chansung's picture
Model save
3a2eccc verified
raw
history blame
71.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.997590361445782,
"eval_steps": 500,
"global_step": 2070,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004819277108433735,
"grad_norm": 7.09375,
"learning_rate": 9.66183574879227e-07,
"loss": 3.0067,
"step": 1
},
{
"epoch": 0.024096385542168676,
"grad_norm": 6.625,
"learning_rate": 4.830917874396135e-06,
"loss": 3.0384,
"step": 5
},
{
"epoch": 0.04819277108433735,
"grad_norm": 4.65625,
"learning_rate": 9.66183574879227e-06,
"loss": 2.9932,
"step": 10
},
{
"epoch": 0.07228915662650602,
"grad_norm": 3.0625,
"learning_rate": 1.4492753623188407e-05,
"loss": 2.8805,
"step": 15
},
{
"epoch": 0.0963855421686747,
"grad_norm": 2.828125,
"learning_rate": 1.932367149758454e-05,
"loss": 2.7091,
"step": 20
},
{
"epoch": 0.12048192771084337,
"grad_norm": 2.265625,
"learning_rate": 2.4154589371980676e-05,
"loss": 2.5046,
"step": 25
},
{
"epoch": 0.14457831325301204,
"grad_norm": 1.359375,
"learning_rate": 2.8985507246376814e-05,
"loss": 2.3296,
"step": 30
},
{
"epoch": 0.1686746987951807,
"grad_norm": 1.53125,
"learning_rate": 3.381642512077295e-05,
"loss": 2.1499,
"step": 35
},
{
"epoch": 0.1927710843373494,
"grad_norm": 6.21875,
"learning_rate": 3.864734299516908e-05,
"loss": 1.9713,
"step": 40
},
{
"epoch": 0.21686746987951808,
"grad_norm": 1.2421875,
"learning_rate": 4.347826086956522e-05,
"loss": 1.8202,
"step": 45
},
{
"epoch": 0.24096385542168675,
"grad_norm": 0.65234375,
"learning_rate": 4.830917874396135e-05,
"loss": 1.6894,
"step": 50
},
{
"epoch": 0.26506024096385544,
"grad_norm": 0.58984375,
"learning_rate": 5.3140096618357496e-05,
"loss": 1.571,
"step": 55
},
{
"epoch": 0.2891566265060241,
"grad_norm": 0.52734375,
"learning_rate": 5.797101449275363e-05,
"loss": 1.4798,
"step": 60
},
{
"epoch": 0.3132530120481928,
"grad_norm": 0.4375,
"learning_rate": 6.280193236714976e-05,
"loss": 1.4004,
"step": 65
},
{
"epoch": 0.3373493975903614,
"grad_norm": 0.470703125,
"learning_rate": 6.76328502415459e-05,
"loss": 1.3436,
"step": 70
},
{
"epoch": 0.3614457831325301,
"grad_norm": 0.265625,
"learning_rate": 7.246376811594203e-05,
"loss": 1.2867,
"step": 75
},
{
"epoch": 0.3855421686746988,
"grad_norm": 0.2890625,
"learning_rate": 7.729468599033817e-05,
"loss": 1.2529,
"step": 80
},
{
"epoch": 0.40963855421686746,
"grad_norm": 0.404296875,
"learning_rate": 8.21256038647343e-05,
"loss": 1.215,
"step": 85
},
{
"epoch": 0.43373493975903615,
"grad_norm": 0.1796875,
"learning_rate": 8.695652173913044e-05,
"loss": 1.1938,
"step": 90
},
{
"epoch": 0.4578313253012048,
"grad_norm": 0.287109375,
"learning_rate": 9.178743961352657e-05,
"loss": 1.1765,
"step": 95
},
{
"epoch": 0.4819277108433735,
"grad_norm": 0.56640625,
"learning_rate": 9.66183574879227e-05,
"loss": 1.1637,
"step": 100
},
{
"epoch": 0.5060240963855421,
"grad_norm": 0.828125,
"learning_rate": 0.00010144927536231885,
"loss": 1.1525,
"step": 105
},
{
"epoch": 0.5301204819277109,
"grad_norm": 0.765625,
"learning_rate": 0.00010628019323671499,
"loss": 1.1378,
"step": 110
},
{
"epoch": 0.5542168674698795,
"grad_norm": 0.2431640625,
"learning_rate": 0.00011111111111111112,
"loss": 1.125,
"step": 115
},
{
"epoch": 0.5783132530120482,
"grad_norm": 0.375,
"learning_rate": 0.00011594202898550725,
"loss": 1.1077,
"step": 120
},
{
"epoch": 0.6024096385542169,
"grad_norm": 0.96484375,
"learning_rate": 0.00012077294685990339,
"loss": 1.1027,
"step": 125
},
{
"epoch": 0.6265060240963856,
"grad_norm": 0.359375,
"learning_rate": 0.00012560386473429953,
"loss": 1.1005,
"step": 130
},
{
"epoch": 0.6506024096385542,
"grad_norm": 0.515625,
"learning_rate": 0.00013043478260869567,
"loss": 1.0961,
"step": 135
},
{
"epoch": 0.6746987951807228,
"grad_norm": 0.8984375,
"learning_rate": 0.0001352657004830918,
"loss": 1.0835,
"step": 140
},
{
"epoch": 0.6987951807228916,
"grad_norm": 0.400390625,
"learning_rate": 0.00014009661835748792,
"loss": 1.0731,
"step": 145
},
{
"epoch": 0.7228915662650602,
"grad_norm": 0.404296875,
"learning_rate": 0.00014492753623188405,
"loss": 1.0655,
"step": 150
},
{
"epoch": 0.7469879518072289,
"grad_norm": 0.341796875,
"learning_rate": 0.0001497584541062802,
"loss": 1.064,
"step": 155
},
{
"epoch": 0.7710843373493976,
"grad_norm": 0.79296875,
"learning_rate": 0.00015458937198067633,
"loss": 1.0539,
"step": 160
},
{
"epoch": 0.7951807228915663,
"grad_norm": 0.87109375,
"learning_rate": 0.00015942028985507247,
"loss": 1.057,
"step": 165
},
{
"epoch": 0.8192771084337349,
"grad_norm": 1.046875,
"learning_rate": 0.0001642512077294686,
"loss": 1.052,
"step": 170
},
{
"epoch": 0.8433734939759037,
"grad_norm": 1.203125,
"learning_rate": 0.00016908212560386474,
"loss": 1.0539,
"step": 175
},
{
"epoch": 0.8674698795180723,
"grad_norm": 0.40625,
"learning_rate": 0.00017391304347826088,
"loss": 1.0393,
"step": 180
},
{
"epoch": 0.891566265060241,
"grad_norm": 0.416015625,
"learning_rate": 0.00017874396135265702,
"loss": 1.0354,
"step": 185
},
{
"epoch": 0.9156626506024096,
"grad_norm": 0.3984375,
"learning_rate": 0.00018357487922705313,
"loss": 1.0443,
"step": 190
},
{
"epoch": 0.9397590361445783,
"grad_norm": 0.27734375,
"learning_rate": 0.00018840579710144927,
"loss": 1.0303,
"step": 195
},
{
"epoch": 0.963855421686747,
"grad_norm": 0.4609375,
"learning_rate": 0.0001932367149758454,
"loss": 1.0281,
"step": 200
},
{
"epoch": 0.9879518072289156,
"grad_norm": 0.64453125,
"learning_rate": 0.00019806763285024154,
"loss": 1.0246,
"step": 205
},
{
"epoch": 0.9975903614457832,
"eval_loss": 2.4549527168273926,
"eval_runtime": 0.4905,
"eval_samples_per_second": 20.386,
"eval_steps_per_second": 2.039,
"step": 207
},
{
"epoch": 1.0120481927710843,
"grad_norm": 0.57421875,
"learning_rate": 0.00019999872036643513,
"loss": 1.0207,
"step": 210
},
{
"epoch": 1.036144578313253,
"grad_norm": 1.0859375,
"learning_rate": 0.00019999090050213636,
"loss": 1.0131,
"step": 215
},
{
"epoch": 1.0602409638554218,
"grad_norm": 0.53515625,
"learning_rate": 0.00019997597223631895,
"loss": 1.0098,
"step": 220
},
{
"epoch": 1.0843373493975903,
"grad_norm": 0.80078125,
"learning_rate": 0.00019995393663024054,
"loss": 1.0082,
"step": 225
},
{
"epoch": 1.108433734939759,
"grad_norm": 1.0625,
"learning_rate": 0.00019992479525042303,
"loss": 1.0136,
"step": 230
},
{
"epoch": 1.1325301204819278,
"grad_norm": 0.33984375,
"learning_rate": 0.0001998885501685412,
"loss": 1.004,
"step": 235
},
{
"epoch": 1.1566265060240963,
"grad_norm": 0.75390625,
"learning_rate": 0.00019984520396127553,
"loss": 1.0012,
"step": 240
},
{
"epoch": 1.180722891566265,
"grad_norm": 0.5234375,
"learning_rate": 0.0001997947597101288,
"loss": 0.9956,
"step": 245
},
{
"epoch": 1.2048192771084336,
"grad_norm": 0.3515625,
"learning_rate": 0.0001997372210012073,
"loss": 0.9968,
"step": 250
},
{
"epoch": 1.2289156626506024,
"grad_norm": 0.82421875,
