Muhammad Khalifa
add llama-2 alpaca
43c74a0
{
"best_metric": 1.0393410921096802,
"best_model_checkpoint": "checkpoints/instrucode/text_models/llama-2-7b/checkpoint-6000",
"epoch": 1.9198464122870171,
"eval_steps": 200,
"global_step": 6000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 9e-06,
"loss": 2.0232,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 1.9e-05,
"loss": 1.8837,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.9127,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 3.8e-05,
"loss": 1.8061,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 4.8e-05,
"loss": 1.5632,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 5.8e-05,
"loss": 1.3373,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 6.800000000000001e-05,
"loss": 1.2455,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 7.800000000000001e-05,
"loss": 1.2518,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 8.800000000000001e-05,
"loss": 1.2229,
"step": 90
},
{
"epoch": 0.03,
"learning_rate": 9.8e-05,
"loss": 1.1142,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 9.994847020933978e-05,
"loss": 1.1445,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 9.989049919484702e-05,
"loss": 1.0731,
"step": 120
},
{
"epoch": 0.04,
"learning_rate": 9.982608695652175e-05,
"loss": 1.1097,
"step": 130
},
{
"epoch": 0.04,
"learning_rate": 9.976167471819646e-05,
"loss": 1.1207,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 9.969726247987118e-05,
"loss": 1.0919,
"step": 150
},
{
"epoch": 0.05,
"learning_rate": 9.96328502415459e-05,
"loss": 1.0958,
"step": 160
},
{
"epoch": 0.05,
"learning_rate": 9.956843800322063e-05,
"loss": 1.1041,
"step": 170
},
{
"epoch": 0.06,
"learning_rate": 9.950402576489533e-05,
"loss": 1.1192,
"step": 180
},
{
"epoch": 0.06,
"learning_rate": 9.943961352657005e-05,
"loss": 1.0308,
"step": 190
},
{
"epoch": 0.06,
"learning_rate": 9.937520128824477e-05,
"loss": 1.0693,
"step": 200
},
{
"epoch": 0.06,
"eval_loss": 1.0856528282165527,
"eval_runtime": 118.5535,
"eval_samples_per_second": 16.87,
"eval_steps_per_second": 2.109,
"step": 200
},
{
"epoch": 0.07,
"learning_rate": 9.931078904991949e-05,
"loss": 1.0917,
"step": 210
},
{
"epoch": 0.07,
"learning_rate": 9.924637681159421e-05,
"loss": 1.0982,
"step": 220
},
{
"epoch": 0.07,
"learning_rate": 9.918196457326893e-05,
"loss": 1.0737,
"step": 230
},
{
"epoch": 0.08,
"learning_rate": 9.911755233494364e-05,
"loss": 1.0501,
"step": 240
},
{
"epoch": 0.08,
"learning_rate": 9.905314009661836e-05,
"loss": 1.0305,
"step": 250
},
{
"epoch": 0.08,
"learning_rate": 9.898872785829308e-05,
"loss": 1.0801,
"step": 260
},
{
"epoch": 0.09,
"learning_rate": 9.89243156199678e-05,
"loss": 1.0732,
"step": 270
},
{
"epoch": 0.09,
"learning_rate": 9.885990338164252e-05,
"loss": 1.0894,
"step": 280
},
{
"epoch": 0.09,
"learning_rate": 9.879549114331724e-05,
"loss": 1.0716,
"step": 290
},
{
"epoch": 0.1,
"learning_rate": 9.873107890499196e-05,
"loss": 1.0448,
"step": 300
},
{
"epoch": 0.1,
"learning_rate": 9.866666666666668e-05,
"loss": 1.0576,
"step": 310
},
{
"epoch": 0.1,
"learning_rate": 9.86022544283414e-05,
"loss": 1.086,
"step": 320
},
{
"epoch": 0.11,
"learning_rate": 9.85378421900161e-05,
"loss": 1.0878,
"step": 330
},
{
"epoch": 0.11,
"learning_rate": 9.847342995169082e-05,
"loss": 1.1065,
"step": 340
},
{
"epoch": 0.11,
"learning_rate": 9.840901771336555e-05,
"loss": 1.0576,
"step": 350
},
{
"epoch": 0.12,
"learning_rate": 9.834460547504027e-05,
"loss": 1.0438,
"step": 360
},
{
"epoch": 0.12,
"learning_rate": 9.828019323671497e-05,
"loss": 1.0566,
"step": 370
},
{
"epoch": 0.12,
"learning_rate": 9.821578099838969e-05,
"loss": 1.026,
"step": 380
},
{
"epoch": 0.12,
"learning_rate": 9.815136876006442e-05,
"loss": 1.047,
"step": 390
},
{
"epoch": 0.13,
"learning_rate": 9.808695652173914e-05,
"loss": 1.0785,
"step": 400
},
{
"epoch": 0.13,
"eval_loss": 1.0718845129013062,
"eval_runtime": 118.4414,
"eval_samples_per_second": 16.886,
"eval_steps_per_second": 2.111,
"step": 400
},
{
"epoch": 0.13,
"learning_rate": 9.802254428341385e-05,
"loss": 1.0367,
"step": 410
},
{
"epoch": 0.13,
"learning_rate": 9.795813204508857e-05,
"loss": 1.0285,
"step": 420
},
{
"epoch": 0.14,
"learning_rate": 9.789371980676329e-05,
"loss": 1.1112,
"step": 430
},
{
"epoch": 0.14,
"learning_rate": 9.7829307568438e-05,
"loss": 1.0778,
"step": 440
},
{
"epoch": 0.14,
"learning_rate": 9.776489533011272e-05,
"loss": 1.0484,
"step": 450
},
{
"epoch": 0.15,
"learning_rate": 9.770048309178744e-05,
"loss": 1.0761,
"step": 460
},
{
"epoch": 0.15,
"learning_rate": 9.763607085346216e-05,
"loss": 1.0681,
"step": 470
},
{
"epoch": 0.15,
"learning_rate": 9.757165861513688e-05,
"loss": 1.0956,
"step": 480
},
{
"epoch": 0.16,
"learning_rate": 9.75072463768116e-05,
"loss": 1.0765,
"step": 490
},
{
"epoch": 0.16,
"learning_rate": 9.744283413848632e-05,
"loss": 1.0752,
"step": 500
},
{
"epoch": 0.16,
"learning_rate": 9.737842190016104e-05,
"loss": 1.0817,
"step": 510
},
{
"epoch": 0.17,
"learning_rate": 9.731400966183575e-05,
"loss": 1.0408,
"step": 520
},
{
"epoch": 0.17,
"learning_rate": 9.724959742351047e-05,
"loss": 1.0893,
"step": 530
},
{
"epoch": 0.17,
"learning_rate": 9.718518518518519e-05,
"loss": 1.0742,
"step": 540
},
{
"epoch": 0.18,
"learning_rate": 9.712077294685991e-05,
"loss": 1.1052,
"step": 550
},
{
"epoch": 0.18,
"learning_rate": 9.705636070853462e-05,
"loss": 1.017,
"step": 560
},
{
"epoch": 0.18,
"learning_rate": 9.699194847020935e-05,
"loss": 1.0808,
"step": 570
},
{
"epoch": 0.19,
"learning_rate": 9.692753623188407e-05,
"loss": 1.048,
"step": 580
},
{
"epoch": 0.19,
"learning_rate": 9.686312399355879e-05,
"loss": 1.0592,
"step": 590
},
{
"epoch": 0.19,
"learning_rate": 9.679871175523349e-05,
"loss": 1.0441,
"step": 600
},
{
"epoch": 0.19,
"eval_loss": 1.0663692951202393,
"eval_runtime": 118.6583,
"eval_samples_per_second": 16.855,
"eval_steps_per_second": 2.107,
"step": 600
},
{
"epoch": 0.2,
"learning_rate": 9.673429951690822e-05,
"loss": 1.0924,
"step": 610
},
{
"epoch": 0.2,
"learning_rate": 9.666988727858294e-05,
"loss": 1.088,
"step": 620
},
{
"epoch": 0.2,
"learning_rate": 9.660547504025766e-05,
"loss": 1.0763,
"step": 630
},
{
"epoch": 0.2,
"learning_rate": 9.654106280193237e-05,
"loss": 1.042,
"step": 640
},
{
"epoch": 0.21,
"learning_rate": 9.647665056360708e-05,
"loss": 1.0745,
"step": 650
},
{
"epoch": 0.21,
"learning_rate": 9.641223832528182e-05,
"loss": 1.0777,
"step": 660
},
{
"epoch": 0.21,
"learning_rate": 9.634782608695652e-05,
"loss": 1.0841,
"step": 670
},
{
"epoch": 0.22,
"learning_rate": 9.628341384863124e-05,
"loss": 1.0393,
"step": 680
},
{
"epoch": 0.22,
"learning_rate": 9.621900161030596e-05,
"loss": 1.0496,
"step": 690
},
{
"epoch": 0.22,
"learning_rate": 9.615458937198069e-05,
"loss": 1.0676,
"step": 700
},
{
"epoch": 0.23,
"learning_rate": 9.60901771336554e-05,
"loss": 1.0929,
"step": 710
},
{
"epoch": 0.23,
"learning_rate": 9.602576489533011e-05,
"loss": 1.08,
"step": 720
},
{
"epoch": 0.23,
"learning_rate": 9.596135265700483e-05,
"loss": 1.0723,
"step": 730
},
{
"epoch": 0.24,
"learning_rate": 9.589694041867955e-05,
"loss": 1.0565,
"step": 740
},
{
"epoch": 0.24,
"learning_rate": 9.583252818035427e-05,
"loss": 1.0756,
"step": 750
},
{
"epoch": 0.24,
"learning_rate": 9.576811594202899e-05,
