gemma2b-summarize-gpt4o-64k / trainer_state.json
chansung's picture
Model save
9ca2da2 verified
raw
history blame
51.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 1460,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00684931506849315,
"grad_norm": 4.9375,
"learning_rate": 1.3698630136986302e-06,
"loss": 3.0017,
"step": 1
},
{
"epoch": 0.03424657534246575,
"grad_norm": 4.5625,
"learning_rate": 6.849315068493151e-06,
"loss": 3.0717,
"step": 5
},
{
"epoch": 0.0684931506849315,
"grad_norm": 5.40625,
"learning_rate": 1.3698630136986302e-05,
"loss": 3.002,
"step": 10
},
{
"epoch": 0.10273972602739725,
"grad_norm": 2.640625,
"learning_rate": 2.0547945205479453e-05,
"loss": 2.8518,
"step": 15
},
{
"epoch": 0.136986301369863,
"grad_norm": 1.734375,
"learning_rate": 2.7397260273972603e-05,
"loss": 2.6474,
"step": 20
},
{
"epoch": 0.17123287671232876,
"grad_norm": 1.59375,
"learning_rate": 3.424657534246575e-05,
"loss": 2.4285,
"step": 25
},
{
"epoch": 0.2054794520547945,
"grad_norm": 75.0,
"learning_rate": 4.1095890410958905e-05,
"loss": 2.2533,
"step": 30
},
{
"epoch": 0.23972602739726026,
"grad_norm": 1.84375,
"learning_rate": 4.794520547945205e-05,
"loss": 2.0584,
"step": 35
},
{
"epoch": 0.273972602739726,
"grad_norm": 0.80859375,
"learning_rate": 5.479452054794521e-05,
"loss": 1.9038,
"step": 40
},
{
"epoch": 0.3082191780821918,
"grad_norm": 0.65625,
"learning_rate": 6.164383561643835e-05,
"loss": 1.797,
"step": 45
},
{
"epoch": 0.3424657534246575,
"grad_norm": 0.5859375,
"learning_rate": 6.84931506849315e-05,
"loss": 1.6455,
"step": 50
},
{
"epoch": 0.3767123287671233,
"grad_norm": 0.40625,
"learning_rate": 7.534246575342466e-05,
"loss": 1.5458,
"step": 55
},
{
"epoch": 0.410958904109589,
"grad_norm": 0.345703125,
"learning_rate": 8.219178082191781e-05,
"loss": 1.4771,
"step": 60
},
{
"epoch": 0.4452054794520548,
"grad_norm": 0.38671875,
"learning_rate": 8.904109589041096e-05,
"loss": 1.4206,
"step": 65
},
{
"epoch": 0.4794520547945205,
"grad_norm": 0.546875,
"learning_rate": 9.58904109589041e-05,
"loss": 1.3804,
"step": 70
},
{
"epoch": 0.5136986301369864,
"grad_norm": 0.353515625,
"learning_rate": 0.00010273972602739728,
"loss": 1.3471,
"step": 75
},
{
"epoch": 0.547945205479452,
"grad_norm": 0.259765625,
"learning_rate": 0.00010958904109589041,
"loss": 1.3165,
"step": 80
},
{
"epoch": 0.5821917808219178,
"grad_norm": 0.53515625,
"learning_rate": 0.00011643835616438356,
"loss": 1.2853,
"step": 85
},
{
"epoch": 0.6164383561643836,
"grad_norm": 0.3828125,
"learning_rate": 0.0001232876712328767,
"loss": 1.2863,
"step": 90
},
{
"epoch": 0.6506849315068494,
"grad_norm": 0.8828125,
"learning_rate": 0.00013013698630136988,
"loss": 1.267,
"step": 95
},
{
"epoch": 0.684931506849315,
"grad_norm": 0.74609375,
"learning_rate": 0.000136986301369863,
"loss": 1.2466,
"step": 100
},
{
"epoch": 0.7191780821917808,
"grad_norm": 1.0,
"learning_rate": 0.00014383561643835618,
"loss": 1.2444,
"step": 105
},
{
"epoch": 0.7534246575342466,
"grad_norm": 0.3671875,
"learning_rate": 0.00015068493150684933,
"loss": 1.2283,
"step": 110
},
{
"epoch": 0.7876712328767124,
"grad_norm": 0.3125,
"learning_rate": 0.00015753424657534247,
"loss": 1.2153,
"step": 115
},
{
"epoch": 0.821917808219178,
"grad_norm": 0.3984375,
"learning_rate": 0.00016438356164383562,
"loss": 1.2106,
"step": 120
},
{
"epoch": 0.8561643835616438,
"grad_norm": 0.330078125,
"learning_rate": 0.00017123287671232877,
"loss": 1.1939,
"step": 125
},
{
"epoch": 0.8904109589041096,
"grad_norm": 0.57421875,
"learning_rate": 0.00017808219178082192,
"loss": 1.1965,
"step": 130
},
{
"epoch": 0.9246575342465754,
"grad_norm": 0.515625,
"learning_rate": 0.0001849315068493151,
"loss": 1.1839,
"step": 135
},
{
"epoch": 0.958904109589041,
"grad_norm": 1.4453125,
"learning_rate": 0.0001917808219178082,
"loss": 1.1983,
"step": 140
},
{
"epoch": 0.9931506849315068,
"grad_norm": 0.470703125,
"learning_rate": 0.00019863013698630139,
"loss": 1.1808,
"step": 145
},
{
"epoch": 1.0,
"eval_loss": 2.487597942352295,
"eval_runtime": 0.541,
"eval_samples_per_second": 18.483,
"eval_steps_per_second": 1.848,
"step": 146
},
{
"epoch": 1.0273972602739727,
"grad_norm": 0.396484375,
"learning_rate": 0.00019999542705801296,
"loss": 1.1618,
"step": 150
},
{
"epoch": 1.0616438356164384,
"grad_norm": 0.8125,
"learning_rate": 0.00019997685019798912,
"loss": 1.1531,
"step": 155
},
{
"epoch": 1.095890410958904,
"grad_norm": 0.390625,
"learning_rate": 0.00019994398626371643,
"loss": 1.1517,
"step": 160
},
{
"epoch": 1.13013698630137,
"grad_norm": 0.333984375,
"learning_rate": 0.00019989683995157677,
"loss": 1.1322,
"step": 165
},
{
"epoch": 1.1643835616438356,
"grad_norm": 0.318359375,
"learning_rate": 0.0001998354179989585,
"loss": 1.1413,
"step": 170
},
{
"epoch": 1.1986301369863013,
"grad_norm": 0.37109375,
"learning_rate": 0.00019975972918329356,
"loss": 1.1275,
"step": 175
},
{
"epoch": 1.2328767123287672,