"learning_rate": 0.0001996725919249657,
"loss": 0.997,
"step": 255
},
{
"epoch": 1.2530120481927711,
"grad_norm": 0.8125,
"learning_rate": 0.00019960087707591626,
"loss": 1.0023,
"step": 260
},
{
"epoch": 1.2771084337349397,
"grad_norm": 0.482421875,
"learning_rate": 0.00019952208155230234,
"loss": 0.9934,
"step": 265
},
{
"epoch": 1.3012048192771084,
"grad_norm": 0.53515625,
"learning_rate": 0.00019943621095573586,
"loss": 0.9971,
"step": 270
},
{
"epoch": 1.3253012048192772,
"grad_norm": 0.259765625,
"learning_rate": 0.00019934327139079915,
"loss": 0.9945,
"step": 275
},
{
"epoch": 1.3493975903614457,
"grad_norm": 0.341796875,
"learning_rate": 0.00019924326946461074,
"loss": 0.9864,
"step": 280
},
{
"epoch": 1.3734939759036144,
"grad_norm": 0.283203125,
"learning_rate": 0.0001991362122863561,
"loss": 0.9804,
"step": 285
},
{
"epoch": 1.3975903614457832,
"grad_norm": 0.447265625,
"learning_rate": 0.0001990221074667818,
"loss": 0.9826,
"step": 290
},
{
"epoch": 1.4216867469879517,
"grad_norm": 0.326171875,
"learning_rate": 0.00019890096311765465,
"loss": 0.9858,
"step": 295
},
{
"epoch": 1.4457831325301205,
"grad_norm": 0.45703125,
"learning_rate": 0.00019877278785118517,
"loss": 0.9808,
"step": 300
},
{
"epoch": 1.4698795180722892,
"grad_norm": 0.54296875,
"learning_rate": 0.00019863759077941504,
"loss": 0.9733,
"step": 305
},
{
"epoch": 1.4939759036144578,
"grad_norm": 0.328125,
"learning_rate": 0.00019849538151356955,
"loss": 0.9788,
"step": 310
},
{
"epoch": 1.5180722891566265,
"grad_norm": 0.474609375,
"learning_rate": 0.0001983461701633742,
"loss": 0.981,
"step": 315
},
{
"epoch": 1.5421686746987953,
"grad_norm": 0.318359375,
"learning_rate": 0.00019818996733633618,
"loss": 0.9806,
"step": 320
},
{
"epoch": 1.5662650602409638,
"grad_norm": 0.33984375,
"learning_rate": 0.00019802678413699006,
"loss": 0.9681,
"step": 325
},
{
"epoch": 1.5903614457831325,
"grad_norm": 0.287109375,
"learning_rate": 0.00019785663216610844,
"loss": 0.9758,
"step": 330
},
{
"epoch": 1.6144578313253013,
"grad_norm": 0.369140625,
"learning_rate": 0.0001976795235198773,
"loss": 0.9711,
"step": 335
},
{
"epoch": 1.6385542168674698,
"grad_norm": 0.3671875,
"learning_rate": 0.00019749547078903604,
"loss": 0.9666,
"step": 340
},
{
"epoch": 1.6626506024096386,
"grad_norm": 0.41015625,
"learning_rate": 0.00019730448705798239,
"loss": 0.9673,
"step": 345
},
{
"epoch": 1.6867469879518073,
"grad_norm": 0.25,
"learning_rate": 0.00019710658590384227,
"loss": 0.9631,
"step": 350
},
{
"epoch": 1.7108433734939759,
"grad_norm": 0.298828125,
"learning_rate": 0.00019690178139550443,
"loss": 0.9646,
"step": 355
},
{
"epoch": 1.7349397590361446,
"grad_norm": 0.287109375,
"learning_rate": 0.00019669008809262062,
"loss": 0.9699,
"step": 360
},
{
"epoch": 1.7590361445783134,
"grad_norm": 0.294921875,
"learning_rate": 0.00019647152104457013,
"loss": 0.9639,
"step": 365
},
{
"epoch": 1.783132530120482,
"grad_norm": 0.337890625,
"learning_rate": 0.00019624609578939027,
"loss": 0.9597,
"step": 370
},
{
"epoch": 1.8072289156626506,
"grad_norm": 0.349609375,
"learning_rate": 0.0001960138283526715,
"loss": 0.962,
"step": 375
},
{
"epoch": 1.8313253012048194,
"grad_norm": 0.74609375,
"learning_rate": 0.0001957747352464184,
"loss": 0.9628,
"step": 380
},
{
"epoch": 1.855421686746988,
"grad_norm": 0.33203125,
"learning_rate": 0.00019552883346787552,
"loss": 0.9582,
"step": 385
},
{
"epoch": 1.8795180722891565,
"grad_norm": 0.4296875,
"learning_rate": 0.0001952761404983194,
"loss": 0.9566,
"step": 390
},
{
"epoch": 1.9036144578313254,
"grad_norm": 0.31640625,
"learning_rate": 0.0001950166743018156,
"loss": 0.9614,
"step": 395
},
{
"epoch": 1.927710843373494,
"grad_norm": 0.28125,
"learning_rate": 0.00019475045332394153,
"loss": 0.9607,
"step": 400
},
{
"epoch": 1.9518072289156625,
"grad_norm": 0.3125,
"learning_rate": 0.00019447749649047542,
"loss": 0.9511,
"step": 405
},
{
"epoch": 1.9759036144578315,
"grad_norm": 0.384765625,
"learning_rate": 0.0001941978232060507,
"loss": 0.9516,
"step": 410
},
{
"epoch": 2.0,
"grad_norm": 0.27734375,
"learning_rate": 0.00019391145335277655,
"loss": 0.9556,
"step": 415
},
{
"epoch": 2.0,
"eval_loss": 2.453037977218628,
"eval_runtime": 0.4785,
"eval_samples_per_second": 20.897,
"eval_steps_per_second": 2.09,
"step": 415
},
{
"epoch": 2.0240963855421685,
"grad_norm": 0.373046875,
"learning_rate": 0.00019361840728882447,
"loss": 0.9377,
"step": 420
},
{
"epoch": 2.0481927710843375,
"grad_norm": 0.4609375,
"learning_rate": 0.00019331870584698093,
"loss": 0.9384,
"step": 425
},
{
"epoch": 2.072289156626506,
"grad_norm": 0.44921875,
"learning_rate": 0.00019301237033316659,
"loss": 0.9315,
"step": 430
},
{
"epoch": 2.0963855421686746,
"grad_norm": 0.26953125,
"learning_rate": 0.00019269942252492133,
"loss": 0.9328,
"step": 435
},
{
"epoch": 2.1204819277108435,
"grad_norm": 0.28515625,
"learning_rate": 0.0001923798846698564,
"loss": 0.9374,
"step": 440
},
{
"epoch": 2.144578313253012,
"grad_norm": 0.283203125,
"learning_rate": 0.00019205377948407258,
"loss": 0.9304,
"step": 445
},
{
"epoch": 2.1686746987951806,
"grad_norm": 0.4453125,
"learning_rate": 0.00019172113015054532,
"loss": 0.9319,
"step": 450
},
{
"epoch": 2.1927710843373496,
"grad_norm": 0.302734375,
"learning_rate": 0.00019138196031747681,
"loss": 0.9386,
"step": 455
},
{
"epoch": 2.216867469879518,
"grad_norm": 0.46484375,
"learning_rate": 0.0001910362940966147,
"loss": 0.9383,
"step": 460
},
{
"epoch": 2.2409638554216866,
"grad_norm": 0.470703125,
"learning_rate": 0.00019068415606153787,
"loss": 0.9369,
"step": 465
},
{
"epoch": 2.2650602409638556,
"grad_norm": 0.265625,
"learning_rate": 0.00019032557124590974,
"loss": 0.9336,
"step": 470
},
{
"epoch": 2.289156626506024,
"grad_norm": 0.29296875,
"learning_rate": 0.00018996056514169844,
"loss": 0.9292,
"step": 475
},
{
"epoch": 2.3132530120481927,
"grad_norm": 0.27734375,
"learning_rate": 0.0001895891636973646,
"loss": 0.9386,
"step": 480
},
{
"epoch": 2.337349397590361,
"grad_norm": 0.279296875,
"learning_rate": 0.00018921139331601667,
"loss": 0.9404,
"step": 485
},
{
"epoch": 2.36144578313253,
"grad_norm": 0.2734375,
"learning_rate": 0.00018882728085353392,
"loss": 0.9267,
"step": 490
},
{
"epoch": 2.3855421686746987,
"grad_norm": 0.34375,
"learning_rate": 0.00018843685361665723,
"loss": 0.9285,
"step": 495
},
{
"epoch": 2.4096385542168672,
"grad_norm": 0.255859375,
"learning_rate": 0.00018804013936104792,
"loss": 0.9396,
"step": 500
},
{
"epoch": 2.433734939759036,
"grad_norm": 0.30078125,
"learning_rate": 0.00018763716628931437,
"loss": 0.929,
"step": 505
},
{
"epoch": 2.4578313253012047,
"grad_norm": 0.2265625,
"learning_rate": 0.0001872279630490074,
"loss": 0.9277,
"step": 510
},
{
"epoch": 2.4819277108433733,
"grad_norm": 0.2275390625,
"learning_rate": 0.00018681255873058338,
"loss": 0.9293,
"step": 515
},
{
"epoch": 2.5060240963855422,
"grad_norm": 0.263671875,