"loss": 1.0197,
"step": 760
},
{
"epoch": 0.25,
"learning_rate": 9.570370370370371e-05,
"loss": 0.9768,
"step": 770
},
{
"epoch": 0.25,
"learning_rate": 9.563929146537843e-05,
"loss": 1.0742,
"step": 780
},
{
"epoch": 0.25,
"learning_rate": 9.557487922705315e-05,
"loss": 1.0732,
"step": 790
},
{
"epoch": 0.26,
"learning_rate": 9.551046698872786e-05,
"loss": 1.0664,
"step": 800
},
{
"epoch": 0.26,
"eval_loss": 1.062617301940918,
"eval_runtime": 118.4976,
"eval_samples_per_second": 16.878,
"eval_steps_per_second": 2.11,
"step": 800
},
{
"epoch": 0.26,
"learning_rate": 9.544605475040258e-05,
"loss": 1.0821,
"step": 810
},
{
"epoch": 0.26,
"learning_rate": 9.53816425120773e-05,
"loss": 1.0551,
"step": 820
},
{
"epoch": 0.27,
"learning_rate": 9.531723027375202e-05,
"loss": 1.0281,
"step": 830
},
{
"epoch": 0.27,
"learning_rate": 9.525281803542674e-05,
"loss": 1.0604,
"step": 840
},
{
"epoch": 0.27,
"learning_rate": 9.518840579710146e-05,
"loss": 1.0327,
"step": 850
},
{
"epoch": 0.28,
"learning_rate": 9.512399355877616e-05,
"loss": 1.0879,
"step": 860
},
{
"epoch": 0.28,
"learning_rate": 9.505958132045088e-05,
"loss": 1.0594,
"step": 870
},
{
"epoch": 0.28,
"learning_rate": 9.499516908212561e-05,
"loss": 1.0701,
"step": 880
},
{
"epoch": 0.28,
"learning_rate": 9.493075684380033e-05,
"loss": 1.0606,
"step": 890
},
{
"epoch": 0.29,
"learning_rate": 9.486634460547504e-05,
"loss": 1.079,
"step": 900
},
{
"epoch": 0.29,
"learning_rate": 9.480193236714976e-05,
"loss": 1.0503,
"step": 910
},
{
"epoch": 0.29,
"learning_rate": 9.473752012882449e-05,
"loss": 1.048,
"step": 920
},
{
"epoch": 0.3,
"learning_rate": 9.467310789049921e-05,
"loss": 1.0758,
"step": 930
},
{
"epoch": 0.3,
"learning_rate": 9.460869565217391e-05,
"loss": 1.0308,
"step": 940
},
{
"epoch": 0.3,
"learning_rate": 9.454428341384863e-05,
"loss": 1.0528,
"step": 950
},
{
"epoch": 0.31,
"learning_rate": 9.447987117552335e-05,
"loss": 1.0377,
"step": 960
},
{
"epoch": 0.31,
"learning_rate": 9.441545893719808e-05,
"loss": 1.0504,
"step": 970
},
{
"epoch": 0.31,
"learning_rate": 9.435104669887279e-05,
"loss": 1.0575,
"step": 980
},
{
"epoch": 0.32,
"learning_rate": 9.42866344605475e-05,
"loss": 1.0842,
"step": 990
},
{
"epoch": 0.32,
"learning_rate": 9.422222222222223e-05,
"loss": 1.099,
"step": 1000
},
{
"epoch": 0.32,
"eval_loss": 1.061242699623108,
"eval_runtime": 118.614,
"eval_samples_per_second": 16.861,
"eval_steps_per_second": 2.108,
"step": 1000
},
{
"epoch": 0.32,
"learning_rate": 9.415780998389694e-05,
"loss": 1.0378,
"step": 1010
},
{
"epoch": 0.33,
"learning_rate": 9.409339774557166e-05,
"loss": 1.0768,
"step": 1020
},
{
"epoch": 0.33,
"learning_rate": 9.402898550724638e-05,
"loss": 1.0809,
"step": 1030
},
{
"epoch": 0.33,
"learning_rate": 9.39645732689211e-05,
"loss": 1.0501,
"step": 1040
},
{
"epoch": 0.34,
"learning_rate": 9.390016103059582e-05,
"loss": 1.0512,
"step": 1050
},
{
"epoch": 0.34,
"learning_rate": 9.383574879227054e-05,
"loss": 1.048,
"step": 1060
},
{
"epoch": 0.34,
"learning_rate": 9.377133655394526e-05,
"loss": 1.1142,
"step": 1070
},
{
"epoch": 0.35,
"learning_rate": 9.370692431561997e-05,
"loss": 1.0862,
"step": 1080
},
{
"epoch": 0.35,
"learning_rate": 9.364251207729468e-05,
"loss": 1.0654,
"step": 1090
},
{
"epoch": 0.35,
"learning_rate": 9.357809983896941e-05,
"loss": 1.0423,
"step": 1100
},
{
"epoch": 0.36,
"learning_rate": 9.351368760064413e-05,
"loss": 1.0398,
"step": 1110
},
{
"epoch": 0.36,
"learning_rate": 9.344927536231885e-05,
"loss": 1.0779,
"step": 1120
},
{
"epoch": 0.36,
"learning_rate": 9.338486312399355e-05,
"loss": 1.0806,
"step": 1130
},
{
"epoch": 0.36,
"learning_rate": 9.332045088566829e-05,
"loss": 1.0668,
"step": 1140
},
{
"epoch": 0.37,
"learning_rate": 9.3256038647343e-05,
"loss": 1.0262,
"step": 1150
},
{
"epoch": 0.37,
"learning_rate": 9.319162640901772e-05,
"loss": 1.0334,
"step": 1160
},
{
"epoch": 0.37,
"learning_rate": 9.312721417069243e-05,
"loss": 1.0793,
"step": 1170
},
{
"epoch": 0.38,
"learning_rate": 9.306280193236715e-05,
"loss": 1.0412,
"step": 1180
},
{
"epoch": 0.38,
"learning_rate": 9.299838969404188e-05,
"loss": 1.079,
"step": 1190
},
{
"epoch": 0.38,
"learning_rate": 9.293397745571659e-05,
"loss": 0.9992,
"step": 1200
},
{
"epoch": 0.38,
"eval_loss": 1.0581145286560059,
"eval_runtime": 124.535,
"eval_samples_per_second": 16.06,
"eval_steps_per_second": 2.007,
"step": 1200
},
{
"epoch": 0.39,
"learning_rate": 9.28695652173913e-05,
"loss": 1.0414,
"step": 1210
},
{
"epoch": 0.39,
"learning_rate": 9.280515297906602e-05,
"loss": 1.0812,
"step": 1220
},
{
"epoch": 0.39,
"learning_rate": 9.274074074074076e-05,
"loss": 1.0552,
"step": 1230
},
{
"epoch": 0.4,
"learning_rate": 9.267632850241546e-05,
"loss": 1.0574,
"step": 1240
},
{
"epoch": 0.4,
"learning_rate": 9.261191626409018e-05,
"loss": 1.0875,
"step": 1250
},
{
"epoch": 0.4,
"learning_rate": 9.25475040257649e-05,
"loss": 1.0563,
"step": 1260
},
{
"epoch": 0.41,
"learning_rate": 9.248309178743962e-05,
"loss": 1.0867,
"step": 1270
},
{
"epoch": 0.41,
"learning_rate": 9.241867954911434e-05,
"loss": 1.0314,
"step": 1280
},
{
"epoch": 0.41,
"learning_rate": 9.235426731078905e-05,
"loss": 1.0841,
"step": 1290
},
{
"epoch": 0.42,
"learning_rate": 9.228985507246377e-05,
"loss": 1.0493,
"step": 1300
},
{
"epoch": 0.42,
"learning_rate": 9.222544283413849e-05,
"loss": 1.1141,
"step": 1310
},
{
"epoch": 0.42,
"learning_rate": 9.216103059581321e-05,
"loss": 1.0405,
"step": 1320
},
{
"epoch": 0.43,
"learning_rate": 9.209661835748793e-05,
"loss": 1.0577,
"step": 1330
},
{
"epoch": 0.43,
"learning_rate": 9.203220611916265e-05,
"loss": 1.0747,
"step": 1340
},
{
"epoch": 0.43,
"learning_rate": 9.196779388083737e-05,
"loss": 1.0313,
"step": 1350
},
{
"epoch": 0.44,
"learning_rate": 9.190338164251207e-05,
"loss": 1.0848,
"step": 1360
},
{
"epoch": 0.44,
"learning_rate": 9.18389694041868e-05,
"loss": 1.0198,
"step": 1370
},
{
"epoch": 0.44,
"learning_rate": 9.177455716586152e-05,
"loss": 1.059,
"step": 1380
},
{
"epoch": 0.44,
"learning_rate": 9.171014492753624e-05,
"loss": 1.013,
"step": 1390
},
{
"epoch": 0.45,
"learning_rate": 9.164573268921095e-05,
"loss": 1.0563,
"step": 1400
},
{
"epoch": 0.45,
"eval_loss": 1.055400013923645,
"eval_runtime": 118.7688,
"eval_samples_per_second": 16.839,
"eval_steps_per_second": 2.105,
"step": 1400
},
{
"epoch": 0.45,
"learning_rate": 9.158132045088568e-05,
"loss": 1.06,
"step": 1410
},
{
"epoch": 0.45,
"learning_rate": 9.15169082125604e-05,
"loss": 1.0426,
"step": 1420
},
{
"epoch": 0.46,
"learning_rate": 9.14524959742351e-05,
"loss": 1.0642,
"step": 1430
},
{
"epoch": 0.46,
"learning_rate": 9.138808373590982e-05,
"loss": 1.0871,
"step": 1440
},
{
"epoch": 0.46,
"learning_rate": 9.132367149758455e-05,
"loss": 1.0328,
"step": 1450
},
{
"epoch": 0.47,
"learning_rate": 9.125925925925927e-05,
"loss": 1.0137,
"step": 1460
},
{
"epoch": 0.47,
"learning_rate": 9.119484702093398e-05,
"loss": 1.0605,
"step": 1470
},
{
"epoch": 0.47,
"learning_rate": 9.11304347826087e-05,
"loss": 1.0404,
"step": 1480
},
{
"epoch": 0.48,
"learning_rate": 9.106602254428341e-05,
"loss": 1.0132,
"step": 1490
},
{
"epoch": 0.48,
"learning_rate": 9.100161030595815e-05,
"loss": 0.9935,
"step": 1500
},
{
"epoch": 0.48,
"learning_rate": 9.093719806763285e-05,
