Muhammad Khalifa
add llama-2 alpaca
0eab2cf
raw
history blame
203 kB
{
"best_metric": 1.0115959644317627,
"best_model_checkpoint": "checkpoints/instrucode/text_models/llama-2-13b/checkpoint-6200",
"epoch": 4.927605791536677,
"eval_steps": 200,
"global_step": 15400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 1.8592,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 1.7835,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 1.7661,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 1.5736,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 5e-05,
"loss": 1.3416,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 6e-05,
"loss": 1.1455,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 7e-05,
"loss": 1.0841,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 7.900000000000001e-05,
"loss": 1.0352,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 8.900000000000001e-05,
"loss": 1.0574,
"step": 90
},
{
"epoch": 0.03,
"learning_rate": 9.900000000000001e-05,
"loss": 1.0802,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 9.994202898550726e-05,
"loss": 1.027,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 9.987761674718196e-05,
"loss": 1.0086,
"step": 120
},
{
"epoch": 0.04,
"learning_rate": 9.981320450885668e-05,
"loss": 1.0188,
"step": 130
},
{
"epoch": 0.04,
"learning_rate": 9.974879227053141e-05,
"loss": 1.0513,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 9.968438003220612e-05,
"loss": 1.074,
"step": 150
},
{
"epoch": 0.05,
"learning_rate": 9.962640901771337e-05,
"loss": 1.0432,
"step": 160
},
{
"epoch": 0.05,
"learning_rate": 9.956199677938809e-05,
"loss": 1.0586,
"step": 170
},
{
"epoch": 0.06,
"learning_rate": 9.949758454106281e-05,
"loss": 1.0195,
"step": 180
},
{
"epoch": 0.06,
"learning_rate": 9.943961352657005e-05,
"loss": 1.1137,
"step": 190
},
{
"epoch": 0.06,
"learning_rate": 9.937520128824477e-05,
"loss": 1.012,
"step": 200
},
{
"epoch": 0.06,
"eval_loss": 1.050466537475586,
"eval_runtime": 186.7925,
"eval_samples_per_second": 10.707,
"eval_steps_per_second": 1.338,
"step": 200
},
{
"epoch": 0.07,
"learning_rate": 9.931078904991949e-05,
"loss": 1.0544,
"step": 210
},
{
"epoch": 0.07,
"learning_rate": 9.924637681159421e-05,
"loss": 1.0796,
"step": 220
},
{
"epoch": 0.07,
"learning_rate": 9.918196457326893e-05,
"loss": 1.0681,
"step": 230
},
{
"epoch": 0.08,
"learning_rate": 9.911755233494364e-05,
"loss": 1.066,
"step": 240
},
{
"epoch": 0.08,
"learning_rate": 9.905314009661836e-05,
"loss": 1.0483,
"step": 250
},
{
"epoch": 0.08,
"learning_rate": 9.898872785829308e-05,
"loss": 1.0917,
"step": 260
},
{
"epoch": 0.09,
"learning_rate": 9.89243156199678e-05,
"loss": 1.0391,
"step": 270
},
{
"epoch": 0.09,
"learning_rate": 9.885990338164252e-05,
"loss": 1.023,
"step": 280
},
{
"epoch": 0.09,
"learning_rate": 9.879549114331724e-05,
"loss": 1.072,
"step": 290
},
{
"epoch": 0.1,
"learning_rate": 9.873107890499196e-05,
"loss": 1.038,
"step": 300
},
{
"epoch": 0.1,
"learning_rate": 9.866666666666668e-05,
"loss": 1.0242,
"step": 310
},
{
"epoch": 0.1,
"learning_rate": 9.86022544283414e-05,
"loss": 1.0045,
"step": 320
},
{
"epoch": 0.11,
"learning_rate": 9.85378421900161e-05,
"loss": 1.0362,
"step": 330
},
{
"epoch": 0.11,
"learning_rate": 9.847342995169082e-05,
"loss": 1.0272,
"step": 340
},
{
"epoch": 0.11,
"learning_rate": 9.840901771336555e-05,
"loss": 0.9938,
"step": 350
},
{
"epoch": 0.12,
"learning_rate": 9.834460547504027e-05,
"loss": 1.0338,
"step": 360
},
{
"epoch": 0.12,
"learning_rate": 9.828019323671497e-05,
"loss": 1.0146,
"step": 370
},
{
"epoch": 0.12,
"learning_rate": 9.821578099838969e-05,
"loss": 1.0324,
"step": 380
},
{
"epoch": 0.12,
"learning_rate": 9.815136876006442e-05,
"loss": 1.0159,
"step": 390
},
{
"epoch": 0.13,
"learning_rate": 9.808695652173914e-05,
"loss": 1.0283,
"step": 400
},
{
"epoch": 0.13,
"eval_loss": 1.041812777519226,
"eval_runtime": 187.3424,
"eval_samples_per_second": 10.676,
"eval_steps_per_second": 1.334,
"step": 400
},
{
"epoch": 0.13,
"learning_rate": 9.802254428341385e-05,
"loss": 1.0189,
"step": 410
},
{
"epoch": 0.13,
"learning_rate": 9.795813204508857e-05,
"loss": 1.0623,
"step": 420
},
{
"epoch": 0.14,
"learning_rate": 9.789371980676329e-05,
"loss": 1.0266,
"step": 430
},
{
"epoch": 0.14,
"learning_rate": 9.7829307568438e-05,
"loss": 1.0436,
"step": 440
},
{
"epoch": 0.14,
"learning_rate": 9.776489533011272e-05,
"loss": 1.0393,
"step": 450
},
{
"epoch": 0.15,
"learning_rate": 9.770048309178744e-05,
"loss": 1.0452,
"step": 460
},
{
"epoch": 0.15,
"learning_rate": 9.763607085346216e-05,
"loss": 1.06,
"step": 470
},
{
"epoch": 0.15,
"learning_rate": 9.757165861513688e-05,
"loss": 1.0115,
"step": 480
},
{
"epoch": 0.16,
"learning_rate": 9.75072463768116e-05,
"loss": 1.0523,
"step": 490
},
{
"epoch": 0.16,
"learning_rate": 9.744283413848632e-05,
"loss": 1.028,
"step": 500
},
{
"epoch": 0.16,
"learning_rate": 9.737842190016104e-05,
"loss": 1.0984,
"step": 510
},
{
"epoch": 0.17,
"learning_rate": 9.731400966183575e-05,
"loss": 1.0312,
"step": 520
},
{
"epoch": 0.17,
"learning_rate": 9.724959742351047e-05,
"loss": 1.0687,
"step": 530
},
{
"epoch": 0.17,
"learning_rate": 9.718518518518519e-05,
"loss": 1.0485,
"step": 540
},
{
"epoch": 0.18,
"learning_rate": 9.712077294685991e-05,
"loss": 1.0423,
"step": 550
},
{
"epoch": 0.18,
"learning_rate": 9.705636070853462e-05,
"loss": 1.0005,
"step": 560
},
{
"epoch": 0.18,
"learning_rate": 9.699194847020935e-05,
"loss": 1.0217,
"step": 570
},
{
"epoch": 0.19,
"learning_rate": 9.692753623188407e-05,
"loss": 1.0233,
"step": 580
},
{
"epoch": 0.19,
"learning_rate": 9.686312399355879e-05,
"loss": 1.0381,
"step": 590
},
{
"epoch": 0.19,
"learning_rate": 9.679871175523349e-05,
"loss": 1.0045,
"step": 600
},
{
"epoch": 0.19,
"eval_loss": 1.0341911315917969,
"eval_runtime": 190.2864,
"eval_samples_per_second": 10.51,
"eval_steps_per_second": 1.314,
"step": 600
},
{
"epoch": 0.2,
"learning_rate": 9.673429951690822e-05,
"loss": 1.0345,
"step": 610
},
{
"epoch": 0.2,
"learning_rate": 9.666988727858294e-05,
"loss": 1.0507,
"step": 620
},
{
"epoch": 0.2,
"learning_rate": 9.660547504025766e-05,
"loss": 1.0261,
"step": 630
},
{
"epoch": 0.2,
"learning_rate": 9.654106280193237e-05,
"loss": 1.0063,
"step": 640
},
{
"epoch": 0.21,
"learning_rate": 9.647665056360708e-05,
"loss": 1.011,
"step": 650
},
{
"epoch": 0.21,
"learning_rate": 9.641223832528182e-05,
"loss": 0.9829,
"step": 660
},
{
"epoch": 0.21,
"learning_rate": 9.634782608695652e-05,
"loss": 1.0007,
"step": 670
},
{
"epoch": 0.22,
"learning_rate": 9.628341384863124e-05,
"loss": 1.0159,
"step": 680
},
{
"epoch": 0.22,
"learning_rate": 9.621900161030596e-05,
"loss": 1.0307,
"step": 690
},
{
"epoch": 0.22,
"learning_rate": 9.615458937198069e-05,
"loss": 0.9949,
"step": 700
},
{
"epoch": 0.23,
"learning_rate": 9.60901771336554e-05,
"loss": 1.0362,
"step": 710
},
{
"epoch": 0.23,
"learning_rate": 9.602576489533011e-05,
"loss": 1.0397,
"step": 720
},
{
"epoch": 0.23,
"learning_rate": 9.596135265700483e-05,
"loss": 1.0709,
"step": 730
},
{
"epoch": 0.24,
"learning_rate": 9.589694041867955e-05,
"loss": 1.0271,
"step": 740
},
{
"epoch": 0.24,
"learning_rate": 9.583252818035427e-05,
"loss": 1.0336,
"step": 750
},
{
"epoch": 0.24,
"learning_rate": 9.576811594202899e-05,
"loss": 0.9954,
"step": 760
},
{
"epoch": 0.25,
"learning_rate": 9.570370370370371e-05,
"loss": 0.9927,
"step": 770
},
{
"epoch": 0.25,
"learning_rate": 9.563929146537843e-05,
"loss": 1.0313,
"step": 780
},
{
"epoch": 0.25,
"learning_rate": 9.557487922705315e-05,
"loss": 1.0671,
"step": 790
},
{
"epoch": 0.26,
"learning_rate": 9.551046698872786e-05,
"loss": 1.0038,
"step": 800
},
{
"epoch": 0.26,
"eval_loss": 1.0327339172363281,
"eval_runtime": 187.9065,
"eval_samples_per_second": 10.644,
"eval_steps_per_second": 1.33,
"step": 800
},
{
"epoch": 0.26,
"learning_rate": 9.544605475040258e-05,
"loss": 1.0013,
"step": 810
},
{
"epoch": 0.26,
"learning_rate": 9.53816425120773e-05,
"loss": 0.9574,
"step": 820
},
{
"epoch": 0.27,
"learning_rate": 9.531723027375202e-05,
"loss": 1.0208,
"step": 830
},
{
"epoch": 0.27,
"learning_rate": 9.525281803542674e-05,
"loss": 1.0067,
"step": 840
},
{
"epoch": 0.27,
"learning_rate": 9.518840579710146e-05,
"loss": 1.0408,
"step": 850
},
{
"epoch": 0.28,
"learning_rate": 9.512399355877616e-05,
"loss": 1.0299,
"step": 860
},
{
"epoch": 0.28,
"learning_rate": 9.505958132045088e-05,
"loss": 1.0195,
"step": 870
},
{
"epoch": 0.28,
"learning_rate": 9.499516908212561e-05,
"loss": 1.0095,
"step": 880
},
{
"epoch": 0.28,
"learning_rate": 9.493075684380033e-05,
"loss": 1.0174,
"step": 890
},
{
"epoch": 0.29,
"learning_rate": 9.486634460547504e-05,
"loss": 1.0238,
"step": 900
},
{
"epoch": 0.29,
"learning_rate": 9.480193236714976e-05,
"loss": 1.0506,
"step": 910
},
{
"epoch": 0.29,
"learning_rate": 9.473752012882449e-05,
"loss": 1.0308,
"step": 920
},
{
"epoch": 0.3,
"learning_rate": 9.467310789049921e-05,
"loss": 1.018,
"step": 930
},
{
"epoch": 0.3,
"learning_rate": 9.460869565217391e-05,
"loss": 1.058,
"step": 940
},
{
"epoch": 0.3,
"learning_rate": 9.454428341384863e-05,
"loss": 1.0226,
"step": 950
},
{
"epoch": 0.31,
"learning_rate": 9.447987117552335e-05,
"loss": 1.0569,
"step": 960
},
{
"epoch": 0.31,
"learning_rate": 9.441545893719808e-05,
"loss": 0.988,
"step": 970
},
{
"epoch": 0.31,
"learning_rate": 9.435104669887279e-05,
"loss": 1.0036,
"step": 980
},
{
"epoch": 0.32,
"learning_rate": 9.42866344605475e-05,
"loss": 1.012,
"step": 990
},
{
"epoch": 0.32,
"learning_rate": 9.422222222222223e-05,
"loss": 0.9998,
"step": 1000
},
{
"epoch": 0.32,
"eval_loss": 1.0286028385162354,
"eval_runtime": 186.8358,
"eval_samples_per_second": 10.705,
"eval_steps_per_second": 1.338,
"step": 1000
},
{
"epoch": 0.32,
"learning_rate": 9.415780998389694e-05,
"loss": 1.0794,
"step": 1010
},
{
"epoch": 0.33,
"learning_rate": 9.409339774557166e-05,
"loss": 1.0211,
"step": 1020
},
{
"epoch": 0.33,
"learning_rate": 9.402898550724638e-05,
"loss": 1.039,
"step": 1030
},
{
"epoch": 0.33,
"learning_rate": 9.39645732689211e-05,
"loss": 1.0337,
"step": 1040
},
{
"epoch": 0.34,
"learning_rate": 9.390016103059582e-05,
"loss": 1.0546,
"step": 1050
},
{
"epoch": 0.34,
"learning_rate": 9.383574879227054e-05,
"loss": 1.0126,
"step": 1060
},
{
"epoch": 0.34,
"learning_rate": 9.377133655394526e-05,
"loss": 1.01,
"step": 1070
},
{
"epoch": 0.35,
"learning_rate": 9.370692431561997e-05,
"loss": 1.005,
"step": 1080
},
{
"epoch": 0.35,
"learning_rate": 9.364251207729468e-05,
"loss": 1.0742,
"step": 1090
},
{
"epoch": 0.35,
"learning_rate": 9.357809983896941e-05,
"loss": 1.0131,
"step": 1100
},
{
"epoch": 0.36,
"learning_rate": 9.351368760064413e-05,
"loss": 1.0148,
"step": 1110
},
{
"epoch": 0.36,
"learning_rate": 9.344927536231885e-05,
"loss": 1.0298,
"step": 1120
},
{
"epoch": 0.36,
"learning_rate": 9.338486312399355e-05,
"loss": 1.0235,
"step": 1130
},
{
"epoch": 0.36,
"learning_rate": 9.332045088566829e-05,
"loss": 1.0461,
"step": 1140
},
{
"epoch": 0.37,
"learning_rate": 9.3256038647343e-05,
"loss": 1.0328,
"step": 1150
},
{
"epoch": 0.37,
"learning_rate": 9.319162640901772e-05,
"loss": 1.0336,
"step": 1160
},
{
"epoch": 0.37,
"learning_rate": 9.312721417069243e-05,
"loss": 1.0651,
"step": 1170
},
{
"epoch": 0.38,
"learning_rate": 9.306280193236715e-05,
"loss": 0.9966,
"step": 1180
},
{
"epoch": 0.38,
"learning_rate": 9.299838969404188e-05,
"loss": 1.0428,
"step": 1190
},
{
"epoch": 0.38,
"learning_rate": 9.293397745571659e-05,
"loss": 1.0506,
"step": 1200
},
{
"epoch": 0.38,
"eval_loss": 1.0272533893585205,
"eval_runtime": 193.4811,
"eval_samples_per_second": 10.337,
"eval_steps_per_second": 1.292,
"step": 1200
},
{
"epoch": 0.39,
"learning_rate": 9.28695652173913e-05,
"loss": 1.0431,
"step": 1210
},
{
"epoch": 0.39,
"learning_rate": 9.280515297906602e-05,
"loss": 0.9844,
"step": 1220
},
{
"epoch": 0.39,
"learning_rate": 9.274074074074076e-05,
"loss": 1.0488,
"step": 1230
},
{
"epoch": 0.4,
"learning_rate": 9.267632850241546e-05,
"loss": 0.9965,
"step": 1240
},
{
"epoch": 0.4,
"learning_rate": 9.261191626409018e-05,
"loss": 1.0397,
"step": 1250
},
{
"epoch": 0.4,
"learning_rate": 9.25475040257649e-05,
"loss": 1.0347,
"step": 1260
},
{
"epoch": 0.41,
"learning_rate": 9.248309178743962e-05,
"loss": 0.9955,
"step": 1270
},
{
"epoch": 0.41,
"learning_rate": 9.241867954911434e-05,
"loss": 0.9883,
"step": 1280
},
{
"epoch": 0.41,
"learning_rate": 9.235426731078905e-05,
"loss": 0.9947,
"step": 1290
},
{
"epoch": 0.42,
"learning_rate": 9.228985507246377e-05,
"loss": 1.0275,
"step": 1300
},
{
"epoch": 0.42,
"learning_rate": 9.222544283413849e-05,
"loss": 0.9823,
"step": 1310
},
{
"epoch": 0.42,
"learning_rate": 9.216103059581321e-05,
"loss": 1.0227,
"step": 1320
},
{
"epoch": 0.43,
"learning_rate": 9.209661835748793e-05,
"loss": 1.0172,
"step": 1330
},
{
"epoch": 0.43,
"learning_rate": 9.203220611916265e-05,
"loss": 0.9689,
"step": 1340
},
{
"epoch": 0.43,
"learning_rate": 9.196779388083737e-05,
"loss": 1.0471,
"step": 1350
},
{
"epoch": 0.44,
"learning_rate": 9.190338164251207e-05,
"loss": 1.0608,
"step": 1360
},
{
"epoch": 0.44,
"learning_rate": 9.18389694041868e-05,
"loss": 1.0556,
"step": 1370
},
{
"epoch": 0.44,
"learning_rate": 9.177455716586152e-05,
"loss": 0.9823,
"step": 1380
},
{
"epoch": 0.44,
"learning_rate": 9.171014492753624e-05,
"loss": 1.0325,
"step": 1390
},
{
"epoch": 0.45,
"learning_rate": 9.164573268921095e-05,
"loss": 1.0067,
"step": 1400
},
{
"epoch": 0.45,
"eval_loss": 1.0259579420089722,
"eval_runtime": 187.0176,
"eval_samples_per_second": 10.694,
"eval_steps_per_second": 1.337,
"step": 1400
},
{
"epoch": 0.45,
"learning_rate": 9.158132045088568e-05,
"loss": 1.0186,
"step": 1410
},
{
"epoch": 0.45,
"learning_rate": 9.15169082125604e-05,
"loss": 1.0293,
"step": 1420
},
{
"epoch": 0.46,
"learning_rate": 9.14524959742351e-05,
"loss": 1.0173,
"step": 1430
},
{
"epoch": 0.46,
"learning_rate": 9.138808373590982e-05,
"loss": 1.064,
"step": 1440
},
{
"epoch": 0.46,
"learning_rate": 9.132367149758455e-05,
"loss": 1.0415,
"step": 1450
},
{
"epoch": 0.47,
"learning_rate": 9.125925925925927e-05,
"loss": 1.0465,
"step": 1460
},
{
"epoch": 0.47,
"learning_rate": 9.119484702093398e-05,
"loss": 1.0284,
"step": 1470
},
{
"epoch": 0.47,
"learning_rate": 9.11304347826087e-05,
"loss": 1.036,
"step": 1480
},
{
"epoch": 0.48,
"learning_rate": 9.106602254428341e-05,
"loss": 1.0351,
"step": 1490
},
{
"epoch": 0.48,
"learning_rate": 9.100161030595815e-05,
"loss": 1.0446,
"step": 1500
},
{
"epoch": 0.48,
"learning_rate": 9.093719806763285e-05,
"loss": 1.0019,
"step": 1510
},
{
"epoch": 0.49,
"learning_rate": 9.087278582930757e-05,
"loss": 1.018,
"step": 1520
},
{
"epoch": 0.49,
"learning_rate": 9.080837359098229e-05,
"loss": 1.0221,
"step": 1530
},
{
"epoch": 0.49,
"learning_rate": 9.074396135265701e-05,
"loss": 1.047,
"step": 1540
},
{
"epoch": 0.5,
"learning_rate": 9.067954911433173e-05,
"loss": 1.0105,
"step": 1550
},
{
"epoch": 0.5,
"learning_rate": 9.061513687600645e-05,
"loss": 1.0245,
"step": 1560
},
{
"epoch": 0.5,
"learning_rate": 9.055072463768116e-05,
"loss": 1.0513,
"step": 1570
},
{
"epoch": 0.51,
"learning_rate": 9.048631239935588e-05,
"loss": 1.0033,
"step": 1580
},
{
"epoch": 0.51,
"learning_rate": 9.04219001610306e-05,
"loss": 0.9867,
"step": 1590
},
{
"epoch": 0.51,
"learning_rate": 9.035748792270532e-05,
"loss": 1.0351,
"step": 1600
},
{
"epoch": 0.51,
"eval_loss": 1.0244308710098267,
"eval_runtime": 186.9957,
"eval_samples_per_second": 10.695,
"eval_steps_per_second": 1.337,
"step": 1600
},
{
"epoch": 0.52,
"learning_rate": 9.029307568438004e-05,
"loss": 1.0109,
"step": 1610
},
{
"epoch": 0.52,
"learning_rate": 9.022866344605474e-05,
"loss": 1.0464,
"step": 1620
},
{
"epoch": 0.52,
"learning_rate": 9.016425120772948e-05,
"loss": 1.0204,
"step": 1630
},
{
"epoch": 0.52,
"learning_rate": 9.00998389694042e-05,
"loss": 1.0605,
"step": 1640
},
{
"epoch": 0.53,
"learning_rate": 9.003542673107891e-05,
"loss": 1.0209,
"step": 1650
},
{
"epoch": 0.53,
"learning_rate": 8.997101449275362e-05,
"loss": 1.0588,
"step": 1660
},
{
"epoch": 0.53,
"learning_rate": 8.990660225442834e-05,
"loss": 1.0094,
"step": 1670
},
{
"epoch": 0.54,
"learning_rate": 8.984219001610307e-05,
"loss": 1.1152,
"step": 1680
},
{
"epoch": 0.54,
"learning_rate": 8.977777777777779e-05,
"loss": 1.0059,
"step": 1690
},
{
"epoch": 0.54,
"learning_rate": 8.97133655394525e-05,
"loss": 1.042,
"step": 1700
},
{
"epoch": 0.55,
"learning_rate": 8.964895330112721e-05,
"loss": 0.9825,
"step": 1710
},
{
"epoch": 0.55,
"learning_rate": 8.958454106280194e-05,
"loss": 1.0188,
"step": 1720
},
{
"epoch": 0.55,
"learning_rate": 8.952012882447666e-05,
"loss": 1.0384,
"step": 1730
},
{
"epoch": 0.56,
"learning_rate": 8.945571658615137e-05,
"loss": 1.0454,
"step": 1740
},
{
"epoch": 0.56,
"learning_rate": 8.939130434782609e-05,
"loss": 1.0252,
"step": 1750
},
{
"epoch": 0.56,
"learning_rate": 8.932689210950082e-05,
"loss": 1.0093,
"step": 1760
},
{
"epoch": 0.57,
"learning_rate": 8.926247987117552e-05,
"loss": 1.0079,
"step": 1770
},
{
"epoch": 0.57,
"learning_rate": 8.919806763285024e-05,
"loss": 1.0162,
"step": 1780
},
{
"epoch": 0.57,
"learning_rate": 8.913365539452496e-05,
"loss": 1.0445,
"step": 1790
},
{
"epoch": 0.58,
"learning_rate": 8.906924315619968e-05,
"loss": 1.0151,
"step": 1800
},
{
"epoch": 0.58,
"eval_loss": 1.022465467453003,
"eval_runtime": 187.4046,
"eval_samples_per_second": 10.672,
"eval_steps_per_second": 1.334,
"step": 1800
},
{
"epoch": 0.58,
"learning_rate": 8.90048309178744e-05,
"loss": 1.0026,
"step": 1810
},
{
"epoch": 0.58,
"learning_rate": 8.894041867954912e-05,
"loss": 1.0338,
"step": 1820
},
{
"epoch": 0.59,
"learning_rate": 8.887600644122384e-05,
"loss": 1.0004,
"step": 1830
},
{
"epoch": 0.59,
"learning_rate": 8.881159420289856e-05,
"loss": 1.0013,
"step": 1840
},
{
"epoch": 0.59,
"learning_rate": 8.874718196457327e-05,
"loss": 0.9698,
"step": 1850
},
{
"epoch": 0.6,
"learning_rate": 8.868276972624799e-05,
"loss": 1.0308,
"step": 1860
},
{
"epoch": 0.6,
"learning_rate": 8.861835748792271e-05,
"loss": 0.9898,
"step": 1870
},
{
"epoch": 0.6,
"learning_rate": 8.855394524959743e-05,
"loss": 1.0491,
"step": 1880
},
{
"epoch": 0.6,
"learning_rate": 8.848953301127214e-05,
"loss": 1.0242,
"step": 1890
},
{
"epoch": 0.61,
"learning_rate": 8.842512077294687e-05,
"loss": 1.0419,
"step": 1900
},
{
"epoch": 0.61,
"learning_rate": 8.836070853462159e-05,
"loss": 1.0346,
"step": 1910
},
{
"epoch": 0.61,
"learning_rate": 8.82962962962963e-05,
"loss": 0.9888,
"step": 1920
},
{
"epoch": 0.62,
"learning_rate": 8.823188405797101e-05,
"loss": 1.0115,
"step": 1930
},
{
"epoch": 0.62,
"learning_rate": 8.816747181964574e-05,
"loss": 1.0193,
"step": 1940
},
{
"epoch": 0.62,
"learning_rate": 8.810305958132046e-05,
"loss": 1.0633,