"learning_rate": 0.00018639098286533644,
"loss": 0.9253,
"step": 520
},
{
"epoch": 2.5301204819277108,
"grad_norm": 0.349609375,
"learning_rate": 0.00018596326542329888,
"loss": 0.9231,
"step": 525
},
{
"epoch": 2.5542168674698793,
"grad_norm": 0.5390625,
"learning_rate": 0.00018552943681111067,
"loss": 0.9241,
"step": 530
},
{
"epoch": 2.5783132530120483,
"grad_norm": 0.279296875,
"learning_rate": 0.0001850895278698579,
"loss": 0.9234,
"step": 535
},
{
"epoch": 2.602409638554217,
"grad_norm": 0.361328125,
"learning_rate": 0.00018464356987288013,
"loss": 0.9284,
"step": 540
},
{
"epoch": 2.6265060240963853,
"grad_norm": 0.2431640625,
"learning_rate": 0.0001841915945235472,
"loss": 0.9247,
"step": 545
},
{
"epoch": 2.6506024096385543,
"grad_norm": 0.34765625,
"learning_rate": 0.00018373363395300554,
"loss": 0.9314,
"step": 550
},
{
"epoch": 2.674698795180723,
"grad_norm": 0.330078125,
"learning_rate": 0.0001832697207178938,
"loss": 0.9308,
"step": 555
},
{
"epoch": 2.6987951807228914,
"grad_norm": 0.49609375,
"learning_rate": 0.00018279988779802833,
"loss": 0.9275,
"step": 560
},
{
"epoch": 2.7228915662650603,
"grad_norm": 0.455078125,
"learning_rate": 0.00018232416859405895,
"loss": 0.9261,
"step": 565
},
{
"epoch": 2.746987951807229,
"grad_norm": 0.353515625,
"learning_rate": 0.00018184259692509406,
"loss": 0.925,
"step": 570
},
{
"epoch": 2.7710843373493974,
"grad_norm": 0.310546875,
"learning_rate": 0.00018135520702629675,
"loss": 0.9211,
"step": 575
},
{
"epoch": 2.7951807228915664,
"grad_norm": 0.234375,
"learning_rate": 0.00018086203354645089,
"loss": 0.9219,
"step": 580
},
{
"epoch": 2.819277108433735,
"grad_norm": 0.28125,
"learning_rate": 0.00018036311154549784,
"loss": 0.9304,
"step": 585
},
{
"epoch": 2.8433734939759034,
"grad_norm": 0.390625,
"learning_rate": 0.00017985847649204417,
"loss": 0.926,
"step": 590
},
{
"epoch": 2.8674698795180724,
"grad_norm": 0.275390625,
"learning_rate": 0.00017934816426084008,
"loss": 0.9136,
"step": 595
},
{
"epoch": 2.891566265060241,
"grad_norm": 0.25390625,
"learning_rate": 0.00017883221113022916,
"loss": 0.9189,
"step": 600
},
{
"epoch": 2.9156626506024095,
"grad_norm": 0.24609375,
"learning_rate": 0.0001783106537795692,
"loss": 0.9138,
"step": 605
},
{
"epoch": 2.9397590361445785,
"grad_norm": 0.44140625,
"learning_rate": 0.00017778352928662474,
"loss": 0.923,
"step": 610
},
{
"epoch": 2.963855421686747,
"grad_norm": 0.24609375,
"learning_rate": 0.0001772508751249311,
"loss": 0.9259,
"step": 615
},
{
"epoch": 2.9879518072289155,
"grad_norm": 0.36328125,
"learning_rate": 0.00017671272916113052,
"loss": 0.9114,
"step": 620
},
{
"epoch": 2.9975903614457833,
"eval_loss": 2.46407151222229,
"eval_runtime": 0.6669,
"eval_samples_per_second": 14.995,
"eval_steps_per_second": 1.5,
"step": 622
},
{
"epoch": 3.0120481927710845,
"grad_norm": 0.259765625,
"learning_rate": 0.00017616912965228001,
"loss": 0.9017,
"step": 625
},
{
"epoch": 3.036144578313253,
"grad_norm": 0.2412109375,
"learning_rate": 0.00017562011524313185,
"loss": 0.897,
"step": 630
},
{
"epoch": 3.0602409638554215,
"grad_norm": 0.28515625,
"learning_rate": 0.0001750657249633861,
"loss": 0.896,
"step": 635
},
{
"epoch": 3.0843373493975905,
"grad_norm": 0.271484375,
"learning_rate": 0.00017450599822491615,
"loss": 0.9036,
"step": 640
},
{
"epoch": 3.108433734939759,
"grad_norm": 0.279296875,
"learning_rate": 0.00017394097481896676,
"loss": 0.9018,
"step": 645
},
{
"epoch": 3.1325301204819276,
"grad_norm": 0.3046875,
"learning_rate": 0.00017337069491332537,
"loss": 0.8983,
"step": 650
},
{
"epoch": 3.1566265060240966,
"grad_norm": 0.255859375,
"learning_rate": 0.00017279519904946647,
"loss": 0.896,
"step": 655
},
{
"epoch": 3.180722891566265,
"grad_norm": 0.251953125,
"learning_rate": 0.0001722145281396697,
"loss": 0.907,
"step": 660
},
{
"epoch": 3.2048192771084336,
"grad_norm": 0.404296875,
"learning_rate": 0.00017162872346411102,
"loss": 0.8986,
"step": 665
},
{
"epoch": 3.2289156626506026,
"grad_norm": 0.302734375,
"learning_rate": 0.00017103782666792844,
"loss": 0.9046,
"step": 670
},
{
"epoch": 3.253012048192771,
"grad_norm": 0.2451171875,
"learning_rate": 0.00017044187975826124,
"loss": 0.9018,
"step": 675
},
{
"epoch": 3.2771084337349397,
"grad_norm": 0.380859375,
"learning_rate": 0.00016984092510126367,
"loss": 0.903,
"step": 680
},
{
"epoch": 3.3012048192771086,
"grad_norm": 0.2431640625,
"learning_rate": 0.0001692350054190932,
"loss": 0.9077,
"step": 685
},
{
"epoch": 3.325301204819277,
"grad_norm": 0.380859375,
"learning_rate": 0.0001686241637868734,
"loss": 0.9033,
"step": 690
},
{
"epoch": 3.3493975903614457,
"grad_norm": 0.25390625,
"learning_rate": 0.00016800844362963147,
"loss": 0.9051,
"step": 695
},
{
"epoch": 3.3734939759036147,
"grad_norm": 0.3203125,
"learning_rate": 0.00016738788871921152,
"loss": 0.8974,
"step": 700
},
{
"epoch": 3.397590361445783,
"grad_norm": 0.2314453125,
"learning_rate": 0.00016676254317116252,
"loss": 0.9016,
"step": 705
},
{
"epoch": 3.4216867469879517,
"grad_norm": 0.263671875,
"learning_rate": 0.0001661324514416022,
"loss": 0.9006,
"step": 710
},
{
"epoch": 3.4457831325301207,
"grad_norm": 0.376953125,
"learning_rate": 0.00016549765832405653,
"loss": 0.9005,
"step": 715
},
{
"epoch": 3.4698795180722892,
"grad_norm": 0.287109375,
"learning_rate": 0.0001648582089462756,
"loss": 0.9024,
"step": 720
},
{
"epoch": 3.4939759036144578,
"grad_norm": 0.3046875,
"learning_rate": 0.00016421414876702518,
"loss": 0.8996,
"step": 725
},
{
"epoch": 3.5180722891566267,
"grad_norm": 0.328125,
"learning_rate": 0.00016356552357285522,
"loss": 0.8988,
"step": 730
},
{
"epoch": 3.5421686746987953,
"grad_norm": 0.392578125,
"learning_rate": 0.0001629123794748447,
"loss": 0.8975,
"step": 735
},
{
"epoch": 3.566265060240964,
"grad_norm": 0.265625,
"learning_rate": 0.00016225476290532374,
"loss": 0.9,
"step": 740
},
{
"epoch": 3.5903614457831328,
"grad_norm": 0.27734375,
"learning_rate": 0.00016159272061457255,
"loss": 0.8948,
"step": 745
},
{
"epoch": 3.6144578313253013,
"grad_norm": 0.265625,
"learning_rate": 0.0001609262996674981,
"loss": 0.8854,
"step": 750
},
{
"epoch": 3.63855421686747,
"grad_norm": 0.244140625,
"learning_rate": 0.0001602555474402881,
"loss": 0.8981,
"step": 755
},
{
"epoch": 3.662650602409639,
"grad_norm": 0.2578125,
"learning_rate": 0.00015958051161704307,
"loss": 0.8997,
"step": 760
},
{
"epoch": 3.6867469879518073,
"grad_norm": 0.220703125,
"learning_rate": 0.00015890124018638638,
"loss": 0.8909,
"step": 765
},
{
"epoch": 3.710843373493976,
"grad_norm": 0.32421875,
"learning_rate": 0.00015821778143805296,
"loss": 0.8904,
"step": 770
},
{
"epoch": 3.734939759036145,
"grad_norm": 0.25390625,
"learning_rate": 0.00015753018395945598,
"loss": 0.896,
"step": 775
},
{
"epoch": 3.7590361445783134,
"grad_norm": 0.421875,
"learning_rate": 0.00015683849663223308,
"loss": 0.9004,
"step": 780
},
{
"epoch": 3.783132530120482,
