FinTwitBERT / trainer_state.json
StephanAkkerman's picture
Added latest model trained on 8 million rows
7e021a6
raw
history blame
182 kB
{
"best_metric": 1.4186582565307617,
"best_model_checkpoint": "checkpoints/checkpoint-680000",
"epoch": 6.301781179915853,
"eval_steps": 10000,
"global_step": 680000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.6336626322910684e-08,
"loss": 4.4724,
"step": 500
},
{
"epoch": 0.01,
"learning_rate": 9.267325264582137e-08,
"loss": 4.3928,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 1.3900987896873205e-07,
"loss": 4.2493,
"step": 1500
},
{
"epoch": 0.02,
"learning_rate": 1.8525383203899695e-07,
"loss": 4.1189,
"step": 2000
},
{
"epoch": 0.02,
"learning_rate": 2.315904583619076e-07,
"loss": 4.008,
"step": 2500
},
{
"epoch": 0.03,
"learning_rate": 2.7792708468481826e-07,
"loss": 3.8695,
"step": 3000
},
{
"epoch": 0.03,
"learning_rate": 3.2417103775508315e-07,
"loss": 3.7698,
"step": 3500
},
{
"epoch": 0.04,
"learning_rate": 3.705076640779939e-07,
"loss": 3.6676,
"step": 4000
},
{
"epoch": 0.04,
"learning_rate": 4.168442904009045e-07,
"loss": 3.6022,
"step": 4500
},
{
"epoch": 0.05,
"learning_rate": 4.631809167238152e-07,
"loss": 3.5249,
"step": 5000
},
{
"epoch": 0.05,
"learning_rate": 5.095175430467259e-07,
"loss": 3.451,
"step": 5500
},
{
"epoch": 0.06,
"learning_rate": 5.558541693696365e-07,
"loss": 3.3994,
"step": 6000
},
{
"epoch": 0.06,
"learning_rate": 6.021907956925473e-07,
"loss": 3.3329,
"step": 6500
},
{
"epoch": 0.06,
"learning_rate": 6.485274220154579e-07,
"loss": 3.3009,
"step": 7000
},
{
"epoch": 0.07,
"learning_rate": 6.948640483383686e-07,
"loss": 3.2577,
"step": 7500
},
{
"epoch": 0.07,
"learning_rate": 7.412006746612794e-07,
"loss": 3.2323,
"step": 8000
},
{
"epoch": 0.08,
"learning_rate": 7.8753730098419e-07,
"loss": 3.1938,
"step": 8500
},
{
"epoch": 0.08,
"learning_rate": 8.337812540544548e-07,
"loss": 3.1491,
"step": 9000
},
{
"epoch": 0.09,
"learning_rate": 8.801178803773655e-07,
"loss": 3.1187,
"step": 9500
},
{
"epoch": 0.09,
"learning_rate": 9.264545067002763e-07,
"loss": 3.0981,
"step": 10000
},
{
"epoch": 0.09,
"eval_loss": 2.981156349182129,
"eval_runtime": 1994.106,
"eval_samples_per_second": 384.799,
"eval_steps_per_second": 6.013,
"step": 10000
},
{
"epoch": 0.1,
"learning_rate": 9.727911330231868e-07,
"loss": 3.0697,
"step": 10500
},
{
"epoch": 0.1,
"learning_rate": 1.0190350860934518e-06,
"loss": 3.051,
"step": 11000
},
{
"epoch": 0.11,
"learning_rate": 1.0653717124163625e-06,
"loss": 3.0217,
"step": 11500
},
{
"epoch": 0.11,
"learning_rate": 1.111708338739273e-06,
"loss": 2.9877,
"step": 12000
},
{
"epoch": 0.12,
"learning_rate": 1.158044965062184e-06,
"loss": 2.9813,
"step": 12500
},
{
"epoch": 0.12,
"learning_rate": 1.2043815913850945e-06,
"loss": 2.9579,
"step": 13000
},
{