"step": 1950
},
{
"epoch": 0.63,
"learning_rate": 8.803864734299517e-05,
"loss": 1.048,
"step": 1960
},
{
"epoch": 0.63,
"learning_rate": 8.797423510466989e-05,
"loss": 1.0345,
"step": 1970
},
{
"epoch": 0.63,
"learning_rate": 8.79098228663446e-05,
"loss": 1.0477,
"step": 1980
},
{
"epoch": 0.64,
"learning_rate": 8.784541062801934e-05,
"loss": 1.0232,
"step": 1990
},
{
"epoch": 0.64,
"learning_rate": 8.778099838969404e-05,
"loss": 1.0614,
"step": 2000
},
{
"epoch": 0.64,
"eval_loss": 1.0219651460647583,
"eval_runtime": 187.5045,
"eval_samples_per_second": 10.666,
"eval_steps_per_second": 1.333,
"step": 2000
},
{
"epoch": 0.64,
"learning_rate": 8.771658615136876e-05,
"loss": 1.0489,
"step": 2010
},
{
"epoch": 0.65,
"learning_rate": 8.765217391304348e-05,
"loss": 0.9984,
"step": 2020
},
{
"epoch": 0.65,
"learning_rate": 8.758776167471821e-05,
"loss": 1.0021,
"step": 2030
},
{
"epoch": 0.65,
"learning_rate": 8.752334943639292e-05,
"loss": 1.0382,
"step": 2040
},
{
"epoch": 0.66,
"learning_rate": 8.745893719806763e-05,
"loss": 1.0086,
"step": 2050
},
{
"epoch": 0.66,
"learning_rate": 8.739452495974235e-05,
"loss": 1.0211,
"step": 2060
},
{
"epoch": 0.66,
"learning_rate": 8.733011272141707e-05,
"loss": 0.9975,
"step": 2070
},
{
"epoch": 0.67,
"learning_rate": 8.726570048309179e-05,
"loss": 1.0468,
"step": 2080
},
{
"epoch": 0.67,
"learning_rate": 8.720128824476651e-05,
"loss": 1.0646,
"step": 2090
},
{
"epoch": 0.67,
"learning_rate": 8.713687600644123e-05,
"loss": 1.0311,
"step": 2100
},
{
"epoch": 0.68,
"learning_rate": 8.707246376811595e-05,
"loss": 1.0253,
"step": 2110
},
{
"epoch": 0.68,
"learning_rate": 8.700805152979067e-05,
"loss": 1.0511,
"step": 2120
},
{
"epoch": 0.68,
"learning_rate": 8.694363929146538e-05,
"loss": 1.0652,
"step": 2130
},
{
"epoch": 0.68,
"learning_rate": 8.68792270531401e-05,
"loss": 1.0397,
"step": 2140
},
{
"epoch": 0.69,
"learning_rate": 8.681481481481482e-05,
"loss": 1.0262,
"step": 2150
},
{
"epoch": 0.69,
"learning_rate": 8.675040257648954e-05,
"loss": 1.0374,
"step": 2160
},
{
"epoch": 0.69,
"learning_rate": 8.668599033816426e-05,
"loss": 1.0446,
"step": 2170
},
{
"epoch": 0.7,
"learning_rate": 8.662157809983898e-05,
"loss": 1.0278,
"step": 2180
},
{
"epoch": 0.7,
"learning_rate": 8.655716586151368e-05,
"loss": 0.9984,
"step": 2190
},
{
"epoch": 0.7,
"learning_rate": 8.64927536231884e-05,
"loss": 1.0373,
"step": 2200
},
{
"epoch": 0.7,
"eval_loss": 1.020651936531067,
"eval_runtime": 187.3402,
"eval_samples_per_second": 10.676,
"eval_steps_per_second": 1.334,
"step": 2200
},
{
"epoch": 0.71,
"learning_rate": 8.642834138486313e-05,
"loss": 1.0451,
"step": 2210
},
{
"epoch": 0.71,
"learning_rate": 8.636392914653785e-05,
"loss": 1.0249,
"step": 2220
},
{
"epoch": 0.71,
"learning_rate": 8.629951690821256e-05,
"loss": 0.9943,
"step": 2230
},
{
"epoch": 0.72,
"learning_rate": 8.623510466988728e-05,
"loss": 1.0084,
"step": 2240
},
{
"epoch": 0.72,
"learning_rate": 8.617069243156201e-05,
"loss": 1.0046,
"step": 2250
},
{
"epoch": 0.72,
"learning_rate": 8.610628019323673e-05,
"loss": 0.982,
"step": 2260
},
{
"epoch": 0.73,
"learning_rate": 8.604186795491143e-05,
"loss": 1.0438,
"step": 2270
},
{
"epoch": 0.73,
"learning_rate": 8.597745571658615e-05,
"loss": 1.032,
"step": 2280
},
{
"epoch": 0.73,
"learning_rate": 8.591304347826087e-05,
"loss": 1.0066,
"step": 2290
},
{
"epoch": 0.74,
"learning_rate": 8.584863123993559e-05,
"loss": 1.0412,
"step": 2300
},
{
"epoch": 0.74,
"learning_rate": 8.578421900161031e-05,
"loss": 0.9981,
"step": 2310
},
{
"epoch": 0.74,
"learning_rate": 8.571980676328503e-05,
"loss": 1.0111,
"step": 2320
},
{
"epoch": 0.75,
"learning_rate": 8.565539452495974e-05,
"loss": 1.0057,
"step": 2330
},
{
"epoch": 0.75,
"learning_rate": 8.559098228663446e-05,
"loss": 1.022,
"step": 2340
},
{
"epoch": 0.75,
"learning_rate": 8.552657004830918e-05,
"loss": 0.9963,
"step": 2350
},
{
"epoch": 0.76,
"learning_rate": 8.54621578099839e-05,
"loss": 1.0382,
"step": 2360
},
{
"epoch": 0.76,
"learning_rate": 8.539774557165862e-05,
"loss": 1.0083,
"step": 2370
},
{
"epoch": 0.76,
"learning_rate": 8.533333333333334e-05,
"loss": 1.0126,
"step": 2380
},
{
"epoch": 0.76,
"learning_rate": 8.526892109500806e-05,
"loss": 0.9937,
"step": 2390
},
{
"epoch": 0.77,
"learning_rate": 8.520450885668278e-05,
"loss": 1.0266,
"step": 2400
},
{
"epoch": 0.77,
"eval_loss": 1.0203664302825928,
"eval_runtime": 188.9153,
"eval_samples_per_second": 10.587,
"eval_steps_per_second": 1.323,
"step": 2400
},
{
"epoch": 0.77,
"learning_rate": 8.51400966183575e-05,
"loss": 1.0608,
"step": 2410
},
{
"epoch": 0.77,
"learning_rate": 8.50756843800322e-05,
"loss": 1.0238,
"step": 2420
},
{
"epoch": 0.78,
"learning_rate": 8.501127214170693e-05,
"loss": 1.0271,
"step": 2430
},
{
"epoch": 0.78,
"learning_rate": 8.494685990338165e-05,
"loss": 1.0275,
"step": 2440
},
{
"epoch": 0.78,
"learning_rate": 8.488244766505637e-05,
"loss": 1.0453,
"step": 2450
},
{
"epoch": 0.79,
"learning_rate": 8.481803542673107e-05,
"loss": 1.045,
"step": 2460
},
{
"epoch": 0.79,
"learning_rate": 8.475362318840581e-05,
"loss": 1.0463,
"step": 2470
},
{
"epoch": 0.79,
"learning_rate": 8.468921095008053e-05,
"loss": 1.0199,
"step": 2480
},
{
"epoch": 0.8,
"learning_rate": 8.462479871175524e-05,
"loss": 0.9889,
"step": 2490
},
{
"epoch": 0.8,
"learning_rate": 8.456038647342995e-05,
"loss": 0.9973,
"step": 2500
},
{
"epoch": 0.8,
"learning_rate": 8.449597423510467e-05,
"loss": 1.041,
"step": 2510
},
{
"epoch": 0.81,
"learning_rate": 8.44315619967794e-05,
"loss": 1.0169,
"step": 2520
},
{
"epoch": 0.81,
"learning_rate": 8.43671497584541e-05,
"loss": 1.0221,
"step": 2530
},
{
"epoch": 0.81,
"learning_rate": 8.430273752012882e-05,
"loss": 1.0357,
"step": 2540
},
{
"epoch": 0.82,
"learning_rate": 8.423832528180354e-05,
"loss": 0.9808,
"step": 2550
},
{
"epoch": 0.82,
"learning_rate": 8.417391304347828e-05,
"loss": 1.0055,
"step": 2560
},
{
"epoch": 0.82,
"learning_rate": 8.410950080515298e-05,
"loss": 1.0113,
"step": 2570
},
{
"epoch": 0.83,
"learning_rate": 8.40450885668277e-05,
"loss": 1.0418,
"step": 2580
},
{
"epoch": 0.83,
"learning_rate": 8.398067632850242e-05,
"loss": 1.0252,
"step": 2590
},
{
"epoch": 0.83,
"learning_rate": 8.391626409017714e-05,
"loss": 1.0141,
"step": 2600
},
{
"epoch": 0.83,
"eval_loss": 1.0183026790618896,
"eval_runtime": 188.3677,
"eval_samples_per_second": 10.618,
"eval_steps_per_second": 1.327,
"step": 2600
},
{
"epoch": 0.84,
"learning_rate": 8.385185185185186e-05,
"loss": 0.9696,
"step": 2610
},
{
"epoch": 0.84,
"learning_rate": 8.378743961352657e-05,
"loss": 1.0527,
"step": 2620
},
{
"epoch": 0.84,
"learning_rate": 8.372302737520129e-05,
"loss": 1.0197,
"step": 2630
},
{
"epoch": 0.84,
"learning_rate": 8.365861513687601e-05,
"loss": 1.0035,
"step": 2640
},
{
"epoch": 0.85,
"learning_rate": 8.359420289855073e-05,
"loss": 1.0426,
"step": 2650
},
{
"epoch": 0.85,
"learning_rate": 8.352979066022545e-05,
"loss": 1.0199,
"step": 2660
},
{
"epoch": 0.85,
"learning_rate": 8.346537842190017e-05,
"loss": 1.0231,
"step": 2670
},
{
"epoch": 0.86,
"learning_rate": 8.340096618357489e-05,
"loss": 1.0153,
"step": 2680
},
{
"epoch": 0.86,
"learning_rate": 8.33365539452496e-05,
"loss": 0.9991,
"step": 2690
},
{
"epoch": 0.86,
"learning_rate": 8.327214170692432e-05,
"loss": 1.0103,
"step": 2700
},
{
"epoch": 0.87,
"learning_rate": 8.320772946859904e-05,
"loss": 0.9782,
"step": 2710
},
{
"epoch": 0.87,
"learning_rate": 8.314331723027375e-05,
"loss": 1.0254,
"step": 2720
},
{
"epoch": 0.87,
"learning_rate": 8.307890499194847e-05,
"loss": 1.0162,
"step": 2730
},
{
"epoch": 0.88,
"learning_rate": 8.30144927536232e-05,
"loss": 0.9674,
"step": 2740
},
{
"epoch": 0.88,
"learning_rate": 8.295008051529792e-05,
"loss": 1.0262,
"step": 2750
},
{
"epoch": 0.88,
"learning_rate": 8.288566827697262e-05,
"loss": 1.0294,
"step": 2760
},
{
"epoch": 0.89,
"learning_rate": 8.282125603864734e-05,
"loss": 1.0064,
"step": 2770
},
{
"epoch": 0.89,
"learning_rate": 8.275684380032207e-05,
"loss": 0.9869,
"step": 2780
},
{
"epoch": 0.89,
"learning_rate": 8.269243156199679e-05,
"loss": 1.0191,
"step": 2790
},
{
"epoch": 0.9,
"learning_rate": 8.26280193236715e-05,
"loss": 1.0347,
"step": 2800
},
{
"epoch": 0.9,
"eval_loss": 1.0175596475601196,
"eval_runtime": 187.2212,
"eval_samples_per_second": 10.683,
"eval_steps_per_second": 1.335,
"step": 2800
},
{
"epoch": 0.9,
"learning_rate": 8.256360708534622e-05,
"loss": 1.0247,
"step": 2810
},
{
"epoch": 0.9,
"learning_rate": 8.249919484702093e-05,
"loss": 1.016,
"step": 2820
},
{
"epoch": 0.91,
"learning_rate": 8.243478260869565e-05,
"loss": 1.0039,
"step": 2830
},
{
"epoch": 0.91,
"learning_rate": 8.237037037037037e-05,
"loss": 1.0306,
"step": 2840
},
{
"epoch": 0.91,
"learning_rate": 8.230595813204509e-05,
"loss": 1.0314,
"step": 2850
},
{
"epoch": 0.92,
"learning_rate": 8.224154589371981e-05,
"loss": 0.9795,
"step": 2860
},
{
"epoch": 0.92,
"learning_rate": 8.217713365539453e-05,
"loss": 1.0489,
"step": 2870
},
{
"epoch": 0.92,
"learning_rate": 8.211272141706925e-05,
"loss": 1.0023,
"step": 2880
},
{
"epoch": 0.92,
"learning_rate": 8.204830917874397e-05,
"loss": 0.9973,
"step": 2890
},
{
"epoch": 0.93,
"learning_rate": 8.198389694041868e-05,
"loss": 1.0281,
"step": 2900
},
{
"epoch": 0.93,
"learning_rate": 8.19194847020934e-05,
"loss": 1.0256,
"step": 2910
},
{
"epoch": 0.93,
"learning_rate": 8.185507246376812e-05,
"loss": 1.015,
"step": 2920
},
{
"epoch": 0.94,
"learning_rate": 8.179066022544284e-05,
"loss": 0.981,
"step": 2930
},
{
"epoch": 0.94,
"learning_rate": 8.172624798711756e-05,
"loss": 1.0001,
"step": 2940
},
{
"epoch": 0.94,
"learning_rate": 8.166183574879226e-05,
"loss": 1.0324,
"step": 2950
},
{
"epoch": 0.95,
"learning_rate": 8.1597423510467e-05,
"loss": 0.9589,
"step": 2960
},
{
"epoch": 0.95,
"learning_rate": 8.153301127214171e-05,
"loss": 0.994,
"step": 2970
},
{
"epoch": 0.95,
"learning_rate": 8.146859903381643e-05,
"loss": 1.0238,
"step": 2980
},
{
"epoch": 0.96,
"learning_rate": 8.140418679549114e-05,
"loss": 1.0347,
"step": 2990
},
{
"epoch": 0.96,
"learning_rate": 8.133977455716587e-05,
"loss": 1.0248,
"step": 3000
},
{
"epoch": 0.96,
"eval_loss": 1.0177215337753296,
"eval_runtime": 187.3372,
"eval_samples_per_second": 10.676,
"eval_steps_per_second": 1.334,
"step": 3000
},
{
"epoch": 0.96,
"learning_rate": 8.127536231884059e-05,
"loss": 1.0349,
"step": 3010
},
{
"epoch": 0.97,
"learning_rate": 8.121095008051531e-05,
"loss": 1.0264,
"step": 3020
},
{
"epoch": 0.97,
"learning_rate": 8.114653784219001e-05,
"loss": 0.9841,
"step": 3030
},
{
"epoch": 0.97,
"learning_rate": 8.108212560386473e-05,
"loss": 1.0262,
"step": 3040
},
{
"epoch": 0.98,
"learning_rate": 8.101771336553946e-05,
"loss": 1.0255,
"step": 3050
},
{
"epoch": 0.98,
"learning_rate": 8.095330112721417e-05,
"loss": 0.9856,
"step": 3060
},
{
"epoch": 0.98,
"learning_rate": 8.088888888888889e-05,
"loss": 1.0685,
"step": 3070
},
{
"epoch": 0.99,
"learning_rate": 8.082447665056361e-05,
"loss": 1.0094,
"step": 3080
},
{
"epoch": 0.99,
"learning_rate": 8.076006441223834e-05,
"loss": 1.022,
"step": 3090
},
{
"epoch": 0.99,
"learning_rate": 8.069565217391304e-05,
"loss": 0.9743,
"step": 3100
},
{
"epoch": 1.0,
"learning_rate": 8.063123993558776e-05,
"loss": 1.0228,
"step": 3110
},
{
"epoch": 1.0,
"learning_rate": 8.056682769726248e-05,
"loss": 1.0398,
"step": 3120
},
{
"epoch": 1.0,
"learning_rate": 8.05024154589372e-05,
"loss": 1.0022,
"step": 3130
},
{
"epoch": 1.0,
"learning_rate": 8.043800322061192e-05,
"loss": 1.0136,
"step": 3140
},
{
"epoch": 1.01,
"learning_rate": 8.038003220611917e-05,
"loss": 0.9806,
"step": 3150
},
{
"epoch": 1.01,
"learning_rate": 8.031561996779389e-05,
"loss": 1.0222,
"step": 3160
},
{
"epoch": 1.01,
"learning_rate": 8.02512077294686e-05,
"loss": 0.9584,
"step": 3170
},
{
"epoch": 1.02,
"learning_rate": 8.018679549114332e-05,
"loss": 0.9746,
"step": 3180
},
{
"epoch": 1.02,
"learning_rate": 8.012238325281803e-05,
"loss": 1.0131,
"step": 3190
},
{
"epoch": 1.02,
"learning_rate": 8.005797101449277e-05,
"loss": 0.977,
"step": 3200
},
{
"epoch": 1.02,
"eval_loss": 1.0170557498931885,
"eval_runtime": 187.1066,
"eval_samples_per_second": 10.689,
"eval_steps_per_second": 1.336,
"step": 3200
},
{
"epoch": 1.03,
"learning_rate": 7.999355877616747e-05,
"loss": 1.0382,
"step": 3210
},
{
"epoch": 1.03,
"learning_rate": 7.992914653784219e-05,
"loss": 0.958,
"step": 3220
},
{
"epoch": 1.03,
"learning_rate": 7.986473429951691e-05,
"loss": 1.0106,
"step": 3230
},
{
"epoch": 1.04,
"learning_rate": 7.980032206119164e-05,
"loss": 1.0137,
"step": 3240
},
{
"epoch": 1.04,
"learning_rate": 7.973590982286635e-05,
"loss": 0.9941,
"step": 3250
},
{
"epoch": 1.04,
"learning_rate": 7.967149758454107e-05,
"loss": 1.0061,
"step": 3260
},
{
"epoch": 1.05,
"learning_rate": 7.960708534621578e-05,
"loss": 1.0035,
"step": 3270
},
{
"epoch": 1.05,
"learning_rate": 7.95426731078905e-05,
"loss": 1.0023,
"step": 3280
},
{
"epoch": 1.05,
"learning_rate": 7.947826086956522e-05,
"loss": 0.9759,
"step": 3290
},
{
"epoch": 1.06,
"learning_rate": 7.941384863123994e-05,
"loss": 0.9744,
"step": 3300
},
{
"epoch": 1.06,
"learning_rate": 7.934943639291466e-05,
"loss": 1.0105,
"step": 3310
},
{
"epoch": 1.06,
"learning_rate": 7.928502415458938e-05,
"loss": 0.9845,
"step": 3320
},
{
"epoch": 1.07,
"learning_rate": 7.92206119162641e-05,
"loss": 1.0166,
"step": 3330
},
{
"epoch": 1.07,
"learning_rate": 7.915619967793881e-05,
"loss": 0.9917,
"step": 3340
},
{
"epoch": 1.07,
"learning_rate": 7.909178743961353e-05,
"loss": 0.994,
"step": 3350
},
{
"epoch": 1.08,
"learning_rate": 7.902737520128824e-05,
"loss": 1.0173,
"step": 3360
},
{
"epoch": 1.08,
"learning_rate": 7.896296296296297e-05,
"loss": 1.0043,
"step": 3370
},
{
"epoch": 1.08,
"learning_rate": 7.889855072463769e-05,
"loss": 1.0058,
"step": 3380
},
{
"epoch": 1.08,
"learning_rate": 7.883413848631241e-05,
"loss": 1.0035,
"step": 3390
},
{
"epoch": 1.09,
"learning_rate": 7.876972624798711e-05,
"loss": 0.9418,
"step": 3400
},
{
"epoch": 1.09,
"eval_loss": 1.017248511314392,
"eval_runtime": 187.1833,
"eval_samples_per_second": 10.685,
"eval_steps_per_second": 1.336,
"step": 3400
},
{
"epoch": 1.09,
"learning_rate": 7.870531400966183e-05,
"loss": 1.0129,
"step": 3410
},
{
"epoch": 1.09,
"learning_rate": 7.864090177133656e-05,
"loss": 0.9637,
"step": 3420
},
{
"epoch": 1.1,
"learning_rate": 7.857648953301128e-05,
"loss": 0.9824,
"step": 3430
},
{
"epoch": 1.1,
"learning_rate": 7.851207729468599e-05,
"loss": 0.9758,
"step": 3440
},
{
"epoch": 1.1,
"learning_rate": 7.844766505636071e-05,
"loss": 0.9935,
"step": 3450
},
{
"epoch": 1.11,
"learning_rate": 7.838325281803544e-05,
"loss": 1.0135,
"step": 3460
},
{
"epoch": 1.11,
"learning_rate": 7.831884057971014e-05,
"loss": 1.0353,
"step": 3470
},
{
"epoch": 1.11,
"learning_rate": 7.825442834138486e-05,
"loss": 0.9855,
"step": 3480
},
{
"epoch": 1.12,
"learning_rate": 7.819001610305958e-05,
"loss": 0.9416,
"step": 3490
},
{
"epoch": 1.12,
"learning_rate": 7.81256038647343e-05,
"loss": 0.9333,
"step": 3500
},
{
"epoch": 1.12,
"learning_rate": 7.806119162640902e-05,
"loss": 0.9864,
"step": 3510
},
{
"epoch": 1.13,
"learning_rate": 7.799677938808374e-05,
"loss": 1.0263,
"step": 3520
},
{
"epoch": 1.13,
"learning_rate": 7.793236714975846e-05,
"loss": 0.9814,
"step": 3530
},
{
"epoch": 1.13,
"learning_rate": 7.786795491143318e-05,
"loss": 1.011,
"step": 3540
},
{
"epoch": 1.14,
"learning_rate": 7.78035426731079e-05,
"loss": 1.0106,
"step": 3550
},
{
"epoch": 1.14,
"learning_rate": 7.773913043478261e-05,
"loss": 0.9994,
"step": 3560
},
{
"epoch": 1.14,
"learning_rate": 7.767471819645733e-05,
"loss": 0.993,
"step": 3570
},
{
"epoch": 1.15,
"learning_rate": 7.761030595813205e-05,
"loss": 0.9515,
"step": 3580
},
{
"epoch": 1.15,
"learning_rate": 7.754589371980677e-05,
"loss": 1.0204,
"step": 3590
},
{
"epoch": 1.15,
"learning_rate": 7.748148148148149e-05,
"loss": 1.0048,
"step": 3600
},
{
"epoch": 1.15,
"eval_loss": 1.016575574874878,
"eval_runtime": 187.3536,
"eval_samples_per_second": 10.675,
"eval_steps_per_second": 1.334,
"step": 3600
},
{
"epoch": 1.16,
"learning_rate": 7.74170692431562e-05,
"loss": 0.9734,
"step": 3610
},
{
"epoch": 1.16,
"learning_rate": 7.735265700483092e-05,
"loss": 0.9742,
"step": 3620
},
{
"epoch": 1.16,
"learning_rate": 7.728824476650563e-05,
"loss": 1.0187,
"step": 3630
},
{
"epoch": 1.16,
"learning_rate": 7.722383252818036e-05,
"loss": 1.0016,
"step": 3640
},
{
"epoch": 1.17,
"learning_rate": 7.715942028985508e-05,
"loss": 0.9926,
"step": 3650
},
{
"epoch": 1.17,
"learning_rate": 7.70950080515298e-05,
"loss": 0.9847,
"step": 3660
},
{
"epoch": 1.17,
"learning_rate": 7.70305958132045e-05,
"loss": 1.0032,
"step": 3670
},
{
"epoch": 1.18,
"learning_rate": 7.696618357487924e-05,
"loss": 1.0086,
"step": 3680
},
{
"epoch": 1.18,
"learning_rate": 7.690177133655396e-05,
"loss": 0.9906,
"step": 3690
},
{
"epoch": 1.18,
"learning_rate": 7.683735909822866e-05,
"loss": 0.9989,
"step": 3700
},
{
"epoch": 1.19,
"learning_rate": 7.677294685990338e-05,
"loss": 0.9741,
"step": 3710
},
{
"epoch": 1.19,
"learning_rate": 7.67085346215781e-05,
"loss": 1.0101,
"step": 3720
},
{
"epoch": 1.19,
"learning_rate": 7.664412238325283e-05,
"loss": 1.012,
"step": 3730
},
{
"epoch": 1.2,
"learning_rate": 7.657971014492754e-05,
"loss": 0.9715,
"step": 3740
},
{
"epoch": 1.2,
"learning_rate": 7.651529790660225e-05,
"loss": 1.028,
"step": 3750
},
{
"epoch": 1.2,
"learning_rate": 7.645088566827697e-05,
"loss": 0.9875,
"step": 3760
},
{
"epoch": 1.21,
"learning_rate": 7.63864734299517e-05,
"loss": 0.9787,
"step": 3770
},
{
"epoch": 1.21,
"learning_rate": 7.632206119162641e-05,
"loss": 0.9776,
"step": 3780
},
{
"epoch": 1.21,
"learning_rate": 7.625764895330113e-05,
"loss": 1.0093,
"step": 3790
},
{
"epoch": 1.22,
"learning_rate": 7.619323671497585e-05,
"loss": 0.9882,
"step": 3800
},
{
"epoch": 1.22,
"eval_loss": 1.0168739557266235,
"eval_runtime": 187.0506,
"eval_samples_per_second": 10.692,
"eval_steps_per_second": 1.337,
"step": 3800
},
{
"epoch": 1.22,
"learning_rate": 7.612882447665057e-05,
"loss": 1.0298,
"step": 3810
},
{
"epoch": 1.22,
"learning_rate": 7.606441223832529e-05,
"loss": 1.0028,
"step": 3820
},
{
"epoch": 1.23,
"learning_rate": 7.6e-05,
"loss": 1.0006,
"step": 3830
},
{
"epoch": 1.23,
"learning_rate": 7.593558776167472e-05,
"loss": 1.037,
"step": 3840
},
{
"epoch": 1.23,
"learning_rate": 7.587117552334944e-05,
"loss": 1.0014,
"step": 3850
},
{
"epoch": 1.24,
"learning_rate": 7.580676328502416e-05,
"loss": 0.9677,
"step": 3860
},
{
"epoch": 1.24,
"learning_rate": 7.574235104669888e-05,
"loss": 1.0172,
"step": 3870
},
{
"epoch": 1.24,
"learning_rate": 7.56779388083736e-05,
"loss": 1.0142,
"step": 3880
},
{
"epoch": 1.24,
"learning_rate": 7.561352657004832e-05,