"grad_norm": 0.298828125,
"learning_rate": 0.00015614276862877113,
"loss": 0.8979,
"step": 785
},
{
"epoch": 3.807228915662651,
"grad_norm": 0.353515625,
"learning_rate": 0.0001554430494087107,
"loss": 0.893,
"step": 790
},
{
"epoch": 3.8313253012048194,
"grad_norm": 0.40234375,
"learning_rate": 0.00015473938871542986,
"loss": 0.8977,
"step": 795
},
{
"epoch": 3.855421686746988,
"grad_norm": 0.2294921875,
"learning_rate": 0.00015403183657250788,
"loss": 0.8969,
"step": 800
},
{
"epoch": 3.8795180722891565,
"grad_norm": 0.291015625,
"learning_rate": 0.00015332044328016914,
"loss": 0.8921,
"step": 805
},
{
"epoch": 3.9036144578313254,
"grad_norm": 0.330078125,
"learning_rate": 0.00015260525941170712,
"loss": 0.8913,
"step": 810
},
{
"epoch": 3.927710843373494,
"grad_norm": 0.22265625,
"learning_rate": 0.00015188633580988926,
"loss": 0.896,
"step": 815
},
{
"epoch": 3.9518072289156625,
"grad_norm": 0.2265625,
"learning_rate": 0.00015116372358334233,
"loss": 0.892,
"step": 820
},
{
"epoch": 3.9759036144578315,
"grad_norm": 0.271484375,
"learning_rate": 0.00015043747410291945,
"loss": 0.8948,
"step": 825
},
{
"epoch": 4.0,
"grad_norm": 0.2451171875,
"learning_rate": 0.00014970763899804763,
"loss": 0.8927,
"step": 830
},
{
"epoch": 4.0,
"eval_loss": 2.4882054328918457,
"eval_runtime": 0.482,
"eval_samples_per_second": 20.748,
"eval_steps_per_second": 2.075,
"step": 830
},
{
"epoch": 4.024096385542169,
"grad_norm": 0.251953125,
"learning_rate": 0.0001489742701530578,
"loss": 0.8742,
"step": 835
},
{
"epoch": 4.048192771084337,
"grad_norm": 0.296875,
"learning_rate": 0.00014823741970349606,
"loss": 0.8702,
"step": 840
},
{
"epoch": 4.072289156626506,
"grad_norm": 0.234375,
"learning_rate": 0.0001474971400324177,
"loss": 0.8777,
"step": 845
},
{
"epoch": 4.096385542168675,
"grad_norm": 0.50390625,
"learning_rate": 0.00014675348376666278,
"loss": 0.8776,
"step": 850
},
{
"epoch": 4.120481927710843,
"grad_norm": 0.3125,
"learning_rate": 0.00014600650377311522,
"loss": 0.875,
"step": 855
},
{
"epoch": 4.144578313253012,
"grad_norm": 0.294921875,
"learning_rate": 0.00014525625315494435,
"loss": 0.8817,
"step": 860
},
{
"epoch": 4.168674698795181,
"grad_norm": 0.4140625,
"learning_rate": 0.00014450278524782986,
"loss": 0.8808,
"step": 865
},
{
"epoch": 4.192771084337349,
"grad_norm": 0.49609375,
"learning_rate": 0.00014374615361616985,
"loss": 0.8775,
"step": 870
},
{
"epoch": 4.216867469879518,
"grad_norm": 0.455078125,
"learning_rate": 0.00014298641204927342,
"loss": 0.8796,
"step": 875
},
{
"epoch": 4.240963855421687,
"grad_norm": 0.322265625,
"learning_rate": 0.0001422236145575362,
"loss": 0.8753,
"step": 880
},
{
"epoch": 4.265060240963855,
"grad_norm": 0.2578125,
"learning_rate": 0.00014145781536860122,
"loss": 0.8735,
"step": 885
},
{
"epoch": 4.289156626506024,
"grad_norm": 0.21484375,
"learning_rate": 0.00014068906892350343,
"loss": 0.8753,
"step": 890
},
{
"epoch": 4.313253012048193,
"grad_norm": 0.416015625,
"learning_rate": 0.0001399174298727998,
"loss": 0.8752,
"step": 895
},
{
"epoch": 4.337349397590361,
"grad_norm": 0.314453125,
"learning_rate": 0.00013914295307268396,
"loss": 0.8734,
"step": 900
},
{
"epoch": 4.36144578313253,
"grad_norm": 0.240234375,
"learning_rate": 0.00013836569358108647,
"loss": 0.8815,
"step": 905
},
{
"epoch": 4.385542168674699,
"grad_norm": 0.32421875,
"learning_rate": 0.00013758570665376086,
"loss": 0.8834,
"step": 910
},
{
"epoch": 4.409638554216867,
"grad_norm": 0.349609375,
"learning_rate": 0.00013680304774035538,
"loss": 0.8787,
"step": 915
},
{
"epoch": 4.433734939759036,
"grad_norm": 0.26171875,
"learning_rate": 0.00013601777248047105,
"loss": 0.8785,
"step": 920
},
{
"epoch": 4.457831325301205,
"grad_norm": 0.255859375,
"learning_rate": 0.0001352299366997062,
"loss": 0.8729,
"step": 925
},
{
"epoch": 4.481927710843373,
"grad_norm": 0.412109375,
"learning_rate": 0.0001344395964056878,
"loss": 0.8778,
"step": 930
},
{
"epoch": 4.506024096385542,
"grad_norm": 0.404296875,
"learning_rate": 0.00013364680778409,
"loss": 0.8816,
"step": 935
},
{
"epoch": 4.530120481927711,
"grad_norm": 0.283203125,
"learning_rate": 0.00013285162719463961,
"loss": 0.8762,
"step": 940
},
{
"epoch": 4.554216867469879,
"grad_norm": 0.27734375,
"learning_rate": 0.00013205411116710972,
"loss": 0.8776,
"step": 945
},
{
"epoch": 4.578313253012048,
"grad_norm": 0.33203125,
"learning_rate": 0.0001312543163973007,
"loss": 0.8674,
"step": 950
},
{
"epoch": 4.602409638554217,
"grad_norm": 0.33984375,
"learning_rate": 0.00013045229974300993,
"loss": 0.8759,
"step": 955
},
{
"epoch": 4.626506024096385,
"grad_norm": 0.47265625,
"learning_rate": 0.0001296481182199896,
"loss": 0.8727,
"step": 960
},
{
"epoch": 4.650602409638554,
"grad_norm": 0.2353515625,
"learning_rate": 0.00012884182899789343,
"loss": 0.8739,
"step": 965
},
{
"epoch": 4.674698795180722,
"grad_norm": 0.25,
"learning_rate": 0.00012803348939621252,
"loss": 0.874,
"step": 970
},
{
"epoch": 4.698795180722891,
"grad_norm": 0.236328125,
"learning_rate": 0.00012722315688020047,
"loss": 0.8745,
"step": 975
},
{
"epoch": 4.72289156626506,
"grad_norm": 0.2421875,
"learning_rate": 0.00012641088905678802,
"loss": 0.8738,
"step": 980
},
{
"epoch": 4.746987951807229,
"grad_norm": 0.23046875,
"learning_rate": 0.000125596743670488,
"loss": 0.8721,
"step": 985
},
{
"epoch": 4.771084337349397,
"grad_norm": 0.296875,
"learning_rate": 0.00012478077859929,
"loss": 0.8734,
"step": 990
},
{
"epoch": 4.795180722891566,
"grad_norm": 0.2431640625,
"learning_rate": 0.0001239630518505459,
"loss": 0.876,
"step": 995
},
{
"epoch": 4.8192771084337345,
"grad_norm": 0.279296875,
"learning_rate": 0.00012314362155684612,
"loss": 0.874,
"step": 1000
},
{
"epoch": 4.843373493975903,
"grad_norm": 0.29296875,
"learning_rate": 0.00012232254597188688,
"loss": 0.8752,
"step": 1005
},
{
"epoch": 4.867469879518072,
"grad_norm": 0.287109375,
"learning_rate": 0.00012149988346632894,
"loss": 0.8689,
"step": 1010
},
{
"epoch": 4.891566265060241,
"grad_norm": 0.2373046875,
"learning_rate": 0.00012067569252364809,
"loss": 0.8704,
"step": 1015
},
{
"epoch": 4.9156626506024095,
"grad_norm": 0.2236328125,
"learning_rate": 0.0001198500317359774,
"loss": 0.8785,
"step": 1020
},
{
"epoch": 4.9397590361445785,
"grad_norm": 0.25,
"learning_rate": 0.00011902295979994192,
"loss": 0.8732,
"step": 1025
},
{
"epoch": 4.9638554216867465,
"grad_norm": 0.2451171875,
"learning_rate": 0.00011819453551248592,
"loss": 0.8796,
"step": 1030
},
{
"epoch": 4.9879518072289155,
"grad_norm": 0.248046875,
"learning_rate": 0.00011736481776669306,
"loss": 0.8752,
"step": 1035
},
{
"epoch": 4.997590361445783,
"eval_loss": 2.508066177368164,
"eval_runtime": 0.5,
"eval_samples_per_second": 20.0,
"eval_steps_per_second": 2.0,
"step": 1037
},
{
"epoch": 5.0120481927710845,
"grad_norm": 0.27734375,
"learning_rate": 0.00011653386554759946,
"loss": 0.8612,
"step": 1040
