Roleplay-LoRA / Yi-1.5-9B-Chat-LoRA /trainer_state.json
ukk0708's picture
Upload 12 files
3d54587 verified
{
"best_metric": 2.2857470512390137,
"best_model_checkpoint": "../../saves/Yi-1.5-9B-Chat/lora/sft/checkpoint-2800",
"epoch": 4.148148148148148,
"eval_steps": 200,
"global_step": 2800,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 11.507218360900879,
"learning_rate": 2e-05,
"loss": 3.995,
"step": 10
},
{
"epoch": 0.03,
"grad_norm": 7.0516510009765625,
"learning_rate": 4.5e-05,
"loss": 3.8373,
"step": 20
},
{
"epoch": 0.04,
"grad_norm": 5.1662492752075195,
"learning_rate": 4.999929854041747e-05,
"loss": 3.4376,
"step": 30
},
{
"epoch": 0.06,
"grad_norm": 2.265901565551758,
"learning_rate": 4.999644892832738e-05,
"loss": 3.0327,
"step": 40
},
{
"epoch": 0.07,
"grad_norm": 4.507016658782959,
"learning_rate": 4.999140757217391e-05,
"loss": 2.7494,
"step": 50
},
{
"epoch": 0.09,
"grad_norm": 3.204484462738037,
"learning_rate": 4.9984174913994355e-05,
"loss": 2.6219,
"step": 60
},
{
"epoch": 0.1,
"grad_norm": 1.585574746131897,
"learning_rate": 4.9974751587964214e-05,
"loss": 2.6297,
"step": 70
},
{
"epoch": 0.12,
"grad_norm": 2.005038261413574,
"learning_rate": 4.9963138420341604e-05,
"loss": 2.6139,
"step": 80
},
{
"epoch": 0.13,
"grad_norm": 2.9263103008270264,
"learning_rate": 4.994933642939482e-05,
"loss": 2.6403,
"step": 90
},
{
"epoch": 0.15,
"grad_norm": 2.398559331893921,
"learning_rate": 4.993334682531302e-05,
"loss": 2.7009,
"step": 100
},
{
"epoch": 0.16,
"grad_norm": 2.3030171394348145,
"learning_rate": 4.991517101010015e-05,
"loss": 2.9349,
"step": 110
},
{
"epoch": 0.18,
"grad_norm": 2.3386640548706055,
"learning_rate": 4.9894810577451975e-05,
"loss": 2.2748,
"step": 120
},
{
"epoch": 0.19,
"grad_norm": 1.8978828191757202,
"learning_rate": 4.9872267312616384e-05,
"loss": 2.3982,
"step": 130
},
{
"epoch": 0.21,
"grad_norm": 2.644758939743042,
"learning_rate": 4.9847543192236815e-05,
"loss": 2.4243,
"step": 140
},
{
"epoch": 0.22,
"grad_norm": 1.887523889541626,
"learning_rate": 4.9820640384178954e-05,
"loss": 2.5096,
"step": 150
},
{
"epoch": 0.24,
"grad_norm": 1.8633583784103394,
"learning_rate": 4.9791561247340674e-05,
"loss": 2.3775,
"step": 160
},
{
"epoch": 0.25,
"grad_norm": 2.8847458362579346,
"learning_rate": 4.976030833144516e-05,
"loss": 2.2988,
"step": 170
},
{
"epoch": 0.27,
"grad_norm": 1.756564974784851,
"learning_rate": 4.972688437681736e-05,
"loss": 2.3573,
"step": 180
},
{
"epoch": 0.28,
"grad_norm": 4.001959800720215,
"learning_rate": 4.969129231414374e-05,
"loss": 2.5404,
"step": 190
},
{
"epoch": 0.3,
"grad_norm": 2.489682674407959,
"learning_rate": 4.9653535264215256e-05,
"loss": 2.5707,
"step": 200
},
{
"epoch": 0.3,
"eval_loss": 2.391483783721924,
"eval_runtime": 96.186,
"eval_samples_per_second": 6.238,
"eval_steps_per_second": 3.119,
"step": 200
},
{
"epoch": 0.31,
"grad_norm": 2.316711187362671,
"learning_rate": 4.961361653765377e-05,
"loss": 2.5629,
"step": 210
},
{
"epoch": 0.33,
"grad_norm": 2.2436294555664062,
"learning_rate": 4.957153963462172e-05,
"loss": 2.3062,
"step": 220
},
{
"epoch": 0.34,
"grad_norm": 1.6833086013793945,
"learning_rate": 4.952730824451527e-05,
"loss": 2.4841,
"step": 230
},
{
"epoch": 0.36,
"grad_norm": 2.4797868728637695,
"learning_rate": 4.9480926245640754e-05,
"loss": 2.4149,
"step": 240
},
{
"epoch": 0.37,
"grad_norm": 2.539104700088501,
"learning_rate": 4.943239770487469e-05,
"loss": 2.5375,
"step": 250
},
{
"epoch": 0.39,
"grad_norm": 2.656684637069702,
"learning_rate": 4.9381726877307124e-05,
"loss": 2.58,
"step": 260
},
{
"epoch": 0.4,
"grad_norm": 2.8903274536132812,
"learning_rate": 4.9328918205868556e-05,
"loss": 2.36,
"step": 270
},
{
"epoch": 0.41,
"grad_norm": 3.5389297008514404,
"learning_rate": 4.927397632094039e-05,
"loss": 2.4487,
"step": 280
},
{
"epoch": 0.43,
"grad_norm": 2.3600199222564697,
"learning_rate": 4.9216906039948896e-05,
"loss": 2.5569,
"step": 290
},
{
"epoch": 0.44,
"grad_norm": 2.797351837158203,
"learning_rate": 4.915771236694286e-05,
"loss": 2.5081,
"step": 300
},
{
"epoch": 0.46,
"grad_norm": 2.2043402194976807,
"learning_rate": 4.909640049215478e-05,
"loss": 2.6873,
"step": 310
},
{
"epoch": 0.47,
"grad_norm": 2.070732831954956,
"learning_rate": 4.903297579154577e-05,
"loss": 2.4935,
"step": 320
},
{
"epoch": 0.49,
"grad_norm": 2.1852307319641113,
"learning_rate": 4.896744382633419e-05,
"loss": 2.4865,
"step": 330
},
{
"epoch": 0.5,
"grad_norm": 1.5772058963775635,
"learning_rate": 4.889981034250807e-05,
"loss": 2.3605,
"step": 340
},
{
"epoch": 0.52,
"grad_norm": 2.855281114578247,