"loss": 1.0057,
"step": 3890
},
{
"epoch": 1.25,
"learning_rate": 7.554911433172304e-05,
"loss": 0.9965,
"step": 3900
},
{
"epoch": 1.25,
"learning_rate": 7.548470209339775e-05,
"loss": 1.003,
"step": 3910
},
{
"epoch": 1.25,
"learning_rate": 7.542028985507247e-05,
"loss": 0.9872,
"step": 3920
},
{
"epoch": 1.26,
"learning_rate": 7.535587761674718e-05,
"loss": 0.9755,
"step": 3930
},
{
"epoch": 1.26,
"learning_rate": 7.52914653784219e-05,
"loss": 0.9956,
"step": 3940
},
{
"epoch": 1.26,
"learning_rate": 7.522705314009663e-05,
"loss": 0.9961,
"step": 3950
},
{
"epoch": 1.27,
"learning_rate": 7.516264090177135e-05,
"loss": 0.9804,
"step": 3960
},
{
"epoch": 1.27,
"learning_rate": 7.509822866344605e-05,
"loss": 0.983,
"step": 3970
},
{
"epoch": 1.27,
"learning_rate": 7.503381642512077e-05,
"loss": 1.0013,
"step": 3980
},
{
"epoch": 1.28,
"learning_rate": 7.49694041867955e-05,
"loss": 0.9991,
"step": 3990
},
{
"epoch": 1.28,
"learning_rate": 7.490499194847022e-05,
"loss": 1.0178,
"step": 4000
},
{
"epoch": 1.28,
"eval_loss": 1.0156399011611938,
"eval_runtime": 187.0787,
"eval_samples_per_second": 10.691,
"eval_steps_per_second": 1.336,
"step": 4000
},
{
"epoch": 1.28,
"learning_rate": 7.484057971014493e-05,
"loss": 1.0248,
"step": 4010
},
{
"epoch": 1.29,
"learning_rate": 7.477616747181965e-05,
"loss": 0.9947,
"step": 4020
},
{
"epoch": 1.29,
"learning_rate": 7.471175523349436e-05,
"loss": 0.9559,
"step": 4030
},
{
"epoch": 1.29,
"learning_rate": 7.464734299516908e-05,
"loss": 1.0175,
"step": 4040
},
{
"epoch": 1.3,
"learning_rate": 7.45829307568438e-05,
"loss": 0.9885,
"step": 4050
},
{
"epoch": 1.3,
"learning_rate": 7.451851851851852e-05,
"loss": 0.9748,
"step": 4060
},
{
"epoch": 1.3,
"learning_rate": 7.445410628019324e-05,
"loss": 0.9759,
"step": 4070
},
{
"epoch": 1.31,
"learning_rate": 7.438969404186796e-05,
"loss": 1.0137,
"step": 4080
},
{
"epoch": 1.31,
"learning_rate": 7.432528180354268e-05,
"loss": 0.9924,
"step": 4090
},
{
"epoch": 1.31,
"learning_rate": 7.42608695652174e-05,
"loss": 0.9475,
"step": 4100
},
{
"epoch": 1.32,
"learning_rate": 7.419645732689211e-05,
"loss": 0.9703,
"step": 4110
},
{
"epoch": 1.32,
"learning_rate": 7.413204508856682e-05,
"loss": 0.9994,
"step": 4120
},
{
"epoch": 1.32,
"learning_rate": 7.406763285024155e-05,
"loss": 0.9504,
"step": 4130
},
{
"epoch": 1.32,
"learning_rate": 7.400322061191627e-05,
"loss": 1.0119,
"step": 4140
},
{
"epoch": 1.33,
"learning_rate": 7.393880837359099e-05,
"loss": 0.9706,
"step": 4150
},
{
"epoch": 1.33,
"learning_rate": 7.38743961352657e-05,
"loss": 1.0015,
"step": 4160
},
{
"epoch": 1.33,
"learning_rate": 7.380998389694043e-05,
"loss": 0.9691,
"step": 4170
},
{
"epoch": 1.34,
"learning_rate": 7.374557165861515e-05,
"loss": 0.952,
"step": 4180
},
{
"epoch": 1.34,
"learning_rate": 7.368115942028986e-05,
"loss": 1.0084,
"step": 4190
},
{
"epoch": 1.34,
"learning_rate": 7.361674718196457e-05,
"loss": 1.0056,
"step": 4200
},
{
"epoch": 1.34,
"eval_loss": 1.0150794982910156,
"eval_runtime": 187.7211,
"eval_samples_per_second": 10.654,
"eval_steps_per_second": 1.332,
"step": 4200
},
{
"epoch": 1.35,
"learning_rate": 7.355233494363929e-05,
"loss": 0.996,
"step": 4210
},
{
"epoch": 1.35,
"learning_rate": 7.348792270531402e-05,
"loss": 1.0038,
"step": 4220
},
{
"epoch": 1.35,
"learning_rate": 7.342351046698873e-05,
"loss": 0.9989,
"step": 4230
},
{
"epoch": 1.36,
"learning_rate": 7.335909822866344e-05,
"loss": 1.0098,
"step": 4240
},
{
"epoch": 1.36,
"learning_rate": 7.329468599033816e-05,
"loss": 0.975,
"step": 4250
},
{
"epoch": 1.36,
"learning_rate": 7.32302737520129e-05,
"loss": 0.9879,
"step": 4260
},
{
"epoch": 1.37,
"learning_rate": 7.31658615136876e-05,
"loss": 1.0246,
"step": 4270
},
{
"epoch": 1.37,
"learning_rate": 7.310144927536232e-05,
"loss": 0.9887,
"step": 4280
},
{
"epoch": 1.37,
"learning_rate": 7.303703703703704e-05,
"loss": 0.9639,
"step": 4290
},
{
"epoch": 1.38,
"learning_rate": 7.297262479871177e-05,
"loss": 0.9882,
"step": 4300
},
{
"epoch": 1.38,
"learning_rate": 7.290821256038647e-05,
"loss": 1.003,
"step": 4310
},
{
"epoch": 1.38,
"learning_rate": 7.28438003220612e-05,
"loss": 0.9804,
"step": 4320
},
{
"epoch": 1.39,
"learning_rate": 7.277938808373591e-05,
"loss": 0.999,
"step": 4330
},
{
"epoch": 1.39,
"learning_rate": 7.271497584541063e-05,
"loss": 0.9829,
"step": 4340
},
{
"epoch": 1.39,
"learning_rate": 7.265056360708535e-05,
"loss": 1.0062,
"step": 4350
},
{
"epoch": 1.4,
"learning_rate": 7.258615136876007e-05,
"loss": 1.0131,
"step": 4360
},
{
"epoch": 1.4,
"learning_rate": 7.252173913043479e-05,
"loss": 0.9988,
"step": 4370
},
{
"epoch": 1.4,
"learning_rate": 7.24573268921095e-05,
"loss": 1.018,
"step": 4380
},
{
"epoch": 1.4,
"learning_rate": 7.239291465378422e-05,
"loss": 1.0007,
"step": 4390
},
{
"epoch": 1.41,
"learning_rate": 7.232850241545894e-05,
"loss": 1.0071,
"step": 4400
},
{
"epoch": 1.41,
"eval_loss": 1.0151050090789795,
"eval_runtime": 187.3911,
"eval_samples_per_second": 10.673,
"eval_steps_per_second": 1.334,
"step": 4400
},
{
"epoch": 1.41,
"learning_rate": 7.226409017713366e-05,
"loss": 1.0332,
"step": 4410
},
{
"epoch": 1.41,
"learning_rate": 7.219967793880838e-05,
"loss": 0.9705,
"step": 4420
},
{
"epoch": 1.42,
"learning_rate": 7.213526570048309e-05,
"loss": 1.0056,
"step": 4430
},
{
"epoch": 1.42,
"learning_rate": 7.207085346215782e-05,
"loss": 0.9856,
"step": 4440
},
{
"epoch": 1.42,
"learning_rate": 7.200644122383254e-05,
"loss": 0.9867,
"step": 4450
},
{
"epoch": 1.43,
"learning_rate": 7.194202898550724e-05,
"loss": 1.0127,
"step": 4460
},
{
"epoch": 1.43,
"learning_rate": 7.187761674718196e-05,
"loss": 0.9923,
"step": 4470
},
{
"epoch": 1.43,
"learning_rate": 7.181320450885669e-05,
"loss": 0.9255,
"step": 4480
},
{
"epoch": 1.44,
"learning_rate": 7.174879227053141e-05,
"loss": 1.0205,
"step": 4490
},
{
"epoch": 1.44,
"learning_rate": 7.168438003220612e-05,
"loss": 0.9925,
"step": 4500
},
{
"epoch": 1.44,
"learning_rate": 7.161996779388084e-05,
"loss": 0.9856,
"step": 4510
},
{
"epoch": 1.45,
"learning_rate": 7.155555555555555e-05,
"loss": 1.0136,
"step": 4520
},
{
"epoch": 1.45,
"learning_rate": 7.149114331723029e-05,
"loss": 1.0018,
"step": 4530
},
{
"epoch": 1.45,
"learning_rate": 7.142673107890499e-05,
"loss": 0.9814,
"step": 4540
},
{
"epoch": 1.46,
"learning_rate": 7.136231884057971e-05,
"loss": 0.9785,
"step": 4550
},
{
"epoch": 1.46,
"learning_rate": 7.129790660225443e-05,
"loss": 1.0153,
"step": 4560
},
{
"epoch": 1.46,
"learning_rate": 7.123349436392915e-05,
"loss": 1.0266,
"step": 4570
},
{
"epoch": 1.47,
"learning_rate": 7.116908212560387e-05,
"loss": 1.0527,
"step": 4580
},
{
"epoch": 1.47,
"learning_rate": 7.110466988727859e-05,
"loss": 0.9867,
"step": 4590
},
{
"epoch": 1.47,
"learning_rate": 7.10402576489533e-05,
"loss": 1.0175,
"step": 4600
},
{
"epoch": 1.47,
"eval_loss": 1.0150611400604248,
"eval_runtime": 187.508,
"eval_samples_per_second": 10.666,
"eval_steps_per_second": 1.333,
"step": 4600
},
{
"epoch": 1.48,
"learning_rate": 7.097584541062802e-05,
"loss": 1.0153,
"step": 4610
},
{
"epoch": 1.48,
"learning_rate": 7.091143317230274e-05,
"loss": 0.9565,
"step": 4620
},
{
"epoch": 1.48,
"learning_rate": 7.084702093397746e-05,
"loss": 0.9942,
"step": 4630
},
{
"epoch": 1.48,
"learning_rate": 7.078260869565218e-05,
"loss": 1.0096,
"step": 4640
},
{
"epoch": 1.49,
"learning_rate": 7.07181964573269e-05,
"loss": 0.9973,
"step": 4650
},
{
"epoch": 1.49,
"learning_rate": 7.065378421900162e-05,
"loss": 0.9457,
"step": 4660
},
{
"epoch": 1.49,
"learning_rate": 7.058937198067633e-05,
"loss": 0.9938,
"step": 4670
},
{
"epoch": 1.5,
"learning_rate": 7.052495974235105e-05,
"loss": 0.9798,
"step": 4680
},
{
"epoch": 1.5,
"learning_rate": 7.046054750402576e-05,
"loss": 0.9603,
"step": 4690
},
{
"epoch": 1.5,
"learning_rate": 7.039613526570049e-05,
"loss": 0.975,
"step": 4700
},
{
"epoch": 1.51,
"learning_rate": 7.033172302737521e-05,
"loss": 0.998,
"step": 4710
},
{
"epoch": 1.51,
"learning_rate": 7.026731078904993e-05,
"loss": 1.0167,
"step": 4720
},
{
"epoch": 1.51,
"learning_rate": 7.020289855072463e-05,
"loss": 0.9682,
"step": 4730
},
{
"epoch": 1.52,
"learning_rate": 7.013848631239935e-05,
"loss": 0.9827,
"step": 4740
},
{
"epoch": 1.52,
"learning_rate": 7.007407407407408e-05,
"loss": 0.9866,
"step": 4750
},
{
"epoch": 1.52,
"learning_rate": 7.00096618357488e-05,
"loss": 1.0018,
"step": 4760
},
{
"epoch": 1.53,
"learning_rate": 6.994524959742351e-05,
"loss": 1.0173,
"step": 4770
},
{
"epoch": 1.53,
"learning_rate": 6.988083735909823e-05,
"loss": 1.0103,
"step": 4780
},
{
"epoch": 1.53,
"learning_rate": 6.981642512077296e-05,
"loss": 0.9881,
"step": 4790
},
{
"epoch": 1.54,
"learning_rate": 6.975201288244766e-05,
"loss": 1.0108,
"step": 4800
},
{
"epoch": 1.54,
"eval_loss": 1.014174461364746,
"eval_runtime": 187.5385,
"eval_samples_per_second": 10.664,
"eval_steps_per_second": 1.333,
"step": 4800
},
{
"epoch": 1.54,
"learning_rate": 6.968760064412238e-05,
"loss": 0.9903,
"step": 4810
},
{
"epoch": 1.54,
"learning_rate": 6.96231884057971e-05,
"loss": 1.0169,
"step": 4820
},
{
"epoch": 1.55,
"learning_rate": 6.955877616747182e-05,
"loss": 0.9837,
"step": 4830
},
{
"epoch": 1.55,
"learning_rate": 6.949436392914654e-05,
"loss": 0.9573,
"step": 4840
},
{
"epoch": 1.55,
"learning_rate": 6.942995169082126e-05,
"loss": 0.9814,
"step": 4850
},
{
"epoch": 1.56,
"learning_rate": 6.936553945249598e-05,
"loss": 0.9829,
"step": 4860
},
{
"epoch": 1.56,
"learning_rate": 6.93011272141707e-05,
"loss": 0.9956,
"step": 4870
},
{
"epoch": 1.56,
"learning_rate": 6.923671497584541e-05,
"loss": 1.0234,
"step": 4880
},
{
"epoch": 1.56,
"learning_rate": 6.917230273752013e-05,
"loss": 0.986,
"step": 4890
},
{
"epoch": 1.57,
"learning_rate": 6.910789049919485e-05,
"loss": 0.9829,
"step": 4900
},
{
"epoch": 1.57,
"learning_rate": 6.904347826086957e-05,
"loss": 1.0251,
"step": 4910
},
{
"epoch": 1.57,
"learning_rate": 6.897906602254429e-05,
"loss": 0.9879,
"step": 4920
},
{
"epoch": 1.58,
"learning_rate": 6.891465378421901e-05,
"loss": 1.039,
"step": 4930
},
{
"epoch": 1.58,
"learning_rate": 6.885024154589373e-05,
"loss": 0.9752,
"step": 4940
},
{
"epoch": 1.58,
"learning_rate": 6.878582930756844e-05,
"loss": 1.0013,
"step": 4950
},
{
"epoch": 1.59,
"learning_rate": 6.872141706924315e-05,
"loss": 0.9558,
"step": 4960
},
{
"epoch": 1.59,
"learning_rate": 6.865700483091788e-05,
"loss": 1.0102,
"step": 4970
},
{
"epoch": 1.59,
"learning_rate": 6.85925925925926e-05,
"loss": 0.9936,
"step": 4980
},
{
"epoch": 1.6,
"learning_rate": 6.85281803542673e-05,
"loss": 0.9864,
"step": 4990
},
{
"epoch": 1.6,
"learning_rate": 6.846376811594202e-05,
"loss": 1.0204,
"step": 5000
},
{
"epoch": 1.6,
"eval_loss": 1.013562798500061,
"eval_runtime": 187.3848,
"eval_samples_per_second": 10.673,
"eval_steps_per_second": 1.334,
"step": 5000
},
{
"epoch": 1.6,
"learning_rate": 6.839935587761676e-05,
"loss": 0.9885,
"step": 5010
},
{
"epoch": 1.61,
"learning_rate": 6.833494363929148e-05,
"loss": 0.9857,
"step": 5020
},
{
"epoch": 1.61,
"learning_rate": 6.827053140096618e-05,
"loss": 0.9764,
"step": 5030
},
{
"epoch": 1.61,
"learning_rate": 6.82061191626409e-05,
"loss": 0.9809,
"step": 5040
},
{
"epoch": 1.62,
"learning_rate": 6.814170692431562e-05,
"loss": 0.9855,
"step": 5050
},
{
"epoch": 1.62,
"learning_rate": 6.807729468599035e-05,
"loss": 1.0134,
"step": 5060
},
{
"epoch": 1.62,
"learning_rate": 6.801288244766506e-05,
"loss": 0.9927,
"step": 5070
},
{
"epoch": 1.63,
"learning_rate": 6.794847020933977e-05,
"loss": 1.0337,
"step": 5080
},
{
"epoch": 1.63,
"learning_rate": 6.788405797101449e-05,
"loss": 0.9835,
"step": 5090
},
{
"epoch": 1.63,
"learning_rate": 6.781964573268923e-05,
"loss": 1.0772,
"step": 5100
},
{
"epoch": 1.64,
"learning_rate": 6.775523349436393e-05,
"loss": 0.9874,
"step": 5110
},
{
"epoch": 1.64,
"learning_rate": 6.769082125603865e-05,
"loss": 0.9956,
"step": 5120
},
{
"epoch": 1.64,
"learning_rate": 6.762640901771337e-05,
"loss": 1.014,
"step": 5130
},
{
"epoch": 1.64,
"learning_rate": 6.756199677938809e-05,
"loss": 0.9957,
"step": 5140
},
{
"epoch": 1.65,
"learning_rate": 6.74975845410628e-05,
"loss": 0.9861,
"step": 5150
},
{
"epoch": 1.65,
"learning_rate": 6.743317230273752e-05,
"loss": 0.9824,
"step": 5160
},
{
"epoch": 1.65,
"learning_rate": 6.736876006441224e-05,
"loss": 1.0184,
"step": 5170
},
{
"epoch": 1.66,
"learning_rate": 6.730434782608696e-05,
"loss": 1.0121,
"step": 5180
},
{
"epoch": 1.66,
"learning_rate": 6.723993558776168e-05,
"loss": 0.9957,
"step": 5190
},
{
"epoch": 1.66,
"learning_rate": 6.71755233494364e-05,
"loss": 1.0209,
"step": 5200
},
{
"epoch": 1.66,
"eval_loss": 1.0133100748062134,
"eval_runtime": 187.3315,
"eval_samples_per_second": 10.676,
"eval_steps_per_second": 1.335,
"step": 5200
},
{
"epoch": 1.67,
"learning_rate": 6.711111111111112e-05,
"loss": 0.9808,
"step": 5210
},
{
"epoch": 1.67,
"learning_rate": 6.704669887278582e-05,
"loss": 1.0036,
"step": 5220
},
{
"epoch": 1.67,
"learning_rate": 6.698228663446055e-05,
"loss": 0.9727,
"step": 5230
},
{
"epoch": 1.68,
"learning_rate": 6.691787439613527e-05,
"loss": 1.0178,
"step": 5240
},
{
"epoch": 1.68,
"learning_rate": 6.685346215780999e-05,
"loss": 0.976,
"step": 5250
},
{
"epoch": 1.68,
"learning_rate": 6.67890499194847e-05,
"loss": 0.9991,
"step": 5260
},
{
"epoch": 1.69,
"learning_rate": 6.672463768115942e-05,
"loss": 0.9956,
"step": 5270
},
{
"epoch": 1.69,
"learning_rate": 6.666022544283415e-05,
"loss": 0.9791,
"step": 5280
},
{
"epoch": 1.69,
"learning_rate": 6.659581320450887e-05,
"loss": 1.0081,
"step": 5290
},
{
"epoch": 1.7,
"learning_rate": 6.653140096618357e-05,
"loss": 1.0244,
"step": 5300
},
{
"epoch": 1.7,
"learning_rate": 6.646698872785829e-05,
"loss": 1.0103,
"step": 5310
},
{
"epoch": 1.7,
"learning_rate": 6.640257648953302e-05,
"loss": 1.0579,
"step": 5320
},
{
"epoch": 1.71,
"learning_rate": 6.633816425120773e-05,
"loss": 0.9774,
"step": 5330
},
{
"epoch": 1.71,
"learning_rate": 6.627375201288245e-05,
"loss": 0.9376,
"step": 5340
},
{
"epoch": 1.71,
"learning_rate": 6.620933977455717e-05,
"loss": 1.006,
"step": 5350
},
{
"epoch": 1.72,
"learning_rate": 6.614492753623188e-05,
"loss": 0.9889,
"step": 5360
},
{
"epoch": 1.72,
"learning_rate": 6.60805152979066e-05,
"loss": 1.0201,
"step": 5370
},
{
"epoch": 1.72,
"learning_rate": 6.601610305958132e-05,
"loss": 1.0034,
"step": 5380
},
{
"epoch": 1.72,
"learning_rate": 6.595169082125604e-05,
"loss": 1.0556,
"step": 5390
},
{
"epoch": 1.73,
"learning_rate": 6.588727858293076e-05,
"loss": 1.0124,
"step": 5400
},
{
"epoch": 1.73,
"eval_loss": 1.012602686882019,
"eval_runtime": 187.4458,
"eval_samples_per_second": 10.67,
"eval_steps_per_second": 1.334,
"step": 5400
},
{
"epoch": 1.73,
"learning_rate": 6.582286634460548e-05,
"loss": 0.9938,
"step": 5410
},
{
"epoch": 1.73,
"learning_rate": 6.57584541062802e-05,
"loss": 0.9905,
"step": 5420
},
{
"epoch": 1.74,
"learning_rate": 6.569404186795492e-05,
"loss": 0.9896,
"step": 5430
},
{
"epoch": 1.74,
"learning_rate": 6.562962962962963e-05,
"loss": 1.0039,
"step": 5440
},
{
"epoch": 1.74,
"learning_rate": 6.556521739130434e-05,
"loss": 1.0021,
"step": 5450
},
{
"epoch": 1.75,
"learning_rate": 6.550080515297907e-05,
"loss": 0.99,
"step": 5460
},
{
"epoch": 1.75,
"learning_rate": 6.543639291465379e-05,
"loss": 0.9826,
"step": 5470
},
{
"epoch": 1.75,
"learning_rate": 6.537198067632851e-05,
"loss": 0.9841,
"step": 5480
},
{
"epoch": 1.76,
"learning_rate": 6.530756843800321e-05,
"loss": 0.9749,
"step": 5490
},
{
"epoch": 1.76,
"learning_rate": 6.524315619967795e-05,
"loss": 0.9905,
"step": 5500
},
{
"epoch": 1.76,
"learning_rate": 6.517874396135267e-05,
"loss": 1.0376,
"step": 5510
},
{
"epoch": 1.77,
"learning_rate": 6.511433172302738e-05,
"loss": 1.0513,
"step": 5520
},
{
"epoch": 1.77,
"learning_rate": 6.504991948470209e-05,
"loss": 1.0093,
"step": 5530
},
{
"epoch": 1.77,
"learning_rate": 6.498550724637682e-05,
"loss": 1.0263,
"step": 5540
},
{
"epoch": 1.78,
"learning_rate": 6.492109500805154e-05,
"loss": 0.9843,
"step": 5550
},
{
"epoch": 1.78,
"learning_rate": 6.485668276972625e-05,
"loss": 1.0204,
"step": 5560
},
{
"epoch": 1.78,
"learning_rate": 6.479227053140096e-05,
"loss": 0.9995,
"step": 5570
},
{
"epoch": 1.79,
"learning_rate": 6.472785829307568e-05,
"loss": 1.0205,
"step": 5580
},
{
"epoch": 1.79,
"learning_rate": 6.466344605475041e-05,
"loss": 0.9466,
"step": 5590
},
{
"epoch": 1.79,
"learning_rate": 6.459903381642512e-05,
"loss": 1.0259,
"step": 5600
},
{
"epoch": 1.79,
"eval_loss": 1.0134350061416626,
"eval_runtime": 187.4026,
"eval_samples_per_second": 10.672,
"eval_steps_per_second": 1.334,
"step": 5600
},
{
"epoch": 1.8,
"learning_rate": 6.453462157809984e-05,
"loss": 0.9799,
"step": 5610
},
{
"epoch": 1.8,
"learning_rate": 6.447020933977456e-05,
"loss": 1.014,
"step": 5620
},
{
"epoch": 1.8,
"learning_rate": 6.440579710144929e-05,
"loss": 1.0418,
"step": 5630
},
{
"epoch": 1.8,
"learning_rate": 6.4341384863124e-05,
"loss": 1.0168,
"step": 5640
},
{
"epoch": 1.81,
"learning_rate": 6.427697262479871e-05,
"loss": 0.948,
"step": 5650
},
{
"epoch": 1.81,
"learning_rate": 6.421256038647343e-05,
"loss": 1.0076,
"step": 5660
},
{
"epoch": 1.81,
"learning_rate": 6.414814814814815e-05,
"loss": 1.0181,
"step": 5670
},
{
"epoch": 1.82,
"learning_rate": 6.408373590982287e-05,
"loss": 1.0225,
"step": 5680
},
{
"epoch": 1.82,
"learning_rate": 6.401932367149759e-05,
"loss": 1.0063,
"step": 5690
},
{
"epoch": 1.82,
"learning_rate": 6.395491143317231e-05,
"loss": 1.0238,
"step": 5700
},
{
"epoch": 1.83,
"learning_rate": 6.389049919484703e-05,
"loss": 0.9782,
"step": 5710
},
{
"epoch": 1.83,
"learning_rate": 6.382608695652174e-05,
"loss": 1.0378,
"step": 5720
},
{
"epoch": 1.83,
"learning_rate": 6.376167471819646e-05,
"loss": 0.954,
"step": 5730
},
{
"epoch": 1.84,
"learning_rate": 6.369726247987118e-05,
"loss": 1.004,
"step": 5740
},
{
"epoch": 1.84,
"learning_rate": 6.36328502415459e-05,
"loss": 0.9934,
"step": 5750
},
{
"epoch": 1.84,
"learning_rate": 6.35684380032206e-05,
"loss": 0.9874,
"step": 5760
},
{
"epoch": 1.85,
"learning_rate": 6.350402576489534e-05,
"loss": 0.9677,
"step": 5770
},
{
"epoch": 1.85,
"learning_rate": 6.343961352657006e-05,
"loss": 0.9833,
"step": 5780
},
{
"epoch": 1.85,
"learning_rate": 6.337520128824476e-05,
"loss": 0.9972,
"step": 5790
},
{
"epoch": 1.86,
"learning_rate": 6.331078904991948e-05,
"loss": 1.0289,
"step": 5800
},
{
"epoch": 1.86,
"eval_loss": 1.0126157999038696,
"eval_runtime": 187.3366,
"eval_samples_per_second": 10.676,
"eval_steps_per_second": 1.334,
"step": 5800
},
{
"epoch": 1.86,
"learning_rate": 6.324637681159421e-05,
"loss": 0.9907,
"step": 5810
},
{
"epoch": 1.86,
"learning_rate": 6.318196457326893e-05,
"loss": 0.9942,
"step": 5820
},
{