"loss": 1.0954,
"step": 1510
},
{
"epoch": 0.49,
"learning_rate": 9.087278582930757e-05,
"loss": 1.0853,
"step": 1520
},
{
"epoch": 0.49,
"learning_rate": 9.080837359098229e-05,
"loss": 1.0688,
"step": 1530
},
{
"epoch": 0.49,
"learning_rate": 9.074396135265701e-05,
"loss": 1.0509,
"step": 1540
},
{
"epoch": 0.5,
"learning_rate": 9.067954911433173e-05,
"loss": 1.0424,
"step": 1550
},
{
"epoch": 0.5,
"learning_rate": 9.061513687600645e-05,
"loss": 1.0711,
"step": 1560
},
{
"epoch": 0.5,
"learning_rate": 9.055072463768116e-05,
"loss": 1.0537,
"step": 1570
},
{
"epoch": 0.51,
"learning_rate": 9.048631239935588e-05,
"loss": 1.1012,
"step": 1580
},
{
"epoch": 0.51,
"learning_rate": 9.04219001610306e-05,
"loss": 1.0725,
"step": 1590
},
{
"epoch": 0.51,
"learning_rate": 9.035748792270532e-05,
"loss": 1.0444,
"step": 1600
},
{
"epoch": 0.51,
"eval_loss": 1.0541496276855469,
"eval_runtime": 118.5768,
"eval_samples_per_second": 16.867,
"eval_steps_per_second": 2.108,
"step": 1600
},
{
"epoch": 0.52,
"learning_rate": 9.029307568438004e-05,
"loss": 1.0641,
"step": 1610
},
{
"epoch": 0.52,
"learning_rate": 9.022866344605474e-05,
"loss": 1.0323,
"step": 1620
},
{
"epoch": 0.52,
"learning_rate": 9.016425120772948e-05,
"loss": 1.0538,
"step": 1630
},
{
"epoch": 0.52,
"learning_rate": 9.00998389694042e-05,
"loss": 1.0588,
"step": 1640
},
{
"epoch": 0.53,
"learning_rate": 9.003542673107891e-05,
"loss": 1.0026,
"step": 1650
},
{
"epoch": 0.53,
"learning_rate": 8.997101449275362e-05,
"loss": 1.0614,
"step": 1660
},
{
"epoch": 0.53,
"learning_rate": 8.990660225442834e-05,
"loss": 1.0737,
"step": 1670
},
{
"epoch": 0.54,
"learning_rate": 8.984219001610307e-05,
"loss": 1.058,
"step": 1680
},
{
"epoch": 0.54,
"learning_rate": 8.977777777777779e-05,
"loss": 1.0653,
"step": 1690
},
{
"epoch": 0.54,
"learning_rate": 8.97133655394525e-05,
"loss": 0.9893,
"step": 1700
},
{
"epoch": 0.55,
"learning_rate": 8.964895330112721e-05,
"loss": 1.0182,
"step": 1710
},
{
"epoch": 0.55,
"learning_rate": 8.958454106280194e-05,
"loss": 1.0247,
"step": 1720
},
{
"epoch": 0.55,
"learning_rate": 8.952012882447666e-05,
"loss": 1.016,
"step": 1730
},
{
"epoch": 0.56,
"learning_rate": 8.945571658615137e-05,
"loss": 1.019,
"step": 1740
},
{
"epoch": 0.56,
"learning_rate": 8.939130434782609e-05,
"loss": 1.0312,
"step": 1750
},
{
"epoch": 0.56,
"learning_rate": 8.932689210950082e-05,
"loss": 1.0646,
"step": 1760
},
{
"epoch": 0.57,
"learning_rate": 8.926247987117552e-05,
"loss": 1.0485,
"step": 1770
},
{
"epoch": 0.57,
"learning_rate": 8.919806763285024e-05,
"loss": 1.1001,
"step": 1780
},
{
"epoch": 0.57,
"learning_rate": 8.913365539452496e-05,
"loss": 1.0379,
"step": 1790
},
{
"epoch": 0.58,
"learning_rate": 8.906924315619968e-05,
"loss": 1.0264,
"step": 1800
},
{
"epoch": 0.58,
"eval_loss": 1.05194890499115,
"eval_runtime": 119.277,
"eval_samples_per_second": 16.768,
"eval_steps_per_second": 2.096,
"step": 1800
},
{
"epoch": 0.58,
"learning_rate": 8.90048309178744e-05,
"loss": 1.0574,
"step": 1810
},
{
"epoch": 0.58,
"learning_rate": 8.894041867954912e-05,
"loss": 1.0484,
"step": 1820
},
{
"epoch": 0.59,
"learning_rate": 8.887600644122384e-05,
"loss": 1.0297,
"step": 1830
},
{
"epoch": 0.59,
"learning_rate": 8.881159420289856e-05,
"loss": 1.0167,
"step": 1840
},
{
"epoch": 0.59,
"learning_rate": 8.874718196457327e-05,
"loss": 1.0421,
"step": 1850
},
{
"epoch": 0.6,
"learning_rate": 8.868276972624799e-05,
"loss": 1.0276,
"step": 1860
},
{
"epoch": 0.6,
"learning_rate": 8.861835748792271e-05,
"loss": 1.0477,
"step": 1870
},
{
"epoch": 0.6,
"learning_rate": 8.855394524959743e-05,
"loss": 1.0671,
"step": 1880
},
{
"epoch": 0.6,
"learning_rate": 8.848953301127214e-05,
"loss": 0.9882,
"step": 1890
},
{
"epoch": 0.61,
"learning_rate": 8.842512077294687e-05,
"loss": 1.006,
"step": 1900
},
{
"epoch": 0.61,
"learning_rate": 8.836070853462159e-05,
"loss": 1.018,
"step": 1910
},
{
"epoch": 0.61,
"learning_rate": 8.82962962962963e-05,
"loss": 1.0346,
"step": 1920
},
{
"epoch": 0.62,
"learning_rate": 8.823188405797101e-05,
"loss": 1.0879,
"step": 1930
},
{
"epoch": 0.62,
"learning_rate": 8.816747181964574e-05,
"loss": 1.0687,
"step": 1940
},
{
"epoch": 0.62,
"learning_rate": 8.810305958132046e-05,
"loss": 1.0331,
"step": 1950
},
{
"epoch": 0.63,
"learning_rate": 8.803864734299517e-05,
"loss": 1.0115,
"step": 1960
},
{
"epoch": 0.63,
"learning_rate": 8.797423510466989e-05,
"loss": 1.0119,
"step": 1970
},
{
"epoch": 0.63,
"learning_rate": 8.79098228663446e-05,
"loss": 1.0575,
"step": 1980
},
{
"epoch": 0.64,
"learning_rate": 8.784541062801934e-05,
"loss": 1.0744,
"step": 1990
},
{
"epoch": 0.64,
"learning_rate": 8.778099838969404e-05,
"loss": 1.0341,
"step": 2000
},
{
"epoch": 0.64,
"eval_loss": 1.0501959323883057,
"eval_runtime": 120.6722,
"eval_samples_per_second": 16.574,
"eval_steps_per_second": 2.072,
"step": 2000
},
{
"epoch": 0.64,
"learning_rate": 8.771658615136876e-05,
"loss": 1.0206,
"step": 2010
},
{
"epoch": 0.65,
"learning_rate": 8.765217391304348e-05,
"loss": 1.0297,
"step": 2020
},
{
"epoch": 0.65,
"learning_rate": 8.758776167471821e-05,
"loss": 1.0848,
"step": 2030
},
{
"epoch": 0.65,
"learning_rate": 8.752334943639292e-05,
"loss": 1.0528,
"step": 2040
},
{
"epoch": 0.66,
"learning_rate": 8.745893719806763e-05,
"loss": 1.0074,
"step": 2050
},
{
"epoch": 0.66,
"learning_rate": 8.739452495974235e-05,
"loss": 1.0934,
"step": 2060
},
{
"epoch": 0.66,
"learning_rate": 8.733011272141707e-05,
"loss": 1.034,
"step": 2070
},
{
"epoch": 0.67,
"learning_rate": 8.726570048309179e-05,
"loss": 1.0866,
"step": 2080
},
{
"epoch": 0.67,
"learning_rate": 8.720128824476651e-05,
"loss": 1.0517,
"step": 2090
},
{
"epoch": 0.67,
"learning_rate": 8.713687600644123e-05,
"loss": 1.0339,
"step": 2100
},
{
"epoch": 0.68,
"learning_rate": 8.707246376811595e-05,
"loss": 1.0164,
"step": 2110
},
{
"epoch": 0.68,
"learning_rate": 8.700805152979067e-05,
"loss": 1.0597,
"step": 2120
},
{
"epoch": 0.68,
"learning_rate": 8.694363929146538e-05,
"loss": 1.0539,
"step": 2130
},
{
"epoch": 0.68,
"learning_rate": 8.68792270531401e-05,
"loss": 0.9942,
"step": 2140
},
{
"epoch": 0.69,
"learning_rate": 8.681481481481482e-05,
"loss": 1.0192,
"step": 2150
},
{
"epoch": 0.69,
"learning_rate": 8.675040257648954e-05,
"loss": 1.0685,
"step": 2160
},
{
"epoch": 0.69,
"learning_rate": 8.668599033816426e-05,
"loss": 1.0198,
"step": 2170
},
{
"epoch": 0.7,
"learning_rate": 8.662157809983898e-05,
"loss": 1.0623,
"step": 2180
},
{
"epoch": 0.7,
"learning_rate": 8.655716586151368e-05,
"loss": 1.0441,
"step": 2190
},
{
"epoch": 0.7,
"learning_rate": 8.64927536231884e-05,
"loss": 1.0155,
"step": 2200
},
{
"epoch": 0.7,
"eval_loss": 1.0501713752746582,
"eval_runtime": 122.07,
"eval_samples_per_second": 16.384,
"eval_steps_per_second": 2.048,
"step": 2200
},
{
"epoch": 0.71,
"learning_rate": 8.642834138486313e-05,
"loss": 1.0347,
"step": 2210
},
{
"epoch": 0.71,
"learning_rate": 8.636392914653785e-05,
"loss": 1.0301,
"step": 2220
},
{
"epoch": 0.71,
"learning_rate": 8.629951690821256e-05,
"loss": 1.085,
"step": 2230
},
{
"epoch": 0.72,
"learning_rate": 8.623510466988728e-05,
"loss": 1.0661,
"step": 2240
},
{
"epoch": 0.72,
"learning_rate": 8.617069243156201e-05,
"loss": 1.0196,
"step": 2250
},
{
"epoch": 0.72,
"learning_rate": 8.610628019323673e-05,