"grad_norm": 0.54296875,
"learning_rate": 0.00019966978432080316,
"loss": 1.1261,
"step": 180
},
{
"epoch": 1.2671232876712328,
"grad_norm": 0.43359375,
"learning_rate": 0.00019956559626495212,
"loss": 1.1384,
"step": 185
},
{
"epoch": 1.3013698630136985,
"grad_norm": 2.4375,
"learning_rate": 0.00019944717990461207,
"loss": 1.1376,
"step": 190
},
{
"epoch": 1.3356164383561644,
"grad_norm": 0.423828125,
"learning_rate": 0.00019931455216193382,
"loss": 1.1376,
"step": 195
},
{
"epoch": 1.36986301369863,
"grad_norm": 0.55078125,
"learning_rate": 0.000199167731989929,
"loss": 1.14,
"step": 200
},
{
"epoch": 1.404109589041096,
"grad_norm": 0.44140625,
"learning_rate": 0.00019900674036976173,
"loss": 1.1281,
"step": 205
},
{
"epoch": 1.4383561643835616,
"grad_norm": 0.63671875,
"learning_rate": 0.00019883160030775016,
"loss": 1.1221,
"step": 210
},
{
"epoch": 1.4726027397260273,
"grad_norm": 0.36328125,
"learning_rate": 0.00019864233683207906,
"loss": 1.1217,
"step": 215
},
{
"epoch": 1.5068493150684932,
"grad_norm": 0.412109375,
"learning_rate": 0.00019843897698922284,
"loss": 1.1086,
"step": 220
},
{
"epoch": 1.541095890410959,
"grad_norm": 0.357421875,
"learning_rate": 0.00019822154984008088,
"loss": 1.1132,
"step": 225
},
{
"epoch": 1.5753424657534247,
"grad_norm": 0.314453125,
"learning_rate": 0.0001979900864558242,
"loss": 1.1094,
"step": 230
},
{
"epoch": 1.6095890410958904,
"grad_norm": 0.48046875,
"learning_rate": 0.00019774461991345577,
"loss": 1.1048,
"step": 235
},
{
"epoch": 1.643835616438356,
"grad_norm": 0.32421875,
"learning_rate": 0.00019748518529108316,
"loss": 1.0937,
"step": 240
},
{
"epoch": 1.678082191780822,
"grad_norm": 0.431640625,
"learning_rate": 0.00019721181966290613,
"loss": 1.1099,
"step": 245
},
{
"epoch": 1.7123287671232876,
"grad_norm": 0.35546875,
"learning_rate": 0.00019692456209391846,
"loss": 1.0998,
"step": 250
},
{
"epoch": 1.7465753424657535,
"grad_norm": 0.33984375,
"learning_rate": 0.0001966234536343253,
"loss": 1.0985,
"step": 255
},
{
"epoch": 1.7808219178082192,
"grad_norm": 0.455078125,
"learning_rate": 0.00019630853731367713,
"loss": 1.1036,
"step": 260
},
{
"epoch": 1.8150684931506849,
"grad_norm": 0.52734375,
"learning_rate": 0.00019597985813472052,
"loss": 1.0853,
"step": 265
},
{
"epoch": 1.8493150684931505,
"grad_norm": 0.30078125,
"learning_rate": 0.0001956374630669672,
"loss": 1.0958,
"step": 270
},
{
"epoch": 1.8835616438356164,
"grad_norm": 0.62890625,
"learning_rate": 0.00019528140103998177,
"loss": 1.0911,
"step": 275
},
{
"epoch": 1.9178082191780823,
"grad_norm": 0.5234375,
"learning_rate": 0.00019491172293638968,
"loss": 1.0812,
"step": 280
},
{
"epoch": 1.952054794520548,
"grad_norm": 0.44921875,
"learning_rate": 0.0001945284815846057,
"loss": 1.0777,
"step": 285
},
{
"epoch": 1.9863013698630136,
"grad_norm": 0.53515625,
"learning_rate": 0.00019413173175128473,
"loss": 1.0819,
"step": 290
},
{
"epoch": 2.0,
"eval_loss": 2.4820380210876465,
"eval_runtime": 0.5459,
"eval_samples_per_second": 18.32,
"eval_steps_per_second": 1.832,
"step": 292
},
{
"epoch": 2.0205479452054793,
"grad_norm": 0.412109375,
"learning_rate": 0.00019372153013349523,
"loss": 1.0712,
"step": 295
},
{
"epoch": 2.0547945205479454,
"grad_norm": 0.302734375,
"learning_rate": 0.00019329793535061723,
"loss": 1.0467,
"step": 300
},
{
"epoch": 2.089041095890411,
"grad_norm": 0.34765625,
"learning_rate": 0.0001928610079359652,
"loss": 1.0444,
"step": 305
},
{
"epoch": 2.1232876712328768,
"grad_norm": 0.376953125,
"learning_rate": 0.00019241081032813772,
"loss": 1.0393,
"step": 310
},
{
"epoch": 2.1575342465753424,
"grad_norm": 0.33984375,
"learning_rate": 0.00019194740686209464,
"loss": 1.0475,
"step": 315
},
{
"epoch": 2.191780821917808,
"grad_norm": 1.2578125,
"learning_rate": 0.0001914708637599636,
"loss": 1.0427,
"step": 320
},
{
"epoch": 2.2260273972602738,
"grad_norm": 1.5546875,
"learning_rate": 0.00019098124912157632,
"loss": 1.0486,
"step": 325
},
{
"epoch": 2.26027397260274,
"grad_norm": 0.458984375,
"learning_rate": 0.00019047863291473717,
"loss": 1.0412,
"step": 330
},
{
"epoch": 2.2945205479452055,
"grad_norm": 0.62109375,
"learning_rate": 0.00018996308696522433,
"loss": 1.0414,
"step": 335
},
{
"epoch": 2.328767123287671,
"grad_norm": 0.2890625,
"learning_rate": 0.0001894346849465257,
"loss": 1.033,
"step": 340
},
{
"epoch": 2.363013698630137,
"grad_norm": 0.328125,
"learning_rate": 0.00018889350236931055,
"loss": 1.0325,
"step": 345
},
{
"epoch": 2.3972602739726026,
"grad_norm": 0.333984375,
"learning_rate": 0.00018833961657063885,
"loss": 1.0499,
"step": 350
},
{
"epoch": 2.4315068493150687,
"grad_norm": 0.578125,
"learning_rate": 0.0001877731067029096,
"loss": 1.0361,
"step": 355
},
{
"epoch": 2.4657534246575343,
"grad_norm": 0.4921875,
"learning_rate": 0.00018719405372254948,
"loss": 1.0412,
"step": 360
},
{
"epoch": 2.5,
"grad_norm": 0.298828125,