"learning_rate": 4.883008127032121e-05,
"loss": 2.6443,
"step": 350
},
{
"epoch": 0.53,
"grad_norm": 2.7813808917999268,
"learning_rate": 4.8758262723773255e-05,
"loss": 2.2597,
"step": 360
},
{
"epoch": 0.55,
"grad_norm": 3.336205244064331,
"learning_rate": 4.86843610000736e-05,
"loss": 2.4404,
"step": 370
},
{
"epoch": 0.56,
"grad_norm": 1.562402367591858,
"learning_rate": 4.860838257908925e-05,
"loss": 2.3216,
"step": 380
},
{
"epoch": 0.58,
"grad_norm": 1.9673439264297485,
"learning_rate": 4.85303341227766e-05,
"loss": 2.3308,
"step": 390
},
{
"epoch": 0.59,
"grad_norm": 2.689194440841675,
"learning_rate": 4.845022247459736e-05,
"loss": 2.5978,
"step": 400
},
{
"epoch": 0.59,
"eval_loss": 2.3469619750976562,
"eval_runtime": 96.7403,
"eval_samples_per_second": 6.202,
"eval_steps_per_second": 3.101,
"step": 400
},
{
"epoch": 0.61,
"grad_norm": 2.1179988384246826,
"learning_rate": 4.836805465891844e-05,
"loss": 2.679,
"step": 410
},
{
"epoch": 0.62,
"grad_norm": 2.770677089691162,
"learning_rate": 4.828383788039611e-05,
"loss": 2.3037,
"step": 420
},
{
"epoch": 0.64,
"grad_norm": 2.4875175952911377,
"learning_rate": 4.819757952334425e-05,
"loss": 2.1605,
"step": 430
},
{
"epoch": 0.65,
"grad_norm": 2.146296501159668,
"learning_rate": 4.810928715108683e-05,
"loss": 2.4998,
"step": 440
},
{
"epoch": 0.67,
"grad_norm": 1.9566316604614258,
"learning_rate": 4.801896850529482e-05,
"loss": 2.6092,
"step": 450
},
{
"epoch": 0.68,
"grad_norm": 2.384901285171509,
"learning_rate": 4.792663150530733e-05,
"loss": 2.5815,
"step": 460
},
{
"epoch": 0.7,
"grad_norm": 2.225851535797119,
"learning_rate": 4.783228424743726e-05,
"loss": 2.3677,
"step": 470
},
{
"epoch": 0.71,
"grad_norm": 2.222594976425171,
"learning_rate": 4.773593500426134e-05,
"loss": 2.3782,
"step": 480
},
{
"epoch": 0.73,
"grad_norm": 1.6287986040115356,
"learning_rate": 4.763759222389487e-05,
"loss": 2.4165,
"step": 490
},
{
"epoch": 0.74,
"grad_norm": 2.4728448390960693,
"learning_rate": 4.7537264529250835e-05,
"loss": 2.3643,
"step": 500
},
{
"epoch": 0.76,
"grad_norm": 1.7345590591430664,
"learning_rate": 4.743496071728396e-05,
"loss": 2.4526,
"step": 510
},
{
"epoch": 0.77,
"grad_norm": 1.9642170667648315,
"learning_rate": 4.7330689758219314e-05,
"loss": 2.3306,
"step": 520
},
{
"epoch": 0.79,
"grad_norm": 2.757434368133545,
"learning_rate": 4.722446079476576e-05,
"loss": 2.5495,
"step": 530
},
{
"epoch": 0.8,
"grad_norm": 2.5214667320251465,
"learning_rate": 4.711628314131436e-05,
"loss": 2.5145,
"step": 540
},
{
"epoch": 0.81,
"grad_norm": 2.977623462677002,
"learning_rate": 4.700616628312158e-05,
"loss": 2.4552,
"step": 550
},
{
"epoch": 0.83,
"grad_norm": 3.109473466873169,
"learning_rate": 4.689411987547773e-05,
"loss": 2.4047,
"step": 560
},
{
"epoch": 0.84,
"grad_norm": 1.7021738290786743,
"learning_rate": 4.678015374286025e-05,
"loss": 2.5649,
"step": 570
},
{
"epoch": 0.86,
"grad_norm": 2.258920669555664,
"learning_rate": 4.666427787807232e-05,
"loss": 2.5556,
"step": 580
},
{
"epoch": 0.87,
"grad_norm": 2.1758129596710205,
"learning_rate": 4.654650244136669e-05,
"loss": 2.4234,
"step": 590
},
{
"epoch": 0.89,
"grad_norm": 2.581289529800415,
"learning_rate": 4.642683775955476e-05,
"loss": 2.5284,
"step": 600
},
{
"epoch": 0.89,
"eval_loss": 2.327061414718628,
"eval_runtime": 96.1253,
"eval_samples_per_second": 6.242,
"eval_steps_per_second": 3.121,
"step": 600
},
{
"epoch": 0.9,
"grad_norm": 3.0182411670684814,
"learning_rate": 4.630529432510118e-05,
"loss": 2.3928,
"step": 610
},
{
"epoch": 0.92,
"grad_norm": 2.1703760623931885,
"learning_rate": 4.618188279520374e-05,
"loss": 2.675,
"step": 620
},
{
"epoch": 0.93,
"grad_norm": 2.2590174674987793,
"learning_rate": 4.6056613990859024e-05,
"loss": 2.4192,
"step": 630
},
{
"epoch": 0.95,
"grad_norm": 3.697880744934082,
"learning_rate": 4.5929498895913514e-05,
"loss": 2.1851,
"step": 640
},
{
"epoch": 0.96,
"grad_norm": 1.6290298700332642,
"learning_rate": 4.580054865610059e-05,
"loss": 2.452,
"step": 650
},
{
"epoch": 0.98,
"grad_norm": 2.1037967205047607,
"learning_rate": 4.5669774578063174e-05,
"loss": 2.368,
"step": 660
},
{
"epoch": 0.99,
"grad_norm": 3.8899028301239014,
"learning_rate": 4.5537188128362384e-05,
"loss": 2.4681,
"step": 670
},
{
"epoch": 1.01,
"grad_norm": 2.6862452030181885,
"learning_rate": 4.54028009324721e-05,
"loss": 2.5741,
"step": 680
},
{
"epoch": 1.02,
"grad_norm": 2.2980988025665283,
"learning_rate": 4.52666247737596e-05,
"loss": 2.3131,
"step": 690
},
{
"epoch": 1.04,
"grad_norm": 2.9786365032196045,
"learning_rate": 4.512867159245242e-05,