"epoch": 1.87,
"learning_rate": 6.311755233494364e-05,
"loss": 0.9764,
"step": 5830
},
{
"epoch": 1.87,
"learning_rate": 6.305314009661836e-05,
"loss": 0.9942,
"step": 5840
},
{
"epoch": 1.87,
"learning_rate": 6.298872785829309e-05,
"loss": 1.0397,
"step": 5850
},
{
"epoch": 1.88,
"learning_rate": 6.29243156199678e-05,
"loss": 1.0182,
"step": 5860
},
{
"epoch": 1.88,
"learning_rate": 6.285990338164251e-05,
"loss": 0.9443,
"step": 5870
},
{
"epoch": 1.88,
"learning_rate": 6.279549114331723e-05,
"loss": 0.973,
"step": 5880
},
{
"epoch": 1.88,
"learning_rate": 6.273107890499195e-05,
"loss": 0.951,
"step": 5890
},
{
"epoch": 1.89,
"learning_rate": 6.266666666666667e-05,
"loss": 0.9824,
"step": 5900
},
{
"epoch": 1.89,
"learning_rate": 6.260225442834139e-05,
"loss": 1.0014,
"step": 5910
},
{
"epoch": 1.89,
"learning_rate": 6.25378421900161e-05,
"loss": 1.0029,
"step": 5920
},
{
"epoch": 1.9,
"learning_rate": 6.247342995169082e-05,
"loss": 1.0166,
"step": 5930
},
{
"epoch": 1.9,
"learning_rate": 6.240901771336554e-05,
"loss": 1.0011,
"step": 5940
},
{
"epoch": 1.9,
"learning_rate": 6.234460547504026e-05,
"loss": 1.0156,
"step": 5950
},
{
"epoch": 1.91,
"learning_rate": 6.228019323671498e-05,
"loss": 1.0166,
"step": 5960
},
{
"epoch": 1.91,
"learning_rate": 6.22157809983897e-05,
"loss": 0.9613,
"step": 5970
},
{
"epoch": 1.91,
"learning_rate": 6.21513687600644e-05,
"loss": 0.9551,
"step": 5980
},
{
"epoch": 1.92,
"learning_rate": 6.208695652173914e-05,
"loss": 0.9628,
"step": 5990
},
{
"epoch": 1.92,
"learning_rate": 6.202254428341385e-05,
"loss": 0.9675,
"step": 6000
},
{
"epoch": 1.92,
"eval_loss": 1.012001633644104,
"eval_runtime": 187.1833,
"eval_samples_per_second": 10.685,
"eval_steps_per_second": 1.336,
"step": 6000
},
{
"epoch": 1.92,
"learning_rate": 6.195813204508857e-05,
"loss": 0.9864,
"step": 6010
},
{
"epoch": 1.93,
"learning_rate": 6.189371980676328e-05,
"loss": 0.9786,
"step": 6020
},
{
"epoch": 1.93,
"learning_rate": 6.182930756843801e-05,
"loss": 0.9732,
"step": 6030
},
{
"epoch": 1.93,
"learning_rate": 6.176489533011273e-05,
"loss": 0.9915,
"step": 6040
},
{
"epoch": 1.94,
"learning_rate": 6.170048309178745e-05,
"loss": 0.967,
"step": 6050
},
{
"epoch": 1.94,
"learning_rate": 6.163607085346215e-05,
"loss": 1.0035,
"step": 6060
},
{
"epoch": 1.94,
"learning_rate": 6.157165861513687e-05,
"loss": 1.0008,
"step": 6070
},
{
"epoch": 1.95,
"learning_rate": 6.15072463768116e-05,
"loss": 0.9626,
"step": 6080
},
{
"epoch": 1.95,
"learning_rate": 6.144283413848631e-05,
"loss": 1.0128,
"step": 6090
},
{
"epoch": 1.95,
"learning_rate": 6.137842190016103e-05,
"loss": 0.9504,
"step": 6100
},
{
"epoch": 1.96,
"learning_rate": 6.131400966183575e-05,
"loss": 1.004,
"step": 6110
},
{
"epoch": 1.96,
"learning_rate": 6.124959742351048e-05,
"loss": 1.0037,
"step": 6120
},
{
"epoch": 1.96,
"learning_rate": 6.118518518518518e-05,
"loss": 1.0124,
"step": 6130
},
{
"epoch": 1.96,
"learning_rate": 6.11207729468599e-05,
"loss": 1.0248,
"step": 6140
},
{
"epoch": 1.97,
"learning_rate": 6.105636070853462e-05,
"loss": 0.9643,
"step": 6150
},
{
"epoch": 1.97,
"learning_rate": 6.099194847020935e-05,
"loss": 0.9443,
"step": 6160
},
{
"epoch": 1.97,
"learning_rate": 6.0927536231884066e-05,
"loss": 1.0231,
"step": 6170
},
{
"epoch": 1.98,
"learning_rate": 6.086312399355878e-05,
"loss": 1.0228,
"step": 6180
},
{
"epoch": 1.98,
"learning_rate": 6.0798711755233496e-05,
"loss": 1.0145,
"step": 6190
},
{
"epoch": 1.98,
"learning_rate": 6.073429951690821e-05,
"loss": 1.0081,
"step": 6200
},
{
"epoch": 1.98,
"eval_loss": 1.0115959644317627,
"eval_runtime": 187.1705,
"eval_samples_per_second": 10.685,
"eval_steps_per_second": 1.336,
"step": 6200
},
{
"epoch": 1.99,
"learning_rate": 6.066988727858294e-05,
"loss": 0.9809,
"step": 6210
},
{
"epoch": 1.99,
"learning_rate": 6.060547504025765e-05,
"loss": 0.9942,
"step": 6220
},
{
"epoch": 1.99,
"learning_rate": 6.054106280193237e-05,
"loss": 1.0487,
"step": 6230
},
{
"epoch": 2.0,
"learning_rate": 6.047665056360708e-05,
"loss": 0.9674,
"step": 6240
},
{
"epoch": 2.0,
"learning_rate": 6.041223832528181e-05,
"loss": 0.9941,
"step": 6250
},
{
"epoch": 2.0,
"learning_rate": 6.034782608695653e-05,
"loss": 0.98,
"step": 6260
},
{
"epoch": 2.01,
"learning_rate": 6.0283413848631246e-05,
"loss": 0.9749,
"step": 6270
},
{
"epoch": 2.01,
"learning_rate": 6.021900161030596e-05,
"loss": 0.9085,
"step": 6280
},
{
"epoch": 2.01,
"learning_rate": 6.015458937198068e-05,
"loss": 0.9835,
"step": 6290
},
{
"epoch": 2.02,
"learning_rate": 6.00901771336554e-05,
"loss": 0.9691,
"step": 6300
},
{
"epoch": 2.02,
"learning_rate": 6.0025764895330114e-05,
"loss": 0.9643,
"step": 6310
},
{
"epoch": 2.02,
"learning_rate": 5.996135265700483e-05,
"loss": 0.9596,
"step": 6320
},
{
"epoch": 2.03,
"learning_rate": 5.9896940418679545e-05,
"loss": 0.9899,
"step": 6330
},
{
"epoch": 2.03,
"learning_rate": 5.983252818035428e-05,
"loss": 0.974,
"step": 6340
},
{
"epoch": 2.03,
"learning_rate": 5.976811594202899e-05,
"loss": 0.9449,
"step": 6350
},
{
"epoch": 2.04,
"learning_rate": 5.970370370370371e-05,
"loss": 0.9808,
"step": 6360
},
{
"epoch": 2.04,
"learning_rate": 5.963929146537842e-05,
"loss": 0.9546,
"step": 6370
},
{
"epoch": 2.04,
"learning_rate": 5.957487922705314e-05,
"loss": 0.9845,
"step": 6380
},
{
"epoch": 2.04,
"learning_rate": 5.9510466988727864e-05,
"loss": 0.9513,
"step": 6390
},
{
"epoch": 2.05,
"learning_rate": 5.944605475040258e-05,
"loss": 0.9811,
"step": 6400
},
{
"epoch": 2.05,
"eval_loss": 1.0142450332641602,
"eval_runtime": 187.1141,
"eval_samples_per_second": 10.689,
"eval_steps_per_second": 1.336,
"step": 6400
},
{
"epoch": 2.05,
"learning_rate": 5.9381642512077294e-05,
"loss": 0.9986,
"step": 6410
},
{
"epoch": 2.05,
"learning_rate": 5.931723027375201e-05,
"loss": 0.9792,
"step": 6420
},
{
"epoch": 2.06,
"learning_rate": 5.925281803542674e-05,
"loss": 0.962,
"step": 6430
},
{
"epoch": 2.06,
"learning_rate": 5.918840579710146e-05,
"loss": 0.971,
"step": 6440
},
{
"epoch": 2.06,
"learning_rate": 5.912399355877617e-05,
"loss": 0.9833,
"step": 6450
},
{
"epoch": 2.07,
"learning_rate": 5.905958132045089e-05,
"loss": 0.9825,
"step": 6460
},
{
"epoch": 2.07,
"learning_rate": 5.899516908212561e-05,
"loss": 0.9646,
"step": 6470
},
{
"epoch": 2.07,
"learning_rate": 5.8930756843800325e-05,
"loss": 0.9543,
"step": 6480
},
{
"epoch": 2.08,
"learning_rate": 5.8866344605475044e-05,
"loss": 1.0055,
"step": 6490
},
{
"epoch": 2.08,
"learning_rate": 5.8801932367149756e-05,
"loss": 0.9524,
"step": 6500
},
{
"epoch": 2.08,
"learning_rate": 5.8737520128824475e-05,
"loss": 0.9463,
"step": 6510
},
{
"epoch": 2.09,
"learning_rate": 5.86731078904992e-05,
"loss": 0.9943,
"step": 6520
},
{
"epoch": 2.09,
"learning_rate": 5.860869565217392e-05,
"loss": 0.9899,
"step": 6530
},
{
"epoch": 2.09,
"learning_rate": 5.854428341384863e-05,
"loss": 1.0231,
"step": 6540
},
{
"epoch": 2.1,
"learning_rate": 5.847987117552335e-05,
"loss": 0.9453,
"step": 6550
},
{
"epoch": 2.1,
"learning_rate": 5.8415458937198075e-05,
"loss": 0.9887,
"step": 6560
},
{
"epoch": 2.1,
"learning_rate": 5.8351046698872794e-05,
"loss": 0.9487,
"step": 6570
},
{
"epoch": 2.11,
"learning_rate": 5.8286634460547505e-05,
"loss": 0.9814,
"step": 6580
},
{
"epoch": 2.11,
"learning_rate": 5.8222222222222224e-05,
"loss": 0.9312,
"step": 6590
},
{
"epoch": 2.11,
"learning_rate": 5.8157809983896936e-05,
"loss": 0.9525,
"step": 6600
},
{
"epoch": 2.11,
"eval_loss": 1.0148019790649414,
"eval_runtime": 187.2863,
"eval_samples_per_second": 10.679,
"eval_steps_per_second": 1.335,
"step": 6600
},
{
"epoch": 2.12,
"learning_rate": 5.809339774557166e-05,
"loss": 0.9827,
"step": 6610
},
{
"epoch": 2.12,
"learning_rate": 5.802898550724638e-05,
"loss": 1.0076,
"step": 6620
},
{
"epoch": 2.12,
"learning_rate": 5.79645732689211e-05,
"loss": 0.9929,
"step": 6630
},
{
"epoch": 2.12,
"learning_rate": 5.790016103059581e-05,
"loss": 0.9358,
"step": 6640
},
{
"epoch": 2.13,
"learning_rate": 5.7835748792270536e-05,
"loss": 0.9382,
"step": 6650
},
{
"epoch": 2.13,
"learning_rate": 5.7771336553945255e-05,
"loss": 0.9894,
"step": 6660
},
{
"epoch": 2.13,
"learning_rate": 5.770692431561997e-05,
"loss": 0.9757,
"step": 6670
},
{
"epoch": 2.14,
"learning_rate": 5.7642512077294686e-05,
"loss": 0.9541,
"step": 6680
},
{
"epoch": 2.14,
"learning_rate": 5.7578099838969404e-05,
"loss": 0.9451,
"step": 6690
},
{
"epoch": 2.14,
"learning_rate": 5.751368760064413e-05,
"loss": 1.0106,
"step": 6700
},
{
"epoch": 2.15,
"learning_rate": 5.744927536231884e-05,
"loss": 0.9709,
"step": 6710
},
{
"epoch": 2.15,
"learning_rate": 5.738486312399356e-05,
"loss": 0.9139,
"step": 6720
},
{
"epoch": 2.15,
"learning_rate": 5.732045088566827e-05,
"loss": 0.9994,
"step": 6730
},
{
"epoch": 2.16,
"learning_rate": 5.7256038647343005e-05,
"loss": 0.9361,
"step": 6740
},
{
"epoch": 2.16,
"learning_rate": 5.719162640901772e-05,
"loss": 0.9798,
"step": 6750
},
{
"epoch": 2.16,
"learning_rate": 5.7127214170692435e-05,
"loss": 0.9802,
"step": 6760
},
{
"epoch": 2.17,
"learning_rate": 5.706280193236715e-05,
"loss": 0.9239,
"step": 6770
},
{
"epoch": 2.17,
"learning_rate": 5.699838969404187e-05,
"loss": 0.9608,
"step": 6780
},
{
"epoch": 2.17,
"learning_rate": 5.693397745571659e-05,
"loss": 0.9406,
"step": 6790
},
{
"epoch": 2.18,
"learning_rate": 5.686956521739131e-05,
"loss": 0.9859,
"step": 6800
},
{
"epoch": 2.18,
"eval_loss": 1.0146571397781372,
"eval_runtime": 187.2691,
"eval_samples_per_second": 10.68,
"eval_steps_per_second": 1.335,
"step": 6800
},
{
"epoch": 2.18,
"learning_rate": 5.680515297906602e-05,
"loss": 0.9655,
"step": 6810
},
{
"epoch": 2.18,
"learning_rate": 5.674074074074074e-05,
"loss": 1.0016,
"step": 6820
},
{
"epoch": 2.19,
"learning_rate": 5.6676328502415466e-05,
"loss": 0.9549,
"step": 6830
},
{
"epoch": 2.19,
"learning_rate": 5.661191626409018e-05,
"loss": 0.9516,
"step": 6840
},
{
"epoch": 2.19,
"learning_rate": 5.65475040257649e-05,
"loss": 0.9834,
"step": 6850
},
{
"epoch": 2.2,
"learning_rate": 5.6483091787439616e-05,
"loss": 0.9359,
"step": 6860
},
{
"epoch": 2.2,
"learning_rate": 5.641867954911434e-05,
"loss": 0.9511,
"step": 6870
},
{
"epoch": 2.2,
"learning_rate": 5.635426731078905e-05,
"loss": 0.9848,
"step": 6880
},
{
"epoch": 2.2,
"learning_rate": 5.628985507246377e-05,
"loss": 0.9289,
"step": 6890
},
{
"epoch": 2.21,
"learning_rate": 5.6225442834138484e-05,
"loss": 0.9918,
"step": 6900
},
{
"epoch": 2.21,
"learning_rate": 5.61610305958132e-05,
"loss": 1.0145,
"step": 6910
},
{
"epoch": 2.21,
"learning_rate": 5.609661835748793e-05,
"loss": 0.9003,
"step": 6920
},
{
"epoch": 2.22,
"learning_rate": 5.6032206119162647e-05,
"loss": 0.9625,
"step": 6930
},
{
"epoch": 2.22,
"learning_rate": 5.596779388083736e-05,
"loss": 0.98,
"step": 6940
},
{
"epoch": 2.22,
"learning_rate": 5.590338164251208e-05,
"loss": 0.9497,
"step": 6950
},
{
"epoch": 2.23,
"learning_rate": 5.58389694041868e-05,
"loss": 0.9297,
"step": 6960
},
{
"epoch": 2.23,
"learning_rate": 5.577455716586152e-05,
"loss": 0.9802,
"step": 6970
},
{
"epoch": 2.23,
"learning_rate": 5.571014492753623e-05,
"loss": 0.9524,
"step": 6980
},
{
"epoch": 2.24,
"learning_rate": 5.564573268921095e-05,
"loss": 0.9421,
"step": 6990
},
{
"epoch": 2.24,
"learning_rate": 5.5581320450885664e-05,
"loss": 1.0126,
"step": 7000
},
{
"epoch": 2.24,
"eval_loss": 1.0157631635665894,
"eval_runtime": 187.2785,
"eval_samples_per_second": 10.679,
"eval_steps_per_second": 1.335,
"step": 7000
},
{
"epoch": 2.24,
"learning_rate": 5.551690821256039e-05,
"loss": 0.9211,
"step": 7010
},
{
"epoch": 2.25,
"learning_rate": 5.545249597423511e-05,
"loss": 0.9814,
"step": 7020
},
{
"epoch": 2.25,
"learning_rate": 5.538808373590983e-05,
"loss": 0.9696,
"step": 7030
},
{
"epoch": 2.25,
"learning_rate": 5.532367149758454e-05,
"loss": 0.9691,
"step": 7040
},
{
"epoch": 2.26,
"learning_rate": 5.5259259259259264e-05,
"loss": 0.9357,
"step": 7050
},
{
"epoch": 2.26,
"learning_rate": 5.519484702093398e-05,
"loss": 0.9451,
"step": 7060
},
{
"epoch": 2.26,
"learning_rate": 5.5130434782608695e-05,
"loss": 0.968,
"step": 7070
},
{
"epoch": 2.27,
"learning_rate": 5.5066022544283414e-05,
"loss": 0.946,
"step": 7080
},
{
"epoch": 2.27,
"learning_rate": 5.500161030595814e-05,
"loss": 0.961,
"step": 7090
},
{
"epoch": 2.27,
"learning_rate": 5.493719806763286e-05,
"loss": 0.9741,
"step": 7100
},
{
"epoch": 2.28,
"learning_rate": 5.487278582930757e-05,
"loss": 0.9341,
"step": 7110
},
{
"epoch": 2.28,
"learning_rate": 5.480837359098229e-05,
"loss": 0.9488,
"step": 7120
},
{
"epoch": 2.28,
"learning_rate": 5.4743961352657e-05,
"loss": 0.9791,
"step": 7130
},
{
"epoch": 2.28,
"learning_rate": 5.467954911433173e-05,
"loss": 0.9957,
"step": 7140
},
{
"epoch": 2.29,
"learning_rate": 5.4615136876006445e-05,
"loss": 0.978,
"step": 7150
},
{
"epoch": 2.29,
"learning_rate": 5.455072463768116e-05,
"loss": 0.9768,
"step": 7160
},
{
"epoch": 2.29,
"learning_rate": 5.4486312399355875e-05,
"loss": 0.9585,
"step": 7170
},
{
"epoch": 2.3,
"learning_rate": 5.44219001610306e-05,
"loss": 0.9307,
"step": 7180
},
{
"epoch": 2.3,
"learning_rate": 5.435748792270532e-05,
"loss": 1.0232,
"step": 7190
},
{
"epoch": 2.3,
"learning_rate": 5.429307568438004e-05,
"loss": 0.9892,
"step": 7200
},
{
"epoch": 2.3,
"eval_loss": 1.0147501230239868,
"eval_runtime": 187.244,
"eval_samples_per_second": 10.681,
"eval_steps_per_second": 1.335,
"step": 7200
},
{
"epoch": 2.31,
"learning_rate": 5.422866344605475e-05,
"loss": 0.9983,
"step": 7210
},
{
"epoch": 2.31,
"learning_rate": 5.416425120772947e-05,
"loss": 0.9572,
"step": 7220
},
{
"epoch": 2.31,
"learning_rate": 5.4099838969404194e-05,
"loss": 0.9815,
"step": 7230
},
{
"epoch": 2.32,
"learning_rate": 5.4035426731078906e-05,
"loss": 0.9854,
"step": 7240
},
{
"epoch": 2.32,
"learning_rate": 5.3971014492753625e-05,
"loss": 0.9947,
"step": 7250
},
{
"epoch": 2.32,
"learning_rate": 5.390660225442834e-05,
"loss": 0.9893,
"step": 7260
},
{
"epoch": 2.33,
"learning_rate": 5.384219001610307e-05,
"loss": 0.9645,
"step": 7270
},
{
"epoch": 2.33,
"learning_rate": 5.377777777777778e-05,
"loss": 0.9776,
"step": 7280
},
{
"epoch": 2.33,
"learning_rate": 5.37133655394525e-05,
"loss": 0.9974,
"step": 7290
},
{
"epoch": 2.34,
"learning_rate": 5.364895330112721e-05,
"loss": 0.9439,
"step": 7300
},
{
"epoch": 2.34,
"learning_rate": 5.358454106280193e-05,
"loss": 0.996,
"step": 7310
},
{
"epoch": 2.34,
"learning_rate": 5.3520128824476656e-05,
"loss": 0.8993,
"step": 7320
},
{
"epoch": 2.35,
"learning_rate": 5.3455716586151374e-05,
"loss": 0.984,
"step": 7330
},
{
"epoch": 2.35,
"learning_rate": 5.3391304347826086e-05,
"loss": 0.9444,
"step": 7340
},
{
"epoch": 2.35,
"learning_rate": 5.3326892109500805e-05,
"loss": 0.9773,
"step": 7350
},
{
"epoch": 2.36,
"learning_rate": 5.326247987117553e-05,
"loss": 0.9527,
"step": 7360
},
{
"epoch": 2.36,
"learning_rate": 5.319806763285025e-05,
"loss": 0.9611,
"step": 7370
},
{
"epoch": 2.36,
"learning_rate": 5.313365539452496e-05,
"loss": 0.9423,
"step": 7380
},
{
"epoch": 2.36,
"learning_rate": 5.306924315619968e-05,
"loss": 0.9939,
"step": 7390
},
{
"epoch": 2.37,
"learning_rate": 5.3004830917874405e-05,
"loss": 0.9833,
"step": 7400
},
{
"epoch": 2.37,
"eval_loss": 1.0141487121582031,
"eval_runtime": 187.1541,
"eval_samples_per_second": 10.686,
"eval_steps_per_second": 1.336,
"step": 7400
},
{
"epoch": 2.37,
"learning_rate": 5.294041867954912e-05,
"loss": 0.9883,
"step": 7410
},
{
"epoch": 2.37,
"learning_rate": 5.2876006441223836e-05,
"loss": 0.9374,
"step": 7420
},
{
"epoch": 2.38,
"learning_rate": 5.281159420289855e-05,
"loss": 0.9671,
"step": 7430
},
{
"epoch": 2.38,
"learning_rate": 5.2747181964573267e-05,
"loss": 0.9635,
"step": 7440
},
{
"epoch": 2.38,
"learning_rate": 5.268276972624799e-05,
"loss": 0.9736,
"step": 7450
},
{
"epoch": 2.39,
"learning_rate": 5.261835748792271e-05,
"loss": 0.9731,
"step": 7460
},
{
"epoch": 2.39,
"learning_rate": 5.255394524959742e-05,
"loss": 0.9757,
"step": 7470
},
{
"epoch": 2.39,
"learning_rate": 5.248953301127214e-05,
"loss": 0.9522,
"step": 7480
},
{
"epoch": 2.4,
"learning_rate": 5.242512077294687e-05,
"loss": 0.965,
"step": 7490
},
{
"epoch": 2.4,
"learning_rate": 5.2360708534621586e-05,
"loss": 0.928,
"step": 7500
},
{
"epoch": 2.4,
"learning_rate": 5.22962962962963e-05,
"loss": 0.9651,
"step": 7510
},
{
"epoch": 2.41,
"learning_rate": 5.2231884057971016e-05,
"loss": 0.9773,
"step": 7520
},
{
"epoch": 2.41,
"learning_rate": 5.216747181964573e-05,
"loss": 0.9923,
"step": 7530
},
{
"epoch": 2.41,
"learning_rate": 5.2103059581320454e-05,
"loss": 0.9781,
"step": 7540
},
{
"epoch": 2.42,
"learning_rate": 5.203864734299517e-05,
"loss": 0.9443,
"step": 7550
},
{
"epoch": 2.42,
"learning_rate": 5.197423510466989e-05,
"loss": 0.9917,
"step": 7560
},
{
"epoch": 2.42,
"learning_rate": 5.19098228663446e-05,
"loss": 0.9616,
"step": 7570
},
{
"epoch": 2.43,
"learning_rate": 5.184541062801933e-05,
"loss": 0.9467,
"step": 7580
},
{
"epoch": 2.43,
"learning_rate": 5.178099838969405e-05,
"loss": 0.9879,
"step": 7590
},
{
"epoch": 2.43,
"learning_rate": 5.171658615136876e-05,
"loss": 1.0006,
"step": 7600
},
{
"epoch": 2.43,
"eval_loss": 1.0145756006240845,
"eval_runtime": 186.84,
"eval_samples_per_second": 10.704,
"eval_steps_per_second": 1.338,
"step": 7600
},
{
"epoch": 2.44,
"learning_rate": 5.165217391304348e-05,
"loss": 0.9786,
"step": 7610
},
{
"epoch": 2.44,
"learning_rate": 5.1587761674718197e-05,
"loss": 1.0002,
"step": 7620
},
{
"epoch": 2.44,
"learning_rate": 5.152334943639292e-05,
"loss": 0.9648,
"step": 7630
},
{
"epoch": 2.44,
"learning_rate": 5.1458937198067634e-05,
"loss": 0.9719,
"step": 7640
},
{
"epoch": 2.45,
"learning_rate": 5.139452495974235e-05,
"loss": 0.9647,
"step": 7650
},
{
"epoch": 2.45,
"learning_rate": 5.1330112721417065e-05,
"loss": 0.9868,
"step": 7660
},
{
"epoch": 2.45,
"learning_rate": 5.12657004830918e-05,
"loss": 0.9521,
"step": 7670
},
{
"epoch": 2.46,
"learning_rate": 5.120128824476651e-05,
"loss": 0.9742,
"step": 7680
},
{
"epoch": 2.46,
"learning_rate": 5.113687600644123e-05,
"loss": 0.9976,
"step": 7690
},
{
"epoch": 2.46,
"learning_rate": 5.107246376811594e-05,
"loss": 0.9621,
"step": 7700
},
{
"epoch": 2.47,
"learning_rate": 5.1008051529790665e-05,
"loss": 0.9312,
"step": 7710
},
{
"epoch": 2.47,
"learning_rate": 5.0943639291465384e-05,
"loss": 0.9685,
"step": 7720
},
{
"epoch": 2.47,
"learning_rate": 5.08792270531401e-05,
"loss": 1.0045,
"step": 7730
},
{
"epoch": 2.48,
"learning_rate": 5.0814814814814814e-05,
"loss": 0.9582,
"step": 7740
},
{
"epoch": 2.48,
"learning_rate": 5.075040257648953e-05,
"loss": 0.9393,
"step": 7750
},
{
"epoch": 2.48,
"learning_rate": 5.068599033816426e-05,
"loss": 0.94,
"step": 7760
},
{
"epoch": 2.49,
"learning_rate": 5.062157809983897e-05,
"loss": 0.9547,