"loss": 1.0601,
"step": 2260
},
{
"epoch": 0.73,
"learning_rate": 8.604186795491143e-05,
"loss": 1.0719,
"step": 2270
},
{
"epoch": 0.73,
"learning_rate": 8.597745571658615e-05,
"loss": 1.0123,
"step": 2280
},
{
"epoch": 0.73,
"learning_rate": 8.591304347826087e-05,
"loss": 1.0766,
"step": 2290
},
{
"epoch": 0.74,
"learning_rate": 8.584863123993559e-05,
"loss": 1.0474,
"step": 2300
},
{
"epoch": 0.74,
"learning_rate": 8.578421900161031e-05,
"loss": 1.0737,
"step": 2310
},
{
"epoch": 0.74,
"learning_rate": 8.571980676328503e-05,
"loss": 1.0482,
"step": 2320
},
{
"epoch": 0.75,
"learning_rate": 8.565539452495974e-05,
"loss": 1.0543,
"step": 2330
},
{
"epoch": 0.75,
"learning_rate": 8.559098228663446e-05,
"loss": 1.0549,
"step": 2340
},
{
"epoch": 0.75,
"learning_rate": 8.552657004830918e-05,
"loss": 1.0869,
"step": 2350
},
{
"epoch": 0.76,
"learning_rate": 8.54621578099839e-05,
"loss": 1.0821,
"step": 2360
},
{
"epoch": 0.76,
"learning_rate": 8.539774557165862e-05,
"loss": 1.0302,
"step": 2370
},
{
"epoch": 0.76,
"learning_rate": 8.533333333333334e-05,
"loss": 1.0653,
"step": 2380
},
{
"epoch": 0.76,
"learning_rate": 8.526892109500806e-05,
"loss": 1.0328,
"step": 2390
},
{
"epoch": 0.77,
"learning_rate": 8.520450885668278e-05,
"loss": 1.0685,
"step": 2400
},
{
"epoch": 0.77,
"eval_loss": 1.0498476028442383,
"eval_runtime": 118.8004,
"eval_samples_per_second": 16.835,
"eval_steps_per_second": 2.104,
"step": 2400
},
{
"epoch": 0.77,
"learning_rate": 8.51400966183575e-05,
"loss": 1.0243,
"step": 2410
},
{
"epoch": 0.77,
"learning_rate": 8.50756843800322e-05,
"loss": 1.075,
"step": 2420
},
{
"epoch": 0.78,
"learning_rate": 8.501127214170693e-05,
"loss": 1.0475,
"step": 2430
},
{
"epoch": 0.78,
"learning_rate": 8.494685990338165e-05,
"loss": 1.0269,
"step": 2440
},
{
"epoch": 0.78,
"learning_rate": 8.488244766505637e-05,
"loss": 1.0431,
"step": 2450
},
{
"epoch": 0.79,
"learning_rate": 8.481803542673107e-05,
"loss": 1.0412,
"step": 2460
},
{
"epoch": 0.79,
"learning_rate": 8.475362318840581e-05,
"loss": 1.029,
"step": 2470
},
{
"epoch": 0.79,
"learning_rate": 8.468921095008053e-05,
"loss": 1.0884,
"step": 2480
},
{
"epoch": 0.8,
"learning_rate": 8.462479871175524e-05,
"loss": 1.0268,
"step": 2490
},
{
"epoch": 0.8,
"learning_rate": 8.456038647342995e-05,
"loss": 1.0475,
"step": 2500
},
{
"epoch": 0.8,
"learning_rate": 8.449597423510467e-05,
"loss": 1.0258,
"step": 2510
},
{
"epoch": 0.81,
"learning_rate": 8.44315619967794e-05,
"loss": 1.0797,
"step": 2520
},
{
"epoch": 0.81,
"learning_rate": 8.43671497584541e-05,
"loss": 1.0914,
"step": 2530
},
{
"epoch": 0.81,
"learning_rate": 8.430273752012882e-05,
"loss": 1.0445,
"step": 2540
},
{
"epoch": 0.82,
"learning_rate": 8.423832528180354e-05,
"loss": 1.016,
"step": 2550
},
{
"epoch": 0.82,
"learning_rate": 8.417391304347828e-05,
"loss": 1.0463,
"step": 2560
},
{
"epoch": 0.82,
"learning_rate": 8.410950080515298e-05,
"loss": 0.9827,
"step": 2570
},
{
"epoch": 0.83,
"learning_rate": 8.40450885668277e-05,
"loss": 1.0417,
"step": 2580
},
{
"epoch": 0.83,
"learning_rate": 8.398067632850242e-05,
"loss": 1.0501,
"step": 2590
},
{
"epoch": 0.83,
"learning_rate": 8.391626409017714e-05,
"loss": 1.0037,
"step": 2600
},
{
"epoch": 0.83,
"eval_loss": 1.0493232011795044,
"eval_runtime": 118.6245,
"eval_samples_per_second": 16.86,
"eval_steps_per_second": 2.107,
"step": 2600
},
{
"epoch": 0.84,
"learning_rate": 8.385185185185186e-05,
"loss": 1.0176,
"step": 2610
},
{
"epoch": 0.84,
"learning_rate": 8.378743961352657e-05,
"loss": 1.0409,
"step": 2620
},
{
"epoch": 0.84,
"learning_rate": 8.372302737520129e-05,
"loss": 1.0449,
"step": 2630
},
{
"epoch": 0.84,
"learning_rate": 8.365861513687601e-05,
"loss": 1.0731,
"step": 2640
},
{
"epoch": 0.85,
"learning_rate": 8.359420289855073e-05,
"loss": 1.1184,
"step": 2650
},
{
"epoch": 0.85,
"learning_rate": 8.352979066022545e-05,
"loss": 1.0286,
"step": 2660
},
{
"epoch": 0.85,
"learning_rate": 8.346537842190017e-05,
"loss": 1.0409,
"step": 2670
},
{
"epoch": 0.86,
"learning_rate": 8.340096618357489e-05,
"loss": 1.0627,
"step": 2680
},
{
"epoch": 0.86,
"learning_rate": 8.33365539452496e-05,
"loss": 1.0625,
"step": 2690
},
{
"epoch": 0.86,
"learning_rate": 8.327214170692432e-05,
"loss": 1.0324,
"step": 2700
},
{
"epoch": 0.87,
"learning_rate": 8.320772946859904e-05,
"loss": 1.0755,
"step": 2710
},
{
"epoch": 0.87,
"learning_rate": 8.314331723027375e-05,
"loss": 1.0663,
"step": 2720
},
{
"epoch": 0.87,
"learning_rate": 8.307890499194847e-05,
"loss": 1.0512,
"step": 2730
},
{
"epoch": 0.88,
"learning_rate": 8.30144927536232e-05,
"loss": 1.0399,
"step": 2740
},
{
"epoch": 0.88,
"learning_rate": 8.295008051529792e-05,
"loss": 1.0016,
"step": 2750
},
{
"epoch": 0.88,
"learning_rate": 8.288566827697262e-05,
"loss": 1.0499,
"step": 2760
},
{
"epoch": 0.89,
"learning_rate": 8.282125603864734e-05,
"loss": 1.0846,
"step": 2770
},
{
"epoch": 0.89,
"learning_rate": 8.275684380032207e-05,
"loss": 1.0197,
"step": 2780
},
{
"epoch": 0.89,
"learning_rate": 8.269243156199679e-05,
"loss": 1.0626,
"step": 2790
},
{
"epoch": 0.9,
"learning_rate": 8.26280193236715e-05,
"loss": 1.0752,
"step": 2800
},
{
"epoch": 0.9,
"eval_loss": 1.0474530458450317,
"eval_runtime": 118.8942,
"eval_samples_per_second": 16.822,
"eval_steps_per_second": 2.103,
"step": 2800
},
{
"epoch": 0.9,
"learning_rate": 8.256360708534622e-05,
"loss": 1.0803,
"step": 2810
},
{
"epoch": 0.9,
"learning_rate": 8.249919484702093e-05,
"loss": 0.9713,
"step": 2820
},
{
"epoch": 0.91,
"learning_rate": 8.243478260869565e-05,
"loss": 1.0177,
"step": 2830
},
{
"epoch": 0.91,
"learning_rate": 8.237037037037037e-05,
"loss": 1.0667,
"step": 2840
},
{
"epoch": 0.91,
"learning_rate": 8.230595813204509e-05,
"loss": 1.0138,
"step": 2850
},
{
"epoch": 0.92,
"learning_rate": 8.224154589371981e-05,
"loss": 1.0347,
"step": 2860
},
{
"epoch": 0.92,
"learning_rate": 8.217713365539453e-05,
"loss": 1.0308,
"step": 2870
},
{
"epoch": 0.92,
"learning_rate": 8.211272141706925e-05,
"loss": 1.0261,
"step": 2880
},
{
"epoch": 0.92,
"learning_rate": 8.204830917874397e-05,
"loss": 1.0751,
"step": 2890
},
{
"epoch": 0.93,
"learning_rate": 8.198389694041868e-05,
"loss": 0.9864,
"step": 2900
},
{
"epoch": 0.93,
"learning_rate": 8.19194847020934e-05,
"loss": 1.0282,
"step": 2910
},
{
"epoch": 0.93,
"learning_rate": 8.185507246376812e-05,
"loss": 1.0381,
"step": 2920
},
{
"epoch": 0.94,
"learning_rate": 8.179066022544284e-05,
"loss": 1.0368,
"step": 2930
},
{
"epoch": 0.94,
"learning_rate": 8.172624798711756e-05,
"loss": 1.0216,
"step": 2940
},
{
"epoch": 0.94,
"learning_rate": 8.166183574879226e-05,
"loss": 1.0745,
"step": 2950
},
{
"epoch": 0.95,
"learning_rate": 8.1597423510467e-05,
"loss": 1.0904,
"step": 2960
},
{
"epoch": 0.95,
"learning_rate": 8.153301127214171e-05,
"loss": 1.0684,
"step": 2970
},
{
"epoch": 0.95,
"learning_rate": 8.146859903381643e-05,
"loss": 1.04,
"step": 2980
},
{
"epoch": 0.96,
"learning_rate": 8.140418679549114e-05,
"loss": 0.9984,
"step": 2990
},
{
"epoch": 0.96,
"learning_rate": 8.133977455716587e-05,
"loss": 1.0787,
"step": 3000
},
{
"epoch": 0.96,
"eval_loss": 1.046216607093811,
"eval_runtime": 118.7583,
"eval_samples_per_second": 16.841,
"eval_steps_per_second": 2.105,
"step": 3000
},
{
"epoch": 0.96,
"learning_rate": 8.127536231884059e-05,