"learning_rate": 0.00018660254037844388,
"loss": 1.0435,
"step": 365
},
{
"epoch": 2.5342465753424657,
"grad_norm": 0.4296875,
"learning_rate": 0.00018599865120011192,
"loss": 1.0369,
"step": 370
},
{
"epoch": 2.5684931506849313,
"grad_norm": 0.31640625,
"learning_rate": 0.00018538247248562674,
"loss": 1.0298,
"step": 375
},
{
"epoch": 2.602739726027397,
"grad_norm": 0.3125,
"learning_rate": 0.00018475409228928312,
"loss": 1.0325,
"step": 380
},
{
"epoch": 2.636986301369863,
"grad_norm": 0.41015625,
"learning_rate": 0.0001841136004090144,
"loss": 1.0411,
"step": 385
},
{
"epoch": 2.671232876712329,
"grad_norm": 0.310546875,
"learning_rate": 0.00018346108837355972,
"loss": 1.0372,
"step": 390
},
{
"epoch": 2.7054794520547945,
"grad_norm": 0.384765625,
"learning_rate": 0.00018279664942938447,
"loss": 1.0364,
"step": 395
},
{
"epoch": 2.73972602739726,
"grad_norm": 0.279296875,
"learning_rate": 0.00018212037852735486,
"loss": 1.0237,
"step": 400
},
{
"epoch": 2.7739726027397262,
"grad_norm": 0.375,
"learning_rate": 0.0001814323723091692,
"loss": 1.0341,
"step": 405
},
{
"epoch": 2.808219178082192,
"grad_norm": 0.486328125,
"learning_rate": 0.00018073272909354727,
"loss": 1.0256,
"step": 410
},
{
"epoch": 2.8424657534246576,
"grad_norm": 0.287109375,
"learning_rate": 0.00018002154886218033,
"loss": 1.0347,
"step": 415
},
{
"epoch": 2.8767123287671232,
"grad_norm": 0.427734375,
"learning_rate": 0.00017929893324544332,
"loss": 1.0357,
"step": 420
},
{
"epoch": 2.910958904109589,
"grad_norm": 0.408203125,
"learning_rate": 0.00017856498550787144,
"loss": 1.029,
"step": 425
},
{
"epoch": 2.9452054794520546,
"grad_norm": 0.375,
"learning_rate": 0.00017781981053340337,
"loss": 1.0263,
"step": 430
},
{
"epoch": 2.9794520547945207,
"grad_norm": 0.474609375,
"learning_rate": 0.00017706351481039284,
"loss": 1.035,
"step": 435
},
{
"epoch": 3.0,
"eval_loss": 2.4995357990264893,
"eval_runtime": 0.5513,
"eval_samples_per_second": 18.139,
"eval_steps_per_second": 1.814,
"step": 438
},
{
"epoch": 3.0136986301369864,
"grad_norm": 0.302734375,
"learning_rate": 0.00017629620641639103,
"loss": 1.006,
"step": 440
},
{
"epoch": 3.047945205479452,
"grad_norm": 0.349609375,
"learning_rate": 0.00017551799500270198,
"loss": 0.9868,
"step": 445
},
{
"epoch": 3.0821917808219177,
"grad_norm": 0.37109375,
"learning_rate": 0.00017472899177871297,
"loss": 0.9878,
"step": 450
},
{
"epoch": 3.1164383561643834,
"grad_norm": 0.35546875,
"learning_rate": 0.00017392930949600217,
"loss": 0.9897,
"step": 455
},
{
"epoch": 3.1506849315068495,
"grad_norm": 0.50390625,
"learning_rate": 0.00017311906243222614,
"loss": 0.9801,
"step": 460
},
{
"epoch": 3.184931506849315,
"grad_norm": 0.322265625,
"learning_rate": 0.00017229836637478902,
"loss": 0.9837,
"step": 465
},
{
"epoch": 3.219178082191781,
"grad_norm": 0.38671875,
"learning_rate": 0.00017146733860429612,
"loss": 0.9774,
"step": 470
},
{
"epoch": 3.2534246575342465,
"grad_norm": 0.59765625,
"learning_rate": 0.00017062609787779403,
"loss": 0.9918,
"step": 475
},
{
"epoch": 3.287671232876712,
"grad_norm": 0.310546875,
"learning_rate": 0.00016977476441179992,
"loss": 0.9844,
"step": 480
},
{
"epoch": 3.3219178082191783,
"grad_norm": 0.337890625,
"learning_rate": 0.0001689134598651219,
"loss": 0.9841,
"step": 485
},
{
"epoch": 3.356164383561644,
"grad_norm": 0.30078125,
"learning_rate": 0.0001680423073214737,
"loss": 0.993,
"step": 490
},
{
"epoch": 3.3904109589041096,
"grad_norm": 0.349609375,
"learning_rate": 0.00016716143127188548,
"loss": 0.9842,
"step": 495
},
{
"epoch": 3.4246575342465753,
"grad_norm": 0.37109375,
"learning_rate": 0.00016627095759691362,
"loss": 0.9925,
"step": 500
},
{
"epoch": 3.458904109589041,
"grad_norm": 0.474609375,
"learning_rate": 0.0001653710135486518,
"loss": 0.9822,
"step": 505
},
{
"epoch": 3.493150684931507,
"grad_norm": 0.3046875,
"learning_rate": 0.00016446172773254629,
"loss": 0.985,
"step": 510
},
{
"epoch": 3.5273972602739727,
"grad_norm": 0.37109375,
"learning_rate": 0.00016354323008901776,
"loss": 0.9937,
"step": 515
},
{
"epoch": 3.5616438356164384,
"grad_norm": 0.314453125,
"learning_rate": 0.0001626156518748922,
"loss": 0.9889,
"step": 520
},
{
"epoch": 3.595890410958904,
"grad_norm": 0.3046875,
"learning_rate": 0.00016167912564464383,
"loss": 0.9816,
"step": 525
},
{
"epoch": 3.6301369863013697,
"grad_norm": 0.314453125,
"learning_rate": 0.0001607337852314527,
"loss": 0.9873,
"step": 530
},
{
"epoch": 3.6643835616438354,
"grad_norm": 0.3046875,
"learning_rate": 0.0001597797657280792,
"loss": 0.9935,
"step": 535
},
{
"epoch": 3.6986301369863015,
"grad_norm": 0.287109375,
"learning_rate": 0.00015881720346755905,
"loss": 0.9863,
"step": 540
},
{
"epoch": 3.732876712328767,
"grad_norm": 0.34375,
"learning_rate": 0.00015784623600372042,
"loss": 0.9782,
"step": 545
},
{
"epoch": 3.767123287671233,
"grad_norm": 0.375,
"learning_rate": 0.00015686700209152738,
"loss": 0.9779,