},
{
"epoch": 5.036144578313253,
"grad_norm": 0.2216796875,
"learning_rate": 0.00011570173792800066,
"loss": 0.8559,
"step": 1045
},
{
"epoch": 5.0602409638554215,
"grad_norm": 0.228515625,
"learning_rate": 0.00011486849406425188,
"loss": 0.8507,
"step": 1050
},
{
"epoch": 5.0843373493975905,
"grad_norm": 0.3125,
"learning_rate": 0.00011403419319206284,
"loss": 0.8603,
"step": 1055
},
{
"epoch": 5.108433734939759,
"grad_norm": 0.26171875,
"learning_rate": 0.0001131988946222863,
"loss": 0.8592,
"step": 1060
},
{
"epoch": 5.132530120481928,
"grad_norm": 0.2333984375,
"learning_rate": 0.00011236265773670196,
"loss": 0.855,
"step": 1065
},
{
"epoch": 5.156626506024097,
"grad_norm": 0.234375,
"learning_rate": 0.00011152554198379484,
"loss": 0.8566,
"step": 1070
},
{
"epoch": 5.180722891566265,
"grad_norm": 0.25390625,
"learning_rate": 0.00011068760687452895,
"loss": 0.8521,
"step": 1075
},
{
"epoch": 5.204819277108434,
"grad_norm": 0.25390625,
"learning_rate": 0.00010984891197811687,
"loss": 0.8605,
"step": 1080
},
{
"epoch": 5.228915662650603,
"grad_norm": 0.2578125,
"learning_rate": 0.00010900951691778481,
"loss": 0.8623,
"step": 1085
},
{
"epoch": 5.253012048192771,
"grad_norm": 0.2265625,
"learning_rate": 0.00010816948136653386,
"loss": 0.8583,
"step": 1090
},
{
"epoch": 5.27710843373494,
"grad_norm": 0.2353515625,
"learning_rate": 0.000107328865042898,
"loss": 0.8571,
"step": 1095
},
{
"epoch": 5.301204819277109,
"grad_norm": 0.3125,
"learning_rate": 0.00010648772770669861,
"loss": 0.862,
"step": 1100
},
{
"epoch": 5.325301204819277,
"grad_norm": 0.244140625,
"learning_rate": 0.00010564612915479612,
"loss": 0.8531,
"step": 1105
},
{
"epoch": 5.349397590361446,
"grad_norm": 0.28125,
"learning_rate": 0.00010480412921683888,
"loss": 0.8646,
"step": 1110
},
{
"epoch": 5.373493975903615,
"grad_norm": 0.2734375,
"learning_rate": 0.00010396178775101014,
"loss": 0.858,
"step": 1115
},
{
"epoch": 5.397590361445783,
"grad_norm": 0.29296875,
"learning_rate": 0.00010311916463977242,
"loss": 0.863,
"step": 1120
},
{
"epoch": 5.421686746987952,
"grad_norm": 0.263671875,
"learning_rate": 0.00010227631978561056,
"loss": 0.8601,
"step": 1125
},
{
"epoch": 5.445783132530121,
"grad_norm": 0.2421875,
"learning_rate": 0.00010143331310677331,
"loss": 0.8566,
"step": 1130
},
{
"epoch": 5.469879518072289,
"grad_norm": 0.240234375,
"learning_rate": 0.00010059020453301345,
"loss": 0.8538,
"step": 1135
},
{
"epoch": 5.493975903614458,
"grad_norm": 0.263671875,
"learning_rate": 9.974705400132764e-05,
"loss": 0.8591,
"step": 1140
},
{
"epoch": 5.518072289156627,
"grad_norm": 0.2119140625,
"learning_rate": 9.890392145169531e-05,
"loss": 0.8576,
"step": 1145
},
{
"epoch": 5.542168674698795,
"grad_norm": 0.2392578125,
"learning_rate": 9.806086682281758e-05,
"loss": 0.8615,
"step": 1150
},
{
"epoch": 5.566265060240964,
"grad_norm": 0.291015625,
"learning_rate": 9.721795004785605e-05,
"loss": 0.8572,
"step": 1155
},
{
"epoch": 5.590361445783133,
"grad_norm": 0.283203125,
"learning_rate": 9.637523105017229e-05,
"loss": 0.8644,
"step": 1160
},
{
"epoch": 5.614457831325301,
"grad_norm": 0.2333984375,
"learning_rate": 9.553276973906786e-05,
"loss": 0.854,
"step": 1165
},
{
"epoch": 5.63855421686747,
"grad_norm": 0.2578125,
"learning_rate": 9.469062600552509e-05,
"loss": 0.8526,
"step": 1170
},
{
"epoch": 5.662650602409639,
"grad_norm": 0.2470703125,
"learning_rate": 9.384885971794961e-05,
"loss": 0.8563,
"step": 1175
},
{
"epoch": 5.686746987951807,
"grad_norm": 0.220703125,
"learning_rate": 9.300753071791434e-05,
"loss": 0.8614,
"step": 1180
},
{
"epoch": 5.710843373493976,
"grad_norm": 0.22265625,
"learning_rate": 9.216669881590515e-05,
"loss": 0.8633,
"step": 1185
},
{
"epoch": 5.734939759036145,
"grad_norm": 0.2255859375,
"learning_rate": 9.132642378706894e-05,
"loss": 0.8548,
"step": 1190
},
{
"epoch": 5.759036144578313,
"grad_norm": 0.2890625,
"learning_rate": 9.048676536696425e-05,
"loss": 0.8603,
"step": 1195
},
{
"epoch": 5.783132530120482,
"grad_norm": 0.251953125,
"learning_rate": 8.964778324731467e-05,
"loss": 0.8643,
"step": 1200
},
{
"epoch": 5.807228915662651,
"grad_norm": 0.330078125,
"learning_rate": 8.880953707176514e-05,
"loss": 0.8562,
"step": 1205
},
{
"epoch": 5.831325301204819,
"grad_norm": 0.25,
"learning_rate": 8.797208643164212e-05,
"loss": 0.8565,
"step": 1210
},
{
"epoch": 5.855421686746988,
"grad_norm": 0.234375,
"learning_rate": 8.713549086171691e-05,
"loss": 0.8566,
"step": 1215
},
{
"epoch": 5.879518072289157,
"grad_norm": 0.279296875,
"learning_rate": 8.629980983597358e-05,
"loss": 0.8596,
"step": 1220
},
{
"epoch": 5.903614457831325,
"grad_norm": 0.34375,
"learning_rate": 8.546510276338078e-05,
"loss": 0.8522,
"step": 1225
},
{
"epoch": 5.927710843373494,
"grad_norm": 0.263671875,
"learning_rate": 8.463142898366834e-05,
"loss": 0.8561,
"step": 1230
},
{
"epoch": 5.951807228915663,
"grad_norm": 0.275390625,
"learning_rate": 8.37988477631088e-05,
"loss": 0.8611,
"step": 1235
},
{
"epoch": 5.975903614457831,
"grad_norm": 0.267578125,
"learning_rate": 8.296741829030418e-05,
"loss": 0.8552,
"step": 1240
},
{
"epoch": 6.0,
"grad_norm": 0.248046875,
"learning_rate": 8.213719967197817e-05,
"loss": 0.8602,
"step": 1245
},
{
"epoch": 6.0,
"eval_loss": 2.5277345180511475,
"eval_runtime": 0.4824,
"eval_samples_per_second": 20.732,
"eval_steps_per_second": 2.073,
"step": 1245
},
{
"epoch": 6.024096385542169,
"grad_norm": 0.2431640625,
"learning_rate": 8.130825092877418e-05,
"loss": 0.8432,
"step": 1250
},
{
"epoch": 6.048192771084337,
"grad_norm": 0.2255859375,
"learning_rate": 8.04806309910597e-05,
"loss": 0.8387,
"step": 1255
},
{
"epoch": 6.072289156626506,
"grad_norm": 0.21484375,
"learning_rate": 7.965439869473664e-05,
"loss": 0.8463,
"step": 1260
},
{
"epoch": 6.096385542168675,
"grad_norm": 0.21875,
"learning_rate": 7.882961277705895e-05,
"loss": 0.8402,
"step": 1265
},
{
"epoch": 6.120481927710843,
"grad_norm": 0.2451171875,
"learning_rate": 7.800633187245673e-05,
"loss": 0.8472,
"step": 1270
},
{
"epoch": 6.144578313253012,
"grad_norm": 0.271484375,
"learning_rate": 7.718461450836804e-05,
"loss": 0.8457,
"step": 1275
},
{
"epoch": 6.168674698795181,
"grad_norm": 0.27734375,
"learning_rate": 7.636451910107806e-05,
"loss": 0.8381,
"step": 1280
},
{
"epoch": 6.192771084337349,
"grad_norm": 0.2275390625,
"learning_rate": 7.554610395156624e-05,
"loss": 0.8384,
"step": 1285
},
{
"epoch": 6.216867469879518,
"grad_norm": 0.2314453125,
"learning_rate": 7.472942724136174e-05,
"loss": 0.8468,
"step": 1290
},
{
"epoch": 6.240963855421687,
"grad_norm": 0.2275390625,
"learning_rate": 7.391454702840722e-05,
"loss": 0.8472,
"step": 1295
},
{
"epoch": 6.265060240963855,
"grad_norm": 0.251953125,
"learning_rate": 7.310152124293146e-05,
"loss": 0.8441,
"step": 1300
},
{
"epoch": 6.289156626506024,
"grad_norm": 0.251953125,
"learning_rate": 7.229040768333115e-05,
"loss": 0.8424,