"epoch": 0.13,
"learning_rate": 1.2507182177080053e-06,
"loss": 2.9291,
"step": 13500
},
{
"epoch": 0.13,
"learning_rate": 1.29696217077827e-06,
"loss": 2.9017,
"step": 14000
},
{
"epoch": 0.13,
"learning_rate": 1.343206123848535e-06,
"loss": 2.8966,
"step": 14500
},
{
"epoch": 0.14,
"learning_rate": 1.3895427501714457e-06,
"loss": 2.8773,
"step": 15000
},
{
"epoch": 0.14,
"learning_rate": 1.4358793764943562e-06,
"loss": 2.8355,
"step": 15500
},
{
"epoch": 0.15,
"learning_rate": 1.482216002817267e-06,
"loss": 2.8121,
"step": 16000
},
{
"epoch": 0.15,
"learning_rate": 1.5285526291401779e-06,
"loss": 2.8013,
"step": 16500
},
{
"epoch": 0.16,
"learning_rate": 1.5748892554630884e-06,
"loss": 2.8018,
"step": 17000
},
{
"epoch": 0.16,
"learning_rate": 1.6212258817859991e-06,
"loss": 2.7618,
"step": 17500
},
{
"epoch": 0.17,
"learning_rate": 1.6675625081089097e-06,
"loss": 2.7622,
"step": 18000
},
{
"epoch": 0.17,
"learning_rate": 1.7138991344318204e-06,
"loss": 2.7396,
"step": 18500
},
{
"epoch": 0.18,
"learning_rate": 1.760235760754731e-06,
"loss": 2.7417,
"step": 19000
},
{
"epoch": 0.18,
"learning_rate": 1.8065723870776419e-06,
"loss": 2.7226,
"step": 19500
},
{
"epoch": 0.19,
"learning_rate": 1.8529090134005526e-06,
"loss": 2.6954,
"step": 20000
},
{
"epoch": 0.19,
"eval_loss": 2.601823091506958,
"eval_runtime": 1994.2728,
"eval_samples_per_second": 384.767,
"eval_steps_per_second": 6.012,
"step": 20000
},
{
"epoch": 0.19,
"learning_rate": 1.8991529664708176e-06,
"loss": 2.6976,
"step": 20500
},
{
"epoch": 0.19,
"learning_rate": 1.945489592793728e-06,
"loss": 2.6626,
"step": 21000
},
{
"epoch": 0.2,
"learning_rate": 1.9918262191166386e-06,
"loss": 2.6702,
"step": 21500
},
{
"epoch": 0.2,
"learning_rate": 2.0381628454395496e-06,
"loss": 2.6601,
"step": 22000
},
{
"epoch": 0.21,
"learning_rate": 2.08449947176246e-06,
"loss": 2.6294,
"step": 22500
},
{
"epoch": 0.21,
"learning_rate": 2.1308360980853706e-06,
"loss": 2.6219,
"step": 23000
},
{
"epoch": 0.22,
"learning_rate": 2.1770800511556356e-06,
"loss": 2.6089,
"step": 23500
},
{
"epoch": 0.22,
"learning_rate": 2.223416677478546e-06,
"loss": 2.5921,
"step": 24000
},
{
"epoch": 0.23,
"learning_rate": 2.269753303801457e-06,
"loss": 2.6006,
"step": 24500
},
{
"epoch": 0.23,
"learning_rate": 2.316089930124368e-06,
"loss": 2.5975,
"step": 25000
},
{
"epoch": 0.24,
"learning_rate": 2.3624265564472785e-06,
"loss": 2.5739,
"step": 25500
},
{
"epoch": 0.24,
"learning_rate": 2.4086705095175435e-06,
"loss": 2.5605,
"step": 26000
},
{
"epoch": 0.25,
"learning_rate": 2.455007135840454e-06,
"loss": 2.5515,
"step": 26500
},
{
"epoch": 0.25,
"learning_rate": 2.5013437621633645e-06,
"loss": 2.5337,
"step": 27000
},
{
"epoch": 0.25,
"learning_rate": 2.5476803884862755e-06,
"loss": 2.5397,
"step": 27500
},
{
"epoch": 0.26,