"step": 7770
},
{
"epoch": 2.49,
"learning_rate": 5.055716586151369e-05,
"loss": 0.978,
"step": 7780
},
{
"epoch": 2.49,
"learning_rate": 5.049275362318841e-05,
"loss": 0.993,
"step": 7790
},
{
"epoch": 2.5,
"learning_rate": 5.042834138486313e-05,
"loss": 0.998,
"step": 7800
},
{
"epoch": 2.5,
"eval_loss": 1.015630841255188,
"eval_runtime": 187.1282,
"eval_samples_per_second": 10.688,
"eval_steps_per_second": 1.336,
"step": 7800
},
{
"epoch": 2.5,
"learning_rate": 5.0363929146537845e-05,
"loss": 0.9846,
"step": 7810
},
{
"epoch": 2.5,
"learning_rate": 5.0299516908212564e-05,
"loss": 0.9118,
"step": 7820
},
{
"epoch": 2.51,
"learning_rate": 5.0235104669887276e-05,
"loss": 1.0075,
"step": 7830
},
{
"epoch": 2.51,
"learning_rate": 5.0170692431561994e-05,
"loss": 0.9677,
"step": 7840
},
{
"epoch": 2.51,
"learning_rate": 5.010628019323672e-05,
"loss": 0.9867,
"step": 7850
},
{
"epoch": 2.51,
"learning_rate": 5.004186795491144e-05,
"loss": 0.9946,
"step": 7860
},
{
"epoch": 2.52,
"learning_rate": 4.997745571658615e-05,
"loss": 0.9275,
"step": 7870
},
{
"epoch": 2.52,
"learning_rate": 4.9913043478260876e-05,
"loss": 0.9904,
"step": 7880
},
{
"epoch": 2.52,
"learning_rate": 4.985507246376812e-05,
"loss": 0.9669,
"step": 7890
},
{
"epoch": 2.53,
"learning_rate": 4.9790660225442835e-05,
"loss": 0.9631,
"step": 7900
},
{
"epoch": 2.53,
"learning_rate": 4.9726247987117554e-05,
"loss": 0.9708,
"step": 7910
},
{
"epoch": 2.53,
"learning_rate": 4.966183574879227e-05,
"loss": 0.9634,
"step": 7920
},
{
"epoch": 2.54,
"learning_rate": 4.959742351046699e-05,
"loss": 0.9495,
"step": 7930
},
{
"epoch": 2.54,
"learning_rate": 4.953301127214171e-05,
"loss": 0.9572,
"step": 7940
},
{
"epoch": 2.54,
"learning_rate": 4.946859903381643e-05,
"loss": 0.9966,
"step": 7950
},
{
"epoch": 2.55,
"learning_rate": 4.940418679549115e-05,
"loss": 0.9309,
"step": 7960
},
{
"epoch": 2.55,
"learning_rate": 4.9339774557165866e-05,
"loss": 0.9672,
"step": 7970
},
{
"epoch": 2.55,
"learning_rate": 4.9275362318840584e-05,
"loss": 0.9842,
"step": 7980
},
{
"epoch": 2.56,
"learning_rate": 4.92109500805153e-05,
"loss": 0.9883,
"step": 7990
},
{
"epoch": 2.56,
"learning_rate": 4.9146537842190015e-05,
"loss": 0.9761,
"step": 8000
},
{
"epoch": 2.56,
"eval_loss": 1.0148636102676392,
"eval_runtime": 187.0058,
"eval_samples_per_second": 10.695,
"eval_steps_per_second": 1.337,
"step": 8000
},
{
"epoch": 2.56,
"learning_rate": 4.9082125603864734e-05,
"loss": 0.9617,
"step": 8010
},
{
"epoch": 2.57,
"learning_rate": 4.901771336553945e-05,
"loss": 0.9516,
"step": 8020
},
{
"epoch": 2.57,
"learning_rate": 4.895330112721417e-05,
"loss": 0.9722,
"step": 8030
},
{
"epoch": 2.57,
"learning_rate": 4.888888888888889e-05,
"loss": 0.9616,
"step": 8040
},
{
"epoch": 2.58,
"learning_rate": 4.882447665056361e-05,
"loss": 0.9258,
"step": 8050
},
{
"epoch": 2.58,
"learning_rate": 4.876006441223833e-05,
"loss": 0.981,
"step": 8060
},
{
"epoch": 2.58,
"learning_rate": 4.8695652173913046e-05,
"loss": 0.9976,
"step": 8070
},
{
"epoch": 2.59,
"learning_rate": 4.8631239935587765e-05,
"loss": 0.9362,
"step": 8080
},
{
"epoch": 2.59,
"learning_rate": 4.8566827697262483e-05,
"loss": 0.9574,
"step": 8090
},
{
"epoch": 2.59,
"learning_rate": 4.85024154589372e-05,
"loss": 0.9829,
"step": 8100
},
{
"epoch": 2.59,
"learning_rate": 4.8438003220611914e-05,
"loss": 0.9812,
"step": 8110
},
{
"epoch": 2.6,
"learning_rate": 4.837359098228664e-05,
"loss": 0.9608,
"step": 8120
},
{
"epoch": 2.6,
"learning_rate": 4.830917874396135e-05,
"loss": 0.9526,
"step": 8130
},
{
"epoch": 2.6,
"learning_rate": 4.824476650563608e-05,
"loss": 0.9605,
"step": 8140
},
{
"epoch": 2.61,
"learning_rate": 4.818035426731079e-05,
"loss": 0.974,
"step": 8150
},
{
"epoch": 2.61,
"learning_rate": 4.8115942028985514e-05,
"loss": 0.9996,
"step": 8160
},
{
"epoch": 2.61,
"learning_rate": 4.8051529790660226e-05,
"loss": 0.9518,
"step": 8170
},
{
"epoch": 2.62,
"learning_rate": 4.7987117552334945e-05,
"loss": 1.0006,
"step": 8180
},
{
"epoch": 2.62,
"learning_rate": 4.7922705314009664e-05,
"loss": 0.9218,
"step": 8190
},
{
"epoch": 2.62,
"learning_rate": 4.785829307568438e-05,
"loss": 0.9336,
"step": 8200
},
{
"epoch": 2.62,
"eval_loss": 1.0153106451034546,
"eval_runtime": 187.0257,
"eval_samples_per_second": 10.694,
"eval_steps_per_second": 1.337,
"step": 8200
},
{
"epoch": 2.63,
"learning_rate": 4.77938808373591e-05,
"loss": 0.981,
"step": 8210
},
{
"epoch": 2.63,
"learning_rate": 4.772946859903382e-05,
"loss": 0.9565,
"step": 8220
},
{
"epoch": 2.63,
"learning_rate": 4.766505636070854e-05,
"loss": 1.0248,
"step": 8230
},
{
"epoch": 2.64,
"learning_rate": 4.760064412238325e-05,
"loss": 0.9458,
"step": 8240
},
{
"epoch": 2.64,
"learning_rate": 4.7536231884057976e-05,
"loss": 0.9753,
"step": 8250
},
{
"epoch": 2.64,
"learning_rate": 4.747181964573269e-05,
"loss": 0.9396,
"step": 8260
},
{
"epoch": 2.65,
"learning_rate": 4.740740740740741e-05,
"loss": 0.9538,
"step": 8270
},
{
"epoch": 2.65,
"learning_rate": 4.7342995169082125e-05,
"loss": 0.9652,
"step": 8280
},
{
"epoch": 2.65,
"learning_rate": 4.727858293075685e-05,
"loss": 0.9746,
"step": 8290
},
{
"epoch": 2.66,
"learning_rate": 4.721417069243156e-05,
"loss": 0.9441,
"step": 8300
},
{
"epoch": 2.66,
"learning_rate": 4.714975845410628e-05,
"loss": 0.9899,
"step": 8310
},
{
"epoch": 2.66,
"learning_rate": 4.7085346215781e-05,
"loss": 0.9278,
"step": 8320
},
{
"epoch": 2.67,
"learning_rate": 4.702093397745572e-05,
"loss": 0.9441,
"step": 8330
},
{
"epoch": 2.67,
"learning_rate": 4.695652173913044e-05,
"loss": 0.9635,
"step": 8340
},
{
"epoch": 2.67,
"learning_rate": 4.6892109500805156e-05,
"loss": 0.9947,
"step": 8350
},
{
"epoch": 2.67,
"learning_rate": 4.6827697262479875e-05,
"loss": 0.9693,
"step": 8360
},
{
"epoch": 2.68,
"learning_rate": 4.6763285024154594e-05,
"loss": 0.9755,
"step": 8370
},
{
"epoch": 2.68,
"learning_rate": 4.669887278582931e-05,
"loss": 0.9791,
"step": 8380
},
{
"epoch": 2.68,
"learning_rate": 4.6634460547504024e-05,
"loss": 0.9476,
"step": 8390
},
{
"epoch": 2.69,
"learning_rate": 4.657004830917875e-05,
"loss": 1.0156,
"step": 8400
},
{
"epoch": 2.69,
"eval_loss": 1.0150635242462158,
"eval_runtime": 187.2093,
"eval_samples_per_second": 10.683,
"eval_steps_per_second": 1.335,
"step": 8400
},
{
"epoch": 2.69,
"learning_rate": 4.650563607085346e-05,
"loss": 0.952,
"step": 8410
},
{
"epoch": 2.69,
"learning_rate": 4.644122383252818e-05,
"loss": 0.95,
"step": 8420
},
{
"epoch": 2.7,
"learning_rate": 4.63768115942029e-05,
"loss": 0.9887,
"step": 8430
},
{
"epoch": 2.7,
"learning_rate": 4.631239935587762e-05,
"loss": 0.9511,
"step": 8440
},
{
"epoch": 2.7,
"learning_rate": 4.6247987117552336e-05,
"loss": 0.9746,
"step": 8450
},
{
"epoch": 2.71,
"learning_rate": 4.6183574879227055e-05,
"loss": 0.9705,
"step": 8460
},
{
"epoch": 2.71,
"learning_rate": 4.6119162640901774e-05,
"loss": 1.0017,
"step": 8470
},
{
"epoch": 2.71,
"learning_rate": 4.605475040257649e-05,
"loss": 0.9205,
"step": 8480
},
{
"epoch": 2.72,
"learning_rate": 4.599033816425121e-05,
"loss": 0.9397,
"step": 8490
},
{
"epoch": 2.72,
"learning_rate": 4.592592592592593e-05,
"loss": 0.9969,
"step": 8500
},
{
"epoch": 2.72,
"learning_rate": 4.586151368760065e-05,
"loss": 0.9735,
"step": 8510
},
{
"epoch": 2.73,
"learning_rate": 4.579710144927537e-05,
"loss": 0.9382,
"step": 8520
},
{
"epoch": 2.73,
"learning_rate": 4.573268921095008e-05,
"loss": 0.9465,
"step": 8530
},
{
"epoch": 2.73,
"learning_rate": 4.5668276972624805e-05,
"loss": 0.9855,
"step": 8540
},
{
"epoch": 2.74,
"learning_rate": 4.560386473429952e-05,
"loss": 0.9988,
"step": 8550
},
{
"epoch": 2.74,
"learning_rate": 4.5539452495974235e-05,
"loss": 0.9556,
"step": 8560
},
{
"epoch": 2.74,
"learning_rate": 4.5475040257648954e-05,
"loss": 0.9487,
"step": 8570
},
{
"epoch": 2.75,
"learning_rate": 4.541062801932367e-05,
"loss": 0.9595,
"step": 8580
},
{
"epoch": 2.75,
"learning_rate": 4.534621578099839e-05,
"loss": 0.9676,
"step": 8590
},
{
"epoch": 2.75,
"learning_rate": 4.528180354267311e-05,
"loss": 0.9626,
"step": 8600
},
{
"epoch": 2.75,
"eval_loss": 1.0142388343811035,
"eval_runtime": 187.0049,
"eval_samples_per_second": 10.695,
"eval_steps_per_second": 1.337,
"step": 8600
},
{
"epoch": 2.75,
"learning_rate": 4.521739130434783e-05,
"loss": 0.9475,
"step": 8610
},
{
"epoch": 2.76,
"learning_rate": 4.515297906602254e-05,
"loss": 0.9718,
"step": 8620
},
{
"epoch": 2.76,
"learning_rate": 4.5088566827697266e-05,
"loss": 1.0018,
"step": 8630
},
{
"epoch": 2.76,
"learning_rate": 4.502415458937198e-05,
"loss": 0.9209,
"step": 8640
},
{
"epoch": 2.77,
"learning_rate": 4.4959742351046704e-05,
"loss": 1.0049,
"step": 8650
},
{
"epoch": 2.77,
"learning_rate": 4.4895330112721416e-05,
"loss": 0.9694,
"step": 8660
},
{
"epoch": 2.77,
"learning_rate": 4.483091787439614e-05,
"loss": 0.9897,
"step": 8670
},
{
"epoch": 2.78,
"learning_rate": 4.476650563607085e-05,
"loss": 0.9217,
"step": 8680
},
{
"epoch": 2.78,
"learning_rate": 4.470209339774558e-05,
"loss": 0.938,
"step": 8690
},
{
"epoch": 2.78,
"learning_rate": 4.463768115942029e-05,
"loss": 0.96,
"step": 8700
},
{
"epoch": 2.79,
"learning_rate": 4.4573268921095016e-05,
"loss": 0.9891,
"step": 8710
},
{
"epoch": 2.79,
"learning_rate": 4.450885668276973e-05,
"loss": 0.99,
"step": 8720
},
{
"epoch": 2.79,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.9262,
"step": 8730
},
{
"epoch": 2.8,
"learning_rate": 4.4380032206119165e-05,
"loss": 0.9725,
"step": 8740
},
{
"epoch": 2.8,
"learning_rate": 4.4315619967793884e-05,
"loss": 0.9849,
"step": 8750
},
{
"epoch": 2.8,
"learning_rate": 4.42512077294686e-05,
"loss": 0.9607,
"step": 8760
},
{
"epoch": 2.81,
"learning_rate": 4.4186795491143315e-05,
"loss": 0.972,
"step": 8770
},
{
"epoch": 2.81,
"learning_rate": 4.412238325281804e-05,
"loss": 0.9642,
"step": 8780
},
{
"epoch": 2.81,
"learning_rate": 4.405797101449275e-05,
"loss": 0.9878,
"step": 8790
},
{
"epoch": 2.82,
"learning_rate": 4.399355877616748e-05,
"loss": 0.9221,
"step": 8800
},
{
"epoch": 2.82,
"eval_loss": 1.013732671737671,
"eval_runtime": 187.1182,
"eval_samples_per_second": 10.688,
"eval_steps_per_second": 1.336,
"step": 8800
},
{
"epoch": 2.82,
"learning_rate": 4.392914653784219e-05,
"loss": 0.9452,
"step": 8810
},
{
"epoch": 2.82,
"learning_rate": 4.3864734299516915e-05,
"loss": 0.9913,
"step": 8820
},
{
"epoch": 2.83,
"learning_rate": 4.380032206119163e-05,
"loss": 0.9799,
"step": 8830
},
{
"epoch": 2.83,
"learning_rate": 4.3735909822866346e-05,
"loss": 0.9718,
"step": 8840
},
{
"epoch": 2.83,
"learning_rate": 4.3671497584541064e-05,
"loss": 0.9797,
"step": 8850
},
{
"epoch": 2.83,
"learning_rate": 4.360708534621578e-05,
"loss": 0.9495,
"step": 8860
},
{
"epoch": 2.84,
"learning_rate": 4.35426731078905e-05,
"loss": 0.9621,
"step": 8870
},
{
"epoch": 2.84,
"learning_rate": 4.347826086956522e-05,
"loss": 0.9725,
"step": 8880
},
{
"epoch": 2.84,
"learning_rate": 4.341384863123994e-05,
"loss": 0.9885,
"step": 8890
},
{
"epoch": 2.85,
"learning_rate": 4.334943639291466e-05,
"loss": 0.9793,
"step": 8900
},
{
"epoch": 2.85,
"learning_rate": 4.3285024154589376e-05,
"loss": 0.9414,
"step": 8910
},
{
"epoch": 2.85,
"learning_rate": 4.3220611916264095e-05,
"loss": 0.967,
"step": 8920
},
{
"epoch": 2.86,
"learning_rate": 4.315619967793881e-05,
"loss": 0.9524,
"step": 8930
},
{
"epoch": 2.86,
"learning_rate": 4.3091787439613526e-05,
"loss": 0.946,
"step": 8940
},
{
"epoch": 2.86,
"learning_rate": 4.3027375201288245e-05,
"loss": 0.9985,
"step": 8950
},
{
"epoch": 2.87,
"learning_rate": 4.296296296296296e-05,
"loss": 0.9851,
"step": 8960
},
{
"epoch": 2.87,
"learning_rate": 4.289855072463768e-05,
"loss": 0.9708,
"step": 8970
},
{
"epoch": 2.87,
"learning_rate": 4.28341384863124e-05,
"loss": 1.0027,
"step": 8980
},
{
"epoch": 2.88,
"learning_rate": 4.276972624798712e-05,
"loss": 0.9281,
"step": 8990
},
{
"epoch": 2.88,
"learning_rate": 4.270531400966184e-05,
"loss": 0.9813,
"step": 9000
},
{
"epoch": 2.88,
"eval_loss": 1.0139975547790527,
"eval_runtime": 187.2523,
"eval_samples_per_second": 10.681,
"eval_steps_per_second": 1.335,
"step": 9000
},
{
"epoch": 2.88,
"learning_rate": 4.264090177133656e-05,
"loss": 0.9759,
"step": 9010
},
{
"epoch": 2.89,
"learning_rate": 4.2576489533011275e-05,
"loss": 0.9611,
"step": 9020
},
{
"epoch": 2.89,
"learning_rate": 4.2512077294685994e-05,
"loss": 0.9823,
"step": 9030
},
{
"epoch": 2.89,
"learning_rate": 4.2447665056360706e-05,
"loss": 1.007,
"step": 9040
},
{
"epoch": 2.9,
"learning_rate": 4.238325281803543e-05,
"loss": 0.981,
"step": 9050
},
{
"epoch": 2.9,
"learning_rate": 4.2318840579710143e-05,
"loss": 0.948,
"step": 9060
},
{
"epoch": 2.9,
"learning_rate": 4.225442834138487e-05,
"loss": 0.9801,
"step": 9070
},
{
"epoch": 2.91,
"learning_rate": 4.219001610305958e-05,
"loss": 0.9826,
"step": 9080
},
{
"epoch": 2.91,
"learning_rate": 4.2125603864734306e-05,
"loss": 0.9682,
"step": 9090
},
{
"epoch": 2.91,
"learning_rate": 4.206119162640902e-05,
"loss": 0.9964,
"step": 9100
},
{
"epoch": 2.91,
"learning_rate": 4.199677938808374e-05,
"loss": 0.9624,
"step": 9110
},
{
"epoch": 2.92,
"learning_rate": 4.1932367149758456e-05,
"loss": 0.9617,
"step": 9120
},
{
"epoch": 2.92,
"learning_rate": 4.1867954911433174e-05,
"loss": 0.9658,
"step": 9130
},
{
"epoch": 2.92,
"learning_rate": 4.180354267310789e-05,
"loss": 0.9926,
"step": 9140
},
{
"epoch": 2.93,
"learning_rate": 4.1739130434782605e-05,
"loss": 0.9645,
"step": 9150
},
{
"epoch": 2.93,
"learning_rate": 4.167471819645733e-05,
"loss": 0.9907,
"step": 9160
},
{
"epoch": 2.93,
"learning_rate": 4.161030595813204e-05,
"loss": 0.9988,
"step": 9170
},
{
"epoch": 2.94,
"learning_rate": 4.154589371980677e-05,
"loss": 0.9527,
"step": 9180
},
{
"epoch": 2.94,
"learning_rate": 4.148148148148148e-05,
"loss": 0.9935,
"step": 9190
},
{
"epoch": 2.94,
"learning_rate": 4.1417069243156205e-05,
"loss": 0.9716,
"step": 9200
},
{
"epoch": 2.94,
"eval_loss": 1.013387680053711,
"eval_runtime": 185.6135,
"eval_samples_per_second": 10.775,
"eval_steps_per_second": 1.347,
"step": 9200
},
{
"epoch": 2.95,
"learning_rate": 4.135265700483092e-05,
"loss": 0.9595,
"step": 9210
},
{
"epoch": 2.95,
"learning_rate": 4.128824476650564e-05,
"loss": 0.9971,
"step": 9220
},
{
"epoch": 2.95,
"learning_rate": 4.1223832528180355e-05,
"loss": 0.9503,
"step": 9230
},
{
"epoch": 2.96,
"learning_rate": 4.115942028985507e-05,
"loss": 1.0049,
"step": 9240
},
{
"epoch": 2.96,
"learning_rate": 4.109500805152979e-05,
"loss": 0.9448,
"step": 9250
},
{
"epoch": 2.96,
"learning_rate": 4.103059581320451e-05,
"loss": 0.9209,
"step": 9260
},
{
"epoch": 2.97,
"learning_rate": 4.096618357487923e-05,
"loss": 0.9852,
"step": 9270
},
{
"epoch": 2.97,
"learning_rate": 4.090177133655395e-05,
"loss": 0.9536,
"step": 9280
},
{
"epoch": 2.97,
"learning_rate": 4.083735909822867e-05,
"loss": 0.9979,
"step": 9290
},
{
"epoch": 2.98,
"learning_rate": 4.0772946859903386e-05,
"loss": 0.976,
"step": 9300
},
{
"epoch": 2.98,
"learning_rate": 4.0708534621578104e-05,
"loss": 0.9783,
"step": 9310
},
{
"epoch": 2.98,
"learning_rate": 4.0644122383252816e-05,
"loss": 1.0021,
"step": 9320
},
{
"epoch": 2.99,
"learning_rate": 4.057971014492754e-05,
"loss": 0.9696,
"step": 9330
},
{
"epoch": 2.99,
"learning_rate": 4.0515297906602254e-05,
"loss": 0.9533,
"step": 9340
},
{
"epoch": 2.99,
"learning_rate": 4.045088566827697e-05,
"loss": 0.9493,
"step": 9350
},
{
"epoch": 2.99,
"learning_rate": 4.038647342995169e-05,
"loss": 0.9244,
"step": 9360
},
{
"epoch": 3.0,
"learning_rate": 4.032206119162641e-05,
"loss": 0.9857,
"step": 9370
},
{
"epoch": 3.0,
"learning_rate": 4.025764895330113e-05,
"loss": 0.9501,
"step": 9380
},
{
"epoch": 3.0,
"learning_rate": 4.019323671497585e-05,
"loss": 0.9155,
"step": 9390
},
{
"epoch": 3.01,
"learning_rate": 4.0128824476650566e-05,
"loss": 0.9645,
"step": 9400
},
{
"epoch": 3.01,
"eval_loss": 1.0159056186676025,
"eval_runtime": 185.5657,
"eval_samples_per_second": 10.778,
"eval_steps_per_second": 1.347,
"step": 9400
},
{
"epoch": 3.01,
"learning_rate": 4.0064412238325285e-05,
"loss": 0.9724,
"step": 9410
},
{
"epoch": 3.01,
"learning_rate": 4e-05,
"loss": 0.9588,
"step": 9420
},
{
"epoch": 3.02,
"learning_rate": 3.993558776167472e-05,
"loss": 0.9152,
"step": 9430
},
{
"epoch": 3.02,
"learning_rate": 3.987117552334944e-05,
"loss": 0.9943,
"step": 9440
},
{
"epoch": 3.02,
"learning_rate": 3.980676328502416e-05,
"loss": 0.9171,
"step": 9450
},
{
"epoch": 3.03,
"learning_rate": 3.974235104669887e-05,
"loss": 0.9249,
"step": 9460
},
{
"epoch": 3.03,
"learning_rate": 3.96779388083736e-05,
"loss": 0.9021,
"step": 9470
},
{
"epoch": 3.03,
"learning_rate": 3.961352657004831e-05,
"loss": 0.9527,
"step": 9480
},
{
"epoch": 3.04,
"learning_rate": 3.954911433172303e-05,
"loss": 0.9116,
"step": 9490
},
{
"epoch": 3.04,
"learning_rate": 3.9484702093397746e-05,
"loss": 0.8851,
"step": 9500
},
{
"epoch": 3.04,
"learning_rate": 3.9420289855072465e-05,
"loss": 0.9686,
"step": 9510
},
{
"epoch": 3.05,
"learning_rate": 3.9355877616747184e-05,
"loss": 0.9302,
"step": 9520
},
{
"epoch": 3.05,
"learning_rate": 3.92914653784219e-05,
"loss": 0.9466,
"step": 9530
},
{
"epoch": 3.05,
"learning_rate": 3.922705314009662e-05,
"loss": 0.9057,
"step": 9540
},
{
"epoch": 3.06,
"learning_rate": 3.916264090177133e-05,
"loss": 0.9495,
"step": 9550
},
{
"epoch": 3.06,
"learning_rate": 3.909822866344606e-05,
"loss": 0.9586,
"step": 9560
},
{
"epoch": 3.06,
"learning_rate": 3.903381642512077e-05,
"loss": 0.9013,
"step": 9570
},
{
"epoch": 3.07,
"learning_rate": 3.8969404186795496e-05,
"loss": 0.9334,
"step": 9580
},
{
"epoch": 3.07,
"learning_rate": 3.890499194847021e-05,
"loss": 0.9388,
"step": 9590
},
{
"epoch": 3.07,
"learning_rate": 3.884057971014493e-05,
"loss": 0.9922,
"step": 9600
},
{
"epoch": 3.07,
"eval_loss": 1.0189166069030762,
"eval_runtime": 185.5091,
"eval_samples_per_second": 10.781,
"eval_steps_per_second": 1.348,
"step": 9600
},
{
"epoch": 3.07,
"learning_rate": 3.8776167471819645e-05,
"loss": 0.9233,
"step": 9610
},
{
"epoch": 3.08,
"learning_rate": 3.871175523349437e-05,
"loss": 0.9634,
"step": 9620
},
{
"epoch": 3.08,
"learning_rate": 3.864734299516908e-05,
"loss": 0.9194,
"step": 9630
},
{
"epoch": 3.08,
"learning_rate": 3.858293075684381e-05,
"loss": 0.9787,
"step": 9640
},
{
"epoch": 3.09,
"learning_rate": 3.851851851851852e-05,
"loss": 0.9738,
"step": 9650
},
{
"epoch": 3.09,
"learning_rate": 3.845410628019324e-05,
"loss": 0.974,
"step": 9660
},
{
"epoch": 3.09,
"learning_rate": 3.838969404186796e-05,
"loss": 0.9409,
"step": 9670
},
{
"epoch": 3.1,
"learning_rate": 3.8325281803542676e-05,
"loss": 0.9536,
"step": 9680
},
{
"epoch": 3.1,
"learning_rate": 3.8260869565217395e-05,
"loss": 0.9244,
"step": 9690
},
{
"epoch": 3.1,
"learning_rate": 3.819645732689211e-05,