"step": 1305
},
{
"epoch": 6.313253012048193,
"grad_norm": 0.2216796875,
"learning_rate": 7.14812640120618e-05,
"loss": 0.8377,
"step": 1310
},
{
"epoch": 6.337349397590361,
"grad_norm": 0.25390625,
"learning_rate": 7.067414775153871e-05,
"loss": 0.8428,
"step": 1315
},
{
"epoch": 6.36144578313253,
"grad_norm": 0.31640625,
"learning_rate": 6.986911628004753e-05,
"loss": 0.8411,
"step": 1320
},
{
"epoch": 6.385542168674699,
"grad_norm": 0.302734375,
"learning_rate": 6.906622682766526e-05,
"loss": 0.8451,
"step": 1325
},
{
"epoch": 6.409638554216867,
"grad_norm": 0.263671875,
"learning_rate": 6.826553647219175e-05,
"loss": 0.8468,
"step": 1330
},
{
"epoch": 6.433734939759036,
"grad_norm": 0.2294921875,
"learning_rate": 6.74671021350919e-05,
"loss": 0.8499,
"step": 1335
},
{
"epoch": 6.457831325301205,
"grad_norm": 0.234375,
"learning_rate": 6.667098057744927e-05,
"loss": 0.8447,
"step": 1340
},
{
"epoch": 6.481927710843373,
"grad_norm": 0.31640625,
"learning_rate": 6.587722839593073e-05,
"loss": 0.8462,
"step": 1345
},
{
"epoch": 6.506024096385542,
"grad_norm": 0.3125,
"learning_rate": 6.508590201876317e-05,
"loss": 0.8477,
"step": 1350
},
{
"epoch": 6.530120481927711,
"grad_norm": 0.2314453125,
"learning_rate": 6.429705770172168e-05,
"loss": 0.8473,
"step": 1355
},
{
"epoch": 6.554216867469879,
"grad_norm": 0.2333984375,
"learning_rate": 6.351075152413068e-05,
"loss": 0.8411,
"step": 1360
},
{
"epoch": 6.578313253012048,
"grad_norm": 0.2470703125,
"learning_rate": 6.272703938487694e-05,
"loss": 0.8514,
"step": 1365
},
{
"epoch": 6.602409638554217,
"grad_norm": 0.2177734375,
"learning_rate": 6.194597699843581e-05,
"loss": 0.8415,
"step": 1370
},
{
"epoch": 6.626506024096385,
"grad_norm": 0.2255859375,
"learning_rate": 6.116761989091042e-05,
"loss": 0.8429,
"step": 1375
},
{
"epoch": 6.650602409638554,
"grad_norm": 0.228515625,
"learning_rate": 6.039202339608432e-05,
"loss": 0.8435,
"step": 1380
},
{
"epoch": 6.674698795180722,
"grad_norm": 0.220703125,
"learning_rate": 5.961924265148777e-05,
"loss": 0.8455,
"step": 1385
},
{
"epoch": 6.698795180722891,
"grad_norm": 0.2255859375,
"learning_rate": 5.884933259447798e-05,
"loss": 0.8457,
"step": 1390
},
{
"epoch": 6.72289156626506,
"grad_norm": 0.2177734375,
"learning_rate": 5.8082347958333625e-05,
"loss": 0.8481,
"step": 1395
},
{
"epoch": 6.746987951807229,
"grad_norm": 0.298828125,
"learning_rate": 5.731834326836366e-05,
"loss": 0.8469,
"step": 1400
},
{
"epoch": 6.771084337349397,
"grad_norm": 0.21875,
"learning_rate": 5.6557372838031384e-05,
"loss": 0.8459,
"step": 1405
},
{
"epoch": 6.795180722891566,
"grad_norm": 0.2412109375,
"learning_rate": 5.579949076509305e-05,
"loss": 0.8455,
"step": 1410
},
{
"epoch": 6.8192771084337345,
"grad_norm": 0.2119140625,
"learning_rate": 5.5044750927752106e-05,
"loss": 0.8444,
"step": 1415
},
{
"epoch": 6.843373493975903,
"grad_norm": 0.251953125,
"learning_rate": 5.429320698082887e-05,
"loss": 0.8427,
"step": 1420
},
{
"epoch": 6.867469879518072,
"grad_norm": 0.2041015625,
"learning_rate": 5.354491235194635e-05,
"loss": 0.8466,
"step": 1425
},
{
"epoch": 6.891566265060241,
"grad_norm": 0.228515625,
"learning_rate": 5.279992023773195e-05,
"loss": 0.8419,
"step": 1430
},
{
"epoch": 6.9156626506024095,
"grad_norm": 0.232421875,
"learning_rate": 5.205828360003568e-05,
"loss": 0.8468,
"step": 1435
},
{
"epoch": 6.9397590361445785,
"grad_norm": 0.2236328125,
"learning_rate": 5.1320055162165115e-05,
"loss": 0.8435,
"step": 1440
},
{
"epoch": 6.9638554216867465,
"grad_norm": 0.2041015625,
"learning_rate": 5.0585287405137305e-05,
"loss": 0.8444,
"step": 1445
},
{
"epoch": 6.9879518072289155,
"grad_norm": 0.228515625,
"learning_rate": 4.9854032563947714e-05,
"loss": 0.8464,
"step": 1450
},
{
"epoch": 6.997590361445783,
"eval_loss": 2.5512688159942627,
"eval_runtime": 0.4955,
"eval_samples_per_second": 20.183,
"eval_steps_per_second": 2.018,
"step": 1452
},
{
"epoch": 7.0120481927710845,
"grad_norm": 0.20703125,
"learning_rate": 4.912634262385695e-05,
"loss": 0.8349,
"step": 1455
},
{
"epoch": 7.036144578313253,
"grad_norm": 0.2158203125,
"learning_rate": 4.8402269316695134e-05,
"loss": 0.8372,
"step": 1460
},
{
"epoch": 7.0602409638554215,
"grad_norm": 0.2158203125,
"learning_rate": 4.768186411718417e-05,
"loss": 0.8283,
"step": 1465
},
{
"epoch": 7.0843373493975905,
"grad_norm": 0.2255859375,
"learning_rate": 4.696517823927842e-05,
"loss": 0.842,
"step": 1470
},
{
"epoch": 7.108433734939759,
"grad_norm": 0.2138671875,
"learning_rate": 4.625226263252386e-05,
"loss": 0.8375,
"step": 1475
},
{
"epoch": 7.132530120481928,
"grad_norm": 0.2197265625,
"learning_rate": 4.554316797843609e-05,
"loss": 0.8257,
"step": 1480
},
{
"epoch": 7.156626506024097,
"grad_norm": 0.2255859375,
"learning_rate": 4.483794468689728e-05,
"loss": 0.8347,
"step": 1485
},
{
"epoch": 7.180722891566265,
"grad_norm": 0.2314453125,
"learning_rate": 4.413664289257265e-05,
"loss": 0.8354,
"step": 1490
},
{
"epoch": 7.204819277108434,
"grad_norm": 0.2177734375,
"learning_rate": 4.343931245134616e-05,
"loss": 0.8382,
"step": 1495
},
{
"epoch": 7.228915662650603,
"grad_norm": 0.21875,
"learning_rate": 4.274600293677647e-05,
"loss": 0.8359,
"step": 1500
},
{
"epoch": 7.253012048192771,
"grad_norm": 0.2109375,
"learning_rate": 4.2056763636572574e-05,
"loss": 0.8351,
"step": 1505
},
{
"epoch": 7.27710843373494,
"grad_norm": 0.2265625,
"learning_rate": 4.137164354908999e-05,
"loss": 0.8377,
"step": 1510
},
{
"epoch": 7.301204819277109,
"grad_norm": 0.2197265625,
"learning_rate": 4.069069137984731e-05,
"loss": 0.8313,
"step": 1515
},
{
"epoch": 7.325301204819277,
"grad_norm": 0.224609375,
"learning_rate": 4.001395553806391e-05,
"loss": 0.8382,
"step": 1520
},
{
"epoch": 7.349397590361446,
"grad_norm": 0.2431640625,
"learning_rate": 3.9341484133218366e-05,
"loss": 0.8368,
"step": 1525
},
{
"epoch": 7.373493975903615,
"grad_norm": 0.21484375,
"learning_rate": 3.8673324971628357e-05,
"loss": 0.8419,
"step": 1530
},
{
"epoch": 7.397590361445783,
"grad_norm": 0.212890625,
"learning_rate": 3.800952555305216e-05,
"loss": 0.8357,
"step": 1535
},
{
"epoch": 7.421686746987952,
"grad_norm": 0.2138671875,
"learning_rate": 3.7350133067311686e-05,
"loss": 0.8393,
"step": 1540
},
{
"epoch": 7.445783132530121,
"grad_norm": 0.2412109375,
"learning_rate": 3.669519439093801e-05,
"loss": 0.8319,
"step": 1545
},
{
"epoch": 7.469879518072289,
"grad_norm": 0.23828125,
"learning_rate": 3.604475608383858e-05,
"loss": 0.8358,
"step": 1550
},
{
"epoch": 7.493975903614458,
"grad_norm": 0.212890625,
"learning_rate": 3.539886438598756e-05,
"loss": 0.8369,
"step": 1555
},
{
"epoch": 7.518072289156627,
"grad_norm": 0.2158203125,
"learning_rate": 3.475756521413839e-05,
"loss": 0.8355,
"step": 1560
},
{
"epoch": 7.542168674698795,
"grad_norm": 0.212890625,
"learning_rate": 3.412090415855963e-05,
"loss": 0.8374,
"step": 1565
},
{
"epoch": 7.566265060240964,