"loss": 2.4059,
"step": 700
},
{
"epoch": 1.05,
"grad_norm": 2.39225435256958,
"learning_rate": 4.498895348459135e-05,
"loss": 2.3781,
"step": 710
},
{
"epoch": 1.07,
"grad_norm": 1.9918076992034912,
"learning_rate": 4.484748270096988e-05,
"loss": 2.399,
"step": 720
},
{
"epoch": 1.08,
"grad_norm": 2.9783575534820557,
"learning_rate": 4.470427164605997e-05,
"loss": 2.4341,
"step": 730
},
{
"epoch": 1.1,
"grad_norm": 1.9173182249069214,
"learning_rate": 4.455933287692444e-05,
"loss": 2.3917,
"step": 740
},
{
"epoch": 1.11,
"grad_norm": 5.648810863494873,
"learning_rate": 4.441267910211594e-05,
"loss": 2.6513,
"step": 750
},
{
"epoch": 1.13,
"grad_norm": 4.045050144195557,
"learning_rate": 4.4264323180562574e-05,
"loss": 2.5065,
"step": 760
},
{
"epoch": 1.14,
"grad_norm": 3.8237059116363525,
"learning_rate": 4.411427812044049e-05,
"loss": 2.3481,
"step": 770
},
{
"epoch": 1.16,
"grad_norm": 2.632697582244873,
"learning_rate": 4.396255707803323e-05,
"loss": 2.445,
"step": 780
},
{
"epoch": 1.17,
"grad_norm": 3.1144275665283203,
"learning_rate": 4.3809173356578184e-05,
"loss": 2.3096,
"step": 790
},
{
"epoch": 1.19,
"grad_norm": 1.7161847352981567,
"learning_rate": 4.3654140405100116e-05,
"loss": 2.4712,
"step": 800
},
{
"epoch": 1.19,
"eval_loss": 2.317145824432373,
"eval_runtime": 96.3893,
"eval_samples_per_second": 6.225,
"eval_steps_per_second": 3.112,
"step": 800
},
{
"epoch": 1.2,
"grad_norm": 2.709351062774658,
"learning_rate": 4.349747181723197e-05,
"loss": 2.4706,
"step": 810
},
{
"epoch": 1.21,
"grad_norm": 2.301166534423828,
"learning_rate": 4.3339181330022876e-05,
"loss": 2.5085,
"step": 820
},
{
"epoch": 1.23,
"grad_norm": 2.3112149238586426,
"learning_rate": 4.3179282822733706e-05,
"loss": 2.3204,
"step": 830
},
{
"epoch": 1.24,
"grad_norm": 1.850696325302124,
"learning_rate": 4.301779031562011e-05,
"loss": 2.4174,
"step": 840
},
{
"epoch": 1.26,
"grad_norm": 2.511995315551758,
"learning_rate": 4.285471796870316e-05,
"loss": 2.3967,
"step": 850
},
{
"epoch": 1.27,
"grad_norm": 3.4540021419525146,
"learning_rate": 4.26900800805278e-05,
"loss": 2.2189,
"step": 860
},
{
"epoch": 1.29,
"grad_norm": 3.0399599075317383,
"learning_rate": 4.252389108690909e-05,
"loss": 2.4208,
"step": 870
},
{
"epoch": 1.3,
"grad_norm": 2.1426591873168945,
"learning_rate": 4.235616555966645e-05,
"loss": 2.479,
"step": 880
},
{
"epoch": 1.32,
"grad_norm": 2.262714147567749,
"learning_rate": 4.218691820534601e-05,
"loss": 2.5144,
"step": 890
},
{
"epoch": 1.33,
"grad_norm": 2.40321683883667,
"learning_rate": 4.201616386393102e-05,
"loss": 2.332,
"step": 900
},
{
"epoch": 1.35,
"grad_norm": 2.4343059062957764,
"learning_rate": 4.184391750754075e-05,
"loss": 2.4799,
"step": 910
},
{
"epoch": 1.36,
"grad_norm": 2.6487956047058105,
"learning_rate": 4.167019423911761e-05,
"loss": 2.4492,
"step": 920
},
{
"epoch": 1.38,
"grad_norm": 3.0731077194213867,
"learning_rate": 4.149500929110295e-05,
"loss": 2.4789,
"step": 930
},
{
"epoch": 1.39,
"grad_norm": 2.791496515274048,
"learning_rate": 4.1318378024101435e-05,
"loss": 2.2895,
"step": 940
},
{
"epoch": 1.41,
"grad_norm": 2.860171318054199,
"learning_rate": 4.114031592553417e-05,
"loss": 2.3098,
"step": 950
},
{
"epoch": 1.42,
"grad_norm": 2.6719272136688232,
"learning_rate": 4.096083860828076e-05,
"loss": 2.2381,
"step": 960
},
{
"epoch": 1.44,
"grad_norm": 3.2551610469818115,
"learning_rate": 4.07799618093103e-05,
"loss": 2.4553,
"step": 970
},
{
"epoch": 1.45,
"grad_norm": 2.201517105102539,
"learning_rate": 4.059770138830157e-05,
"loss": 2.4248,
"step": 980
},
{
"epoch": 1.47,
"grad_norm": 3.5828166007995605,
"learning_rate": 4.041407332625238e-05,
"loss": 2.3741,
"step": 990
},
{
"epoch": 1.48,
"grad_norm": 2.608720064163208,
"learning_rate": 4.022909372407835e-05,
"loss": 2.4542,
"step": 1000
},
{
"epoch": 1.48,
"eval_loss": 2.308347463607788,
"eval_runtime": 96.2879,
"eval_samples_per_second": 6.231,
"eval_steps_per_second": 3.116,
"step": 1000
},
{
"epoch": 1.5,
"grad_norm": 2.607658624649048,
"learning_rate": 4.004277880120113e-05,
"loss": 2.5501,
"step": 1010
},
{
"epoch": 1.51,
"grad_norm": 2.599700450897217,
"learning_rate": 3.9855144894126235e-05,
"loss": 2.2606,
"step": 1020
},
{
"epoch": 1.53,
"grad_norm": 2.6854465007781982,
"learning_rate": 3.966620845501067e-05,
"loss": 2.3407,
"step": 1030
},
{
"epoch": 1.54,
"grad_norm": 2.488729476928711,
"learning_rate": 3.9475986050220314e-05,
"loss": 2.4184,
"step": 1040
},
{
"epoch": 1.56,
"grad_norm": 2.6692395210266113,
"learning_rate": 3.928449435887737e-05,
"loss": 2.4879,
"step": 1050
},
{
"epoch": 1.57,