"loss": 0.9427,
"step": 9700
},
{
"epoch": 3.11,
"learning_rate": 3.813204508856683e-05,
"loss": 0.9354,
"step": 9710
},
{
"epoch": 3.11,
"learning_rate": 3.8067632850241544e-05,
"loss": 0.9299,
"step": 9720
},
{
"epoch": 3.11,
"learning_rate": 3.800322061191627e-05,
"loss": 0.9283,
"step": 9730
},
{
"epoch": 3.12,
"learning_rate": 3.793880837359098e-05,
"loss": 0.9511,
"step": 9740
},
{
"epoch": 3.12,
"learning_rate": 3.787439613526571e-05,
"loss": 0.9484,
"step": 9750
},
{
"epoch": 3.12,
"learning_rate": 3.780998389694042e-05,
"loss": 0.9257,
"step": 9760
},
{
"epoch": 3.13,
"learning_rate": 3.774557165861514e-05,
"loss": 0.9735,
"step": 9770
},
{
"epoch": 3.13,
"learning_rate": 3.7681159420289856e-05,
"loss": 0.9484,
"step": 9780
},
{
"epoch": 3.13,
"learning_rate": 3.7616747181964575e-05,
"loss": 0.9602,
"step": 9790
},
{
"epoch": 3.14,
"learning_rate": 3.7552334943639294e-05,
"loss": 0.9633,
"step": 9800
},
{
"epoch": 3.14,
"eval_loss": 1.0187861919403076,
"eval_runtime": 185.4008,
"eval_samples_per_second": 10.787,
"eval_steps_per_second": 1.348,
"step": 9800
},
{
"epoch": 3.14,
"learning_rate": 3.748792270531401e-05,
"loss": 0.9493,
"step": 9810
},
{
"epoch": 3.14,
"learning_rate": 3.742351046698873e-05,
"loss": 0.9233,
"step": 9820
},
{
"epoch": 3.15,
"learning_rate": 3.735909822866345e-05,
"loss": 0.9254,
"step": 9830
},
{
"epoch": 3.15,
"learning_rate": 3.729468599033817e-05,
"loss": 0.9369,
"step": 9840
},
{
"epoch": 3.15,
"learning_rate": 3.723027375201289e-05,
"loss": 0.9657,
"step": 9850
},
{
"epoch": 3.15,
"learning_rate": 3.71658615136876e-05,
"loss": 0.9604,
"step": 9860
},
{
"epoch": 3.16,
"learning_rate": 3.710144927536232e-05,
"loss": 0.9487,
"step": 9870
},
{
"epoch": 3.16,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.9339,
"step": 9880
},
{
"epoch": 3.16,
"learning_rate": 3.6972624798711755e-05,
"loss": 0.9448,
"step": 9890
},
{
"epoch": 3.17,
"learning_rate": 3.6908212560386474e-05,
"loss": 0.9705,
"step": 9900
},
{
"epoch": 3.17,
"learning_rate": 3.684380032206119e-05,
"loss": 0.9557,
"step": 9910
},
{
"epoch": 3.17,
"learning_rate": 3.677938808373591e-05,
"loss": 0.9182,
"step": 9920
},
{
"epoch": 3.18,
"learning_rate": 3.671497584541063e-05,
"loss": 0.9427,
"step": 9930
},
{
"epoch": 3.18,
"learning_rate": 3.665056360708535e-05,
"loss": 0.9685,
"step": 9940
},
{
"epoch": 3.18,
"learning_rate": 3.658615136876007e-05,
"loss": 0.9145,
"step": 9950
},
{
"epoch": 3.19,
"learning_rate": 3.6521739130434786e-05,
"loss": 0.9437,
"step": 9960
},
{
"epoch": 3.19,
"learning_rate": 3.64573268921095e-05,
"loss": 0.9433,
"step": 9970
},
{
"epoch": 3.19,
"learning_rate": 3.6392914653784224e-05,
"loss": 0.9535,
"step": 9980
},
{
"epoch": 3.2,
"learning_rate": 3.6328502415458936e-05,
"loss": 0.9413,
"step": 9990
},
{
"epoch": 3.2,
"learning_rate": 3.626409017713366e-05,
"loss": 0.9191,
"step": 10000
},
{
"epoch": 3.2,
"eval_loss": 1.021185278892517,
"eval_runtime": 185.5678,
"eval_samples_per_second": 10.778,
"eval_steps_per_second": 1.347,
"step": 10000
},
{
"epoch": 3.2,
"learning_rate": 3.619967793880837e-05,
"loss": 0.9523,
"step": 10010
},
{
"epoch": 3.21,
"learning_rate": 3.61352657004831e-05,
"loss": 0.9134,
"step": 10020
},
{
"epoch": 3.21,
"learning_rate": 3.607085346215781e-05,
"loss": 0.9614,
"step": 10030
},
{
"epoch": 3.21,
"learning_rate": 3.600644122383253e-05,
"loss": 1.0293,
"step": 10040
},
{
"epoch": 3.22,
"learning_rate": 3.594202898550725e-05,
"loss": 0.9625,
"step": 10050
},
{
"epoch": 3.22,
"learning_rate": 3.5877616747181966e-05,
"loss": 0.9045,
"step": 10060
},
{
"epoch": 3.22,
"learning_rate": 3.5813204508856685e-05,
"loss": 0.9246,
"step": 10070
},
{
"epoch": 3.23,
"learning_rate": 3.57487922705314e-05,
"loss": 0.8946,
"step": 10080
},
{
"epoch": 3.23,
"learning_rate": 3.568438003220612e-05,
"loss": 0.9478,
"step": 10090
},
{
"epoch": 3.23,
"learning_rate": 3.5619967793880834e-05,
"loss": 0.9524,
"step": 10100
},
{
"epoch": 3.23,
"learning_rate": 3.555555555555556e-05,
"loss": 0.9536,
"step": 10110
},
{
"epoch": 3.24,
"learning_rate": 3.549114331723027e-05,
"loss": 0.967,
"step": 10120
},
{
"epoch": 3.24,
"learning_rate": 3.5426731078905e-05,
"loss": 0.9211,
"step": 10130
},
{
"epoch": 3.24,
"learning_rate": 3.536231884057971e-05,
"loss": 0.9923,
"step": 10140
},
{
"epoch": 3.25,
"learning_rate": 3.5297906602254435e-05,
"loss": 0.9603,
"step": 10150
},
{
"epoch": 3.25,
"learning_rate": 3.523349436392915e-05,
"loss": 0.9683,
"step": 10160
},
{
"epoch": 3.25,
"learning_rate": 3.5169082125603865e-05,
"loss": 0.9934,
"step": 10170
},
{
"epoch": 3.26,
"learning_rate": 3.5104669887278584e-05,
"loss": 0.9405,
"step": 10180
},
{
"epoch": 3.26,
"learning_rate": 3.50402576489533e-05,
"loss": 0.965,
"step": 10190
},
{
"epoch": 3.26,
"learning_rate": 3.497584541062802e-05,
"loss": 0.9408,
"step": 10200
},
{
"epoch": 3.26,
"eval_loss": 1.0209527015686035,
"eval_runtime": 185.3872,
"eval_samples_per_second": 10.788,
"eval_steps_per_second": 1.349,
"step": 10200
},
{
"epoch": 3.27,
"learning_rate": 3.491143317230274e-05,
"loss": 0.9095,
"step": 10210
},
{
"epoch": 3.27,
"learning_rate": 3.484702093397746e-05,
"loss": 0.9343,
"step": 10220
},
{
"epoch": 3.27,
"learning_rate": 3.478260869565218e-05,
"loss": 0.9609,
"step": 10230
},
{
"epoch": 3.28,
"learning_rate": 3.4718196457326896e-05,
"loss": 0.9451,
"step": 10240
},
{
"epoch": 3.28,
"learning_rate": 3.465378421900161e-05,
"loss": 0.983,
"step": 10250
},
{
"epoch": 3.28,
"learning_rate": 3.4589371980676334e-05,
"loss": 0.9515,
"step": 10260
},
{
"epoch": 3.29,
"learning_rate": 3.4524959742351046e-05,
"loss": 0.9411,
"step": 10270
},
{
"epoch": 3.29,
"learning_rate": 3.4460547504025764e-05,
"loss": 0.9106,
"step": 10280
},
{
"epoch": 3.29,
"learning_rate": 3.439613526570048e-05,
"loss": 0.9859,
"step": 10290
},
{
"epoch": 3.3,
"learning_rate": 3.43317230273752e-05,
"loss": 0.9778,
"step": 10300
},
{
"epoch": 3.3,
"learning_rate": 3.426731078904992e-05,
"loss": 0.9504,
"step": 10310
},
{
"epoch": 3.3,
"learning_rate": 3.420289855072464e-05,
"loss": 0.9215,
"step": 10320
},
{
"epoch": 3.31,
"learning_rate": 3.413848631239936e-05,
"loss": 0.9195,
"step": 10330
},
{
"epoch": 3.31,
"learning_rate": 3.4074074074074077e-05,
"loss": 0.9375,
"step": 10340
},
{
"epoch": 3.31,
"learning_rate": 3.4009661835748795e-05,
"loss": 0.9505,
"step": 10350
},
{
"epoch": 3.31,
"learning_rate": 3.3945249597423514e-05,
"loss": 0.9539,
"step": 10360
},
{
"epoch": 3.32,
"learning_rate": 3.3880837359098226e-05,
"loss": 0.9822,
"step": 10370
},
{
"epoch": 3.32,
"learning_rate": 3.381642512077295e-05,
"loss": 0.9272,
"step": 10380
},
{
"epoch": 3.32,
"learning_rate": 3.375201288244766e-05,
"loss": 0.9588,
"step": 10390
},
{
"epoch": 3.33,
"learning_rate": 3.368760064412239e-05,
"loss": 0.919,
"step": 10400
},
{
"epoch": 3.33,
"eval_loss": 1.0204192399978638,
"eval_runtime": 185.6273,
"eval_samples_per_second": 10.774,
"eval_steps_per_second": 1.347,
"step": 10400
},
{
"epoch": 3.33,
"learning_rate": 3.36231884057971e-05,
"loss": 0.9416,
"step": 10410
},
{
"epoch": 3.33,
"learning_rate": 3.355877616747182e-05,
"loss": 0.9138,
"step": 10420
},
{
"epoch": 3.34,
"learning_rate": 3.349436392914654e-05,
"loss": 0.9681,
"step": 10430
},
{
"epoch": 3.34,
"learning_rate": 3.342995169082126e-05,
"loss": 0.9824,
"step": 10440
},
{
"epoch": 3.34,
"learning_rate": 3.3365539452495976e-05,
"loss": 0.9876,
"step": 10450
},
{
"epoch": 3.35,
"learning_rate": 3.3301127214170694e-05,
"loss": 0.9239,
"step": 10460
},
{
"epoch": 3.35,
"learning_rate": 3.323671497584541e-05,
"loss": 0.9314,
"step": 10470
},
{
"epoch": 3.35,
"learning_rate": 3.3172302737520125e-05,
"loss": 0.9426,
"step": 10480
},
{
"epoch": 3.36,
"learning_rate": 3.310789049919485e-05,
"loss": 0.9282,
"step": 10490
},
{
"epoch": 3.36,
"learning_rate": 3.304347826086956e-05,
"loss": 0.9742,
"step": 10500
},
{
"epoch": 3.36,
"learning_rate": 3.297906602254429e-05,
"loss": 0.9916,
"step": 10510
},
{
"epoch": 3.37,
"learning_rate": 3.2914653784219e-05,
"loss": 0.9346,
"step": 10520
},
{
"epoch": 3.37,
"learning_rate": 3.2850241545893725e-05,
"loss": 0.9036,
"step": 10530
},
{
"epoch": 3.37,
"learning_rate": 3.278582930756844e-05,
"loss": 0.9029,
"step": 10540
},
{
"epoch": 3.38,
"learning_rate": 3.272141706924316e-05,
"loss": 0.9495,
"step": 10550
},
{
"epoch": 3.38,
"learning_rate": 3.2657004830917875e-05,
"loss": 0.9441,
"step": 10560
},
{
"epoch": 3.38,
"learning_rate": 3.25925925925926e-05,
"loss": 0.9757,
"step": 10570
},
{
"epoch": 3.39,
"learning_rate": 3.252818035426731e-05,
"loss": 0.9667,
"step": 10580
},
{
"epoch": 3.39,
"learning_rate": 3.246376811594203e-05,
"loss": 0.9603,
"step": 10590
},
{
"epoch": 3.39,
"learning_rate": 3.239935587761675e-05,
"loss": 0.9362,
"step": 10600
},
{
"epoch": 3.39,
"eval_loss": 1.0204658508300781,
"eval_runtime": 185.6227,
"eval_samples_per_second": 10.775,
"eval_steps_per_second": 1.347,
"step": 10600
},
{
"epoch": 3.39,
"learning_rate": 3.233494363929147e-05,
"loss": 0.915,
"step": 10610
},
{
"epoch": 3.4,
"learning_rate": 3.227053140096619e-05,
"loss": 0.9603,
"step": 10620
},
{
"epoch": 3.4,
"learning_rate": 3.22061191626409e-05,
"loss": 0.91,
"step": 10630
},
{
"epoch": 3.4,
"learning_rate": 3.2141706924315624e-05,
"loss": 0.9411,
"step": 10640
},
{
"epoch": 3.41,
"learning_rate": 3.2077294685990336e-05,
"loss": 0.9688,
"step": 10650
},
{
"epoch": 3.41,
"learning_rate": 3.201288244766506e-05,
"loss": 0.9213,
"step": 10660
},
{
"epoch": 3.41,
"learning_rate": 3.1948470209339774e-05,
"loss": 0.9911,
"step": 10670
},
{
"epoch": 3.42,
"learning_rate": 3.188405797101449e-05,
"loss": 0.9298,
"step": 10680
},
{
"epoch": 3.42,
"learning_rate": 3.181964573268921e-05,
"loss": 0.9331,
"step": 10690
},
{
"epoch": 3.42,
"learning_rate": 3.175523349436393e-05,
"loss": 0.938,
"step": 10700
},
{
"epoch": 3.43,
"learning_rate": 3.169082125603865e-05,
"loss": 0.97,
"step": 10710
},
{
"epoch": 3.43,
"learning_rate": 3.162640901771337e-05,
"loss": 0.9349,
"step": 10720
},
{
"epoch": 3.43,
"learning_rate": 3.1561996779388086e-05,
"loss": 0.9143,
"step": 10730
},
{
"epoch": 3.44,
"learning_rate": 3.1497584541062804e-05,
"loss": 0.986,
"step": 10740
},
{
"epoch": 3.44,
"learning_rate": 3.143317230273752e-05,
"loss": 0.9483,
"step": 10750
},
{
"epoch": 3.44,
"learning_rate": 3.136876006441224e-05,
"loss": 0.9623,
"step": 10760
},
{
"epoch": 3.45,
"learning_rate": 3.130434782608696e-05,
"loss": 0.9497,
"step": 10770
},
{
"epoch": 3.45,
"learning_rate": 3.123993558776168e-05,
"loss": 0.928,
"step": 10780
},
{
"epoch": 3.45,
"learning_rate": 3.117552334943639e-05,
"loss": 0.9597,
"step": 10790
},
{
"epoch": 3.46,
"learning_rate": 3.111111111111111e-05,
"loss": 0.9228,
"step": 10800
},
{
"epoch": 3.46,
"eval_loss": 1.019952416419983,
"eval_runtime": 185.7809,
"eval_samples_per_second": 10.765,
"eval_steps_per_second": 1.346,
"step": 10800
},
{
"epoch": 3.46,
"learning_rate": 3.104669887278583e-05,
"loss": 0.9535,
"step": 10810
},
{
"epoch": 3.46,
"learning_rate": 3.098228663446055e-05,
"loss": 0.9234,
"step": 10820
},
{
"epoch": 3.47,
"learning_rate": 3.0917874396135266e-05,
"loss": 0.968,
"step": 10830
},
{
"epoch": 3.47,
"learning_rate": 3.0853462157809985e-05,
"loss": 0.9003,
"step": 10840
},
{
"epoch": 3.47,
"learning_rate": 3.0789049919484703e-05,
"loss": 0.9745,
"step": 10850
},
{
"epoch": 3.47,
"learning_rate": 3.072463768115942e-05,
"loss": 0.9016,
"step": 10860
},
{
"epoch": 3.48,
"learning_rate": 3.066022544283414e-05,
"loss": 0.9605,
"step": 10870
},
{
"epoch": 3.48,
"learning_rate": 3.059581320450886e-05,
"loss": 0.8885,
"step": 10880
},
{
"epoch": 3.48,
"learning_rate": 3.053140096618358e-05,
"loss": 0.962,
"step": 10890
},
{
"epoch": 3.49,
"learning_rate": 3.0466988727858294e-05,
"loss": 0.9208,
"step": 10900
},
{
"epoch": 3.49,
"learning_rate": 3.0402576489533012e-05,
"loss": 0.9032,
"step": 10910
},
{
"epoch": 3.49,
"learning_rate": 3.0338164251207728e-05,
"loss": 0.9875,
"step": 10920
},
{
"epoch": 3.5,
"learning_rate": 3.027375201288245e-05,
"loss": 0.9408,
"step": 10930
},
{
"epoch": 3.5,
"learning_rate": 3.0209339774557165e-05,
"loss": 0.9283,
"step": 10940
},
{
"epoch": 3.5,
"learning_rate": 3.0144927536231887e-05,
"loss": 0.9668,
"step": 10950
},
{
"epoch": 3.51,
"learning_rate": 3.0080515297906602e-05,
"loss": 0.9202,
"step": 10960
},
{
"epoch": 3.51,
"learning_rate": 3.0016103059581324e-05,
"loss": 0.9675,
"step": 10970
},
{
"epoch": 3.51,
"learning_rate": 2.995169082125604e-05,
"loss": 0.9549,
"step": 10980
},
{
"epoch": 3.52,
"learning_rate": 2.9887278582930755e-05,
"loss": 0.9618,
"step": 10990
},
{
"epoch": 3.52,
"learning_rate": 2.9822866344605477e-05,
"loss": 0.9135,
"step": 11000
},
{
"epoch": 3.52,
"eval_loss": 1.0204010009765625,
"eval_runtime": 185.6196,
"eval_samples_per_second": 10.775,
"eval_steps_per_second": 1.347,
"step": 11000
},
{
"epoch": 3.52,
"learning_rate": 2.9758454106280193e-05,
"loss": 0.9539,
"step": 11010
},
{
"epoch": 3.53,
"learning_rate": 2.9694041867954915e-05,
"loss": 0.964,
"step": 11020
},
{
"epoch": 3.53,
"learning_rate": 2.962962962962963e-05,
"loss": 0.9265,
"step": 11030
},
{
"epoch": 3.53,
"learning_rate": 2.9565217391304352e-05,
"loss": 0.9267,
"step": 11040
},
{
"epoch": 3.54,
"learning_rate": 2.9500805152979067e-05,
"loss": 0.9282,
"step": 11050
},
{
"epoch": 3.54,
"learning_rate": 2.9436392914653786e-05,
"loss": 0.9555,
"step": 11060
},
{
"epoch": 3.54,
"learning_rate": 2.9371980676328505e-05,
"loss": 0.925,
"step": 11070
},
{
"epoch": 3.55,
"learning_rate": 2.9307568438003223e-05,
"loss": 0.9174,
"step": 11080
},
{
"epoch": 3.55,
"learning_rate": 2.924315619967794e-05,
"loss": 0.9491,
"step": 11090
},
{
"epoch": 3.55,
"learning_rate": 2.9178743961352657e-05,
"loss": 0.9035,
"step": 11100
},
{
"epoch": 3.55,
"learning_rate": 2.9114331723027376e-05,
"loss": 0.9239,
"step": 11110
},
{
"epoch": 3.56,
"learning_rate": 2.904991948470209e-05,
"loss": 0.9158,
"step": 11120
},
{
"epoch": 3.56,
"learning_rate": 2.8985507246376814e-05,
"loss": 0.9734,
"step": 11130
},
{
"epoch": 3.56,
"learning_rate": 2.892109500805153e-05,
"loss": 0.9419,
"step": 11140
},
{
"epoch": 3.57,
"learning_rate": 2.885668276972625e-05,
"loss": 0.9582,
"step": 11150
},
{
"epoch": 3.57,
"learning_rate": 2.8792270531400966e-05,
"loss": 0.9283,
"step": 11160
},
{
"epoch": 3.57,
"learning_rate": 2.872785829307569e-05,
"loss": 0.932,
"step": 11170
},
{
"epoch": 3.58,
"learning_rate": 2.8663446054750404e-05,
"loss": 0.9349,
"step": 11180
},
{
"epoch": 3.58,
"learning_rate": 2.8599033816425126e-05,
"loss": 0.9378,
"step": 11190
},
{
"epoch": 3.58,
"learning_rate": 2.853462157809984e-05,
"loss": 0.9915,
"step": 11200
},
{
"epoch": 3.58,
"eval_loss": 1.0208972692489624,
"eval_runtime": 185.8582,
"eval_samples_per_second": 10.761,
"eval_steps_per_second": 1.345,
"step": 11200
},
{
"epoch": 3.59,
"learning_rate": 2.8470209339774556e-05,
"loss": 0.957,
"step": 11210
},
{
"epoch": 3.59,
"learning_rate": 2.840579710144928e-05,
"loss": 0.9514,
"step": 11220
},
{
"epoch": 3.59,
"learning_rate": 2.8341384863123994e-05,
"loss": 0.9931,
"step": 11230
},
{
"epoch": 3.6,
"learning_rate": 2.8276972624798716e-05,
"loss": 0.9304,
"step": 11240
},
{
"epoch": 3.6,
"learning_rate": 2.821256038647343e-05,
"loss": 0.9281,
"step": 11250
},
{
"epoch": 3.6,
"learning_rate": 2.814814814814815e-05,
"loss": 0.9726,
"step": 11260
},
{
"epoch": 3.61,
"learning_rate": 2.8083735909822865e-05,
"loss": 0.9539,
"step": 11270
},
{
"epoch": 3.61,
"learning_rate": 2.8019323671497587e-05,
"loss": 0.959,
"step": 11280
},
{
"epoch": 3.61,
"learning_rate": 2.7954911433172303e-05,
"loss": 0.9409,
"step": 11290
},
{
"epoch": 3.62,
"learning_rate": 2.7890499194847018e-05,
"loss": 0.8763,
"step": 11300
},
{
"epoch": 3.62,
"learning_rate": 2.782608695652174e-05,
"loss": 0.9532,
"step": 11310
},
{
"epoch": 3.62,
"learning_rate": 2.7761674718196455e-05,
"loss": 0.9698,
"step": 11320
},
{
"epoch": 3.63,
"learning_rate": 2.7697262479871177e-05,
"loss": 0.9248,
"step": 11330
},
{
"epoch": 3.63,
"learning_rate": 2.7632850241545893e-05,
"loss": 0.9537,
"step": 11340
},
{
"epoch": 3.63,
"learning_rate": 2.7568438003220615e-05,
"loss": 0.8953,
"step": 11350
},
{
"epoch": 3.63,
"learning_rate": 2.750402576489533e-05,
"loss": 0.9163,
"step": 11360
},
{
"epoch": 3.64,
"learning_rate": 2.7439613526570052e-05,
"loss": 0.9223,
"step": 11370
},
{
"epoch": 3.64,
"learning_rate": 2.7375201288244768e-05,
"loss": 0.9459,
"step": 11380
},
{
"epoch": 3.64,
"learning_rate": 2.731078904991949e-05,
"loss": 0.9296,
"step": 11390
},
{
"epoch": 3.65,
"learning_rate": 2.7246376811594205e-05,
"loss": 0.9182,
"step": 11400
},
{
"epoch": 3.65,
"eval_loss": 1.020736813545227,
"eval_runtime": 185.7004,
"eval_samples_per_second": 10.77,
"eval_steps_per_second": 1.346,
"step": 11400
},
{
"epoch": 3.65,
"learning_rate": 2.718196457326892e-05,
"loss": 0.8978,
"step": 11410
},
{
"epoch": 3.65,
"learning_rate": 2.7117552334943642e-05,
"loss": 0.952,
"step": 11420
},
{
"epoch": 3.66,
"learning_rate": 2.7053140096618358e-05,
"loss": 0.9485,
"step": 11430
},
{
"epoch": 3.66,
"learning_rate": 2.6988727858293076e-05,
"loss": 0.9477,
"step": 11440
},
{
"epoch": 3.66,
"learning_rate": 2.6924315619967795e-05,
"loss": 0.9488,
"step": 11450
},
{
"epoch": 3.67,
"learning_rate": 2.6859903381642514e-05,
"loss": 0.9239,
"step": 11460
},
{
"epoch": 3.67,
"learning_rate": 2.679549114331723e-05,
"loss": 0.9253,
"step": 11470
},
{
"epoch": 3.67,
"learning_rate": 2.673107890499195e-05,
"loss": 0.9307,
"step": 11480
},
{
"epoch": 3.68,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.9309,
"step": 11490
},
{
"epoch": 3.68,
"learning_rate": 2.660225442834139e-05,
"loss": 0.9163,
"step": 11500
},
{
"epoch": 3.68,
"learning_rate": 2.6537842190016104e-05,
"loss": 0.9616,
"step": 11510
},
{
"epoch": 3.69,
"learning_rate": 2.647342995169082e-05,
"loss": 0.9303,
"step": 11520
},
{
"epoch": 3.69,
"learning_rate": 2.640901771336554e-05,
"loss": 0.9434,
"step": 11530
},
{
"epoch": 3.69,
"learning_rate": 2.6344605475040257e-05,
"loss": 0.9441,
"step": 11540
},
{
"epoch": 3.7,
"learning_rate": 2.628019323671498e-05,
"loss": 0.9193,
"step": 11550
},
{
"epoch": 3.7,
"learning_rate": 2.6215780998389694e-05,
"loss": 0.9246,
"step": 11560
},
{
"epoch": 3.7,
"learning_rate": 2.6151368760064416e-05,
"loss": 0.9663,
"step": 11570
},
{
"epoch": 3.71,
"learning_rate": 2.608695652173913e-05,
"loss": 0.9627,
"step": 11580
},
{
"epoch": 3.71,
"learning_rate": 2.6022544283413854e-05,
"loss": 0.9495,
"step": 11590
},
{
"epoch": 3.71,
"learning_rate": 2.595813204508857e-05,
"loss": 0.9912,
"step": 11600
},
{
"epoch": 3.71,
"eval_loss": 1.0197750329971313,
"eval_runtime": 185.734,
"eval_samples_per_second": 10.768,
"eval_steps_per_second": 1.346,
"step": 11600
},
{
"epoch": 3.71,