"learning_rate": 2.594017014809186e-06,
"loss": 2.5208,
"step": 28000
},
{
"epoch": 0.26,
"learning_rate": 2.640353641132097e-06,
"loss": 2.5116,
"step": 28500
},
{
"epoch": 0.27,
"learning_rate": 2.686690267455007e-06,
"loss": 2.5145,
"step": 29000
},
{
"epoch": 0.27,
"learning_rate": 2.733026893777918e-06,
"loss": 2.5016,
"step": 29500
},
{
"epoch": 0.28,
"learning_rate": 2.7792708468481825e-06,
"loss": 2.4901,
"step": 30000
},
{
"epoch": 0.28,
"eval_loss": 2.3954684734344482,
"eval_runtime": 1994.0444,
"eval_samples_per_second": 384.811,
"eval_steps_per_second": 6.013,
"step": 30000
},
{
"epoch": 0.28,
"learning_rate": 2.8256074731710935e-06,
"loss": 2.4757,
"step": 30500
},
{
"epoch": 0.29,
"learning_rate": 2.8718514262413584e-06,
"loss": 2.4778,
"step": 31000
},
{
"epoch": 0.29,
"learning_rate": 2.9181880525642693e-06,
"loss": 2.4868,
"step": 31500
},
{
"epoch": 0.3,
"learning_rate": 2.9645246788871803e-06,
"loss": 2.4565,
"step": 32000
},
{
"epoch": 0.3,
"learning_rate": 3.0108613052100904e-06,
"loss": 2.4482,
"step": 32500
},
{
"epoch": 0.31,
"learning_rate": 3.0571979315330013e-06,
"loss": 2.4431,
"step": 33000
},
{
"epoch": 0.31,
"learning_rate": 3.103534557855912e-06,
"loss": 2.4353,
"step": 33500
},
{
"epoch": 0.32,
"learning_rate": 3.149871184178823e-06,
"loss": 2.4286,
"step": 34000
},
{
"epoch": 0.32,
"learning_rate": 3.196207810501733e-06,
"loss": 2.4332,
"step": 34500
},
{
"epoch": 0.32,
"learning_rate": 3.2424517635719983e-06,
"loss": 2.4146,
"step": 35000
},
{
"epoch": 0.33,
"learning_rate": 3.288695716642263e-06,
"loss": 2.4008,
"step": 35500
},
{
"epoch": 0.33,
"learning_rate": 3.334939669712528e-06,
"loss": 2.411,
"step": 36000
},
{
"epoch": 0.34,
"learning_rate": 3.3812762960354383e-06,
"loss": 2.3848,
"step": 36500
},
{
"epoch": 0.34,
"learning_rate": 3.4276129223583492e-06,
"loss": 2.388,
"step": 37000
},
{
"epoch": 0.35,
"learning_rate": 3.4739495486812598e-06,
"loss": 2.384,
"step": 37500
},
{
"epoch": 0.35,
"learning_rate": 3.5202861750041707e-06,
"loss": 2.3743,
"step": 38000
},
{
"epoch": 0.36,
"learning_rate": 3.5666228013270817e-06,
"loss": 2.3734,
"step": 38500
},
{
"epoch": 0.36,
"learning_rate": 3.6129594276499918e-06,
"loss": 2.3695,
"step": 39000
},
{
"epoch": 0.37,
"learning_rate": 3.6592960539729027e-06,
"loss": 2.3352,
"step": 39500
},
{
"epoch": 0.37,
"learning_rate": 3.7056326802958132e-06,
"loss": 2.3453,
"step": 40000
},
{
"epoch": 0.37,
"eval_loss": 2.262512683868408,
"eval_runtime": 1997.4067,
"eval_samples_per_second": 384.163,
"eval_steps_per_second": 6.003,
"step": 40000
},
{
"epoch": 0.38,
"learning_rate": 3.751969306618724e-06,
"loss": 2.342,
"step": 40500
},
{
"epoch": 0.38,
"learning_rate": 3.7982132596889887e-06,
"loss": 2.3493,
"step": 41000
},
{
"epoch": 0.38,
"learning_rate": 3.844549886011899e-06,