"step": 550
},
{
"epoch": 3.8013698630136985,
"grad_norm": 0.3515625,
"learning_rate": 0.00015587964166725095,
"loss": 0.9883,
"step": 555
},
{
"epoch": 3.8356164383561646,
"grad_norm": 0.33203125,
"learning_rate": 0.00015488429582847192,
"loss": 0.968,
"step": 560
},
{
"epoch": 3.8698630136986303,
"grad_norm": 0.478515625,
"learning_rate": 0.00015388110681391725,
"loss": 0.9858,
"step": 565
},
{
"epoch": 3.904109589041096,
"grad_norm": 0.294921875,
"learning_rate": 0.0001528702179831338,
"loss": 0.9668,
"step": 570
},
{
"epoch": 3.9383561643835616,
"grad_norm": 0.3203125,
"learning_rate": 0.00015185177379600152,
"loss": 0.9853,
"step": 575
},
{
"epoch": 3.9726027397260273,
"grad_norm": 0.302734375,
"learning_rate": 0.00015082591979208976,
"loss": 0.9796,
"step": 580
},
{
"epoch": 4.0,
"eval_loss": 2.5387372970581055,
"eval_runtime": 0.5485,
"eval_samples_per_second": 18.233,
"eval_steps_per_second": 1.823,
"step": 584
},
{
"epoch": 4.006849315068493,
"grad_norm": 0.369140625,
"learning_rate": 0.000149792802569859,
"loss": 0.981,
"step": 585
},
{
"epoch": 4.041095890410959,
"grad_norm": 0.31640625,
"learning_rate": 0.00014875256976571135,
"loss": 0.9259,
"step": 590
},
{
"epoch": 4.075342465753424,
"grad_norm": 0.302734375,
"learning_rate": 0.0001477053700328929,
"loss": 0.9421,
"step": 595
},
{
"epoch": 4.109589041095891,
"grad_norm": 0.310546875,
"learning_rate": 0.00014665135302025035,
"loss": 0.9348,
"step": 600
},
{
"epoch": 4.1438356164383565,
"grad_norm": 0.322265625,
"learning_rate": 0.00014559066935084588,
"loss": 0.9353,
"step": 605
},
{
"epoch": 4.178082191780822,
"grad_norm": 0.314453125,
"learning_rate": 0.00014452347060043237,
"loss": 0.9267,
"step": 610
},
{
"epoch": 4.212328767123288,
"grad_norm": 0.359375,
"learning_rate": 0.00014344990927579268,
"loss": 0.9451,
"step": 615
},
{
"epoch": 4.2465753424657535,
"grad_norm": 0.486328125,
"learning_rate": 0.0001423701387929459,
"loss": 0.9245,
"step": 620
},
{
"epoch": 4.280821917808219,
"grad_norm": 0.4765625,
"learning_rate": 0.0001412843134552235,
"loss": 0.9371,
"step": 625
},
{
"epoch": 4.315068493150685,
"grad_norm": 0.38671875,
"learning_rate": 0.00014019258843121893,
"loss": 0.9309,
"step": 630
},
{
"epoch": 4.3493150684931505,
"grad_norm": 0.4453125,
"learning_rate": 0.0001390951197326134,
"loss": 0.9426,
"step": 635
},
{
"epoch": 4.383561643835616,
"grad_norm": 0.474609375,
"learning_rate": 0.00013799206419188103,
"loss": 0.9359,
"step": 640
},
{
"epoch": 4.417808219178082,
"grad_norm": 0.396484375,
"learning_rate": 0.00013688357943987732,
"loss": 0.945,
"step": 645
},
{
"epoch": 4.4520547945205475,
"grad_norm": 0.36328125,
"learning_rate": 0.0001357698238833126,
"loss": 0.9341,
"step": 650
},
{
"epoch": 4.486301369863014,
"grad_norm": 0.361328125,
"learning_rate": 0.0001346509566821153,
"loss": 0.9454,
"step": 655
},
{
"epoch": 4.52054794520548,
"grad_norm": 0.341796875,
"learning_rate": 0.00013352713772668765,
"loss": 0.9414,
"step": 660
},
{
"epoch": 4.554794520547945,
"grad_norm": 0.431640625,
"learning_rate": 0.00013239852761505626,
"loss": 0.9429,
"step": 665
},
{
"epoch": 4.589041095890411,
"grad_norm": 0.40625,
"learning_rate": 0.00013126528762992247,
"loss": 0.947,
"step": 670
},
{
"epoch": 4.623287671232877,
"grad_norm": 0.3125,
"learning_rate": 0.00013012757971561415,
"loss": 0.9387,
"step": 675
},
{
"epoch": 4.657534246575342,
"grad_norm": 0.33984375,
"learning_rate": 0.00012898556645494325,
"loss": 0.9485,
"step": 680
},
{
"epoch": 4.691780821917808,
"grad_norm": 0.326171875,
"learning_rate": 0.0001278394110459724,
"loss": 0.9457,
"step": 685
},
{
"epoch": 4.726027397260274,
"grad_norm": 0.341796875,
"learning_rate": 0.0001266892772786929,
"loss": 0.9463,
"step": 690
},
{
"epoch": 4.760273972602739,
"grad_norm": 0.31640625,
"learning_rate": 0.0001255353295116187,
"loss": 0.9518,
"step": 695
},
{
"epoch": 4.794520547945205,
"grad_norm": 0.349609375,
"learning_rate": 0.00012437773264829897,
"loss": 0.9382,
"step": 700
},
{
"epoch": 4.828767123287671,
"grad_norm": 0.34765625,
"learning_rate": 0.00012321665211375256,
"loss": 0.9485,
"step": 705
},
{
"epoch": 4.863013698630137,
"grad_norm": 0.3203125,
"learning_rate": 0.00012205225383082843,
"loss": 0.9393,
"step": 710
},
{
"epoch": 4.897260273972603,
"grad_norm": 0.359375,
"learning_rate": 0.00012088470419649432,
"loss": 0.9568,
"step": 715
},
{
"epoch": 4.931506849315069,
"grad_norm": 0.337890625,
"learning_rate": 0.00011971417005805818,
"loss": 0.9352,
"step": 720
},
{
"epoch": 4.965753424657534,
"grad_norm": 0.353515625,
"learning_rate": 0.0001185408186893251,
"loss": 0.9383,
"step": 725
},
{
"epoch": 5.0,
"grad_norm": 0.322265625,
"learning_rate": 0.00011736481776669306,
"loss": 0.9366,
"step": 730
},
{
"epoch": 5.0,
"eval_loss": 2.6037707328796387,
"eval_runtime": 0.5451,
"eval_samples_per_second": 18.346,
"eval_steps_per_second": 1.835,
"step": 730
},
{
"epoch": 5.034246575342466,
