5.885769603097773,
"grad_norm": 0.3515625,
"learning_rate": 8.960739030023095e-05,
"loss": 0.4451,
"step": 1900
},
{
"epoch": 5.91674733785092,
"grad_norm": 0.318359375,
"learning_rate": 8.94919168591224e-05,
"loss": 0.4127,
"step": 1910
},
{
"epoch": 5.947725072604066,
"grad_norm": 0.369140625,
"learning_rate": 8.937644341801386e-05,
"loss": 0.4007,
"step": 1920
},
{
"epoch": 5.978702807357212,
"grad_norm": 0.357421875,
"learning_rate": 8.926096997690532e-05,
"loss": 0.3923,
"step": 1930
},
{
"epoch": 6.009680542110358,
"grad_norm": 0.228515625,
"learning_rate": 8.914549653579677e-05,
"loss": 0.3395,
"step": 1940
},
{
"epoch": 6.040658276863504,
"grad_norm": 0.216796875,
"learning_rate": 8.903002309468824e-05,
"loss": 0.376,
"step": 1950
},
{
"epoch": 6.071636011616651,
"grad_norm": 0.3046875,
"learning_rate": 8.891454965357969e-05,
"loss": 0.3858,
"step": 1960
},
{
"epoch": 6.102613746369797,
"grad_norm": 0.30859375,
"learning_rate": 8.879907621247114e-05,
"loss": 0.3368,
"step": 1970
},
{
"epoch": 6.133591481122943,
"grad_norm": 0.41015625,
"learning_rate": 8.86836027713626e-05,
"loss": 0.4098,
"step": 1980
},
{
"epoch": 6.164569215876089,
"grad_norm": 0.322265625,
"learning_rate": 8.856812933025405e-05,
"loss": 0.3701,
"step": 1990
},
{
"epoch": 6.195546950629235,
"grad_norm": 0.3125,
"learning_rate": 8.84526558891455e-05,
"loss": 0.3528,
"step": 2000
},
{
"epoch": 6.195546950629235,
"eval_loss": 0.09939394146203995,
"eval_runtime": 145.9427,
"eval_samples_per_second": 10.278,
"eval_steps_per_second": 2.57,
"step": 2000
}
],
"logging_steps": 10,
"max_steps": 9660,
"num_input_tokens_seen": 0,
"num_train_epochs": 30,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.189290237341991e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}