"learning_rate": 2.5893719806763284e-05,
"loss": 0.9793,
"step": 11610
},
{
"epoch": 3.72,
"learning_rate": 2.5829307568438006e-05,
"loss": 0.9954,
"step": 11620
},
{
"epoch": 3.72,
"learning_rate": 2.576489533011272e-05,
"loss": 0.9784,
"step": 11630
},
{
"epoch": 3.72,
"learning_rate": 2.570048309178744e-05,
"loss": 0.9772,
"step": 11640
},
{
"epoch": 3.73,
"learning_rate": 2.563607085346216e-05,
"loss": 0.9081,
"step": 11650
},
{
"epoch": 3.73,
"learning_rate": 2.5571658615136878e-05,
"loss": 1.0142,
"step": 11660
},
{
"epoch": 3.73,
"learning_rate": 2.5507246376811593e-05,
"loss": 0.9344,
"step": 11670
},
{
"epoch": 3.74,
"learning_rate": 2.5442834138486315e-05,
"loss": 0.898,
"step": 11680
},
{
"epoch": 3.74,
"learning_rate": 2.537842190016103e-05,
"loss": 0.9452,
"step": 11690
},
{
"epoch": 3.74,
"learning_rate": 2.5314009661835753e-05,
"loss": 0.9549,
"step": 11700
},
{
"epoch": 3.75,
"learning_rate": 2.5249597423510468e-05,
"loss": 0.9725,
"step": 11710
},
{
"epoch": 3.75,
"learning_rate": 2.5185185185185183e-05,
"loss": 0.9805,
"step": 11720
},
{
"epoch": 3.75,
"learning_rate": 2.5120772946859905e-05,
"loss": 0.943,
"step": 11730
},
{
"epoch": 3.76,
"learning_rate": 2.505636070853462e-05,
"loss": 0.9829,
"step": 11740
},
{
"epoch": 3.76,
"learning_rate": 2.4991948470209343e-05,
"loss": 0.8923,
"step": 11750
},
{
"epoch": 3.76,
"learning_rate": 2.492753623188406e-05,
"loss": 0.941,
"step": 11760
},
{
"epoch": 3.77,
"learning_rate": 2.4863123993558777e-05,
"loss": 0.9365,
"step": 11770
},
{
"epoch": 3.77,
"learning_rate": 2.4798711755233495e-05,
"loss": 0.9625,
"step": 11780
},
{
"epoch": 3.77,
"learning_rate": 2.4734299516908214e-05,
"loss": 0.9093,
"step": 11790
},
{
"epoch": 3.78,
"learning_rate": 2.4669887278582933e-05,
"loss": 0.9494,
"step": 11800
},
{
"epoch": 3.78,
"eval_loss": 1.0202767848968506,
"eval_runtime": 185.7202,
"eval_samples_per_second": 10.769,
"eval_steps_per_second": 1.346,
"step": 11800
},
{
"epoch": 3.78,
"learning_rate": 2.460547504025765e-05,
"loss": 0.9672,
"step": 11810
},
{
"epoch": 3.78,
"learning_rate": 2.4541062801932367e-05,
"loss": 0.9556,
"step": 11820
},
{
"epoch": 3.79,
"learning_rate": 2.4476650563607086e-05,
"loss": 0.9633,
"step": 11830
},
{
"epoch": 3.79,
"learning_rate": 2.4412238325281804e-05,
"loss": 0.9554,
"step": 11840
},
{
"epoch": 3.79,
"learning_rate": 2.4347826086956523e-05,
"loss": 0.9376,
"step": 11850
},
{
"epoch": 3.79,
"learning_rate": 2.4283413848631242e-05,
"loss": 0.945,
"step": 11860
},
{
"epoch": 3.8,
"learning_rate": 2.4219001610305957e-05,
"loss": 0.9306,
"step": 11870
},
{
"epoch": 3.8,
"learning_rate": 2.4154589371980676e-05,
"loss": 0.9107,
"step": 11880
},
{
"epoch": 3.8,
"learning_rate": 2.4090177133655394e-05,
"loss": 0.9122,
"step": 11890
},
{
"epoch": 3.81,
"learning_rate": 2.4025764895330113e-05,
"loss": 0.9185,
"step": 11900
},
{
"epoch": 3.81,
"learning_rate": 2.3961352657004832e-05,
"loss": 0.9245,
"step": 11910
},
{
"epoch": 3.81,
"learning_rate": 2.389694041867955e-05,
"loss": 0.978,
"step": 11920
},
{
"epoch": 3.82,
"learning_rate": 2.383252818035427e-05,
"loss": 0.915,
"step": 11930
},
{
"epoch": 3.82,
"learning_rate": 2.3768115942028988e-05,
"loss": 0.9275,
"step": 11940
},
{
"epoch": 3.82,
"learning_rate": 2.3703703703703707e-05,
"loss": 0.8838,
"step": 11950
},
{
"epoch": 3.83,
"learning_rate": 2.3639291465378425e-05,
"loss": 0.9676,
"step": 11960
},
{
"epoch": 3.83,
"learning_rate": 2.357487922705314e-05,
"loss": 0.9168,
"step": 11970
},
{
"epoch": 3.83,
"learning_rate": 2.351046698872786e-05,
"loss": 0.9476,
"step": 11980
},
{
"epoch": 3.84,
"learning_rate": 2.3446054750402578e-05,
"loss": 0.9697,
"step": 11990
},
{
"epoch": 3.84,
"learning_rate": 2.3381642512077297e-05,
"loss": 0.9911,
"step": 12000
},
{
"epoch": 3.84,
"eval_loss": 1.0203664302825928,
"eval_runtime": 185.728,
"eval_samples_per_second": 10.768,
"eval_steps_per_second": 1.346,
"step": 12000
},
{
"epoch": 3.84,
"learning_rate": 2.3317230273752012e-05,
"loss": 0.9203,
"step": 12010
},
{
"epoch": 3.85,
"learning_rate": 2.325281803542673e-05,
"loss": 0.9131,
"step": 12020
},
{
"epoch": 3.85,
"learning_rate": 2.318840579710145e-05,
"loss": 0.9434,
"step": 12030
},
{
"epoch": 3.85,
"learning_rate": 2.3123993558776168e-05,
"loss": 0.9394,
"step": 12040
},
{
"epoch": 3.86,
"learning_rate": 2.3059581320450887e-05,
"loss": 0.9288,
"step": 12050
},
{
"epoch": 3.86,
"learning_rate": 2.2995169082125606e-05,
"loss": 0.8921,
"step": 12060
},
{
"epoch": 3.86,
"learning_rate": 2.2930756843800324e-05,
"loss": 0.9627,
"step": 12070
},
{
"epoch": 3.87,
"learning_rate": 2.286634460547504e-05,
"loss": 0.9223,
"step": 12080
},
{
"epoch": 3.87,
"learning_rate": 2.280193236714976e-05,
"loss": 0.9458,
"step": 12090
},
{
"epoch": 3.87,
"learning_rate": 2.2737520128824477e-05,
"loss": 0.9444,
"step": 12100
},
{
"epoch": 3.87,
"learning_rate": 2.2673107890499196e-05,
"loss": 0.9566,
"step": 12110
},
{
"epoch": 3.88,
"learning_rate": 2.2608695652173914e-05,
"loss": 0.9318,
"step": 12120
},
{
"epoch": 3.88,
"learning_rate": 2.2544283413848633e-05,
"loss": 0.9321,
"step": 12130
},
{
"epoch": 3.88,
"learning_rate": 2.2479871175523352e-05,
"loss": 0.916,
"step": 12140
},
{
"epoch": 3.89,
"learning_rate": 2.241545893719807e-05,
"loss": 0.9448,
"step": 12150
},
{
"epoch": 3.89,
"learning_rate": 2.235104669887279e-05,
"loss": 0.9434,
"step": 12160
},
{
"epoch": 3.89,
"learning_rate": 2.2286634460547508e-05,
"loss": 0.9573,
"step": 12170
},
{
"epoch": 3.9,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.9395,
"step": 12180
},
{
"epoch": 3.9,
"learning_rate": 2.2157809983896942e-05,
"loss": 0.9259,
"step": 12190
},
{
"epoch": 3.9,
"learning_rate": 2.2093397745571657e-05,
"loss": 0.9804,
"step": 12200
},
{
"epoch": 3.9,
"eval_loss": 1.020531177520752,
"eval_runtime": 185.969,
"eval_samples_per_second": 10.754,
"eval_steps_per_second": 1.344,
"step": 12200
},
{
"epoch": 3.91,
"learning_rate": 2.2028985507246376e-05,
"loss": 0.9442,
"step": 12210
},
{
"epoch": 3.91,
"learning_rate": 2.1964573268921095e-05,
"loss": 0.9528,
"step": 12220
},
{
"epoch": 3.91,
"learning_rate": 2.1900161030595813e-05,
"loss": 0.9734,
"step": 12230
},
{
"epoch": 3.92,
"learning_rate": 2.1835748792270532e-05,
"loss": 0.9398,
"step": 12240
},
{
"epoch": 3.92,
"learning_rate": 2.177133655394525e-05,
"loss": 0.9482,
"step": 12250
},
{
"epoch": 3.92,
"learning_rate": 2.170692431561997e-05,
"loss": 0.9219,
"step": 12260
},
{
"epoch": 3.93,
"learning_rate": 2.1642512077294688e-05,
"loss": 0.9085,
"step": 12270
},
{
"epoch": 3.93,
"learning_rate": 2.1578099838969404e-05,
"loss": 0.9246,
"step": 12280
},
{
"epoch": 3.93,
"learning_rate": 2.1513687600644122e-05,
"loss": 0.9608,
"step": 12290
},
{
"epoch": 3.94,
"learning_rate": 2.144927536231884e-05,
"loss": 0.9587,
"step": 12300
},
{
"epoch": 3.94,
"learning_rate": 2.138486312399356e-05,
"loss": 0.9486,
"step": 12310
},
{
"epoch": 3.94,
"learning_rate": 2.132045088566828e-05,
"loss": 0.9677,
"step": 12320
},
{
"epoch": 3.95,
"learning_rate": 2.1256038647342997e-05,
"loss": 0.9397,
"step": 12330
},
{
"epoch": 3.95,
"learning_rate": 2.1191626409017716e-05,
"loss": 0.9501,
"step": 12340
},
{
"epoch": 3.95,
"learning_rate": 2.1127214170692434e-05,
"loss": 0.9385,
"step": 12350
},
{
"epoch": 3.95,
"learning_rate": 2.1062801932367153e-05,
"loss": 0.9012,
"step": 12360
},
{
"epoch": 3.96,
"learning_rate": 2.099838969404187e-05,
"loss": 0.9114,
"step": 12370
},
{
"epoch": 3.96,
"learning_rate": 2.0933977455716587e-05,
"loss": 0.897,
"step": 12380
},
{
"epoch": 3.96,
"learning_rate": 2.0869565217391303e-05,
"loss": 0.9286,
"step": 12390
},
{
"epoch": 3.97,
"learning_rate": 2.080515297906602e-05,
"loss": 0.9204,
"step": 12400
},
{
"epoch": 3.97,
"eval_loss": 1.0194604396820068,
"eval_runtime": 185.8824,
"eval_samples_per_second": 10.759,
"eval_steps_per_second": 1.345,
"step": 12400
},
{
"epoch": 3.97,
"learning_rate": 2.074074074074074e-05,
"loss": 0.9409,
"step": 12410
},
{
"epoch": 3.97,
"learning_rate": 2.067632850241546e-05,
"loss": 0.9488,
"step": 12420
},
{
"epoch": 3.98,
"learning_rate": 2.0611916264090177e-05,
"loss": 0.9582,
"step": 12430
},
{
"epoch": 3.98,
"learning_rate": 2.0547504025764896e-05,
"loss": 0.9216,
"step": 12440
},
{
"epoch": 3.98,
"learning_rate": 2.0483091787439615e-05,
"loss": 0.9372,
"step": 12450
},
{
"epoch": 3.99,
"learning_rate": 2.0418679549114333e-05,
"loss": 0.9349,
"step": 12460
},
{
"epoch": 3.99,
"learning_rate": 2.0354267310789052e-05,
"loss": 0.9378,
"step": 12470
},
{
"epoch": 3.99,
"learning_rate": 2.028985507246377e-05,
"loss": 0.8969,
"step": 12480
},
{
"epoch": 4.0,
"learning_rate": 2.0225442834138486e-05,
"loss": 0.932,
"step": 12490
},
{
"epoch": 4.0,
"learning_rate": 2.0161030595813205e-05,
"loss": 0.9217,
"step": 12500
},
{
"epoch": 4.0,
"learning_rate": 2.0096618357487924e-05,
"loss": 0.9195,
"step": 12510
},
{
"epoch": 4.01,
"learning_rate": 2.0032206119162642e-05,
"loss": 0.8911,
"step": 12520
},
{
"epoch": 4.01,
"learning_rate": 1.996779388083736e-05,
"loss": 0.9525,
"step": 12530
},
{
"epoch": 4.01,
"learning_rate": 1.990338164251208e-05,
"loss": 0.8723,
"step": 12540
},
{
"epoch": 4.02,
"learning_rate": 1.98389694041868e-05,
"loss": 0.9319,
"step": 12550
},
{
"epoch": 4.02,
"learning_rate": 1.9774557165861514e-05,
"loss": 0.9389,
"step": 12560
},
{
"epoch": 4.02,
"learning_rate": 1.9710144927536232e-05,
"loss": 0.951,
"step": 12570
},
{
"epoch": 4.03,
"learning_rate": 1.964573268921095e-05,
"loss": 0.94,
"step": 12580
},
{
"epoch": 4.03,
"learning_rate": 1.9581320450885666e-05,
"loss": 0.8881,
"step": 12590
},
{
"epoch": 4.03,
"learning_rate": 1.9516908212560385e-05,
"loss": 0.9259,
"step": 12600
},
{
"epoch": 4.03,
"eval_loss": 1.0242584943771362,
"eval_runtime": 185.6505,
"eval_samples_per_second": 10.773,
"eval_steps_per_second": 1.347,
"step": 12600
},
{
"epoch": 4.03,
"learning_rate": 1.9452495974235104e-05,
"loss": 0.9263,
"step": 12610
},
{
"epoch": 4.04,
"learning_rate": 1.9388083735909823e-05,
"loss": 0.9086,
"step": 12620
},
{
"epoch": 4.04,
"learning_rate": 1.932367149758454e-05,
"loss": 0.9166,
"step": 12630
},
{
"epoch": 4.04,
"learning_rate": 1.925925925925926e-05,
"loss": 0.8954,
"step": 12640
},
{
"epoch": 4.05,
"learning_rate": 1.919484702093398e-05,
"loss": 0.9404,
"step": 12650
},
{
"epoch": 4.05,
"learning_rate": 1.9130434782608697e-05,
"loss": 0.9082,
"step": 12660
},
{
"epoch": 4.05,
"learning_rate": 1.9066022544283416e-05,
"loss": 0.8876,
"step": 12670
},
{
"epoch": 4.06,
"learning_rate": 1.9001610305958135e-05,
"loss": 0.9323,
"step": 12680
},
{
"epoch": 4.06,
"learning_rate": 1.8937198067632853e-05,
"loss": 0.9473,
"step": 12690
},
{
"epoch": 4.06,
"learning_rate": 1.887278582930757e-05,
"loss": 0.924,
"step": 12700
},
{
"epoch": 4.07,
"learning_rate": 1.8808373590982287e-05,
"loss": 0.9408,
"step": 12710
},
{
"epoch": 4.07,
"learning_rate": 1.8743961352657006e-05,
"loss": 0.9696,
"step": 12720
},
{
"epoch": 4.07,
"learning_rate": 1.8679549114331725e-05,
"loss": 0.8972,
"step": 12730
},
{
"epoch": 4.08,
"learning_rate": 1.8615136876006444e-05,
"loss": 0.9433,
"step": 12740
},
{
"epoch": 4.08,
"learning_rate": 1.855072463768116e-05,
"loss": 0.885,
"step": 12750
},
{
"epoch": 4.08,
"learning_rate": 1.8486312399355878e-05,
"loss": 0.8641,
"step": 12760
},
{
"epoch": 4.09,
"learning_rate": 1.8421900161030596e-05,
"loss": 0.9207,
"step": 12770
},
{
"epoch": 4.09,
"learning_rate": 1.8357487922705315e-05,
"loss": 0.9599,
"step": 12780
},
{
"epoch": 4.09,
"learning_rate": 1.8293075684380034e-05,
"loss": 0.933,
"step": 12790
},
{
"epoch": 4.1,
"learning_rate": 1.822866344605475e-05,
"loss": 0.8847,
"step": 12800
},
{
"epoch": 4.1,
"eval_loss": 1.0249016284942627,
"eval_runtime": 185.1711,
"eval_samples_per_second": 10.801,
"eval_steps_per_second": 1.35,
"step": 12800
},
{
"epoch": 4.1,
"learning_rate": 1.8164251207729468e-05,
"loss": 0.9367,
"step": 12810
},
{
"epoch": 4.1,
"learning_rate": 1.8099838969404186e-05,
"loss": 0.8933,
"step": 12820
},
{
"epoch": 4.11,
"learning_rate": 1.8035426731078905e-05,
"loss": 0.9401,
"step": 12830
},
{
"epoch": 4.11,
"learning_rate": 1.7971014492753624e-05,
"loss": 0.8991,
"step": 12840
},
{
"epoch": 4.11,
"learning_rate": 1.7906602254428343e-05,
"loss": 0.918,
"step": 12850
},
{
"epoch": 4.11,
"learning_rate": 1.784219001610306e-05,
"loss": 0.8747,
"step": 12860
},
{
"epoch": 4.12,
"learning_rate": 1.777777777777778e-05,
"loss": 0.912,
"step": 12870
},
{
"epoch": 4.12,
"learning_rate": 1.77133655394525e-05,
"loss": 0.9363,
"step": 12880
},
{
"epoch": 4.12,
"learning_rate": 1.7648953301127217e-05,
"loss": 0.9562,
"step": 12890
},
{
"epoch": 4.13,
"learning_rate": 1.7584541062801933e-05,
"loss": 0.8962,
"step": 12900
},
{
"epoch": 4.13,
"learning_rate": 1.752012882447665e-05,
"loss": 0.9182,
"step": 12910
},
{
"epoch": 4.13,
"learning_rate": 1.745571658615137e-05,
"loss": 0.8928,
"step": 12920
},
{
"epoch": 4.14,
"learning_rate": 1.739130434782609e-05,
"loss": 0.9068,
"step": 12930
},
{
"epoch": 4.14,
"learning_rate": 1.7326892109500804e-05,
"loss": 0.9521,
"step": 12940
},
{
"epoch": 4.14,
"learning_rate": 1.7262479871175523e-05,
"loss": 0.9492,
"step": 12950
},
{
"epoch": 4.15,
"learning_rate": 1.719806763285024e-05,
"loss": 0.9432,
"step": 12960
},
{
"epoch": 4.15,
"learning_rate": 1.713365539452496e-05,
"loss": 0.9103,
"step": 12970
},
{
"epoch": 4.15,
"learning_rate": 1.706924315619968e-05,
"loss": 0.8698,
"step": 12980
},
{
"epoch": 4.16,
"learning_rate": 1.7004830917874398e-05,
"loss": 0.9173,
"step": 12990
},
{
"epoch": 4.16,
"learning_rate": 1.6940418679549113e-05,
"loss": 0.9322,
"step": 13000
},
{
"epoch": 4.16,
"eval_loss": 1.0260157585144043,
"eval_runtime": 185.2834,
"eval_samples_per_second": 10.794,
"eval_steps_per_second": 1.349,
"step": 13000
},
{
"epoch": 4.16,
"learning_rate": 1.687600644122383e-05,
"loss": 0.9101,
"step": 13010
},
{
"epoch": 4.17,
"learning_rate": 1.681159420289855e-05,
"loss": 0.9106,
"step": 13020
},
{
"epoch": 4.17,
"learning_rate": 1.674718196457327e-05,
"loss": 0.9305,
"step": 13030
},
{
"epoch": 4.17,
"learning_rate": 1.6682769726247988e-05,
"loss": 0.921,
"step": 13040
},
{
"epoch": 4.18,
"learning_rate": 1.6618357487922706e-05,
"loss": 0.9068,
"step": 13050
},
{
"epoch": 4.18,
"learning_rate": 1.6553945249597425e-05,
"loss": 0.9289,
"step": 13060
},
{
"epoch": 4.18,
"learning_rate": 1.6489533011272144e-05,
"loss": 0.9705,
"step": 13070
},
{
"epoch": 4.19,
"learning_rate": 1.6425120772946863e-05,
"loss": 0.904,
"step": 13080
},
{
"epoch": 4.19,
"learning_rate": 1.636070853462158e-05,
"loss": 0.928,
"step": 13090
},
{
"epoch": 4.19,
"learning_rate": 1.62962962962963e-05,
"loss": 0.8668,
"step": 13100
},
{
"epoch": 4.19,
"learning_rate": 1.6231884057971015e-05,
"loss": 0.9068,
"step": 13110
},
{
"epoch": 4.2,
"learning_rate": 1.6167471819645734e-05,
"loss": 0.9461,
"step": 13120
},
{
"epoch": 4.2,
"learning_rate": 1.610305958132045e-05,
"loss": 0.9201,
"step": 13130
},
{
"epoch": 4.2,
"learning_rate": 1.6038647342995168e-05,
"loss": 0.9456,
"step": 13140
},
{
"epoch": 4.21,
"learning_rate": 1.5974235104669887e-05,
"loss": 0.93,
"step": 13150
},
{
"epoch": 4.21,
"learning_rate": 1.5909822866344605e-05,
"loss": 0.9325,
"step": 13160
},
{
"epoch": 4.21,
"learning_rate": 1.5845410628019324e-05,
"loss": 0.9258,
"step": 13170
},
{
"epoch": 4.22,
"learning_rate": 1.5780998389694043e-05,
"loss": 0.9383,
"step": 13180
},
{
"epoch": 4.22,
"learning_rate": 1.571658615136876e-05,
"loss": 0.9102,
"step": 13190
},
{
"epoch": 4.22,
"learning_rate": 1.565217391304348e-05,
"loss": 0.9468,
"step": 13200
},
{
"epoch": 4.22,
"eval_loss": 1.0262330770492554,
"eval_runtime": 185.7469,
"eval_samples_per_second": 10.767,
"eval_steps_per_second": 1.346,
"step": 13200
},
{
"epoch": 4.23,
"learning_rate": 1.5587761674718196e-05,
"loss": 0.8922,
"step": 13210
},
{
"epoch": 4.23,
"learning_rate": 1.5523349436392914e-05,
"loss": 0.8682,
"step": 13220
},
{
"epoch": 4.23,
"learning_rate": 1.5458937198067633e-05,
"loss": 0.9325,
"step": 13230
},
{
"epoch": 4.24,
"learning_rate": 1.5394524959742352e-05,
"loss": 0.9187,
"step": 13240
},
{
"epoch": 4.24,
"learning_rate": 1.533011272141707e-05,
"loss": 0.9496,
"step": 13250
},
{
"epoch": 4.24,
"learning_rate": 1.526570048309179e-05,
"loss": 0.8942,
"step": 13260
},
{
"epoch": 4.25,
"learning_rate": 1.5201288244766506e-05,
"loss": 0.899,
"step": 13270
},
{
"epoch": 4.25,
"learning_rate": 1.5136876006441225e-05,
"loss": 0.923,
"step": 13280
},
{
"epoch": 4.25,
"learning_rate": 1.5072463768115944e-05,
"loss": 0.9093,
"step": 13290
},
{
"epoch": 4.26,
"learning_rate": 1.5008051529790662e-05,
"loss": 0.9187,
"step": 13300
},
{
"epoch": 4.26,
"learning_rate": 1.4943639291465378e-05,
"loss": 0.9003,
"step": 13310
},
{
"epoch": 4.26,
"learning_rate": 1.4879227053140096e-05,
"loss": 0.9492,
"step": 13320
},
{
"epoch": 4.27,
"learning_rate": 1.4814814814814815e-05,
"loss": 0.8683,
"step": 13330
},
{
"epoch": 4.27,
"learning_rate": 1.4750402576489534e-05,
"loss": 0.921,
"step": 13340
},
{
"epoch": 4.27,
"learning_rate": 1.4685990338164252e-05,
"loss": 0.9394,
"step": 13350
},
{
"epoch": 4.27,
"learning_rate": 1.462157809983897e-05,
"loss": 0.914,
"step": 13360
},
{
"epoch": 4.28,
"learning_rate": 1.4557165861513688e-05,
"loss": 0.9091,
"step": 13370
},
{
"epoch": 4.28,
"learning_rate": 1.4492753623188407e-05,
"loss": 0.9052,
"step": 13380
},
{
"epoch": 4.28,
"learning_rate": 1.4428341384863125e-05,
"loss": 0.9106,
"step": 13390
},
{
"epoch": 4.29,
"learning_rate": 1.4363929146537844e-05,
"loss": 0.9246,
"step": 13400
},
{
"epoch": 4.29,
"eval_loss": 1.0260928869247437,
"eval_runtime": 185.7325,
"eval_samples_per_second": 10.768,
"eval_steps_per_second": 1.346,
"step": 13400
},
{
"epoch": 4.29,
"learning_rate": 1.4299516908212563e-05,
"loss": 0.9285,
"step": 13410
},
{
"epoch": 4.29,
"learning_rate": 1.4235104669887278e-05,
"loss": 0.9403,
"step": 13420
},
{
"epoch": 4.3,
"learning_rate": 1.4170692431561997e-05,
"loss": 0.9398,
"step": 13430
},
{
"epoch": 4.3,
"learning_rate": 1.4106280193236716e-05,
"loss": 0.9141,
"step": 13440
},
{
"epoch": 4.3,
"learning_rate": 1.4041867954911433e-05,
"loss": 0.918,
"step": 13450
},
{
"epoch": 4.31,
"learning_rate": 1.3977455716586151e-05,
"loss": 0.9358,
"step": 13460
},
{
"epoch": 4.31,
"learning_rate": 1.391304347826087e-05,
"loss": 0.9295,
"step": 13470
},
{
"epoch": 4.31,
"learning_rate": 1.3848631239935589e-05,
"loss": 0.9361,
"step": 13480
},
{
"epoch": 4.32,
"learning_rate": 1.3784219001610307e-05,
"loss": 0.9246,
"step": 13490
},
{
"epoch": 4.32,
"learning_rate": 1.3719806763285026e-05,
"loss": 0.9352,
"step": 13500
},
{
"epoch": 4.32,
"learning_rate": 1.3655394524959745e-05,
"loss": 0.9274,
"step": 13510
},
{
"epoch": 4.33,
"learning_rate": 1.359098228663446e-05,