"loss": 1.0192,
"step": 3010
},
{
"epoch": 0.97,
"learning_rate": 8.121095008051531e-05,
"loss": 1.0692,
"step": 3020
},
{
"epoch": 0.97,
"learning_rate": 8.114653784219001e-05,
"loss": 1.035,
"step": 3030
},
{
"epoch": 0.97,
"learning_rate": 8.108212560386473e-05,
"loss": 1.0113,
"step": 3040
},
{
"epoch": 0.98,
"learning_rate": 8.101771336553946e-05,
"loss": 1.0744,
"step": 3050
},
{
"epoch": 0.98,
"learning_rate": 8.095330112721417e-05,
"loss": 1.0348,
"step": 3060
},
{
"epoch": 0.98,
"learning_rate": 8.088888888888889e-05,
"loss": 1.059,
"step": 3070
},
{
"epoch": 0.99,
"learning_rate": 8.082447665056361e-05,
"loss": 1.0587,
"step": 3080
},
{
"epoch": 0.99,
"learning_rate": 8.076006441223834e-05,
"loss": 1.0221,
"step": 3090
},
{
"epoch": 0.99,
"learning_rate": 8.069565217391304e-05,
"loss": 1.0645,
"step": 3100
},
{
"epoch": 1.0,
"learning_rate": 8.063123993558776e-05,
"loss": 1.1149,
"step": 3110
},
{
"epoch": 1.0,
"learning_rate": 8.056682769726248e-05,
"loss": 1.0484,
"step": 3120
},
{
"epoch": 1.0,
"learning_rate": 8.05024154589372e-05,
"loss": 1.0725,
"step": 3130
},
{
"epoch": 1.0,
"learning_rate": 8.043800322061192e-05,
"loss": 1.0554,
"step": 3140
},
{
"epoch": 1.01,
"learning_rate": 8.037359098228664e-05,
"loss": 1.0015,
"step": 3150
},
{
"epoch": 1.01,
"learning_rate": 8.030917874396136e-05,
"loss": 1.0234,
"step": 3160
},
{
"epoch": 1.01,
"learning_rate": 8.024476650563608e-05,
"loss": 1.0617,
"step": 3170
},
{
"epoch": 1.02,
"learning_rate": 8.01803542673108e-05,
"loss": 1.0285,
"step": 3180
},
{
"epoch": 1.02,
"learning_rate": 8.011594202898551e-05,
"loss": 1.0525,
"step": 3190
},
{
"epoch": 1.02,
"learning_rate": 8.005152979066023e-05,
"loss": 0.9877,
"step": 3200
},
{
"epoch": 1.02,
"eval_loss": 1.0453153848648071,
"eval_runtime": 118.7099,
"eval_samples_per_second": 16.848,
"eval_steps_per_second": 2.106,
"step": 3200
},
{
"epoch": 1.03,
"learning_rate": 7.998711755233495e-05,
"loss": 1.0163,
"step": 3210
},
{
"epoch": 1.03,
"learning_rate": 7.992270531400966e-05,
"loss": 1.0191,
"step": 3220
},
{
"epoch": 1.03,
"learning_rate": 7.985829307568439e-05,
"loss": 1.0528,
"step": 3230
},
{
"epoch": 1.04,
"learning_rate": 7.97938808373591e-05,
"loss": 1.0427,
"step": 3240
},
{
"epoch": 1.04,
"learning_rate": 7.972946859903383e-05,
"loss": 1.0345,
"step": 3250
},
{
"epoch": 1.04,
"learning_rate": 7.966505636070853e-05,
"loss": 0.9728,
"step": 3260
},
{
"epoch": 1.05,
"learning_rate": 7.960064412238326e-05,
"loss": 1.0709,
"step": 3270
},
{
"epoch": 1.05,
"learning_rate": 7.953623188405798e-05,
"loss": 1.0216,
"step": 3280
},
{
"epoch": 1.05,
"learning_rate": 7.947181964573269e-05,
"loss": 1.0422,
"step": 3290
},
{
"epoch": 1.06,
"learning_rate": 7.94074074074074e-05,
"loss": 1.0559,
"step": 3300
},
{
"epoch": 1.06,
"learning_rate": 7.934299516908214e-05,
"loss": 1.033,
"step": 3310
},
{
"epoch": 1.06,
"learning_rate": 7.927858293075686e-05,
"loss": 1.0307,
"step": 3320
},
{
"epoch": 1.07,
"learning_rate": 7.921417069243156e-05,
"loss": 1.0239,
"step": 3330
},
{
"epoch": 1.07,
"learning_rate": 7.914975845410628e-05,
"loss": 1.022,
"step": 3340
},
{
"epoch": 1.07,
"learning_rate": 7.9085346215781e-05,
"loss": 1.0435,
"step": 3350
},
{
"epoch": 1.08,
"learning_rate": 7.902093397745573e-05,
"loss": 0.9938,
"step": 3360
},
{
"epoch": 1.08,
"learning_rate": 7.895652173913044e-05,
"loss": 1.0168,
"step": 3370
},
{
"epoch": 1.08,
"learning_rate": 7.889210950080515e-05,
"loss": 1.0455,
"step": 3380
},
{
"epoch": 1.08,
"learning_rate": 7.882769726247987e-05,
"loss": 0.99,
"step": 3390
},
{
"epoch": 1.09,
"learning_rate": 7.876328502415459e-05,
"loss": 1.0541,
"step": 3400
},
{
"epoch": 1.09,
"eval_loss": 1.0455336570739746,
"eval_runtime": 118.6315,
"eval_samples_per_second": 16.859,
"eval_steps_per_second": 2.107,
"step": 3400
},
{
"epoch": 1.09,
"learning_rate": 7.869887278582931e-05,
"loss": 0.994,
"step": 3410
},
{
"epoch": 1.09,
"learning_rate": 7.863446054750403e-05,
"loss": 1.0331,
"step": 3420
},
{
"epoch": 1.1,
"learning_rate": 7.857004830917875e-05,
"loss": 1.0379,
"step": 3430
},
{
"epoch": 1.1,
"learning_rate": 7.850563607085347e-05,
"loss": 1.0344,
"step": 3440
},
{
"epoch": 1.1,
"learning_rate": 7.844122383252819e-05,
"loss": 0.9944,
"step": 3450
},
{
"epoch": 1.11,
"learning_rate": 7.83768115942029e-05,
"loss": 1.0271,
"step": 3460
},
{
"epoch": 1.11,
"learning_rate": 7.831239935587762e-05,
"loss": 1.0045,
"step": 3470
},
{
"epoch": 1.11,
"learning_rate": 7.824798711755233e-05,
"loss": 1.0009,
"step": 3480
},
{
"epoch": 1.12,
"learning_rate": 7.818357487922706e-05,
"loss": 1.0289,
"step": 3490
},
{
"epoch": 1.12,
"learning_rate": 7.811916264090178e-05,
"loss": 1.0096,
"step": 3500
},
{
"epoch": 1.12,
"learning_rate": 7.80547504025765e-05,
"loss": 1.0594,
"step": 3510
},
{
"epoch": 1.13,
"learning_rate": 7.79903381642512e-05,
"loss": 1.0305,
"step": 3520
},
{
"epoch": 1.13,
"learning_rate": 7.792592592592592e-05,
"loss": 1.0664,
"step": 3530
},
{
"epoch": 1.13,
"learning_rate": 7.786151368760065e-05,
"loss": 1.0089,
"step": 3540
},
{
"epoch": 1.14,
"learning_rate": 7.779710144927537e-05,
"loss": 1.0596,
"step": 3550
},
{
"epoch": 1.14,
"learning_rate": 7.773268921095008e-05,
"loss": 1.0075,
"step": 3560
},
{
"epoch": 1.14,
"learning_rate": 7.76682769726248e-05,
"loss": 1.0613,
"step": 3570
},
{
"epoch": 1.15,
"learning_rate": 7.760386473429953e-05,
"loss": 1.033,
"step": 3580
},
{
"epoch": 1.15,
"learning_rate": 7.753945249597425e-05,
"loss": 1.0108,
"step": 3590
},
{
"epoch": 1.15,
"learning_rate": 7.747504025764895e-05,
"loss": 1.0601,
"step": 3600
},
{
"epoch": 1.15,
"eval_loss": 1.0447208881378174,
"eval_runtime": 118.6536,
"eval_samples_per_second": 16.856,
"eval_steps_per_second": 2.107,
"step": 3600
},
{
"epoch": 1.16,
"learning_rate": 7.741062801932367e-05,
"loss": 1.0148,
"step": 3610
},
{
"epoch": 1.16,
"learning_rate": 7.73462157809984e-05,
"loss": 1.0283,
"step": 3620
},
{
"epoch": 1.16,
"learning_rate": 7.728180354267311e-05,
"loss": 1.0018,
"step": 3630
},
{
"epoch": 1.16,
"learning_rate": 7.721739130434783e-05,
"loss": 1.0525,
"step": 3640
},
{
"epoch": 1.17,
"learning_rate": 7.715297906602255e-05,
"loss": 1.001,
"step": 3650
},
{
"epoch": 1.17,
"learning_rate": 7.708856682769726e-05,
"loss": 1.0189,
"step": 3660
},
{
"epoch": 1.17,
"learning_rate": 7.702415458937198e-05,
"loss": 1.036,
"step": 3670
},
{
"epoch": 1.18,
"learning_rate": 7.69597423510467e-05,
"loss": 0.9648,
"step": 3680
},
{
"epoch": 1.18,
"learning_rate": 7.689533011272142e-05,
"loss": 0.9938,
"step": 3690
},
{
"epoch": 1.18,
"learning_rate": 7.683091787439614e-05,
"loss": 0.9936,
"step": 3700
},
{
"epoch": 1.19,
"learning_rate": 7.676650563607086e-05,
"loss": 1.0395,
"step": 3710
},
{
"epoch": 1.19,
"learning_rate": 7.670209339774558e-05,
"loss": 1.0354,
"step": 3720
},
{
"epoch": 1.19,
"learning_rate": 7.66376811594203e-05,
"loss": 0.9744,
"step": 3730
},
{
"epoch": 1.2,
"learning_rate": 7.657326892109501e-05,
"loss": 1.0472,
"step": 3740
},
{
"epoch": 1.2,
"learning_rate": 7.650885668276972e-05,
"loss": 0.9919,
"step": 3750
},
{
"epoch": 1.2,
"learning_rate": 7.644444444444445e-05,
"loss": 1.0487,
"step": 3760
},
{
"epoch": 1.21,
"learning_rate": 7.638003220611917e-05,
"loss": 0.9969,
"step": 3770
},
{
"epoch": 1.21,