"grad_norm": 0.349609375,
"learning_rate": 0.00011618633534519141,
"loss": 0.9013,
"step": 735
},
{
"epoch": 5.068493150684931,
"grad_norm": 0.31640625,
"learning_rate": 0.00011500553983446527,
"loss": 0.9034,
"step": 740
},
{
"epoch": 5.102739726027397,
"grad_norm": 0.34765625,
"learning_rate": 0.00011382259997470899,
"loss": 0.8925,
"step": 745
},
{
"epoch": 5.136986301369863,
"grad_norm": 0.345703125,
"learning_rate": 0.00011263768481255264,
"loss": 0.8901,
"step": 750
},
{
"epoch": 5.171232876712328,
"grad_norm": 0.333984375,
"learning_rate": 0.00011145096367690444,
"loss": 0.8945,
"step": 755
},
{
"epoch": 5.205479452054795,
"grad_norm": 0.42578125,
"learning_rate": 0.00011026260615475333,
"loss": 0.8961,
"step": 760
},
{
"epoch": 5.239726027397261,
"grad_norm": 0.4765625,
"learning_rate": 0.00010907278206693395,
"loss": 0.8911,
"step": 765
},
{
"epoch": 5.273972602739726,
"grad_norm": 0.3828125,
"learning_rate": 0.00010788166144385888,
"loss": 0.9018,
"step": 770
},
{
"epoch": 5.308219178082192,
"grad_norm": 0.51953125,
"learning_rate": 0.00010668941450122055,
"loss": 0.9046,
"step": 775
},
{
"epoch": 5.342465753424658,
"grad_norm": 0.54296875,
"learning_rate": 0.0001054962116156667,
"loss": 0.8964,
"step": 780
},
{
"epoch": 5.376712328767123,
"grad_norm": 0.50390625,
"learning_rate": 0.00010430222330045304,
"loss": 0.9071,
"step": 785
},
{
"epoch": 5.410958904109589,
"grad_norm": 0.4921875,
"learning_rate": 0.0001031076201810762,
"loss": 0.8981,
"step": 790
},
{
"epoch": 5.445205479452055,
"grad_norm": 0.3359375,
"learning_rate": 0.00010191257297089052,
"loss": 0.9054,
"step": 795
},
{
"epoch": 5.47945205479452,
"grad_norm": 0.337890625,
"learning_rate": 0.00010071725244671282,
"loss": 0.9061,
"step": 800
},
{
"epoch": 5.513698630136986,
"grad_norm": 0.4140625,
"learning_rate": 9.952182942441733e-05,
"loss": 0.905,
"step": 805
},
{
"epoch": 5.5479452054794525,
"grad_norm": 0.33203125,
"learning_rate": 9.83264747345259e-05,
"loss": 0.8981,
"step": 810
},
{
"epoch": 5.582191780821918,
"grad_norm": 0.416015625,
"learning_rate": 9.713135919779515e-05,
"loss": 0.8956,
"step": 815
},
{
"epoch": 5.616438356164384,
"grad_norm": 0.41015625,
"learning_rate": 9.593665360080599e-05,
"loss": 0.9116,
"step": 820
},
{
"epoch": 5.6506849315068495,
"grad_norm": 0.357421875,
"learning_rate": 9.474252867155732e-05,
"loss": 0.9002,
"step": 825
},
{
"epoch": 5.684931506849315,
"grad_norm": 0.322265625,
"learning_rate": 9.354915505506839e-05,
"loss": 0.8971,
"step": 830
},
{
"epoch": 5.719178082191781,
"grad_norm": 0.3359375,
"learning_rate": 9.235670328899293e-05,
"loss": 0.8988,
"step": 835
},
{
"epoch": 5.7534246575342465,
"grad_norm": 0.3359375,
"learning_rate": 9.116534377924883e-05,
"loss": 0.8922,
"step": 840
},
{
"epoch": 5.787671232876712,
"grad_norm": 0.32421875,
"learning_rate": 8.997524677566627e-05,
"loss": 0.8953,
"step": 845
},
{
"epoch": 5.821917808219178,
"grad_norm": 0.326171875,
"learning_rate": 8.878658234765858e-05,
"loss": 0.8986,
"step": 850
},
{
"epoch": 5.8561643835616435,
"grad_norm": 0.322265625,
"learning_rate": 8.759952035991844e-05,
"loss": 0.8949,
"step": 855
},
{
"epoch": 5.890410958904109,
"grad_norm": 0.33203125,
"learning_rate": 8.641423044814374e-05,
"loss": 0.9013,
"step": 860
},
{
"epoch": 5.924657534246576,
"grad_norm": 0.33203125,
"learning_rate": 8.5230881994796e-05,
"loss": 0.9133,
"step": 865
},
{
"epoch": 5.958904109589041,
"grad_norm": 0.33984375,
"learning_rate": 8.404964410489485e-05,
"loss": 0.9042,
"step": 870
},
{
"epoch": 5.993150684931507,
"grad_norm": 0.33203125,
"learning_rate": 8.287068558185225e-05,
"loss": 0.9051,
"step": 875
},
{
"epoch": 6.0,
"eval_loss": 2.6520962715148926,
"eval_runtime": 0.5512,
"eval_samples_per_second": 18.142,
"eval_steps_per_second": 1.814,
"step": 876
},
{
"epoch": 6.027397260273973,
"grad_norm": 0.33203125,
"learning_rate": 8.169417490335007e-05,
"loss": 0.8764,
"step": 880
},
{
"epoch": 6.061643835616438,
"grad_norm": 0.34765625,
"learning_rate": 8.052028019726371e-05,
"loss": 0.8608,
"step": 885
},
{
"epoch": 6.095890410958904,
"grad_norm": 0.349609375,
"learning_rate": 7.934916921763628e-05,
"loss": 0.8474,
"step": 890
},
{
"epoch": 6.13013698630137,
"grad_norm": 0.361328125,
"learning_rate": 7.818100932070546e-05,
"loss": 0.8558,
"step": 895
},
{
"epoch": 6.164383561643835,
"grad_norm": 0.34375,
"learning_rate": 7.701596744098818e-05,
"loss": 0.858,
"step": 900
},
{
"epoch": 6.198630136986301,
"grad_norm": 0.34375,
"learning_rate": 7.585421006742463e-05,
"loss": 0.8568,
"step": 905
},
{
"epoch": 6.232876712328767,
"grad_norm": 0.333984375,
"learning_rate": 7.469590321958662e-05,
"loss": 0.8626,
"step": 910
},
{
"epoch": 6.267123287671233,
"grad_norm": 0.353515625,
"learning_rate": 7.354121242395254e-05,
"loss": 0.8685,
"step": 915
},
{
"epoch": 6.301369863013699,
"grad_norm": 0.3828125,
"learning_rate": 7.239030269025311e-05,