"loss": 0.903,
"step": 13520
},
{
"epoch": 4.33,
"learning_rate": 1.3526570048309179e-05,
"loss": 0.9416,
"step": 13530
},
{
"epoch": 4.33,
"learning_rate": 1.3462157809983898e-05,
"loss": 0.9134,
"step": 13540
},
{
"epoch": 4.34,
"learning_rate": 1.3397745571658615e-05,
"loss": 0.9292,
"step": 13550
},
{
"epoch": 4.34,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.9274,
"step": 13560
},
{
"epoch": 4.34,
"learning_rate": 1.3268921095008052e-05,
"loss": 0.9214,
"step": 13570
},
{
"epoch": 4.35,
"learning_rate": 1.320450885668277e-05,
"loss": 0.9906,
"step": 13580
},
{
"epoch": 4.35,
"learning_rate": 1.314009661835749e-05,
"loss": 0.903,
"step": 13590
},
{
"epoch": 4.35,
"learning_rate": 1.3075684380032208e-05,
"loss": 0.9098,
"step": 13600
},
{
"epoch": 4.35,
"eval_loss": 1.0272597074508667,
"eval_runtime": 185.8178,
"eval_samples_per_second": 10.763,
"eval_steps_per_second": 1.345,
"step": 13600
},
{
"epoch": 4.35,
"learning_rate": 1.3011272141706927e-05,
"loss": 0.9239,
"step": 13610
},
{
"epoch": 4.36,
"learning_rate": 1.2946859903381642e-05,
"loss": 0.9003,
"step": 13620
},
{
"epoch": 4.36,
"learning_rate": 1.288244766505636e-05,
"loss": 0.9239,
"step": 13630
},
{
"epoch": 4.36,
"learning_rate": 1.281803542673108e-05,
"loss": 0.868,
"step": 13640
},
{
"epoch": 4.37,
"learning_rate": 1.2753623188405797e-05,
"loss": 0.9009,
"step": 13650
},
{
"epoch": 4.37,
"learning_rate": 1.2689210950080515e-05,
"loss": 0.8691,
"step": 13660
},
{
"epoch": 4.37,
"learning_rate": 1.2624798711755234e-05,
"loss": 0.9485,
"step": 13670
},
{
"epoch": 4.38,
"learning_rate": 1.2560386473429953e-05,
"loss": 0.9548,
"step": 13680
},
{
"epoch": 4.38,
"learning_rate": 1.2495974235104671e-05,
"loss": 0.9139,
"step": 13690
},
{
"epoch": 4.38,
"learning_rate": 1.2431561996779388e-05,
"loss": 0.8865,
"step": 13700
},
{
"epoch": 4.39,
"learning_rate": 1.2367149758454107e-05,
"loss": 0.9589,
"step": 13710
},
{
"epoch": 4.39,
"learning_rate": 1.2302737520128826e-05,
"loss": 0.9178,
"step": 13720
},
{
"epoch": 4.39,
"learning_rate": 1.2238325281803543e-05,
"loss": 0.8904,
"step": 13730
},
{
"epoch": 4.4,
"learning_rate": 1.2173913043478261e-05,
"loss": 0.9689,
"step": 13740
},
{
"epoch": 4.4,
"learning_rate": 1.2109500805152979e-05,
"loss": 0.9332,
"step": 13750
},
{
"epoch": 4.4,
"learning_rate": 1.2045088566827697e-05,
"loss": 0.8886,
"step": 13760
},
{
"epoch": 4.41,
"learning_rate": 1.1980676328502416e-05,
"loss": 0.9236,
"step": 13770
},
{
"epoch": 4.41,
"learning_rate": 1.1916264090177135e-05,
"loss": 0.9277,
"step": 13780
},
{
"epoch": 4.41,
"learning_rate": 1.1851851851851853e-05,
"loss": 0.9584,
"step": 13790
},
{
"epoch": 4.42,
"learning_rate": 1.178743961352657e-05,
"loss": 0.9438,
"step": 13800
},
{
"epoch": 4.42,
"eval_loss": 1.0258300304412842,
"eval_runtime": 185.6037,
"eval_samples_per_second": 10.776,
"eval_steps_per_second": 1.347,
"step": 13800
},
{
"epoch": 4.42,
"learning_rate": 1.1723027375201289e-05,
"loss": 0.8793,
"step": 13810
},
{
"epoch": 4.42,
"learning_rate": 1.1658615136876006e-05,
"loss": 0.9195,
"step": 13820
},
{
"epoch": 4.43,
"learning_rate": 1.1594202898550725e-05,
"loss": 0.9315,
"step": 13830
},
{
"epoch": 4.43,
"learning_rate": 1.1529790660225443e-05,
"loss": 0.9155,
"step": 13840
},
{
"epoch": 4.43,
"learning_rate": 1.1465378421900162e-05,
"loss": 0.9861,
"step": 13850
},
{
"epoch": 4.43,
"learning_rate": 1.140096618357488e-05,
"loss": 0.9285,
"step": 13860
},
{
"epoch": 4.44,
"learning_rate": 1.1336553945249598e-05,
"loss": 0.9304,
"step": 13870
},
{
"epoch": 4.44,
"learning_rate": 1.1272141706924317e-05,
"loss": 0.8874,
"step": 13880
},
{
"epoch": 4.44,
"learning_rate": 1.1207729468599035e-05,
"loss": 0.9123,
"step": 13890
},
{
"epoch": 4.45,
"learning_rate": 1.1143317230273754e-05,
"loss": 0.9032,
"step": 13900
},
{
"epoch": 4.45,
"learning_rate": 1.1078904991948471e-05,
"loss": 0.9069,
"step": 13910
},
{
"epoch": 4.45,
"learning_rate": 1.1014492753623188e-05,
"loss": 0.9081,
"step": 13920
},
{
"epoch": 4.46,
"learning_rate": 1.0950080515297907e-05,
"loss": 0.9451,
"step": 13930
},
{
"epoch": 4.46,
"learning_rate": 1.0885668276972625e-05,
"loss": 0.8822,
"step": 13940
},
{
"epoch": 4.46,
"learning_rate": 1.0821256038647344e-05,
"loss": 0.9095,
"step": 13950
},
{
"epoch": 4.47,
"learning_rate": 1.0756843800322061e-05,
"loss": 0.9091,
"step": 13960
},
{
"epoch": 4.47,
"learning_rate": 1.069243156199678e-05,
"loss": 0.9613,
"step": 13970
},
{
"epoch": 4.47,
"learning_rate": 1.0628019323671499e-05,
"loss": 0.9071,
"step": 13980
},
{
"epoch": 4.48,
"learning_rate": 1.0563607085346217e-05,
"loss": 0.9167,
"step": 13990
},
{
"epoch": 4.48,
"learning_rate": 1.0499194847020934e-05,
"loss": 0.9141,
"step": 14000
},
{
"epoch": 4.48,
"eval_loss": 1.0271040201187134,
"eval_runtime": 185.513,
"eval_samples_per_second": 10.781,
"eval_steps_per_second": 1.348,
"step": 14000
},
{
"epoch": 4.48,
"learning_rate": 1.0434782608695651e-05,
"loss": 0.9496,
"step": 14010
},
{
"epoch": 4.49,
"learning_rate": 1.037037037037037e-05,
"loss": 0.9135,
"step": 14020
},
{
"epoch": 4.49,
"learning_rate": 1.0305958132045089e-05,
"loss": 0.93,
"step": 14030
},
{
"epoch": 4.49,
"learning_rate": 1.0241545893719807e-05,
"loss": 0.9371,
"step": 14040
},
{
"epoch": 4.5,
"learning_rate": 1.0177133655394526e-05,
"loss": 0.8959,
"step": 14050
},
{
"epoch": 4.5,
"learning_rate": 1.0112721417069243e-05,
"loss": 0.9462,
"step": 14060
},
{
"epoch": 4.5,
"learning_rate": 1.0048309178743962e-05,
"loss": 0.9088,
"step": 14070
},
{
"epoch": 4.51,
"learning_rate": 9.98389694041868e-06,
"loss": 0.94,
"step": 14080
},
{
"epoch": 4.51,
"learning_rate": 9.9194847020934e-06,
"loss": 0.9294,
"step": 14090
},
{
"epoch": 4.51,
"learning_rate": 9.855072463768116e-06,
"loss": 0.9061,
"step": 14100
},
{
"epoch": 4.51,
"learning_rate": 9.790660225442833e-06,
"loss": 0.9217,
"step": 14110
},
{
"epoch": 4.52,
"learning_rate": 9.726247987117552e-06,
"loss": 0.9119,
"step": 14120
},
{
"epoch": 4.52,
"learning_rate": 9.66183574879227e-06,
"loss": 0.9177,
"step": 14130
},
{
"epoch": 4.52,
"learning_rate": 9.59742351046699e-06,
"loss": 0.9344,
"step": 14140
},
{
"epoch": 4.53,
"learning_rate": 9.533011272141708e-06,
"loss": 0.9323,
"step": 14150
},
{
"epoch": 4.53,
"learning_rate": 9.468599033816427e-06,
"loss": 0.887,
"step": 14160
},
{
"epoch": 4.53,
"learning_rate": 9.404186795491144e-06,
"loss": 0.9849,
"step": 14170
},
{
"epoch": 4.54,
"learning_rate": 9.339774557165862e-06,
"loss": 0.8887,
"step": 14180
},
{
"epoch": 4.54,
"learning_rate": 9.27536231884058e-06,
"loss": 0.8912,
"step": 14190
},
{
"epoch": 4.54,
"learning_rate": 9.210950080515298e-06,
"loss": 0.901,
"step": 14200
},
{
"epoch": 4.54,
"eval_loss": 1.0271906852722168,
"eval_runtime": 185.5026,
"eval_samples_per_second": 10.782,
"eval_steps_per_second": 1.348,
"step": 14200
},
{
"epoch": 4.55,
"learning_rate": 9.146537842190017e-06,
"loss": 0.9378,
"step": 14210
},
{
"epoch": 4.55,
"learning_rate": 9.082125603864734e-06,
"loss": 0.9211,
"step": 14220
},
{
"epoch": 4.55,
"learning_rate": 9.017713365539453e-06,
"loss": 0.9268,
"step": 14230
},
{
"epoch": 4.56,
"learning_rate": 8.953301127214171e-06,
"loss": 0.9014,
"step": 14240
},
{
"epoch": 4.56,
"learning_rate": 8.88888888888889e-06,
"loss": 1.0102,
"step": 14250
},
{
"epoch": 4.56,
"learning_rate": 8.824476650563609e-06,
"loss": 0.8908,
"step": 14260
},
{
"epoch": 4.57,
"learning_rate": 8.760064412238326e-06,
"loss": 0.9336,
"step": 14270
},
{
"epoch": 4.57,
"learning_rate": 8.695652173913044e-06,
"loss": 0.9673,
"step": 14280
},
{
"epoch": 4.57,
"learning_rate": 8.631239935587761e-06,
"loss": 0.9396,
"step": 14290
},
{
"epoch": 4.58,
"learning_rate": 8.56682769726248e-06,
"loss": 0.9446,
"step": 14300
},
{
"epoch": 4.58,
"learning_rate": 8.502415458937199e-06,
"loss": 0.9203,
"step": 14310
},
{
"epoch": 4.58,
"learning_rate": 8.438003220611916e-06,
"loss": 0.8645,
"step": 14320
},
{
"epoch": 4.59,
"learning_rate": 8.373590982286635e-06,
"loss": 0.9053,
"step": 14330
},
{
"epoch": 4.59,
"learning_rate": 8.309178743961353e-06,
"loss": 0.9713,
"step": 14340
},
{
"epoch": 4.59,
"learning_rate": 8.244766505636072e-06,
"loss": 0.9441,
"step": 14350
},
{
"epoch": 4.59,
"learning_rate": 8.18035426731079e-06,
"loss": 0.916,
"step": 14360
},
{
"epoch": 4.6,
"learning_rate": 8.115942028985508e-06,
"loss": 0.9249,
"step": 14370
},
{
"epoch": 4.6,
"learning_rate": 8.051529790660225e-06,
"loss": 0.924,
"step": 14380
},
{
"epoch": 4.6,
"learning_rate": 7.987117552334943e-06,
"loss": 0.9267,
"step": 14390
},
{
"epoch": 4.61,
"learning_rate": 7.922705314009662e-06,
"loss": 0.9236,
"step": 14400
},
{
"epoch": 4.61,
"eval_loss": 1.026214599609375,
"eval_runtime": 185.9209,
"eval_samples_per_second": 10.757,
"eval_steps_per_second": 1.345,
"step": 14400
},
{
"epoch": 4.61,
"learning_rate": 7.85829307568438e-06,
"loss": 0.9255,
"step": 14410
},
{
"epoch": 4.61,
"learning_rate": 7.793880837359098e-06,
"loss": 0.9468,
"step": 14420
},
{
"epoch": 4.62,
"learning_rate": 7.729468599033817e-06,
"loss": 0.9403,
"step": 14430
},
{
"epoch": 4.62,
"learning_rate": 7.665056360708535e-06,
"loss": 0.9465,
"step": 14440
},
{
"epoch": 4.62,
"learning_rate": 7.600644122383253e-06,
"loss": 0.8782,
"step": 14450
},
{
"epoch": 4.63,
"learning_rate": 7.536231884057972e-06,
"loss": 0.9377,
"step": 14460
},
{
"epoch": 4.63,
"learning_rate": 7.471819645732689e-06,
"loss": 0.941,
"step": 14470
},
{
"epoch": 4.63,
"learning_rate": 7.4074074074074075e-06,
"loss": 0.926,
"step": 14480
},
{
"epoch": 4.64,
"learning_rate": 7.342995169082126e-06,
"loss": 0.9418,
"step": 14490
},
{
"epoch": 4.64,
"learning_rate": 7.278582930756844e-06,
"loss": 0.9115,
"step": 14500
},
{
"epoch": 4.64,
"learning_rate": 7.214170692431563e-06,
"loss": 0.9632,
"step": 14510
},
{
"epoch": 4.65,
"learning_rate": 7.1497584541062814e-06,
"loss": 0.9224,
"step": 14520
},
{
"epoch": 4.65,
"learning_rate": 7.0853462157809985e-06,
"loss": 0.9383,
"step": 14530
},
{
"epoch": 4.65,
"learning_rate": 7.020933977455716e-06,
"loss": 0.9366,
"step": 14540
},
{
"epoch": 4.66,
"learning_rate": 6.956521739130435e-06,
"loss": 0.933,
"step": 14550
},
{
"epoch": 4.66,
"learning_rate": 6.892109500805154e-06,
"loss": 0.887,
"step": 14560
},
{
"epoch": 4.66,
"learning_rate": 6.8276972624798724e-06,
"loss": 0.9109,
"step": 14570
},
{
"epoch": 4.67,
"learning_rate": 6.7632850241545894e-06,
"loss": 0.8918,
"step": 14580
},
{
"epoch": 4.67,
"learning_rate": 6.698872785829307e-06,
"loss": 0.9071,
"step": 14590
},
{
"epoch": 4.67,
"learning_rate": 6.634460547504026e-06,
"loss": 0.9541,
"step": 14600
},
{
"epoch": 4.67,
"eval_loss": 1.0271246433258057,
"eval_runtime": 185.9235,
"eval_samples_per_second": 10.757,
"eval_steps_per_second": 1.345,
"step": 14600
},
{
"epoch": 4.67,
"learning_rate": 6.570048309178745e-06,
"loss": 0.9248,
"step": 14610
},
{
"epoch": 4.68,
"learning_rate": 6.505636070853463e-06,
"loss": 0.8734,
"step": 14620
},
{
"epoch": 4.68,
"learning_rate": 6.44122383252818e-06,
"loss": 0.9185,
"step": 14630
},
{
"epoch": 4.68,
"learning_rate": 6.376811594202898e-06,
"loss": 0.8952,
"step": 14640
},
{
"epoch": 4.69,
"learning_rate": 6.312399355877617e-06,
"loss": 0.9259,
"step": 14650
},
{
"epoch": 4.69,
"learning_rate": 6.247987117552336e-06,
"loss": 0.9393,
"step": 14660
},
{
"epoch": 4.69,
"learning_rate": 6.1835748792270535e-06,
"loss": 0.9438,
"step": 14670
},
{
"epoch": 4.7,
"learning_rate": 6.119162640901771e-06,
"loss": 0.9362,
"step": 14680
},
{
"epoch": 4.7,
"learning_rate": 6.054750402576489e-06,
"loss": 0.9455,
"step": 14690
},
{
"epoch": 4.7,
"learning_rate": 5.990338164251208e-06,
"loss": 0.8851,
"step": 14700
},
{
"epoch": 4.71,
"learning_rate": 5.925925925925927e-06,
"loss": 0.9641,
"step": 14710
},
{
"epoch": 4.71,
"learning_rate": 5.8615136876006445e-06,
"loss": 0.933,
"step": 14720
},
{
"epoch": 4.71,
"learning_rate": 5.797101449275362e-06,
"loss": 0.9546,
"step": 14730
},
{
"epoch": 4.72,
"learning_rate": 5.732689210950081e-06,
"loss": 0.923,
"step": 14740
},
{
"epoch": 4.72,
"learning_rate": 5.668276972624799e-06,
"loss": 0.9494,
"step": 14750
},
{
"epoch": 4.72,
"learning_rate": 5.603864734299518e-06,
"loss": 0.9442,
"step": 14760
},
{
"epoch": 4.73,
"learning_rate": 5.5394524959742355e-06,
"loss": 0.9571,
"step": 14770
},
{
"epoch": 4.73,
"learning_rate": 5.475040257648953e-06,
"loss": 0.9171,
"step": 14780
},
{
"epoch": 4.73,
"learning_rate": 5.410628019323672e-06,
"loss": 0.9183,
"step": 14790
},
{
"epoch": 4.74,
"learning_rate": 5.34621578099839e-06,
"loss": 0.9395,
"step": 14800
},
{
"epoch": 4.74,
"eval_loss": 1.026661992073059,
"eval_runtime": 185.6848,
"eval_samples_per_second": 10.771,
"eval_steps_per_second": 1.346,
"step": 14800
},
{
"epoch": 4.74,
"learning_rate": 5.281803542673109e-06,
"loss": 0.9001,
"step": 14810
},
{
"epoch": 4.74,
"learning_rate": 5.217391304347826e-06,
"loss": 0.9535,
"step": 14820
},
{
"epoch": 4.75,
"learning_rate": 5.152979066022544e-06,
"loss": 0.9204,
"step": 14830
},
{
"epoch": 4.75,
"learning_rate": 5.088566827697263e-06,
"loss": 0.9311,
"step": 14840
},
{
"epoch": 4.75,
"learning_rate": 5.024154589371981e-06,
"loss": 0.9117,
"step": 14850
},
{
"epoch": 4.75,
"learning_rate": 4.9597423510467e-06,
"loss": 0.9534,
"step": 14860
},
{
"epoch": 4.76,
"learning_rate": 4.895330112721417e-06,
"loss": 0.9449,
"step": 14870
},
{
"epoch": 4.76,
"learning_rate": 4.830917874396135e-06,
"loss": 0.9474,
"step": 14880
},
{
"epoch": 4.76,
"learning_rate": 4.766505636070854e-06,
"loss": 0.9429,
"step": 14890
},
{
"epoch": 4.77,
"learning_rate": 4.702093397745572e-06,
"loss": 1.0071,
"step": 14900
},
{
"epoch": 4.77,
"learning_rate": 4.63768115942029e-06,
"loss": 0.9075,
"step": 14910
},
{
"epoch": 4.77,
"learning_rate": 4.5732689210950084e-06,
"loss": 0.9184,
"step": 14920
},
{
"epoch": 4.78,
"learning_rate": 4.508856682769726e-06,
"loss": 0.928,
"step": 14930
},
{
"epoch": 4.78,
"learning_rate": 4.444444444444445e-06,
"loss": 0.9877,
"step": 14940
},
{
"epoch": 4.78,
"learning_rate": 4.380032206119163e-06,
"loss": 0.9049,
"step": 14950
},
{
"epoch": 4.79,
"learning_rate": 4.315619967793881e-06,
"loss": 0.9278,
"step": 14960
},
{
"epoch": 4.79,
"learning_rate": 4.251207729468599e-06,
"loss": 0.9215,
"step": 14970
},
{
"epoch": 4.79,
"learning_rate": 4.186795491143317e-06,
"loss": 0.9413,
"step": 14980
},
{
"epoch": 4.8,
"learning_rate": 4.122383252818036e-06,
"loss": 0.9088,
"step": 14990
},
{
"epoch": 4.8,
"learning_rate": 4.057971014492754e-06,
"loss": 0.9334,
"step": 15000
},
{
"epoch": 4.8,
"eval_loss": 1.0265828371047974,
"eval_runtime": 185.8809,
"eval_samples_per_second": 10.76,
"eval_steps_per_second": 1.345,
"step": 15000
},
{
"epoch": 4.8,
"learning_rate": 3.993558776167472e-06,
"loss": 0.9048,
"step": 15010
},
{
"epoch": 4.81,
"learning_rate": 3.92914653784219e-06,
"loss": 0.9295,
"step": 15020
},
{
"epoch": 4.81,
"learning_rate": 3.864734299516908e-06,
"loss": 0.9104,
"step": 15030
},
{
"epoch": 4.81,
"learning_rate": 3.8003220611916265e-06,
"loss": 0.9633,
"step": 15040
},
{
"epoch": 4.82,
"learning_rate": 3.7359098228663444e-06,
"loss": 0.9382,
"step": 15050
},
{
"epoch": 4.82,
"learning_rate": 3.671497584541063e-06,
"loss": 0.9009,
"step": 15060
},
{
"epoch": 4.82,
"learning_rate": 3.6070853462157814e-06,
"loss": 0.9157,
"step": 15070
},
{
"epoch": 4.83,
"learning_rate": 3.5426731078904992e-06,
"loss": 0.9522,
"step": 15080
},
{
"epoch": 4.83,
"learning_rate": 3.4782608695652175e-06,
"loss": 0.8791,
"step": 15090
},
{
"epoch": 4.83,
"learning_rate": 3.4138486312399362e-06,
"loss": 0.9306,
"step": 15100
},
{
"epoch": 4.83,
"learning_rate": 3.3494363929146536e-06,
"loss": 0.9234,
"step": 15110
},
{
"epoch": 4.84,
"learning_rate": 3.2850241545893724e-06,
"loss": 0.9262,
"step": 15120
},
{
"epoch": 4.84,
"learning_rate": 3.22061191626409e-06,
"loss": 0.878,
"step": 15130
},
{
"epoch": 4.84,
"learning_rate": 3.1561996779388085e-06,
"loss": 0.8833,
"step": 15140
},
{
"epoch": 4.85,
"learning_rate": 3.0917874396135268e-06,
"loss": 0.9158,
"step": 15150
},
{
"epoch": 4.85,
"learning_rate": 3.0273752012882446e-06,
"loss": 0.9675,
"step": 15160
},
{
"epoch": 4.85,
"learning_rate": 2.9629629629629633e-06,
"loss": 0.9967,
"step": 15170
},
{
"epoch": 4.86,
"learning_rate": 2.898550724637681e-06,
"loss": 0.918,
"step": 15180
},
{
"epoch": 4.86,
"learning_rate": 2.8341384863123995e-06,
"loss": 0.8854,
"step": 15190
},
{
"epoch": 4.86,
"learning_rate": 2.7697262479871177e-06,
"loss": 0.9589,
"step": 15200
},
{
"epoch": 4.86,
"eval_loss": 1.0268317461013794,
"eval_runtime": 185.8882,
"eval_samples_per_second": 10.759,
"eval_steps_per_second": 1.345,
"step": 15200
},
{
"epoch": 4.87,
"learning_rate": 2.705314009661836e-06,
"loss": 0.9624,
"step": 15210
},
{
"epoch": 4.87,
"learning_rate": 2.6409017713365543e-06,
"loss": 0.9221,
"step": 15220
},
{
"epoch": 4.87,
"learning_rate": 2.576489533011272e-06,
"loss": 0.9157,
"step": 15230
},
{
"epoch": 4.88,
"learning_rate": 2.5120772946859904e-06,
"loss": 0.9513,
"step": 15240
},
{
"epoch": 4.88,
"learning_rate": 2.4476650563607083e-06,
"loss": 0.8803,
"step": 15250
},
{
"epoch": 4.88,
"learning_rate": 2.383252818035427e-06,
"loss": 0.8862,
"step": 15260
},
{
"epoch": 4.89,
"learning_rate": 2.318840579710145e-06,
"loss": 0.8634,
"step": 15270
},
{
"epoch": 4.89,
"learning_rate": 2.254428341384863e-06,
"loss": 0.9381,
"step": 15280
},
{
"epoch": 4.89,
"learning_rate": 2.1900161030595814e-06,
"loss": 0.9557,
"step": 15290
},
{
"epoch": 4.9,
"learning_rate": 2.1256038647342997e-06,
"loss": 0.8925,
"step": 15300
},
{
"epoch": 4.9,
"learning_rate": 2.061191626409018e-06,
"loss": 0.9255,
"step": 15310
},
{
"epoch": 4.9,
"learning_rate": 1.996779388083736e-06,
"loss": 0.9385,
"step": 15320
},
{
"epoch": 4.91,
"learning_rate": 1.932367149758454e-06,
"loss": 0.9084,
"step": 15330
},
{
"epoch": 4.91,
"learning_rate": 1.8679549114331722e-06,
"loss": 0.9499,
"step": 15340
},
{
"epoch": 4.91,
"learning_rate": 1.8035426731078907e-06,
"loss": 0.8961,
"step": 15350
},
{
"epoch": 4.91,
"learning_rate": 1.7391304347826088e-06,
"loss": 0.8908,
"step": 15360
},
{
"epoch": 4.92,
"learning_rate": 1.6747181964573268e-06,
"loss": 0.9399,
"step": 15370
},
{
"epoch": 4.92,
"learning_rate": 1.610305958132045e-06,
"loss": 0.9366,
"step": 15380
},
{
"epoch": 4.92,
"learning_rate": 1.5458937198067634e-06,
"loss": 0.9091,
"step": 15390
},
{
"epoch": 4.93,
"learning_rate": 1.4814814814814817e-06,
"loss": 0.8723,
"step": 15400
},
{
"epoch": 4.93,
"eval_loss": 1.026999831199646,
"eval_runtime": 185.7802,
"eval_samples_per_second": 10.765,
"eval_steps_per_second": 1.346,
"step": 15400
}
],
"logging_steps": 10,
"max_steps": 15625,
"num_train_epochs": 5,
"save_steps": 200,
"total_flos": 3.3050645914425754e+18,
"trial_name": null,
"trial_params": null
}