"grad_norm": 0.2265625,
"learning_rate": 3.348892647979389e-05,
"loss": 0.8353,
"step": 1570
},
{
"epoch": 7.590361445783133,
"grad_norm": 0.2333984375,
"learning_rate": 3.2861677105440336e-05,
"loss": 0.8368,
"step": 1575
},
{
"epoch": 7.614457831325301,
"grad_norm": 0.2119140625,
"learning_rate": 3.223920062696052e-05,
"loss": 0.8315,
"step": 1580
},
{
"epoch": 7.63855421686747,
"grad_norm": 0.212890625,
"learning_rate": 3.1621541296508695e-05,
"loss": 0.8373,
"step": 1585
},
{
"epoch": 7.662650602409639,
"grad_norm": 0.21484375,
"learning_rate": 3.100874302378559e-05,
"loss": 0.8315,
"step": 1590
},
{
"epoch": 7.686746987951807,
"grad_norm": 0.208984375,
"learning_rate": 3.0400849372917073e-05,
"loss": 0.839,
"step": 1595
},
{
"epoch": 7.710843373493976,
"grad_norm": 0.2080078125,
"learning_rate": 2.979790355935703e-05,
"loss": 0.8368,
"step": 1600
},
{
"epoch": 7.734939759036145,
"grad_norm": 0.205078125,
"learning_rate": 2.919994844681524e-05,
"loss": 0.8348,
"step": 1605
},
{
"epoch": 7.759036144578313,
"grad_norm": 0.205078125,
"learning_rate": 2.8607026544210114e-05,
"loss": 0.8323,
"step": 1610
},
{
"epoch": 7.783132530120482,
"grad_norm": 0.2197265625,
"learning_rate": 2.801918000264665e-05,
"loss": 0.8344,
"step": 1615
},
{
"epoch": 7.807228915662651,
"grad_norm": 0.22265625,
"learning_rate": 2.7436450612420095e-05,
"loss": 0.8343,
"step": 1620
},
{
"epoch": 7.831325301204819,
"grad_norm": 0.2099609375,
"learning_rate": 2.6858879800044866e-05,
"loss": 0.8329,
"step": 1625
},
{
"epoch": 7.855421686746988,
"grad_norm": 0.2060546875,
"learning_rate": 2.6286508625309624e-05,
"loss": 0.8354,
"step": 1630
},
{
"epoch": 7.879518072289157,
"grad_norm": 0.208984375,
"learning_rate": 2.57193777783582e-05,
"loss": 0.8399,
"step": 1635
},
{
"epoch": 7.903614457831325,
"grad_norm": 0.2109375,
"learning_rate": 2.515752757679707e-05,
"loss": 0.8325,
"step": 1640
},
{
"epoch": 7.927710843373494,
"grad_norm": 0.2197265625,
"learning_rate": 2.4600997962828987e-05,
"loss": 0.8338,
"step": 1645
},
{
"epoch": 7.951807228915663,
"grad_norm": 0.2109375,
"learning_rate": 2.404982850041363e-05,
"loss": 0.8371,
"step": 1650
},
{
"epoch": 7.975903614457831,
"grad_norm": 0.205078125,
"learning_rate": 2.3504058372454884e-05,
"loss": 0.8319,
"step": 1655
},
{
"epoch": 8.0,
"grad_norm": 0.2265625,
"learning_rate": 2.2963726378015327e-05,
"loss": 0.8353,
"step": 1660
},
{
"epoch": 8.0,
"eval_loss": 2.5614659786224365,
"eval_runtime": 0.4882,
"eval_samples_per_second": 20.483,
"eval_steps_per_second": 2.048,
"step": 1660
},
{
"epoch": 8.024096385542169,
"grad_norm": 0.228515625,
"learning_rate": 2.242887092955801e-05,
"loss": 0.8313,
"step": 1665
},
{
"epoch": 8.048192771084338,
"grad_norm": 0.2275390625,
"learning_rate": 2.189953005021569e-05,
"loss": 0.8278,
"step": 1670
},
{
"epoch": 8.072289156626505,
"grad_norm": 0.22265625,
"learning_rate": 2.1375741371087677e-05,
"loss": 0.8321,
"step": 1675
},
{
"epoch": 8.096385542168674,
"grad_norm": 0.2177734375,
"learning_rate": 2.085754212856471e-05,
"loss": 0.8368,
"step": 1680
},
{
"epoch": 8.120481927710843,
"grad_norm": 0.21875,
"learning_rate": 2.0344969161681792e-05,
"loss": 0.8258,
"step": 1685
},
{
"epoch": 8.144578313253012,
"grad_norm": 0.2236328125,
"learning_rate": 1.983805890949927e-05,
"loss": 0.8273,
"step": 1690
},
{
"epoch": 8.168674698795181,
"grad_norm": 0.212890625,
"learning_rate": 1.9336847408512328e-05,
"loss": 0.8272,
"step": 1695
},
{
"epoch": 8.19277108433735,
"grad_norm": 0.203125,
"learning_rate": 1.884137029008921e-05,
"loss": 0.8334,
"step": 1700
},
{
"epoch": 8.216867469879517,
"grad_norm": 0.20703125,
"learning_rate": 1.8351662777938127e-05,
"loss": 0.8337,
"step": 1705
},
{
"epoch": 8.240963855421686,
"grad_norm": 0.2109375,
"learning_rate": 1.7867759685603114e-05,
"loss": 0.8306,
"step": 1710
},
{
"epoch": 8.265060240963855,
"grad_norm": 0.2138671875,
"learning_rate": 1.738969541398926e-05,
"loss": 0.8306,
"step": 1715
},
{
"epoch": 8.289156626506024,
"grad_norm": 0.2197265625,
"learning_rate": 1.691750394891707e-05,
"loss": 0.8299,
"step": 1720
},
{
"epoch": 8.313253012048193,
"grad_norm": 0.205078125,
"learning_rate": 1.6451218858706374e-05,
"loss": 0.829,
"step": 1725
},
{
"epoch": 8.337349397590362,
"grad_norm": 0.2080078125,
"learning_rate": 1.59908732917899e-05,
"loss": 0.831,
"step": 1730
},
{
"epoch": 8.36144578313253,
"grad_norm": 0.2197265625,
"learning_rate": 1.5536499974356866e-05,
"loss": 0.8269,
"step": 1735
},
{
"epoch": 8.385542168674698,
"grad_norm": 0.20703125,
"learning_rate": 1.5088131208026367e-05,
"loss": 0.834,
"step": 1740
},
{
"epoch": 8.409638554216867,
"grad_norm": 0.2060546875,
"learning_rate": 1.4645798867551008e-05,
"loss": 0.8324,
"step": 1745
},
{
"epoch": 8.433734939759036,
"grad_norm": 0.2060546875,
"learning_rate": 1.4209534398551016e-05,
"loss": 0.8325,
"step": 1750
},
{
"epoch": 8.457831325301205,
"grad_norm": 0.2060546875,
"learning_rate": 1.3779368815278647e-05,
"loss": 0.8392,
"step": 1755
},
{
"epoch": 8.481927710843374,
"grad_norm": 0.2001953125,
"learning_rate": 1.335533269841347e-05,
"loss": 0.8284,
"step": 1760
},
{
"epoch": 8.506024096385541,
"grad_norm": 0.203125,
"learning_rate": 1.2937456192888309e-05,
"loss": 0.8332,
"step": 1765
},
{
"epoch": 8.53012048192771,
"grad_norm": 0.224609375,
"learning_rate": 1.252576900574618e-05,
"loss": 0.8269,
"step": 1770
},
{
"epoch": 8.55421686746988,
"grad_norm": 0.224609375,
"learning_rate": 1.2120300404028507e-05,
"loss": 0.8346,
"step": 1775
},
{
"epoch": 8.578313253012048,
"grad_norm": 0.20703125,
"learning_rate": 1.1721079212694452e-05,
"loss": 0.8331,
"step": 1780
},
{
"epoch": 8.602409638554217,
"grad_norm": 0.203125,
"learning_rate": 1.1328133812571784e-05,
"loss": 0.8324,
"step": 1785
},
{
"epoch": 8.626506024096386,
"grad_norm": 0.2060546875,
"learning_rate": 1.0941492138339183e-05,
"loss": 0.8285,
"step": 1790
},
{
"epoch": 8.650602409638553,
"grad_norm": 0.2099609375,
"learning_rate": 1.0561181676540444e-05,
"loss": 0.838,
"step": 1795
},
{
"epoch": 8.674698795180722,
"grad_norm": 0.203125,
"learning_rate": 1.01872294636304e-05,
"loss": 0.827,
"step": 1800
},
{
"epoch": 8.698795180722891,
"grad_norm": 0.208984375,
"learning_rate": 9.81966208405285e-06,
"loss": 0.8331,
"step": 1805
},
{
"epoch": 8.72289156626506,
"grad_norm": 0.2119140625,
"learning_rate": 9.458505668350759e-06,
"loss": 0.8304,
"step": 1810
},
{
"epoch": 8.74698795180723,
"grad_norm": 0.2080078125,
"learning_rate": 9.103785891308547e-06,
"loss": 0.8333,
"step": 1815
},
{
"epoch": 8.771084337349398,
"grad_norm": 0.205078125,
"learning_rate": 8.755527970126853e-06,
"loss": 0.8325,
"step": 1820
},
{
"epoch": 8.795180722891565,
"grad_norm": 0.21484375,
"learning_rate": 8.413756662629879e-06,
"loss": 0.8326,
"step": 1825
},
{
"epoch": 8.819277108433734,
"grad_norm": 0.208984375,
"learning_rate": 8.07849626550531e-06,
"loss": 0.8315,