"loss": 2.3199,
"step": 41500
},
{
"epoch": 0.39,
"learning_rate": 3.890886512334811e-06,
"loss": 2.3347,
"step": 42000
},
{
"epoch": 0.39,
"learning_rate": 3.937223138657721e-06,
"loss": 2.3212,
"step": 42500
},
{
"epoch": 0.4,
"learning_rate": 3.983559764980632e-06,
"loss": 2.3209,
"step": 43000
},
{
"epoch": 0.4,
"learning_rate": 4.029896391303542e-06,
"loss": 2.3026,
"step": 43500
},
{
"epoch": 0.41,
"learning_rate": 4.076233017626453e-06,
"loss": 2.3117,
"step": 44000
},
{
"epoch": 0.41,
"learning_rate": 4.122569643949363e-06,
"loss": 2.291,
"step": 44500
},
{
"epoch": 0.42,
"learning_rate": 4.168906270272275e-06,
"loss": 2.2732,
"step": 45000
},
{
"epoch": 0.42,
"learning_rate": 4.215150223342539e-06,
"loss": 2.3052,
"step": 45500
},
{
"epoch": 0.43,
"learning_rate": 4.26148684966545e-06,
"loss": 2.2713,
"step": 46000
},
{
"epoch": 0.43,
"learning_rate": 4.307823475988361e-06,
"loss": 2.2813,
"step": 46500
},
{
"epoch": 0.44,
"learning_rate": 4.354160102311271e-06,
"loss": 2.2726,
"step": 47000
},
{
"epoch": 0.44,
"learning_rate": 4.4004967286341825e-06,
"loss": 2.2812,
"step": 47500
},
{
"epoch": 0.44,
"learning_rate": 4.446648008451801e-06,
"loss": 2.2894,
"step": 48000
},
{
"epoch": 0.45,
"learning_rate": 4.4929846347747115e-06,
"loss": 2.2653,
"step": 48500
},
{
"epoch": 0.45,
"learning_rate": 4.539321261097622e-06,
"loss": 2.2515,
"step": 49000
},
{
"epoch": 0.46,
"learning_rate": 4.5856578874205334e-06,
"loss": 2.2578,
"step": 49500
},
{
"epoch": 0.46,
"learning_rate": 4.631994513743444e-06,
"loss": 2.2392,
"step": 50000
},
{
"epoch": 0.46,
"eval_loss": 2.1643872261047363,
"eval_runtime": 1997.1399,
"eval_samples_per_second": 384.214,
"eval_steps_per_second": 6.004,
"step": 50000
},
{
"epoch": 0.47,
"learning_rate": 4.678238466813709e-06,
"loss": 2.2325,
"step": 50500
},
{
"epoch": 0.47,
"learning_rate": 4.7245750931366194e-06,
"loss": 2.233,
"step": 51000
},
{
"epoch": 0.48,
"learning_rate": 4.77091171945953e-06,
"loss": 2.2374,
"step": 51500
},
{
"epoch": 0.48,
"learning_rate": 4.817248345782441e-06,
"loss": 2.2188,
"step": 52000
},
{
"epoch": 0.49,
"learning_rate": 4.863584972105351e-06,
"loss": 2.2198,
"step": 52500
},
{
"epoch": 0.49,
"learning_rate": 4.909921598428262e-06,
"loss": 2.2292,
"step": 53000
},
{
"epoch": 0.5,
"learning_rate": 4.956258224751173e-06,
"loss": 2.218,
"step": 53500
},
{
"epoch": 0.5,
"learning_rate": 5.002594851074083e-06,
"loss": 2.2159,
"step": 54000
},
{
"epoch": 0.51,
"learning_rate": 5.048746130891703e-06,
"loss": 2.2142,
"step": 54500
},
{
"epoch": 0.51,
"learning_rate": 5.095082757214613e-06,
"loss": 2.2211,
"step": 55000
},
{
"epoch": 0.51,
"learning_rate": 5.141419383537524e-06,
"loss": 2.1972,
"step": 55500
},
{
"epoch": 0.52,
"learning_rate": 5.187756009860434e-06,
"loss": 2.1956,
"step": 56000
},
{
"epoch": 0.52,