"grad_norm": 2.208466053009033,
"learning_rate": 3.909175017139791e-05,
"loss": 2.2039,
"step": 1060
},
{
"epoch": 1.59,
"grad_norm": 2.5494725704193115,
"learning_rate": 3.889777038801964e-05,
"loss": 2.3029,
"step": 1070
},
{
"epoch": 1.6,
"grad_norm": 2.0070173740386963,
"learning_rate": 3.870257201732005e-05,
"loss": 2.3363,
"step": 1080
},
{
"epoch": 1.61,
"grad_norm": 2.75435209274292,
"learning_rate": 3.8506172174725066e-05,
"loss": 2.2523,
"step": 1090
},
{
"epoch": 1.63,
"grad_norm": 2.6911637783050537,
"learning_rate": 3.830858808100834e-05,
"loss": 2.4057,
"step": 1100
},
{
"epoch": 1.64,
"grad_norm": 3.0497798919677734,
"learning_rate": 3.810983706078131e-05,
"loss": 2.2635,
"step": 1110
},
{
"epoch": 1.66,
"grad_norm": 3.2239983081817627,
"learning_rate": 3.790993654097405e-05,
"loss": 2.3918,
"step": 1120
},
{
"epoch": 1.67,
"grad_norm": 2.4736838340759277,
"learning_rate": 3.770890404930738e-05,
"loss": 2.3823,
"step": 1130
},
{
"epoch": 1.69,
"grad_norm": 2.585200548171997,
"learning_rate": 3.7506757212755886e-05,
"loss": 2.3349,
"step": 1140
},
{
"epoch": 1.7,
"grad_norm": 2.8950488567352295,
"learning_rate": 3.730351375600239e-05,
"loss": 2.2586,
"step": 1150
},
{
"epoch": 1.72,
"grad_norm": 2.7123405933380127,
"learning_rate": 3.7099191499883806e-05,
"loss": 2.309,
"step": 1160
},
{
"epoch": 1.73,
"grad_norm": 2.049273729324341,
"learning_rate": 3.6893808359828565e-05,
"loss": 2.3608,
"step": 1170
},
{
"epoch": 1.75,
"grad_norm": 2.6950619220733643,
"learning_rate": 3.668738234428575e-05,
"loss": 2.4085,
"step": 1180
},
{
"epoch": 1.76,
"grad_norm": 3.231593370437622,
"learning_rate": 3.64799315531461e-05,
"loss": 2.2365,
"step": 1190
},
{
"epoch": 1.78,
"grad_norm": 3.310612201690674,
"learning_rate": 3.627147417615493e-05,
"loss": 2.3518,
"step": 1200
},
{
"epoch": 1.78,
"eval_loss": 2.2971346378326416,
"eval_runtime": 96.9315,
"eval_samples_per_second": 6.19,
"eval_steps_per_second": 3.095,
"step": 1200
},
{
"epoch": 1.79,
"grad_norm": 2.5581092834472656,
"learning_rate": 3.606202849131723e-05,
"loss": 2.2343,
"step": 1210
},
{
"epoch": 1.81,
"grad_norm": 2.7495291233062744,
"learning_rate": 3.585161286329503e-05,
"loss": 2.3144,
"step": 1220
},
{
"epoch": 1.82,
"grad_norm": 1.433355689048767,
"learning_rate": 3.564024574179713e-05,
"loss": 2.4354,
"step": 1230
},
{
"epoch": 1.84,
"grad_norm": 1.7245852947235107,
"learning_rate": 3.542794565996137e-05,
"loss": 2.405,
"step": 1240
},
{
"epoch": 1.85,
"grad_norm": 2.598426103591919,
"learning_rate": 3.5214731232729626e-05,
"loss": 2.4057,
"step": 1250
},
{
"epoch": 1.87,
"grad_norm": 2.4231202602386475,
"learning_rate": 3.500062115521562e-05,
"loss": 2.233,
"step": 1260
},
{
"epoch": 1.88,
"grad_norm": 2.9336726665496826,
"learning_rate": 3.478563420106565e-05,
"loss": 2.5745,
"step": 1270
},
{
"epoch": 1.9,
"grad_norm": 2.057365655899048,
"learning_rate": 3.4569789220812544e-05,
"loss": 2.4635,
"step": 1280
},
{
"epoch": 1.91,
"grad_norm": 1.8743510246276855,
"learning_rate": 3.435310514022272e-05,
"loss": 2.3892,
"step": 1290
},
{
"epoch": 1.93,
"grad_norm": 2.422725200653076,
"learning_rate": 3.4135600958636794e-05,
"loss": 2.4463,
"step": 1300
},
{
"epoch": 1.94,
"grad_norm": 2.9806418418884277,
"learning_rate": 3.391729574730365e-05,
"loss": 2.2907,
"step": 1310
},
{
"epoch": 1.96,
"grad_norm": 2.656452178955078,
"learning_rate": 3.369820864770822e-05,
"loss": 2.55,
"step": 1320
},
{
"epoch": 1.97,
"grad_norm": 1.4007813930511475,
"learning_rate": 3.347835886989318e-05,
"loss": 2.4001,
"step": 1330
},
{
"epoch": 1.99,
"grad_norm": 2.9661433696746826,
"learning_rate": 3.3257765690774474e-05,
"loss": 2.2728,
"step": 1340
},
{
"epoch": 2.0,
"grad_norm": 2.8605289459228516,
"learning_rate": 3.303644845245114e-05,
"loss": 2.4102,
"step": 1350
},
{
"epoch": 2.01,
"grad_norm": 2.4378559589385986,
"learning_rate": 3.2814426560509335e-05,
"loss": 2.3268,
"step": 1360
},
{
"epoch": 2.03,
"grad_norm": 2.231828212738037,
"learning_rate": 3.259171948232081e-05,
"loss": 2.265,
"step": 1370
},
{
"epoch": 2.04,
"grad_norm": 3.6883370876312256,
"learning_rate": 3.236834674533595e-05,
"loss": 2.3077,
"step": 1380
},
{
"epoch": 2.06,
"grad_norm": 2.531064510345459,
"learning_rate": 3.214432793537159e-05,
"loss": 2.2186,
"step": 1390
},
{
"epoch": 2.07,
"grad_norm": 3.7311625480651855,
"learning_rate": 3.1919682694893676e-05,
"loss": 2.3739,
"step": 1400
},
{
"epoch": 2.07,
"eval_loss": 2.2983055114746094,
"eval_runtime": 97.4749,
"eval_samples_per_second": 6.155,
"eval_steps_per_second": 3.078,
"step": 1400
},
{
"epoch": 2.09,