"loss": 0.8621,
"step": 920
},
{
"epoch": 6.335616438356165,
"grad_norm": 0.404296875,
"learning_rate": 7.124333848789091e-05,
"loss": 0.8687,
"step": 925
},
{
"epoch": 6.36986301369863,
"grad_norm": 0.35546875,
"learning_rate": 7.010048372243698e-05,
"loss": 0.8691,
"step": 930
},
{
"epoch": 6.404109589041096,
"grad_norm": 0.44140625,
"learning_rate": 6.8961901712208e-05,
"loss": 0.8651,
"step": 935
},
{
"epoch": 6.438356164383562,
"grad_norm": 0.353515625,
"learning_rate": 6.782775516492771e-05,
"loss": 0.8656,
"step": 940
},
{
"epoch": 6.472602739726027,
"grad_norm": 0.384765625,
"learning_rate": 6.669820615447522e-05,
"loss": 0.8683,
"step": 945
},
{
"epoch": 6.506849315068493,
"grad_norm": 0.361328125,
"learning_rate": 6.5573416097724e-05,
"loss": 0.8632,
"step": 950
},
{
"epoch": 6.541095890410959,
"grad_norm": 0.353515625,
"learning_rate": 6.445354573147484e-05,
"loss": 0.8693,
"step": 955
},
{
"epoch": 6.575342465753424,
"grad_norm": 0.341796875,
"learning_rate": 6.333875508948593e-05,
"loss": 0.8724,
"step": 960
},
{
"epoch": 6.609589041095891,
"grad_norm": 0.35546875,
"learning_rate": 6.22292034796035e-05,
"loss": 0.8659,
"step": 965
},
{
"epoch": 6.6438356164383565,
"grad_norm": 0.357421875,
"learning_rate": 6.112504946099604e-05,
"loss": 0.8674,
"step": 970
},
{
"epoch": 6.678082191780822,
"grad_norm": 0.390625,
"learning_rate": 6.0026450821495536e-05,
"loss": 0.8762,
"step": 975
},
{
"epoch": 6.712328767123288,
"grad_norm": 0.33984375,
"learning_rate": 5.8933564555049105e-05,
"loss": 0.8581,
"step": 980
},
{
"epoch": 6.7465753424657535,
"grad_norm": 0.34765625,
"learning_rate": 5.784654683928391e-05,
"loss": 0.8718,
"step": 985
},
{
"epoch": 6.780821917808219,
"grad_norm": 0.36328125,
"learning_rate": 5.6765553013188766e-05,
"loss": 0.8637,
"step": 990
},
{
"epoch": 6.815068493150685,
"grad_norm": 0.361328125,
"learning_rate": 5.5690737554915604e-05,
"loss": 0.8684,
"step": 995
},
{
"epoch": 6.8493150684931505,
"grad_norm": 0.353515625,
"learning_rate": 5.462225405970401e-05,
"loss": 0.8693,
"step": 1000
},
{
"epoch": 6.883561643835616,
"grad_norm": 0.34765625,
"learning_rate": 5.3560255217931785e-05,
"loss": 0.871,
"step": 1005
},
{
"epoch": 6.917808219178082,
"grad_norm": 0.369140625,
"learning_rate": 5.2504892793295e-05,
"loss": 0.8644,
"step": 1010
},
{
"epoch": 6.9520547945205475,
"grad_norm": 0.34375,
"learning_rate": 5.145631760112022e-05,
"loss": 0.8688,
"step": 1015
},
{
"epoch": 6.986301369863014,
"grad_norm": 0.34765625,
"learning_rate": 5.041467948681269e-05,
"loss": 0.8676,
"step": 1020
},
{
"epoch": 7.0,
"eval_loss": 2.7248690128326416,
"eval_runtime": 0.5502,
"eval_samples_per_second": 18.174,
"eval_steps_per_second": 1.817,
"step": 1022
},
{
"epoch": 7.02054794520548,
"grad_norm": 0.328125,
"learning_rate": 4.9380127304442634e-05,
"loss": 0.8501,
"step": 1025
},
{
"epoch": 7.054794520547945,
"grad_norm": 0.357421875,
"learning_rate": 4.835280889547351e-05,
"loss": 0.8375,
"step": 1030
},
{
"epoch": 7.089041095890411,
"grad_norm": 0.3515625,
"learning_rate": 4.733287106763481e-05,
"loss": 0.8297,
"step": 1035
},
{
"epoch": 7.123287671232877,
"grad_norm": 0.375,
"learning_rate": 4.6320459573942856e-05,
"loss": 0.8336,
"step": 1040
},
{
"epoch": 7.157534246575342,
"grad_norm": 0.365234375,
"learning_rate": 4.531571909187197e-05,
"loss": 0.832,
"step": 1045
},
{
"epoch": 7.191780821917808,
"grad_norm": 0.376953125,
"learning_rate": 4.431879320267972e-05,
"loss": 0.8393,
"step": 1050
},
{
"epoch": 7.226027397260274,
"grad_norm": 0.361328125,
"learning_rate": 4.332982437088825e-05,
"loss": 0.8425,
"step": 1055
},
{
"epoch": 7.260273972602739,
"grad_norm": 0.34765625,
"learning_rate": 4.2348953923925916e-05,
"loss": 0.846,
"step": 1060
},
{
"epoch": 7.294520547945205,
"grad_norm": 0.349609375,
"learning_rate": 4.137632203193086e-05,
"loss": 0.8396,
"step": 1065
},
{
"epoch": 7.328767123287671,
"grad_norm": 0.3515625,
"learning_rate": 4.041206768772022e-05,
"loss": 0.836,
"step": 1070
},
{
"epoch": 7.363013698630137,
"grad_norm": 0.365234375,
"learning_rate": 3.9456328686927525e-05,
"loss": 0.8442,
"step": 1075
},
{
"epoch": 7.397260273972603,
"grad_norm": 0.34765625,
"learning_rate": 3.850924160831115e-05,
"loss": 0.8358,
"step": 1080
},
{
"epoch": 7.431506849315069,
"grad_norm": 0.3515625,
"learning_rate": 3.757094179423672e-05,
"loss": 0.8381,
"step": 1085
},
{
"epoch": 7.465753424657534,
"grad_norm": 0.349609375,
"learning_rate": 3.6641563331336125e-05,
"loss": 0.837,
"step": 1090
},
{
"epoch": 7.5,
"grad_norm": 0.359375,
"learning_rate": 3.5721239031346066e-05,
"loss": 0.8435,
"step": 1095
},
{
"epoch": 7.534246575342466,
"grad_norm": 0.376953125,
"learning_rate": 3.4810100412128747e-05,
"loss": 0.8412,
"step": 1100
},
{
"epoch": 7.568493150684931,
"grad_norm": 0.34765625,
"learning_rate": 3.3908277678877445e-05,
"loss": 0.8361,
"step": 1105
},
{
"epoch": 7.602739726027397,