"learning_rate": 7.631561996779389e-05,
"loss": 0.9966,
"step": 3780
},
{
"epoch": 1.21,
"learning_rate": 7.62512077294686e-05,
"loss": 1.0435,
"step": 3790
},
{
"epoch": 1.22,
"learning_rate": 7.618679549114333e-05,
"loss": 0.9847,
"step": 3800
},
{
"epoch": 1.22,
"eval_loss": 1.0448102951049805,
"eval_runtime": 118.8166,
"eval_samples_per_second": 16.833,
"eval_steps_per_second": 2.104,
"step": 3800
},
{
"epoch": 1.22,
"learning_rate": 7.612238325281805e-05,
"loss": 1.0465,
"step": 3810
},
{
"epoch": 1.22,
"learning_rate": 7.605797101449275e-05,
"loss": 1.0431,
"step": 3820
},
{
"epoch": 1.23,
"learning_rate": 7.599355877616747e-05,
"loss": 1.0613,
"step": 3830
},
{
"epoch": 1.23,
"learning_rate": 7.592914653784219e-05,
"loss": 1.0558,
"step": 3840
},
{
"epoch": 1.23,
"learning_rate": 7.586473429951692e-05,
"loss": 1.0588,
"step": 3850
},
{
"epoch": 1.24,
"learning_rate": 7.580032206119163e-05,
"loss": 1.0227,
"step": 3860
},
{
"epoch": 1.24,
"learning_rate": 7.573590982286634e-05,
"loss": 1.0089,
"step": 3870
},
{
"epoch": 1.24,
"learning_rate": 7.567149758454106e-05,
"loss": 1.0016,
"step": 3880
},
{
"epoch": 1.24,
"learning_rate": 7.56070853462158e-05,
"loss": 1.0205,
"step": 3890
},
{
"epoch": 1.25,
"learning_rate": 7.55426731078905e-05,
"loss": 1.029,
"step": 3900
},
{
"epoch": 1.25,
"learning_rate": 7.547826086956522e-05,
"loss": 1.0509,
"step": 3910
},
{
"epoch": 1.25,
"learning_rate": 7.541384863123994e-05,
"loss": 1.0208,
"step": 3920
},
{
"epoch": 1.26,
"learning_rate": 7.534943639291466e-05,
"loss": 0.982,
"step": 3930
},
{
"epoch": 1.26,
"learning_rate": 7.528502415458938e-05,
"loss": 1.0413,
"step": 3940
},
{
"epoch": 1.26,
"learning_rate": 7.52206119162641e-05,
"loss": 1.0252,
"step": 3950
},
{
"epoch": 1.27,
"learning_rate": 7.515619967793881e-05,
"loss": 1.0495,
"step": 3960
},
{
"epoch": 1.27,
"learning_rate": 7.509178743961353e-05,
"loss": 1.0006,
"step": 3970
},
{
"epoch": 1.27,
"learning_rate": 7.502737520128825e-05,
"loss": 0.9674,
"step": 3980
},
{
"epoch": 1.28,
"learning_rate": 7.496296296296297e-05,
"loss": 0.9765,
"step": 3990
},
{
"epoch": 1.28,
"learning_rate": 7.489855072463769e-05,
"loss": 0.9765,
"step": 4000
},
{
"epoch": 1.28,
"eval_loss": 1.0446877479553223,
"eval_runtime": 119.0017,
"eval_samples_per_second": 16.806,
"eval_steps_per_second": 2.101,
"step": 4000
},
{
"epoch": 1.28,
"learning_rate": 7.48341384863124e-05,
"loss": 1.0418,
"step": 4010
},
{
"epoch": 1.29,
"learning_rate": 7.476972624798712e-05,
"loss": 0.9666,
"step": 4020
},
{
"epoch": 1.29,
"learning_rate": 7.470531400966184e-05,
"loss": 1.0535,
"step": 4030
},
{
"epoch": 1.29,
"learning_rate": 7.464090177133656e-05,
"loss": 0.9831,
"step": 4040
},
{
"epoch": 1.3,
"learning_rate": 7.457648953301127e-05,
"loss": 1.0021,
"step": 4050
},
{
"epoch": 1.3,
"learning_rate": 7.451207729468599e-05,
"loss": 1.0304,
"step": 4060
},
{
"epoch": 1.3,
"learning_rate": 7.444766505636072e-05,
"loss": 1.0077,
"step": 4070
},
{
"epoch": 1.31,
"learning_rate": 7.438325281803544e-05,
"loss": 1.0215,
"step": 4080
},
{
"epoch": 1.31,
"learning_rate": 7.431884057971014e-05,
"loss": 1.0181,
"step": 4090
},
{
"epoch": 1.31,
"learning_rate": 7.425442834138486e-05,
"loss": 1.047,
"step": 4100
},
{
"epoch": 1.32,
"learning_rate": 7.419001610305959e-05,
"loss": 1.0137,
"step": 4110
},
{
"epoch": 1.32,
"learning_rate": 7.412560386473431e-05,
"loss": 0.9946,
"step": 4120
},
{
"epoch": 1.32,
"learning_rate": 7.406119162640902e-05,
"loss": 1.0567,
"step": 4130
},
{
"epoch": 1.32,
"learning_rate": 7.399677938808374e-05,
"loss": 1.0348,
"step": 4140
},
{
"epoch": 1.33,
"learning_rate": 7.393236714975845e-05,
"loss": 1.0314,
"step": 4150
},
{
"epoch": 1.33,
"learning_rate": 7.386795491143317e-05,
"loss": 1.0446,
"step": 4160
},
{
"epoch": 1.33,
"learning_rate": 7.380354267310789e-05,
"loss": 0.9648,
"step": 4170
},
{
"epoch": 1.34,
"learning_rate": 7.373913043478261e-05,
"loss": 1.0185,
"step": 4180
},
{
"epoch": 1.34,
"learning_rate": 7.367471819645733e-05,
"loss": 1.1056,
"step": 4190
},
{
"epoch": 1.34,
"learning_rate": 7.361030595813205e-05,
"loss": 1.008,
"step": 4200
},
{
"epoch": 1.34,
"eval_loss": 1.0431263446807861,
"eval_runtime": 119.6999,
"eval_samples_per_second": 16.708,
"eval_steps_per_second": 2.089,
"step": 4200
},
{
"epoch": 1.35,
"learning_rate": 7.354589371980677e-05,
"loss": 1.0346,
"step": 4210
},
{
"epoch": 1.35,
"learning_rate": 7.348148148148149e-05,
"loss": 1.0152,
"step": 4220
},
{
"epoch": 1.35,
"learning_rate": 7.34170692431562e-05,
"loss": 1.0362,
"step": 4230
},
{
"epoch": 1.36,
"learning_rate": 7.335265700483092e-05,
"loss": 1.0163,
"step": 4240
},
{
"epoch": 1.36,
"learning_rate": 7.328824476650564e-05,
"loss": 1.0121,
"step": 4250
},
{
"epoch": 1.36,
"learning_rate": 7.322383252818036e-05,
"loss": 1.0123,
"step": 4260
},
{
"epoch": 1.37,
"learning_rate": 7.315942028985508e-05,
"loss": 1.0301,
"step": 4270
},
{
"epoch": 1.37,
"learning_rate": 7.309500805152978e-05,
"loss": 1.0268,
"step": 4280
},
{
"epoch": 1.37,
"learning_rate": 7.303059581320452e-05,
"loss": 0.9811,
"step": 4290
},
{
"epoch": 1.38,
"learning_rate": 7.296618357487923e-05,
"loss": 1.0304,
"step": 4300
},
{
"epoch": 1.38,
"learning_rate": 7.290177133655395e-05,
"loss": 1.0348,
"step": 4310
},
{
"epoch": 1.38,
"learning_rate": 7.283735909822866e-05,
"loss": 1.0158,
"step": 4320
},
{
"epoch": 1.39,
"learning_rate": 7.277294685990339e-05,
"loss": 0.9808,
"step": 4330
},
{
"epoch": 1.39,
"learning_rate": 7.270853462157811e-05,
"loss": 1.0387,
"step": 4340
},
{
"epoch": 1.39,
"learning_rate": 7.264412238325283e-05,
"loss": 1.0669,
"step": 4350
},
{
"epoch": 1.4,
"learning_rate": 7.258615136876007e-05,
"loss": 1.0417,
"step": 4360
},
{
"epoch": 1.4,
"learning_rate": 7.252173913043479e-05,
"loss": 1.0617,
"step": 4370
},
{
"epoch": 1.4,
"learning_rate": 7.24573268921095e-05,
"loss": 1.0563,
"step": 4380
},
{
"epoch": 1.4,
"learning_rate": 7.239291465378422e-05,
"loss": 1.0697,
"step": 4390
},
{
"epoch": 1.41,
"learning_rate": 7.232850241545894e-05,
"loss": 1.0392,
"step": 4400
},
{
"epoch": 1.41,
"eval_loss": 1.0430742502212524,
"eval_runtime": 119.6968,
"eval_samples_per_second": 16.709,
"eval_steps_per_second": 2.089,
"step": 4400
},
{
"epoch": 1.41,
"learning_rate": 7.226409017713366e-05,
"loss": 1.0449,
"step": 4410
},
{
"epoch": 1.41,
"learning_rate": 7.219967793880838e-05,
"loss": 1.0561,
"step": 4420
},
{
"epoch": 1.42,
"learning_rate": 7.213526570048309e-05,
"loss": 0.9966,
"step": 4430
},
{
"epoch": 1.42,
"learning_rate": 7.207085346215782e-05,
"loss": 1.0508,
"step": 4440
},
{
"epoch": 1.42,
"learning_rate": 7.200644122383254e-05,
"loss": 1.0333,
"step": 4450
},
{
"epoch": 1.43,
"learning_rate": 7.194202898550724e-05,
"loss": 1.022,
"step": 4460
},
{
"epoch": 1.43,
"learning_rate": 7.187761674718196e-05,
"loss": 0.993,
"step": 4470
},
{
"epoch": 1.43,
"learning_rate": 7.181320450885669e-05,
"loss": 0.9847,
"step": 4480
},
{
"epoch": 1.44,
"learning_rate": 7.174879227053141e-05,
"loss": 1.0315,
"step": 4490
},
{
"epoch": 1.44,
"learning_rate": 7.168438003220612e-05,
"loss": 1.0533,
"step": 4500
},
{
"epoch": 1.44,
"learning_rate": 7.161996779388084e-05,
"loss": 1.009,
"step": 4510
},
{
"epoch": 1.45,
"learning_rate": 7.155555555555555e-05,
"loss": 1.0426,
"step": 4520