"learning_rate": 5.234092636183346e-06,
"loss": 2.1833,
"step": 56500
},
{
"epoch": 0.53,
"learning_rate": 5.280429262506256e-06,
"loss": 2.1818,
"step": 57000
},
{
"epoch": 0.53,
"learning_rate": 5.326765888829166e-06,
"loss": 2.1961,
"step": 57500
},
{
"epoch": 0.54,
"learning_rate": 5.373102515152077e-06,
"loss": 2.1875,
"step": 58000
},
{
"epoch": 0.54,
"learning_rate": 5.4193464682223414e-06,
"loss": 2.1851,
"step": 58500
},
{
"epoch": 0.55,
"learning_rate": 5.465683094545254e-06,
"loss": 2.1834,
"step": 59000
},
{
"epoch": 0.55,
"learning_rate": 5.512019720868163e-06,
"loss": 2.1759,
"step": 59500
},
{
"epoch": 0.56,
"learning_rate": 5.558356347191074e-06,
"loss": 2.158,
"step": 60000
},
{
"epoch": 0.56,
"eval_loss": 2.090520143508911,
"eval_runtime": 2000.9702,
"eval_samples_per_second": 383.479,
"eval_steps_per_second": 5.992,
"step": 60000
},
{
"epoch": 0.56,
"learning_rate": 5.604600300261339e-06,
"loss": 2.1782,
"step": 60500
},
{
"epoch": 0.57,
"learning_rate": 5.650936926584249e-06,
"loss": 2.1657,
"step": 61000
},
{
"epoch": 0.57,
"learning_rate": 5.697180879654515e-06,
"loss": 2.1559,
"step": 61500
},
{
"epoch": 0.57,
"learning_rate": 5.74342483272478e-06,
"loss": 2.1557,
"step": 62000
},
{
"epoch": 0.58,
"learning_rate": 5.789761459047691e-06,
"loss": 2.15,
"step": 62500
},
{
"epoch": 0.58,
"learning_rate": 5.8360980853706e-06,
"loss": 2.1713,
"step": 63000
},
{
"epoch": 0.59,
"learning_rate": 5.882434711693511e-06,
"loss": 2.1441,
"step": 63500
},
{
"epoch": 0.59,
"learning_rate": 5.928771338016422e-06,
"loss": 2.1607,
"step": 64000
},
{
"epoch": 0.6,
"learning_rate": 5.975107964339333e-06,
"loss": 2.1482,
"step": 64500
},
{
"epoch": 0.6,
"learning_rate": 6.021444590662243e-06,
"loss": 2.1515,
"step": 65000
},
{
"epoch": 0.61,
"learning_rate": 6.067781216985155e-06,
"loss": 2.1504,
"step": 65500
},
{
"epoch": 0.61,
"learning_rate": 6.114117843308065e-06,
"loss": 2.1322,
"step": 66000
},
{
"epoch": 0.62,
"learning_rate": 6.160454469630976e-06,
"loss": 2.1258,
"step": 66500
},
{
"epoch": 0.62,
"learning_rate": 6.206698422701241e-06,
"loss": 2.1202,
"step": 67000
},
{
"epoch": 0.63,
"learning_rate": 6.253035049024151e-06,
"loss": 2.1242,
"step": 67500
},
{
"epoch": 0.63,
"learning_rate": 6.2993716753470625e-06,
"loss": 2.1173,
"step": 68000
},
{
"epoch": 0.63,
"learning_rate": 6.345708301669973e-06,
"loss": 2.1158,
"step": 68500
},
{
"epoch": 0.64,
"learning_rate": 6.391952254740238e-06,
"loss": 2.114,
"step": 69000
},
{
"epoch": 0.64,
"learning_rate": 6.4382888810631485e-06,
"loss": 2.1166,
"step": 69500
},
{
"epoch": 0.65,
"learning_rate": 6.484625507386059e-06,
"loss": 2.1172,
"step": 70000
},
{
"epoch": 0.65,
"eval_loss": 2.0241761207580566,
"eval_runtime": 1997.8511,
"eval_samples_per_second": 384.078,
"eval_steps_per_second": 6.001,