"grad_norm": 0.359375,
"learning_rate": 3.3015899705509734e-05,
"loss": 0.84,
"step": 1110
},
{
"epoch": 7.636986301369863,
"grad_norm": 0.369140625,
"learning_rate": 3.21330940162508e-05,
"loss": 0.8427,
"step": 1115
},
{
"epoch": 7.671232876712329,
"grad_norm": 0.373046875,
"learning_rate": 3.125998676740987e-05,
"loss": 0.8443,
"step": 1120
},
{
"epoch": 7.705479452054795,
"grad_norm": 0.36328125,
"learning_rate": 3.0396702729352023e-05,
"loss": 0.841,
"step": 1125
},
{
"epoch": 7.739726027397261,
"grad_norm": 0.353515625,
"learning_rate": 2.9543365268667867e-05,
"loss": 0.8482,
"step": 1130
},
{
"epoch": 7.773972602739726,
"grad_norm": 0.349609375,
"learning_rate": 2.8700096330544012e-05,
"loss": 0.8388,
"step": 1135
},
{
"epoch": 7.808219178082192,
"grad_norm": 0.3515625,
"learning_rate": 2.7867016421336776e-05,
"loss": 0.8486,
"step": 1140
},
{
"epoch": 7.842465753424658,
"grad_norm": 0.34765625,
"learning_rate": 2.7044244591351232e-05,
"loss": 0.8453,
"step": 1145
},
{
"epoch": 7.876712328767123,
"grad_norm": 0.36328125,
"learning_rate": 2.6231898417828603e-05,
"loss": 0.8358,
"step": 1150
},
{
"epoch": 7.910958904109589,
"grad_norm": 0.35546875,
"learning_rate": 2.5430093988143778e-05,
"loss": 0.8344,
"step": 1155
},
{
"epoch": 7.945205479452055,
"grad_norm": 0.35546875,
"learning_rate": 2.4638945883216235e-05,
"loss": 0.8312,
"step": 1160
},
{
"epoch": 7.97945205479452,
"grad_norm": 0.35546875,
"learning_rate": 2.385856716113587e-05,
"loss": 0.8291,
"step": 1165
},
{
"epoch": 8.0,
"eval_loss": 2.766744613647461,
"eval_runtime": 0.5415,
"eval_samples_per_second": 18.469,
"eval_steps_per_second": 1.847,
"step": 1168
},
{
"epoch": 8.013698630136986,
"grad_norm": 0.369140625,
"learning_rate": 2.3089069341006565e-05,
"loss": 0.8283,
"step": 1170
},
{
"epoch": 8.047945205479452,
"grad_norm": 0.349609375,
"learning_rate": 2.2330562387009745e-05,
"loss": 0.8203,
"step": 1175
},
{
"epoch": 8.082191780821917,
"grad_norm": 0.353515625,
"learning_rate": 2.1583154692689976e-05,
"loss": 0.8221,
"step": 1180
},
{
"epoch": 8.116438356164384,
"grad_norm": 0.36328125,
"learning_rate": 2.08469530654652e-05,
"loss": 0.8256,
"step": 1185
},
{
"epoch": 8.150684931506849,
"grad_norm": 0.36328125,
"learning_rate": 2.0122062711363532e-05,
"loss": 0.8139,
"step": 1190
},
{
"epoch": 8.184931506849315,
"grad_norm": 0.357421875,
"learning_rate": 1.9408587219988805e-05,
"loss": 0.8351,
"step": 1195
},
{
"epoch": 8.219178082191782,
"grad_norm": 0.359375,
"learning_rate": 1.8706628549717452e-05,
"loss": 0.8258,
"step": 1200
},
{
"epoch": 8.253424657534246,
"grad_norm": 0.357421875,
"learning_rate": 1.8016287013128018e-05,
"loss": 0.8139,
"step": 1205
},
{
"epoch": 8.287671232876713,
"grad_norm": 0.357421875,
"learning_rate": 1.7337661262666294e-05,
"loss": 0.8305,
"step": 1210
},
{
"epoch": 8.321917808219178,
"grad_norm": 0.353515625,
"learning_rate": 1.6670848276547334e-05,
"loss": 0.8239,
"step": 1215
},
{
"epoch": 8.356164383561644,
"grad_norm": 0.36328125,
"learning_rate": 1.601594334489702e-05,
"loss": 0.8252,
"step": 1220
},
{
"epoch": 8.39041095890411,
"grad_norm": 0.36328125,
"learning_rate": 1.5373040056134814e-05,
"loss": 0.8194,
"step": 1225
},
{
"epoch": 8.424657534246576,
"grad_norm": 0.359375,
"learning_rate": 1.474223028359939e-05,
"loss": 0.8188,
"step": 1230
},
{
"epoch": 8.45890410958904,
"grad_norm": 0.359375,
"learning_rate": 1.4123604172419713e-05,
"loss": 0.8206,
"step": 1235
},
{
"epoch": 8.493150684931507,
"grad_norm": 0.35546875,
"learning_rate": 1.3517250126632986e-05,
"loss": 0.8223,
"step": 1240
},
{
"epoch": 8.527397260273972,
"grad_norm": 0.357421875,
"learning_rate": 1.292325479655131e-05,
"loss": 0.8257,
"step": 1245
},
{
"epoch": 8.561643835616438,
"grad_norm": 0.349609375,
"learning_rate": 1.2341703066379074e-05,
"loss": 0.8239,
"step": 1250
},
{
"epoch": 8.595890410958905,
"grad_norm": 0.345703125,
"learning_rate": 1.1772678042082607e-05,
"loss": 0.8173,
"step": 1255
},
{
"epoch": 8.63013698630137,
"grad_norm": 0.357421875,
"learning_rate": 1.1216261039514087e-05,
"loss": 0.8266,
"step": 1260
},
{
"epoch": 8.664383561643836,
"grad_norm": 0.3515625,
"learning_rate": 1.0672531572791178e-05,
"loss": 0.8237,
"step": 1265
},
{
"epoch": 8.698630136986301,
"grad_norm": 0.359375,
"learning_rate": 1.0141567342934132e-05,
"loss": 0.8335,
"step": 1270
},
{
"epoch": 8.732876712328768,
"grad_norm": 0.353515625,
"learning_rate": 9.623444226762035e-06,
"loss": 0.8239,
"step": 1275
},
{
"epoch": 8.767123287671232,
"grad_norm": 0.353515625,
"learning_rate": 9.118236266049707e-06,
"loss": 0.8308,
"step": 1280
},
{
"epoch": 8.801369863013699,
"grad_norm": 0.34765625,
"learning_rate": 8.626015656946895e-06,
"loss": 0.8266,
"step": 1285
},
{
"epoch": 8.835616438356164,
"grad_norm": 0.341796875,
"learning_rate": 8.146852739661105e-06,
"loss": 0.8248,
"step": 1290
},
{
"epoch": 8.86986301369863,
"grad_norm": 0.353515625,