"grad_norm": 2.1773197650909424,
"learning_rate": 3.169443072129498e-05,
"loss": 2.3585,
"step": 1410
},
{
"epoch": 2.1,
"grad_norm": 3.2135908603668213,
"learning_rate": 3.146859176516795e-05,
"loss": 2.4114,
"step": 1420
},
{
"epoch": 2.12,
"grad_norm": 2.469650983810425,
"learning_rate": 3.1242185628573e-05,
"loss": 2.4616,
"step": 1430
},
{
"epoch": 2.13,
"grad_norm": 3.1853158473968506,
"learning_rate": 3.101523216330216e-05,
"loss": 2.4351,
"step": 1440
},
{
"epoch": 2.15,
"grad_norm": 3.484740972518921,
"learning_rate": 3.0787751269138454e-05,
"loss": 2.4084,
"step": 1450
},
{
"epoch": 2.16,
"grad_norm": 2.925419330596924,
"learning_rate": 3.055976289211105e-05,
"loss": 2.3629,
"step": 1460
},
{
"epoch": 2.18,
"grad_norm": 2.416266918182373,
"learning_rate": 3.033128702274634e-05,
"loss": 2.3339,
"step": 1470
},
{
"epoch": 2.19,
"grad_norm": 2.828092575073242,
"learning_rate": 3.010234369431511e-05,
"loss": 2.2583,
"step": 1480
},
{
"epoch": 2.21,
"grad_norm": 2.0409436225891113,
"learning_rate": 2.9872952981076008e-05,
"loss": 2.0624,
"step": 1490
},
{
"epoch": 2.22,
"grad_norm": 2.849675416946411,
"learning_rate": 2.9643134996515364e-05,
"loss": 2.3726,
"step": 1500
},
{
"epoch": 2.24,
"grad_norm": 4.13971471786499,
"learning_rate": 2.9412909891583613e-05,
"loss": 2.2965,
"step": 1510
},
{
"epoch": 2.25,
"grad_norm": 3.702918529510498,
"learning_rate": 2.9182297852928407e-05,
"loss": 2.4658,
"step": 1520
},
{
"epoch": 2.27,
"grad_norm": 3.2200419902801514,
"learning_rate": 2.8951319101124598e-05,
"loss": 2.4594,
"step": 1530
},
{
"epoch": 2.28,
"grad_norm": 2.465409517288208,
"learning_rate": 2.8719993888901258e-05,
"loss": 2.4301,
"step": 1540
},
{
"epoch": 2.3,
"grad_norm": 2.5337352752685547,
"learning_rate": 2.848834249936589e-05,
"loss": 2.3253,
"step": 1550
},
{
"epoch": 2.31,
"grad_norm": 3.3071987628936768,
"learning_rate": 2.8256385244225926e-05,
"loss": 2.6393,
"step": 1560
},
{
"epoch": 2.33,
"grad_norm": 2.4905800819396973,
"learning_rate": 2.802414246200781e-05,
"loss": 2.1755,
"step": 1570
},
{
"epoch": 2.34,
"grad_norm": 2.8511528968811035,
"learning_rate": 2.7791634516273574e-05,
"loss": 2.2376,
"step": 1580
},
{
"epoch": 2.36,
"grad_norm": 2.7542080879211426,
"learning_rate": 2.755888179383543e-05,
"loss": 2.3509,
"step": 1590
},
{
"epoch": 2.37,
"grad_norm": 3.257232189178467,
"learning_rate": 2.7325904702968137e-05,
"loss": 2.2619,
"step": 1600
},
{
"epoch": 2.37,
"eval_loss": 2.294617176055908,
"eval_runtime": 98.0772,
"eval_samples_per_second": 6.118,
"eval_steps_per_second": 3.059,
"step": 1600
},
{
"epoch": 2.39,
"grad_norm": 2.707037925720215,
"learning_rate": 2.7092723671619565e-05,
"loss": 2.4258,
"step": 1610
},
{
"epoch": 2.4,
"grad_norm": 3.6930806636810303,
"learning_rate": 2.685935914561954e-05,
"loss": 2.3555,
"step": 1620
},
{
"epoch": 2.41,
"grad_norm": 1.9949381351470947,
"learning_rate": 2.6625831586887116e-05,
"loss": 2.3908,
"step": 1630
},
{
"epoch": 2.43,
"grad_norm": 2.457606554031372,
"learning_rate": 2.6392161471636413e-05,
"loss": 2.2989,
"step": 1640
},
{
"epoch": 2.44,
"grad_norm": 2.2386317253112793,
"learning_rate": 2.615836928858122e-05,
"loss": 2.6807,
"step": 1650
},
{
"epoch": 2.46,
"grad_norm": 2.672177791595459,
"learning_rate": 2.5924475537138497e-05,
"loss": 2.1579,
"step": 1660
},
{
"epoch": 2.47,
"grad_norm": 4.241297721862793,
"learning_rate": 2.569050072563097e-05,
"loss": 2.0706,
"step": 1670
},
{
"epoch": 2.49,
"grad_norm": 2.5108397006988525,
"learning_rate": 2.5456465369488864e-05,
"loss": 2.4219,
"step": 1680
},
{
"epoch": 2.5,
"grad_norm": 2.7684569358825684,
"learning_rate": 2.5222389989451096e-05,
"loss": 2.2234,
"step": 1690
},
{
"epoch": 2.52,
"grad_norm": 3.104278087615967,
"learning_rate": 2.4988295109765972e-05,
"loss": 2.3018,
"step": 1700
},
{
"epoch": 2.53,
"grad_norm": 3.235226631164551,
"learning_rate": 2.4754201256391585e-05,
"loss": 2.364,
"step": 1710
},
{
"epoch": 2.55,
"grad_norm": 2.1415085792541504,
"learning_rate": 2.4520128955196008e-05,
"loss": 2.3683,
"step": 1720
},
{
"epoch": 2.56,
"grad_norm": 2.5002896785736084,
"learning_rate": 2.42860987301576e-05,
"loss": 2.4247,
"step": 1730
},
{
"epoch": 2.58,
"grad_norm": 2.8159451484680176,
"learning_rate": 2.4052131101565364e-05,
"loss": 2.3574,
"step": 1740
},
{
"epoch": 2.59,
"grad_norm": 3.0876357555389404,
"learning_rate": 2.3818246584219726e-05,
"loss": 2.2649,
"step": 1750
},
{
"epoch": 2.61,
"grad_norm": 2.8891026973724365,
"learning_rate": 2.3584465685633738e-05,
"loss": 2.4012,
"step": 1760
},
{
"epoch": 2.62,
"grad_norm": 2.3504886627197266,