},
{
"epoch": 1.45,
"learning_rate": 7.149114331723029e-05,
"loss": 0.9935,
"step": 4530
},
{
"epoch": 1.45,
"learning_rate": 7.142673107890499e-05,
"loss": 1.0453,
"step": 4540
},
{
"epoch": 1.46,
"learning_rate": 7.136231884057971e-05,
"loss": 1.0236,
"step": 4550
},
{
"epoch": 1.46,
"learning_rate": 7.129790660225443e-05,
"loss": 1.0324,
"step": 4560
},
{
"epoch": 1.46,
"learning_rate": 7.123349436392915e-05,
"loss": 0.9708,
"step": 4570
},
{
"epoch": 1.47,
"learning_rate": 7.116908212560387e-05,
"loss": 0.9613,
"step": 4580
},
{
"epoch": 1.47,
"learning_rate": 7.110466988727859e-05,
"loss": 0.9964,
"step": 4590
},
{
"epoch": 1.47,
"learning_rate": 7.10402576489533e-05,
"loss": 1.01,
"step": 4600
},
{
"epoch": 1.47,
"eval_loss": 1.0430107116699219,
"eval_runtime": 118.876,
"eval_samples_per_second": 16.824,
"eval_steps_per_second": 2.103,
"step": 4600
},
{
"epoch": 1.48,
"learning_rate": 7.097584541062802e-05,
"loss": 1.0325,
"step": 4610
},
{
"epoch": 1.48,
"learning_rate": 7.091143317230274e-05,
"loss": 1.0201,
"step": 4620
},
{
"epoch": 1.48,
"learning_rate": 7.084702093397746e-05,
"loss": 1.0044,
"step": 4630
},
{
"epoch": 1.48,
"learning_rate": 7.078260869565218e-05,
"loss": 1.0172,
"step": 4640
},
{
"epoch": 1.49,
"learning_rate": 7.07181964573269e-05,
"loss": 0.9837,
"step": 4650
},
{
"epoch": 1.49,
"learning_rate": 7.065378421900162e-05,
"loss": 0.9713,
"step": 4660
},
{
"epoch": 1.49,
"learning_rate": 7.058937198067633e-05,
"loss": 1.0316,
"step": 4670
},
{
"epoch": 1.5,
"learning_rate": 7.052495974235105e-05,
"loss": 1.0329,
"step": 4680
},
{
"epoch": 1.5,
"learning_rate": 7.046054750402576e-05,
"loss": 1.0332,
"step": 4690
},
{
"epoch": 1.5,
"learning_rate": 7.039613526570049e-05,
"loss": 1.0352,
"step": 4700
},
{
"epoch": 1.51,
"learning_rate": 7.033172302737521e-05,
"loss": 1.0147,
"step": 4710
},
{
"epoch": 1.51,
"learning_rate": 7.026731078904993e-05,
"loss": 1.0397,
"step": 4720
},
{
"epoch": 1.51,
"learning_rate": 7.020289855072463e-05,
"loss": 0.9909,
"step": 4730
},
{
"epoch": 1.52,
"learning_rate": 7.013848631239935e-05,
"loss": 1.0525,
"step": 4740
},
{
"epoch": 1.52,
"learning_rate": 7.007407407407408e-05,
"loss": 1.049,
"step": 4750
},
{
"epoch": 1.52,
"learning_rate": 7.00096618357488e-05,
"loss": 0.9986,
"step": 4760
},
{
"epoch": 1.53,
"learning_rate": 6.994524959742351e-05,
"loss": 1.0441,
"step": 4770
},
{
"epoch": 1.53,
"learning_rate": 6.988083735909823e-05,
"loss": 1.0286,
"step": 4780
},
{
"epoch": 1.53,
"learning_rate": 6.981642512077296e-05,
"loss": 1.0155,
"step": 4790
},
{
"epoch": 1.54,
"learning_rate": 6.975201288244766e-05,
"loss": 1.0787,
"step": 4800
},
{
"epoch": 1.54,
"eval_loss": 1.0421252250671387,
"eval_runtime": 118.8803,
"eval_samples_per_second": 16.824,
"eval_steps_per_second": 2.103,
"step": 4800
},
{
"epoch": 1.54,
"learning_rate": 6.968760064412238e-05,
"loss": 1.0397,
"step": 4810
},
{
"epoch": 1.54,
"learning_rate": 6.96231884057971e-05,
"loss": 1.0473,
"step": 4820
},
{
"epoch": 1.55,
"learning_rate": 6.955877616747182e-05,
"loss": 1.0341,
"step": 4830
},
{
"epoch": 1.55,
"learning_rate": 6.949436392914654e-05,
"loss": 1.0107,
"step": 4840
},
{
"epoch": 1.55,
"learning_rate": 6.942995169082126e-05,
"loss": 1.0231,
"step": 4850
},
{
"epoch": 1.56,
"learning_rate": 6.936553945249598e-05,
"loss": 1.0472,
"step": 4860
},
{
"epoch": 1.56,
"learning_rate": 6.93011272141707e-05,
"loss": 1.0225,
"step": 4870
},
{
"epoch": 1.56,
"learning_rate": 6.923671497584541e-05,
"loss": 1.0247,
"step": 4880
},
{
"epoch": 1.56,
"learning_rate": 6.917230273752013e-05,
"loss": 1.0302,
"step": 4890
},
{
"epoch": 1.57,
"learning_rate": 6.910789049919485e-05,
"loss": 1.007,
"step": 4900
},
{
"epoch": 1.57,
"learning_rate": 6.904347826086957e-05,
"loss": 0.9973,
"step": 4910
},
{
"epoch": 1.57,
"learning_rate": 6.897906602254429e-05,
"loss": 1.0316,
"step": 4920
},
{
"epoch": 1.58,
"learning_rate": 6.891465378421901e-05,
"loss": 1.01,
"step": 4930
},
{
"epoch": 1.58,
"learning_rate": 6.885024154589373e-05,
"loss": 1.0023,
"step": 4940
},
{
"epoch": 1.58,
"learning_rate": 6.878582930756844e-05,
"loss": 0.9919,
"step": 4950
},
{
"epoch": 1.59,
"learning_rate": 6.872141706924315e-05,
"loss": 1.0537,
"step": 4960
},
{
"epoch": 1.59,
"learning_rate": 6.865700483091788e-05,
"loss": 0.9987,
"step": 4970
},
{
"epoch": 1.59,
"learning_rate": 6.85925925925926e-05,
"loss": 0.991,
"step": 4980
},
{
"epoch": 1.6,
"learning_rate": 6.85281803542673e-05,
"loss": 1.043,
"step": 4990
},
{
"epoch": 1.6,
"learning_rate": 6.846376811594202e-05,
"loss": 1.0538,
"step": 5000
},
{
"epoch": 1.6,
"eval_loss": 1.0414823293685913,
"eval_runtime": 118.8401,
"eval_samples_per_second": 16.829,
"eval_steps_per_second": 2.104,
"step": 5000
},
{
"epoch": 1.6,
"learning_rate": 6.839935587761676e-05,
"loss": 1.0458,
"step": 5010
},
{
"epoch": 1.61,
"learning_rate": 6.833494363929148e-05,
"loss": 1.0063,
"step": 5020
},
{
"epoch": 1.61,
"learning_rate": 6.827053140096618e-05,
"loss": 1.011,
"step": 5030
},
{
"epoch": 1.61,
"learning_rate": 6.82061191626409e-05,
"loss": 1.05,
"step": 5040
},
{
"epoch": 1.62,
"learning_rate": 6.814170692431562e-05,
"loss": 1.048,
"step": 5050
},
{
"epoch": 1.62,
"learning_rate": 6.807729468599035e-05,
"loss": 0.9938,
"step": 5060
},
{
"epoch": 1.62,
"learning_rate": 6.801288244766506e-05,
"loss": 1.0101,
"step": 5070
},
{
"epoch": 1.63,
"learning_rate": 6.794847020933977e-05,
"loss": 1.0036,
"step": 5080
},
{
"epoch": 1.63,
"learning_rate": 6.788405797101449e-05,
"loss": 1.0539,
"step": 5090
},
{
"epoch": 1.63,
"learning_rate": 6.781964573268923e-05,
"loss": 1.0127,
"step": 5100
},
{
"epoch": 1.64,
"learning_rate": 6.775523349436393e-05,
"loss": 1.0426,
"step": 5110
},
{
"epoch": 1.64,
"learning_rate": 6.769082125603865e-05,
"loss": 1.0214,
"step": 5120
},
{
"epoch": 1.64,
"learning_rate": 6.762640901771337e-05,
"loss": 1.0157,
"step": 5130
},
{
"epoch": 1.64,
"learning_rate": 6.756199677938809e-05,
"loss": 1.0077,
"step": 5140
},
{
"epoch": 1.65,
"learning_rate": 6.74975845410628e-05,
"loss": 1.0412,
"step": 5150
},
{
"epoch": 1.65,
"learning_rate": 6.743317230273752e-05,
"loss": 1.0017,
"step": 5160
},
{
"epoch": 1.65,
"learning_rate": 6.736876006441224e-05,
"loss": 0.9827,
"step": 5170
},
{
"epoch": 1.66,
"learning_rate": 6.730434782608696e-05,
"loss": 1.0302,
"step": 5180
},
{
"epoch": 1.66,
"learning_rate": 6.723993558776168e-05,
"loss": 1.08,
"step": 5190
},
{
"epoch": 1.66,
"learning_rate": 6.71755233494364e-05,
"loss": 1.0497,
"step": 5200
},
{
"epoch": 1.66,
"eval_loss": 1.0406599044799805,
"eval_runtime": 118.7412,
"eval_samples_per_second": 16.843,
"eval_steps_per_second": 2.105,
"step": 5200
},
{
"epoch": 1.67,
"learning_rate": 6.711111111111112e-05,
"loss": 1.0289,
"step": 5210
},
{
"epoch": 1.67,
"learning_rate": 6.704669887278582e-05,
"loss": 0.9878,
"step": 5220
},
{
"epoch": 1.67,
"learning_rate": 6.698228663446055e-05,
"loss": 1.0198,
"step": 5230
},
{
"epoch": 1.68,
"learning_rate": 6.691787439613527e-05,
"loss": 1.0086,
"step": 5240
},
{
"epoch": 1.68,
"learning_rate": 6.685346215780999e-05,
"loss": 1.0732,
"step": 5250
},
{
"epoch": 1.68,
"learning_rate": 6.67890499194847e-05,
"loss": 1.0408,
"step": 5260
},
{
"epoch": 1.69,
"learning_rate": 6.672463768115942e-05,
"loss": 1.0185,