"learning_rate": 7.6808159884057e-06,
"loss": 0.8322,
"step": 1295
},
{
"epoch": 8.904109589041095,
"grad_norm": 0.349609375,
"learning_rate": 7.2279720016148244e-06,
"loss": 0.823,
"step": 1300
},
{
"epoch": 8.938356164383562,
"grad_norm": 0.3515625,
"learning_rate": 6.788385492426053e-06,
"loss": 0.825,
"step": 1305
},
{
"epoch": 8.972602739726028,
"grad_norm": 0.357421875,
"learning_rate": 6.36211927943271e-06,
"loss": 0.8286,
"step": 1310
},
{
"epoch": 9.0,
"eval_loss": 2.7898991107940674,
"eval_runtime": 0.5501,
"eval_samples_per_second": 18.177,
"eval_steps_per_second": 1.818,
"step": 1314
},
{
"epoch": 9.006849315068493,
"grad_norm": 0.34765625,
"learning_rate": 5.949234277706861e-06,
"loss": 0.8231,
"step": 1315
},
{
"epoch": 9.04109589041096,
"grad_norm": 0.349609375,
"learning_rate": 5.549789490094304e-06,
"loss": 0.8237,
"step": 1320
},
{
"epoch": 9.075342465753424,
"grad_norm": 0.349609375,
"learning_rate": 5.163841998782837e-06,
"loss": 0.8125,
"step": 1325
},
{
"epoch": 9.10958904109589,
"grad_norm": 0.34375,
"learning_rate": 4.79144695714504e-06,
"loss": 0.8179,
"step": 1330
},
{
"epoch": 9.143835616438356,
"grad_norm": 0.34375,
"learning_rate": 4.432657581856525e-06,
"loss": 0.8173,
"step": 1335
},
{
"epoch": 9.178082191780822,
"grad_norm": 0.37109375,
"learning_rate": 4.087525145291204e-06,
"loss": 0.8186,
"step": 1340
},
{
"epoch": 9.212328767123287,
"grad_norm": 0.3515625,
"learning_rate": 3.7560989681941992e-06,
"loss": 0.8233,
"step": 1345
},
{
"epoch": 9.246575342465754,
"grad_norm": 0.345703125,
"learning_rate": 3.4384264126337328e-06,
"loss": 0.8147,
"step": 1350
},
{
"epoch": 9.280821917808218,
"grad_norm": 0.3515625,
"learning_rate": 3.1345528752329212e-06,
"loss": 0.8076,
"step": 1355
},
{
"epoch": 9.315068493150685,
"grad_norm": 0.3515625,
"learning_rate": 2.8445217806824077e-06,
"loss": 0.8259,
"step": 1360
},
{
"epoch": 9.349315068493151,
"grad_norm": 0.3515625,
"learning_rate": 2.5683745755348044e-06,
"loss": 0.819,
"step": 1365
},
{
"epoch": 9.383561643835616,
"grad_norm": 0.361328125,
"learning_rate": 2.30615072228183e-06,
"loss": 0.8218,
"step": 1370
},
{
"epoch": 9.417808219178083,
"grad_norm": 0.359375,
"learning_rate": 2.057887693714988e-06,
"loss": 0.8166,
"step": 1375
},
{
"epoch": 9.452054794520548,
"grad_norm": 0.3515625,
"learning_rate": 1.8236209675705274e-06,
"loss": 0.815,
"step": 1380
},
{
"epoch": 9.486301369863014,
"grad_norm": 0.3515625,
"learning_rate": 1.6033840214595308e-06,
"loss": 0.8287,
"step": 1385
},
{
"epoch": 9.520547945205479,
"grad_norm": 0.349609375,
"learning_rate": 1.397208328083921e-06,
"loss": 0.8239,
"step": 1390
},
{
"epoch": 9.554794520547945,
"grad_norm": 0.3515625,
"learning_rate": 1.205123350738746e-06,
"loss": 0.8238,
"step": 1395
},
{
"epoch": 9.58904109589041,
"grad_norm": 0.34765625,
"learning_rate": 1.0271565391018922e-06,
"loss": 0.8231,
"step": 1400
},
{
"epoch": 9.623287671232877,
"grad_norm": 0.361328125,
"learning_rate": 8.633333253113995e-07,
"loss": 0.8246,
"step": 1405
},
{
"epoch": 9.657534246575342,
"grad_norm": 0.361328125,
"learning_rate": 7.136771203310245e-07,
"loss": 0.8131,
"step": 1410
},
{
"epoch": 9.691780821917808,
"grad_norm": 0.3515625,
"learning_rate": 5.782093106048159e-07,
"loss": 0.8196,
"step": 1415
},
{
"epoch": 9.726027397260275,
"grad_norm": 0.345703125,
"learning_rate": 4.569492550008603e-07,
"loss": 0.8097,
"step": 1420
},
{
"epoch": 9.76027397260274,
"grad_norm": 0.36328125,
"learning_rate": 3.49914282044872e-07,
"loss": 0.8272,
"step": 1425
},
{
"epoch": 9.794520547945206,
"grad_norm": 0.365234375,
"learning_rate": 2.5711968744382974e-07,
"loss": 0.8285,
"step": 1430
},
{
"epoch": 9.82876712328767,
"grad_norm": 0.353515625,
"learning_rate": 1.7857873190019192e-07,
"loss": 0.8323,
"step": 1435
},
{
"epoch": 9.863013698630137,
"grad_norm": 0.359375,
"learning_rate": 1.143026392168789e-07,
"loss": 0.822,
"step": 1440
},
{
"epoch": 9.897260273972602,
"grad_norm": 0.353515625,
"learning_rate": 6.430059469334504e-08,
"loss": 0.8329,
"step": 1445
},
{
"epoch": 9.931506849315069,
"grad_norm": 0.349609375,
"learning_rate": 2.8579743813006432e-08,
"loss": 0.8213,
"step": 1450
},
{
"epoch": 9.965753424657533,
"grad_norm": 0.35546875,
"learning_rate": 7.145191222035497e-09,
"loss": 0.8169,
"step": 1455
},
{
"epoch": 10.0,
"grad_norm": 0.35546875,
"learning_rate": 0.0,
"loss": 0.8185,
"step": 1460
},
{
"epoch": 10.0,
"eval_loss": 2.793144464492798,
"eval_runtime": 0.5503,
"eval_samples_per_second": 18.172,
"eval_steps_per_second": 1.817,
"step": 1460
},
{
"epoch": 10.0,
"step": 1460,
"total_flos": 8.702314001108828e+17,
"train_loss": 0.9981180969982931,
"train_runtime": 8741.0304,
"train_samples_per_second": 8.01,
"train_steps_per_second": 0.167
}
],
"logging_steps": 5,
"max_steps": 1460,
"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": 8.702314001108828e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}