"learning_rate": 2.335080890423491e-05,
"loss": 2.3263,
"step": 1770
},
{
"epoch": 2.64,
"grad_norm": 2.84779691696167,
"learning_rate": 2.3117296727567897e-05,
"loss": 2.4177,
"step": 1780
},
{
"epoch": 2.65,
"grad_norm": 2.4880871772766113,
"learning_rate": 2.288394963049807e-05,
"loss": 2.3029,
"step": 1790
},
{
"epoch": 2.67,
"grad_norm": 2.4965240955352783,
"learning_rate": 2.2650788073416293e-05,
"loss": 2.2876,
"step": 1800
},
{
"epoch": 2.67,
"eval_loss": 2.287304401397705,
"eval_runtime": 97.8793,
"eval_samples_per_second": 6.13,
"eval_steps_per_second": 3.065,
"step": 1800
},
{
"epoch": 2.68,
"grad_norm": 3.6506803035736084,
"learning_rate": 2.2417832500444827e-05,
"loss": 2.2686,
"step": 1810
},
{
"epoch": 2.7,
"grad_norm": 2.156888008117676,
"learning_rate": 2.2185103337644833e-05,
"loss": 2.4572,
"step": 1820
},
{
"epoch": 2.71,
"grad_norm": 2.9049007892608643,
"learning_rate": 2.1952620991225285e-05,
"loss": 2.4824,
"step": 1830
},
{
"epoch": 2.73,
"grad_norm": 3.4357845783233643,
"learning_rate": 2.1720405845753792e-05,
"loss": 2.3334,
"step": 1840
},
{
"epoch": 2.74,
"grad_norm": 2.405451774597168,
"learning_rate": 2.148847826236914e-05,
"loss": 2.4271,
"step": 1850
},
{
"epoch": 2.76,
"grad_norm": 2.0909016132354736,
"learning_rate": 2.125685857699609e-05,
"loss": 2.3499,
"step": 1860
},
{
"epoch": 2.77,
"grad_norm": 3.3600564002990723,
"learning_rate": 2.1025567098562177e-05,
"loss": 2.2665,
"step": 1870
},
{
"epoch": 2.79,
"grad_norm": 3.0894439220428467,
"learning_rate": 2.0794624107217056e-05,
"loss": 2.3211,
"step": 1880
},
{
"epoch": 2.8,
"grad_norm": 2.564870834350586,
"learning_rate": 2.056404985255424e-05,
"loss": 2.3905,
"step": 1890
},
{
"epoch": 2.81,
"grad_norm": 2.177769422531128,
"learning_rate": 2.0333864551835602e-05,
"loss": 2.4703,
"step": 1900
},
{
"epoch": 2.83,
"grad_norm": 2.499175548553467,
"learning_rate": 2.010408838821866e-05,
"loss": 2.3287,
"step": 1910
},
{
"epoch": 2.84,
"grad_norm": 3.076934337615967,
"learning_rate": 1.987474150898691e-05,
"loss": 2.3857,
"step": 1920
},
{
"epoch": 2.86,
"grad_norm": 5.456985950469971,
"learning_rate": 1.9645844023783206e-05,
"loss": 2.3238,
"step": 1930
},
{
"epoch": 2.87,
"grad_norm": 2.502319574356079,
"learning_rate": 1.941741600284656e-05,
"loss": 2.3027,
"step": 1940
},
{
"epoch": 2.89,
"grad_norm": 3.1800990104675293,
"learning_rate": 1.918947747525232e-05,
"loss": 2.086,
"step": 1950
},
{
"epoch": 2.9,
"grad_norm": 3.400146245956421,
"learning_rate": 1.896204842715596e-05,
"loss": 2.5469,
"step": 1960
},
{
"epoch": 2.92,
"grad_norm": 2.4540586471557617,
"learning_rate": 1.873514880004065e-05,
"loss": 2.2501,
"step": 1970
},
{
"epoch": 2.93,
"grad_norm": 3.094639778137207,
"learning_rate": 1.8508798488968803e-05,
"loss": 2.3037,
"step": 1980
},
{
"epoch": 2.95,
"grad_norm": 2.7142815589904785,
"learning_rate": 1.8283017340837517e-05,
"loss": 2.2974,
"step": 1990
},
{
"epoch": 2.96,
"grad_norm": 2.40388560295105,
"learning_rate": 1.8057825152638478e-05,
"loss": 2.2484,
"step": 2000
},
{
"epoch": 2.96,
"eval_loss": 2.2887699604034424,
"eval_runtime": 100.5569,
"eval_samples_per_second": 5.967,
"eval_steps_per_second": 2.983,
"step": 2000
},
{
"epoch": 2.98,
"grad_norm": 3.5946638584136963,
"learning_rate": 1.7833241669722015e-05,
"loss": 2.2191,
"step": 2010
},
{
"epoch": 2.99,
"grad_norm": 3.1359758377075195,
"learning_rate": 1.760928658406587e-05,
"loss": 2.4429,
"step": 2020
},
{
"epoch": 3.01,
"grad_norm": 3.105003833770752,
"learning_rate": 1.738597953254848e-05,
"loss": 2.3241,
"step": 2030
},
{
"epoch": 3.02,
"grad_norm": 2.3050458431243896,
"learning_rate": 1.716334009522726e-05,
"loss": 2.3608,
"step": 2040
},
{
"epoch": 3.04,
"grad_norm": 2.2272346019744873,
"learning_rate": 1.6941387793621673e-05,
"loss": 2.3107,
"step": 2050
},
{
"epoch": 3.05,
"grad_norm": 2.0482161045074463,
"learning_rate": 1.672014208900165e-05,
"loss": 2.1823,
"step": 2060
},
{
"epoch": 3.07,
"grad_norm": 2.0835390090942383,
"learning_rate": 1.6499622380681096e-05,
"loss": 2.1622,
"step": 2070
},
{
"epoch": 3.08,
"grad_norm": 3.687225103378296,
"learning_rate": 1.6279848004316972e-05,
"loss": 2.3643,
"step": 2080
},
{
"epoch": 3.1,
"grad_norm": 3.2139699459075928,
"learning_rate": 1.6060838230213883e-05,
"loss": 2.2241,
"step": 2090
},
{
"epoch": 3.11,
"grad_norm": 3.513046979904175,
"learning_rate": 1.5842612261634392e-05,
"loss": 2.311,
"step": 2100
},
{
"epoch": 3.13,
"grad_norm": 2.698282241821289,
"learning_rate": 1.5625189233115282e-05,
"loss": 2.4009,
"step": 2110
},
{
"epoch": 3.14,
"grad_norm": 2.889256238937378,