"step": 5270
},
{
"epoch": 1.69,
"learning_rate": 6.666022544283415e-05,
"loss": 1.0486,
"step": 5280
},
{
"epoch": 1.69,
"learning_rate": 6.659581320450887e-05,
"loss": 1.0021,
"step": 5290
},
{
"epoch": 1.7,
"learning_rate": 6.653140096618357e-05,
"loss": 1.0195,
"step": 5300
},
{
"epoch": 1.7,
"learning_rate": 6.646698872785829e-05,
"loss": 1.0199,
"step": 5310
},
{
"epoch": 1.7,
"learning_rate": 6.640257648953302e-05,
"loss": 0.995,
"step": 5320
},
{
"epoch": 1.71,
"learning_rate": 6.633816425120773e-05,
"loss": 0.9822,
"step": 5330
},
{
"epoch": 1.71,
"learning_rate": 6.627375201288245e-05,
"loss": 1.0525,
"step": 5340
},
{
"epoch": 1.71,
"learning_rate": 6.620933977455717e-05,
"loss": 1.0204,
"step": 5350
},
{
"epoch": 1.72,
"learning_rate": 6.614492753623188e-05,
"loss": 1.0089,
"step": 5360
},
{
"epoch": 1.72,
"learning_rate": 6.60805152979066e-05,
"loss": 1.0226,
"step": 5370
},
{
"epoch": 1.72,
"learning_rate": 6.601610305958132e-05,
"loss": 1.0142,
"step": 5380
},
{
"epoch": 1.72,
"learning_rate": 6.595169082125604e-05,
"loss": 0.9809,
"step": 5390
},
{
"epoch": 1.73,
"learning_rate": 6.588727858293076e-05,
"loss": 1.0352,
"step": 5400
},
{
"epoch": 1.73,
"eval_loss": 1.0410431623458862,
"eval_runtime": 118.8272,
"eval_samples_per_second": 16.831,
"eval_steps_per_second": 2.104,
"step": 5400
},
{
"epoch": 1.73,
"learning_rate": 6.582286634460548e-05,
"loss": 1.0318,
"step": 5410
},
{
"epoch": 1.73,
"learning_rate": 6.57584541062802e-05,
"loss": 1.0316,
"step": 5420
},
{
"epoch": 1.74,
"learning_rate": 6.569404186795492e-05,
"loss": 1.0124,
"step": 5430
},
{
"epoch": 1.74,
"learning_rate": 6.562962962962963e-05,
"loss": 1.0544,
"step": 5440
},
{
"epoch": 1.74,
"learning_rate": 6.556521739130434e-05,
"loss": 1.0078,
"step": 5450
},
{
"epoch": 1.75,
"learning_rate": 6.550080515297907e-05,
"loss": 1.0065,
"step": 5460
},
{
"epoch": 1.75,
"learning_rate": 6.543639291465379e-05,
"loss": 1.0265,
"step": 5470
},
{
"epoch": 1.75,
"learning_rate": 6.537198067632851e-05,
"loss": 1.0032,
"step": 5480
},
{
"epoch": 1.76,
"learning_rate": 6.530756843800321e-05,
"loss": 1.023,
"step": 5490
},
{
"epoch": 1.76,
"learning_rate": 6.524315619967795e-05,
"loss": 1.0446,
"step": 5500
},
{
"epoch": 1.76,
"learning_rate": 6.517874396135267e-05,
"loss": 0.9889,
"step": 5510
},
{
"epoch": 1.77,
"learning_rate": 6.511433172302738e-05,
"loss": 1.0353,
"step": 5520
},
{
"epoch": 1.77,
"learning_rate": 6.504991948470209e-05,
"loss": 1.0278,
"step": 5530
},
{
"epoch": 1.77,
"learning_rate": 6.498550724637682e-05,
"loss": 1.0253,
"step": 5540
},
{
"epoch": 1.78,
"learning_rate": 6.492109500805154e-05,
"loss": 1.0311,
"step": 5550
},
{
"epoch": 1.78,
"learning_rate": 6.485668276972625e-05,
"loss": 0.9975,
"step": 5560
},
{
"epoch": 1.78,
"learning_rate": 6.479227053140096e-05,
"loss": 1.0454,
"step": 5570
},
{
"epoch": 1.79,
"learning_rate": 6.472785829307568e-05,
"loss": 1.0552,
"step": 5580
},
{
"epoch": 1.79,
"learning_rate": 6.466344605475041e-05,
"loss": 1.025,
"step": 5590
},
{
"epoch": 1.79,
"learning_rate": 6.459903381642512e-05,
"loss": 1.01,
"step": 5600
},
{
"epoch": 1.79,
"eval_loss": 1.041631817817688,
"eval_runtime": 118.7407,
"eval_samples_per_second": 16.843,
"eval_steps_per_second": 2.105,
"step": 5600
},
{
"epoch": 1.8,
"learning_rate": 6.453462157809984e-05,
"loss": 1.0156,
"step": 5610
},
{
"epoch": 1.8,
"learning_rate": 6.447020933977456e-05,
"loss": 1.0479,
"step": 5620
},
{
"epoch": 1.8,
"learning_rate": 6.440579710144929e-05,
"loss": 1.0229,
"step": 5630
},
{
"epoch": 1.8,
"learning_rate": 6.4341384863124e-05,
"loss": 0.9508,
"step": 5640
},
{
"epoch": 1.81,
"learning_rate": 6.427697262479871e-05,
"loss": 1.0362,
"step": 5650
},
{
"epoch": 1.81,
"learning_rate": 6.421256038647343e-05,
"loss": 1.0037,
"step": 5660
},
{
"epoch": 1.81,
"learning_rate": 6.414814814814815e-05,
"loss": 1.0062,
"step": 5670
},
{
"epoch": 1.82,
"learning_rate": 6.408373590982287e-05,
"loss": 1.045,
"step": 5680
},
{
"epoch": 1.82,
"learning_rate": 6.401932367149759e-05,
"loss": 0.9951,
"step": 5690
},
{
"epoch": 1.82,
"learning_rate": 6.395491143317231e-05,
"loss": 0.9898,
"step": 5700
},
{
"epoch": 1.83,
"learning_rate": 6.389049919484703e-05,
"loss": 1.0397,
"step": 5710
},
{
"epoch": 1.83,
"learning_rate": 6.382608695652174e-05,
"loss": 1.0571,
"step": 5720
},
{
"epoch": 1.83,
"learning_rate": 6.376167471819646e-05,
"loss": 1.0252,
"step": 5730
},
{
"epoch": 1.84,
"learning_rate": 6.369726247987118e-05,
"loss": 0.9697,
"step": 5740
},
{
"epoch": 1.84,
"learning_rate": 6.36328502415459e-05,
"loss": 1.0087,
"step": 5750
},
{
"epoch": 1.84,
"learning_rate": 6.35684380032206e-05,
"loss": 1.0284,
"step": 5760
},
{
"epoch": 1.85,
"learning_rate": 6.350402576489534e-05,
"loss": 0.9931,
"step": 5770
},
{
"epoch": 1.85,
"learning_rate": 6.343961352657006e-05,
"loss": 1.043,
"step": 5780
},
{
"epoch": 1.85,
"learning_rate": 6.337520128824476e-05,
"loss": 1.0397,
"step": 5790
},
{
"epoch": 1.86,
"learning_rate": 6.331078904991948e-05,
"loss": 1.0297,
"step": 5800
},
{
"epoch": 1.86,
"eval_loss": 1.0399410724639893,
"eval_runtime": 118.6923,
"eval_samples_per_second": 16.85,
"eval_steps_per_second": 2.106,
"step": 5800
},
{
"epoch": 1.86,
"learning_rate": 6.324637681159421e-05,
"loss": 1.032,
"step": 5810
},
{
"epoch": 1.86,
"learning_rate": 6.318196457326893e-05,
"loss": 1.0077,
"step": 5820
},
{
"epoch": 1.87,
"learning_rate": 6.311755233494364e-05,
"loss": 0.9986,
"step": 5830
},
{
"epoch": 1.87,
"learning_rate": 6.305314009661836e-05,
"loss": 1.0348,
"step": 5840
},
{
"epoch": 1.87,
"learning_rate": 6.298872785829309e-05,
"loss": 1.0383,
"step": 5850
},
{
"epoch": 1.88,
"learning_rate": 6.29243156199678e-05,
"loss": 1.0266,
"step": 5860
},
{
"epoch": 1.88,
"learning_rate": 6.285990338164251e-05,
"loss": 1.0014,
"step": 5870
},
{
"epoch": 1.88,
"learning_rate": 6.279549114331723e-05,
"loss": 1.043,
"step": 5880
},
{
"epoch": 1.88,
"learning_rate": 6.273107890499195e-05,
"loss": 1.0,
"step": 5890
},
{
"epoch": 1.89,
"learning_rate": 6.266666666666667e-05,
"loss": 1.0062,
"step": 5900
},
{
"epoch": 1.89,
"learning_rate": 6.260225442834139e-05,
"loss": 1.0426,
"step": 5910
},
{
"epoch": 1.89,
"learning_rate": 6.25378421900161e-05,
"loss": 0.9844,
"step": 5920
},
{
"epoch": 1.9,
"learning_rate": 6.247342995169082e-05,
"loss": 1.024,
"step": 5930
},
{
"epoch": 1.9,
"learning_rate": 6.240901771336554e-05,
"loss": 0.9982,
"step": 5940
},
{
"epoch": 1.9,
"learning_rate": 6.234460547504026e-05,
"loss": 1.0251,
"step": 5950
},
{
"epoch": 1.91,
"learning_rate": 6.228019323671498e-05,
"loss": 0.9999,
"step": 5960
},
{
"epoch": 1.91,
"learning_rate": 6.22157809983897e-05,
"loss": 1.0115,
"step": 5970
},
{
"epoch": 1.91,
"learning_rate": 6.21513687600644e-05,
"loss": 1.0179,
"step": 5980
},
{
"epoch": 1.92,
"learning_rate": 6.208695652173914e-05,
"loss": 0.9518,
"step": 5990
},
{
"epoch": 1.92,
"learning_rate": 6.202254428341385e-05,
"loss": 0.9966,
"step": 6000
},
{
"epoch": 1.92,
"eval_loss": 1.0393410921096802,
"eval_runtime": 118.6864,
"eval_samples_per_second": 16.851,
"eval_steps_per_second": 2.106,
"step": 6000
}
],
"logging_steps": 10,
"max_steps": 15625,
"num_train_epochs": 5,
"save_steps": 200,
"total_flos": 6.625191289926451e+17,
"trial_name": null,
"trial_params": null
}