"step": 1830
},
{
"epoch": 8.843373493975903,
"grad_norm": 0.2099609375,
"learning_rate": 7.74977061257709e-06,
"loss": 0.833,
"step": 1835
},
{
"epoch": 8.867469879518072,
"grad_norm": 0.2041015625,
"learning_rate": 7.427603073110967e-06,
"loss": 0.8299,
"step": 1840
},
{
"epoch": 8.891566265060241,
"grad_norm": 0.2080078125,
"learning_rate": 7.1120165501533e-06,
"loss": 0.8282,
"step": 1845
},
{
"epoch": 8.91566265060241,
"grad_norm": 0.2041015625,
"learning_rate": 6.803033478902765e-06,
"loss": 0.8267,
"step": 1850
},
{
"epoch": 8.939759036144578,
"grad_norm": 0.2060546875,
"learning_rate": 6.500675825115454e-06,
"loss": 0.83,
"step": 1855
},
{
"epoch": 8.963855421686747,
"grad_norm": 0.2041015625,
"learning_rate": 6.204965083543368e-06,
"loss": 0.8267,
"step": 1860
},
{
"epoch": 8.987951807228916,
"grad_norm": 0.2021484375,
"learning_rate": 5.915922276406249e-06,
"loss": 0.8267,
"step": 1865
},
{
"epoch": 8.997590361445782,
"eval_loss": 2.5673654079437256,
"eval_runtime": 0.7609,
"eval_samples_per_second": 13.142,
"eval_steps_per_second": 1.314,
"step": 1867
},
{
"epoch": 9.012048192771084,
"grad_norm": 0.197265625,
"learning_rate": 5.633567951897145e-06,
"loss": 0.8245,
"step": 1870
},
{
"epoch": 9.036144578313253,
"grad_norm": 0.205078125,
"learning_rate": 5.357922182721687e-06,
"loss": 0.8271,
"step": 1875
},
{
"epoch": 9.060240963855422,
"grad_norm": 0.2109375,
"learning_rate": 5.08900456467103e-06,
"loss": 0.8373,
"step": 1880
},
{
"epoch": 9.08433734939759,
"grad_norm": 0.20703125,
"learning_rate": 4.826834215228826e-06,
"loss": 0.8242,
"step": 1885
},
{
"epoch": 9.108433734939759,
"grad_norm": 0.212890625,
"learning_rate": 4.5714297722121106e-06,
"loss": 0.8283,
"step": 1890
},
{
"epoch": 9.132530120481928,
"grad_norm": 0.19921875,
"learning_rate": 4.322809392446392e-06,
"loss": 0.8313,
"step": 1895
},
{
"epoch": 9.156626506024097,
"grad_norm": 0.208984375,
"learning_rate": 4.080990750474778e-06,
"loss": 0.8287,
"step": 1900
},
{
"epoch": 9.180722891566266,
"grad_norm": 0.2060546875,
"learning_rate": 3.84599103730161e-06,
"loss": 0.8265,
"step": 1905
},
{
"epoch": 9.204819277108435,
"grad_norm": 0.2021484375,
"learning_rate": 3.617826959170256e-06,
"loss": 0.8307,
"step": 1910
},
{
"epoch": 9.228915662650602,
"grad_norm": 0.2119140625,
"learning_rate": 3.3965147363754555e-06,
"loss": 0.8343,
"step": 1915
},
{
"epoch": 9.25301204819277,
"grad_norm": 0.2119140625,
"learning_rate": 3.182070102110257e-06,
"loss": 0.8313,
"step": 1920
},
{
"epoch": 9.27710843373494,
"grad_norm": 0.203125,
"learning_rate": 2.974508301347534e-06,
"loss": 0.8319,
"step": 1925
},
{
"epoch": 9.301204819277109,
"grad_norm": 0.2041015625,
"learning_rate": 2.7738440897561723e-06,
"loss": 0.8307,
"step": 1930
},
{
"epoch": 9.325301204819278,
"grad_norm": 0.2060546875,
"learning_rate": 2.580091732652101e-06,
"loss": 0.8316,
"step": 1935
},
{
"epoch": 9.349397590361447,
"grad_norm": 0.205078125,
"learning_rate": 2.3932650039841687e-06,
"loss": 0.8309,
"step": 1940
},
{
"epoch": 9.373493975903614,
"grad_norm": 0.20703125,
"learning_rate": 2.213377185354959e-06,
"loss": 0.8335,
"step": 1945
},
{
"epoch": 9.397590361445783,
"grad_norm": 0.2060546875,
"learning_rate": 2.0404410650765817e-06,
"loss": 0.8307,
"step": 1950
},
{
"epoch": 9.421686746987952,
"grad_norm": 0.2021484375,
"learning_rate": 1.874468937261531e-06,
"loss": 0.8301,
"step": 1955
},
{
"epoch": 9.44578313253012,
"grad_norm": 0.20703125,
"learning_rate": 1.71547260094872e-06,
"loss": 0.8262,
"step": 1960
},
{
"epoch": 9.46987951807229,
"grad_norm": 0.2294921875,
"learning_rate": 1.5634633592646609e-06,
"loss": 0.8284,
"step": 1965
},
{
"epoch": 9.493975903614459,
"grad_norm": 0.205078125,
"learning_rate": 1.4184520186199202e-06,
"loss": 0.8309,
"step": 1970
},
{
"epoch": 9.518072289156626,
"grad_norm": 0.2041015625,
"learning_rate": 1.2804488879408993e-06,
"loss": 0.8288,
"step": 1975
},
{
"epoch": 9.542168674698795,
"grad_norm": 0.2021484375,
"learning_rate": 1.1494637779369766e-06,
"loss": 0.8309,
"step": 1980
},
{
"epoch": 9.566265060240964,
"grad_norm": 0.2021484375,
"learning_rate": 1.0255060004030093e-06,
"loss": 0.8251,
"step": 1985
},
{
"epoch": 9.590361445783133,
"grad_norm": 0.2119140625,
"learning_rate": 9.085843675574079e-07,
"loss": 0.8351,
"step": 1990
},
{
"epoch": 9.614457831325302,
"grad_norm": 0.201171875,
"learning_rate": 7.987071914156596e-07,
"loss": 0.8259,
"step": 1995
},
{
"epoch": 9.638554216867469,
"grad_norm": 0.2099609375,
"learning_rate": 6.958822831994005e-07,
"loss": 0.8283,
"step": 2000
},
{
"epoch": 9.684337349397591,
"grad_norm": 0.2099609375,
"learning_rate": 6.001169527811268e-07,
"loss": 0.8287,
"step": 2005
},
{
"epoch": 9.708433734939758,
"grad_norm": 0.20703125,
"learning_rate": 5.114180081645214e-07,
"loss": 0.8321,
"step": 2010
},
{
"epoch": 9.732530120481927,
"grad_norm": 0.19921875,
"learning_rate": 4.2979175500050817e-07,
"loss": 0.8297,
"step": 2015
},
{
"epoch": 9.756626506024096,
"grad_norm": 0.228515625,
"learning_rate": 3.552439961389431e-07,
"loss": 0.8235,
"step": 2020
},
{
"epoch": 9.780722891566265,
"grad_norm": 0.203125,
"learning_rate": 2.877800312160783e-07,
"loss": 0.8302,
"step": 2025
},
{
"epoch": 9.804819277108434,
"grad_norm": 0.2109375,
"learning_rate": 2.274046562778409e-07,
"loss": 0.8331,
"step": 2030
},
{
"epoch": 9.828915662650603,
"grad_norm": 0.2119140625,
"learning_rate": 1.7412216343885014e-07,
"loss": 0.8281,
"step": 2035
},
{
"epoch": 9.85301204819277,
"grad_norm": 0.2080078125,
"learning_rate": 1.2793634057732818e-07,
"loss": 0.8321,
"step": 2040
},
{
"epoch": 9.87710843373494,
"grad_norm": 0.212890625,
"learning_rate": 8.885047106578227e-08,
"loss": 0.832,
"step": 2045
},
{
"epoch": 9.901204819277108,
"grad_norm": 0.2080078125,
"learning_rate": 5.6867333537580226e-08,
"loss": 0.8308,
"step": 2050
},
{
"epoch": 9.925301204819277,
"grad_norm": 0.2001953125,
"learning_rate": 3.1989201689452967e-08,
"loss": 0.8283,
"step": 2055
},
{
"epoch": 9.949397590361446,
"grad_norm": 0.2080078125,
"learning_rate": 1.4217844119857048e-08,
"loss": 0.8307,
"step": 2060
},
{
"epoch": 9.973493975903615,
"grad_norm": 0.2080078125,
"learning_rate": 3.554524203175369e-09,
"loss": 0.8252,
"step": 2065
},
{
"epoch": 9.997590361445782,
"grad_norm": 0.203125,
"learning_rate": 0.0,
"loss": 0.8289,
"step": 2070
},
{
"epoch": 9.997590361445782,
"eval_loss": 2.5681488513946533,
"eval_runtime": 0.4835,
"eval_samples_per_second": 20.683,
"eval_steps_per_second": 2.068,
"step": 2070
},
{
"epoch": 9.997590361445782,
"step": 2070,
"total_flos": 3.290190024938619e+18,
"train_loss": 0.02805145143886695,
"train_runtime": 534.5593,
"train_samples_per_second": 495.96,
"train_steps_per_second": 3.872
}
],
"logging_steps": 5,
"max_steps": 2070,
"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": 3.290190024938619e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}