"learning_rate": 1.5408588208789733e-05,
"loss": 2.2708,
"step": 2120
},
{
"epoch": 3.16,
"grad_norm": 2.4953372478485107,
"learning_rate": 1.5192828180715824e-05,
"loss": 2.2726,
"step": 2130
},
{
"epoch": 3.17,
"grad_norm": 3.368839740753174,
"learning_rate": 1.4977928067211178e-05,
"loss": 2.0851,
"step": 2140
},
{
"epoch": 3.19,
"grad_norm": 3.3648414611816406,
"learning_rate": 1.4763906711194229e-05,
"loss": 2.11,
"step": 2150
},
{
"epoch": 3.2,
"grad_norm": 2.7509853839874268,
"learning_rate": 1.4550782878531972e-05,
"loss": 2.3487,
"step": 2160
},
{
"epoch": 3.21,
"grad_norm": 3.071002721786499,
"learning_rate": 1.4338575256394612e-05,
"loss": 2.2536,
"step": 2170
},
{
"epoch": 3.23,
"grad_norm": 2.7192609310150146,
"learning_rate": 1.4127302451616936e-05,
"loss": 2.2367,
"step": 2180
},
{
"epoch": 3.24,
"grad_norm": 5.182852268218994,
"learning_rate": 1.3916982989066915e-05,
"loss": 2.0933,
"step": 2190
},
{
"epoch": 3.26,
"grad_norm": 2.816575527191162,
"learning_rate": 1.370763531002132e-05,
"loss": 2.4534,
"step": 2200
},
{
"epoch": 3.26,
"eval_loss": 2.2867271900177,
"eval_runtime": 98.3879,
"eval_samples_per_second": 6.098,
"eval_steps_per_second": 3.049,
"step": 2200
},
{
"epoch": 3.27,
"grad_norm": 2.238353967666626,
"learning_rate": 1.3499277770548823e-05,
"loss": 2.3927,
"step": 2210
},
{
"epoch": 3.29,
"grad_norm": 3.0616304874420166,
"learning_rate": 1.3291928639900436e-05,
"loss": 2.3978,
"step": 2220
},
{
"epoch": 3.3,
"grad_norm": 3.807537317276001,
"learning_rate": 1.3085606098907682e-05,
"loss": 2.1303,
"step": 2230
},
{
"epoch": 3.32,
"grad_norm": 3.6472954750061035,
"learning_rate": 1.2880328238388393e-05,
"loss": 2.3277,
"step": 2240
},
{
"epoch": 3.33,
"grad_norm": 3.634000301361084,
"learning_rate": 1.2676113057560515e-05,
"loss": 2.358,
"step": 2250
},
{
"epoch": 3.35,
"grad_norm": 5.468724727630615,
"learning_rate": 1.2472978462463874e-05,
"loss": 2.4583,
"step": 2260
},
{
"epoch": 3.36,
"grad_norm": 3.201179265975952,
"learning_rate": 1.2270942264390174e-05,
"loss": 2.2543,
"step": 2270
},
{
"epoch": 3.38,
"grad_norm": 2.4082183837890625,
"learning_rate": 1.2070022178321186e-05,
"loss": 2.2401,
"step": 2280
},
{
"epoch": 3.39,
"grad_norm": 3.068176031112671,
"learning_rate": 1.1870235821375553e-05,
"loss": 2.3446,
"step": 2290
},
{
"epoch": 3.41,
"grad_norm": 2.7859139442443848,
"learning_rate": 1.1671600711263991e-05,
"loss": 2.3761,
"step": 2300
},
{
"epoch": 3.42,
"grad_norm": 2.423513650894165,
"learning_rate": 1.1474134264753384e-05,
"loss": 2.2563,
"step": 2310
},
{
"epoch": 3.44,
"grad_norm": 3.0830302238464355,
"learning_rate": 1.1277853796139554e-05,
"loss": 2.2455,
"step": 2320
},
{
"epoch": 3.45,
"grad_norm": 3.237128734588623,
"learning_rate": 1.1082776515729201e-05,
"loss": 2.3861,
"step": 2330
},
{
"epoch": 3.47,
"grad_norm": 2.9493908882141113,
"learning_rate": 1.0888919528330777e-05,
"loss": 2.0657,
"step": 2340
},
{
"epoch": 3.48,
"grad_norm": 3.7209978103637695,
"learning_rate": 1.0696299831754753e-05,
"loss": 2.4492,
"step": 2350
},
{
"epoch": 3.5,
"grad_norm": 2.332671880722046,
"learning_rate": 1.0504934315323181e-05,
"loss": 2.3108,
"step": 2360
},
{
"epoch": 3.51,
"grad_norm": 3.0048203468322754,
"learning_rate": 1.0314839758388859e-05,
"loss": 2.5104,
"step": 2370
},
{
"epoch": 3.53,
"grad_norm": 3.380918502807617,
"learning_rate": 1.0126032828863982e-05,
"loss": 2.3024,
"step": 2380
},
{
"epoch": 3.54,
"grad_norm": 2.693096876144409,
"learning_rate": 9.938530081758764e-06,
"loss": 2.3422,
"step": 2390
},
{
"epoch": 3.56,
"grad_norm": 2.64311146736145,
"learning_rate": 9.752347957729804e-06,
"loss": 2.3934,
"step": 2400
},
{
"epoch": 3.56,
"eval_loss": 2.2875092029571533,
"eval_runtime": 98.3803,
"eval_samples_per_second": 6.099,
"eval_steps_per_second": 3.049,
"step": 2400
},
{
"epoch": 3.57,
"grad_norm": 2.693216562271118,
"learning_rate": 9.567502781638516e-06,
"loss": 2.3249,
"step": 2410
},
{
"epoch": 3.59,
"grad_norm": 2.68764066696167,
"learning_rate": 9.384010761119787e-06,
"loss": 2.2552,
"step": 2420
},
{
"epoch": 3.6,
"grad_norm": 4.221546649932861,
"learning_rate": 9.201887985160804e-06,
"loss": 2.3362,
"step": 2430
},
{
"epoch": 3.61,
"grad_norm": 2.777925729751587,
"learning_rate": 9.039161391719244e-06,
"loss": 2.3256,
"step": 2440
},
{
"epoch": 3.63,
"grad_norm": 2.7611911296844482,
"learning_rate": 8.859684074465835e-06,
"loss": 2.2209,
"step": 2450
},
{
"epoch": 3.64,
"grad_norm": 2.7354393005371094,
"learning_rate": 8.681621975898577e-06,
"loss": 2.1957,
"step": 2460
},
{
"epoch": 3.66,
"grad_norm": 2.901160478591919,
"learning_rate": 8.504990708897056e-06,
"loss": 2.2935,
"step": 2470
},
{
"epoch": 3.67,
"grad_norm": 2.4266469478607178,
"learning_rate": 8.329805760882403e-06,
"loss": 2.307,
"step": 2480
},
{
"epoch": 3.69,
"grad_norm": 2.3984947204589844,
"learning_rate": 8.156082492459257e-06,
"loss": 2.3943,
"step": 2490
},
{
"epoch": 3.7,
"grad_norm": 2.6705055236816406,
"learning_rate": 7.983836136068984e-06,
"loss": 2.3774,
"step": 2500
},
{
"epoch": 3.72,
"grad_norm": 3.173973321914673,
"learning_rate": 7.813081794653995e-06,
"loss": 2.2757,
"step": 2510
},
{
"epoch": 3.73,
"grad_norm": 3.104217529296875,
"learning_rate": 7.643834440333553e-06,
"loss": 2.2961,
"step": 2520
},
{
"epoch": 3.75,
"grad_norm": 3.088330030441284,
"learning_rate": 7.476108913090915e-06,
"loss": 2.2001,
"step": 2530
},
{
"epoch": 3.76,
"grad_norm": 3.717886447906494,
"learning_rate": 7.309919919472208e-06,
"loss": 2.1859,
"step": 2540
},
{
"epoch": 3.78,
"grad_norm": 3.12146258354187,
"learning_rate": 7.145282031296841e-06,
"loss": 2.2422,
"step": 2550
},
{
"epoch": 3.79,
"grad_norm": 3.212069272994995,
"learning_rate": 6.982209684379892e-06,
"loss": 2.1191,
"step": 2560
},
{
"epoch": 3.81,
"grad_norm": 3.0071327686309814,
"learning_rate": 6.8207171772662976e-06,
"loss": 2.1472,
"step": 2570
},
{
"epoch": 3.82,
"grad_norm": 3.0386757850646973,
"learning_rate": 6.660818669977134e-06,
"loss": 2.3547,
"step": 2580
},
{
"epoch": 3.84,
"grad_norm": 2.2448551654815674,
"learning_rate": 6.5025281827680335e-06,
"loss": 2.2866,
"step": 2590
},
{
"epoch": 3.85,
"grad_norm": 3.914092779159546,
"learning_rate": 6.345859594899886e-06,
"loss": 2.3713,
"step": 2600
},
{
"epoch": 3.85,
"eval_loss": 2.2858927249908447,
"eval_runtime": 98.5519,
"eval_samples_per_second": 6.088,
"eval_steps_per_second": 3.044,
"step": 2600
},
{
"epoch": 3.87,
"grad_norm": 2.350407600402832,
"learning_rate": 6.1908266434218235e-06,
"loss": 2.2876,
"step": 2610
},
{
"epoch": 3.88,
"grad_norm": 2.7468740940093994,
"learning_rate": 6.037442921966771e-06,
"loss": 2.3253,
"step": 2620
},
{
"epoch": 3.9,
"grad_norm": 3.026620626449585,
"learning_rate": 5.885721879559514e-06,
"loss": 2.2033,
"step": 2630
},
{
"epoch": 3.91,
"grad_norm": 2.2398440837860107,
"learning_rate": 5.735676819437425e-06,
"loss": 2.317,
"step": 2640
},
{
"epoch": 3.93,
"grad_norm": 2.4124555587768555,
"learning_rate": 5.587320897884066e-06,
"loss": 2.284,
"step": 2650
},
{
"epoch": 3.94,
"grad_norm": 2.4340391159057617,
"learning_rate": 5.440667123075558e-06,
"loss": 2.3012,
"step": 2660
},
{
"epoch": 3.96,
"grad_norm": 2.7486612796783447,
"learning_rate": 5.295728353940038e-06,
"loss": 2.5206,
"step": 2670
},
{
"epoch": 3.97,
"grad_norm": 2.5270161628723145,
"learning_rate": 5.152517299030127e-06,
"loss": 2.5541,
"step": 2680
},
{
"epoch": 3.99,
"grad_norm": 3.589616298675537,
"learning_rate": 5.011046515408657e-06,
"loss": 2.3475,
"step": 2690
},
{
"epoch": 4.0,
"grad_norm": 2.27154541015625,
"learning_rate": 4.871328407547587e-06,
"loss": 2.4889,
"step": 2700
},
{
"epoch": 4.01,
"grad_norm": 2.9212470054626465,
"learning_rate": 4.733375226240408e-06,
"loss": 2.4318,
"step": 2710
},
{
"epoch": 4.03,
"grad_norm": 3.5055928230285645,
"learning_rate": 4.597199067527907e-06,
"loss": 2.1628,
"step": 2720
},
{
"epoch": 4.04,
"grad_norm": 2.520705223083496,
"learning_rate": 4.462811871637618e-06,
"loss": 2.0723,
"step": 2730
},
{
"epoch": 4.06,
"grad_norm": 3.2816295623779297,
"learning_rate": 4.330225421936823e-06,
"loss": 2.2386,
"step": 2740
},
{
"epoch": 4.07,
"grad_norm": 3.64699649810791,
"learning_rate": 4.1994513438994156e-06,
"loss": 2.1135,
"step": 2750
},
{
"epoch": 4.09,
"grad_norm": 3.278775930404663,
"learning_rate": 4.070501104086488e-06,
"loss": 2.2199,
"step": 2760
},
{
"epoch": 4.1,
"grad_norm": 1.8690662384033203,
"learning_rate": 3.943386009140984e-06,
"loss": 2.2364,
"step": 2770
},
{
"epoch": 4.12,
"grad_norm": 3.0856454372406006,
"learning_rate": 3.818117204796262e-06,
"loss": 2.0439,
"step": 2780
},
{
"epoch": 4.13,
"grad_norm": 3.822516679763794,
"learning_rate": 3.694705674898827e-06,
"loss": 2.2703,
"step": 2790
},
{
"epoch": 4.15,
"grad_norm": 5.145390510559082,
"learning_rate": 3.573162240445238e-06,
"loss": 2.3365,
"step": 2800
},
{
"epoch": 4.15,
"eval_loss": 2.2857470512390137,
"eval_runtime": 98.4481,
"eval_samples_per_second": 6.095,
"eval_steps_per_second": 3.047,
"step": 2800
}
],
"logging_steps": 10,
"max_steps": 3375,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 200,
"total_flos": 7.882780555954094e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}