"step": 70000
},
{
"epoch": 0.65,
"learning_rate": 6.530962133708969e-06,
"loss": 2.1135,
"step": 70500
},
{
"epoch": 0.66,
"learning_rate": 6.577298760031881e-06,
"loss": 2.094,
"step": 71000
},
{
"epoch": 0.66,
"learning_rate": 6.623635386354791e-06,
"loss": 2.1162,
"step": 71500
},
{
"epoch": 0.67,
"learning_rate": 6.669879339425056e-06,
"loss": 2.097,
"step": 72000
},
{
"epoch": 0.67,
"learning_rate": 6.716215965747966e-06,
"loss": 2.0942,
"step": 72500
},
{
"epoch": 0.68,
"learning_rate": 6.7625525920708766e-06,
"loss": 2.0892,
"step": 73000
},
{
"epoch": 0.68,
"learning_rate": 6.808889218393788e-06,
"loss": 2.0964,
"step": 73500
},
{
"epoch": 0.69,
"learning_rate": 6.8552258447166985e-06,
"loss": 2.1009,
"step": 74000
},
{
"epoch": 0.69,
"learning_rate": 6.901469797786963e-06,
"loss": 2.1051,
"step": 74500
},
{
"epoch": 0.7,
"learning_rate": 6.947806424109874e-06,
"loss": 2.0832,
"step": 75000
},
{
"epoch": 0.7,
"learning_rate": 6.9941430504327845e-06,
"loss": 2.088,
"step": 75500
},
{
"epoch": 0.7,
"learning_rate": 7.040479676755695e-06,
"loss": 2.0743,
"step": 76000
},
{
"epoch": 0.71,
"learning_rate": 7.08672362982596e-06,
"loss": 2.0768,
"step": 76500
},
{
"epoch": 0.71,
"learning_rate": 7.1330602561488705e-06,
"loss": 2.0736,
"step": 77000
},
{
"epoch": 0.72,
"learning_rate": 7.179396882471782e-06,
"loss": 2.0731,
"step": 77500
},
{
"epoch": 0.72,
"learning_rate": 7.225733508794692e-06,
"loss": 2.0604,
"step": 78000
},
{
"epoch": 0.73,
"learning_rate": 7.272070135117603e-06,
"loss": 2.0629,
"step": 78500
},
{
"epoch": 0.73,
"learning_rate": 7.318406761440514e-06,
"loss": 2.0601,
"step": 79000
},
{
"epoch": 0.74,
"learning_rate": 7.364743387763425e-06,
"loss": 2.0651,
"step": 79500
},
{
"epoch": 0.74,
"learning_rate": 7.4110800140863345e-06,
"loss": 2.0408,
"step": 80000
},
{
"epoch": 0.74,
"eval_loss": 1.971598744392395,
"eval_runtime": 2000.1671,
"eval_samples_per_second": 383.633,
"eval_steps_per_second": 5.994,
"step": 80000
},
{
"epoch": 0.75,
"learning_rate": 7.4573239671566e-06,
"loss": 2.0527,
"step": 80500
},
{
"epoch": 0.75,
"learning_rate": 7.503660593479511e-06,
"loss": 2.0667,
"step": 81000
},
{
"epoch": 0.76,
"learning_rate": 7.5499972198024205e-06,
"loss": 2.0587,
"step": 81500
},
{
"epoch": 0.76,
"learning_rate": 7.596333846125332e-06,
"loss": 2.031,
"step": 82000
},
{
"epoch": 0.76,
"learning_rate": 7.642670472448242e-06,
"loss": 2.0521,
"step": 82500
},
{
"epoch": 0.77,
"learning_rate": 7.688914425518507e-06,
"loss": 2.0273,
"step": 83000
},
{
"epoch": 0.77,
"learning_rate": 7.735251051841418e-06,
"loss": 2.0268,
"step": 83500
},
{
"epoch": 0.78,
"learning_rate": 7.781587678164328e-06,
"loss": 2.034,
"step": 84000
},
{
"epoch": 0.78,
"learning_rate": 7.82792430448724e-06,
"loss": 2.0375,
"step": 84500
},
{
"epoch": 0.79,
"learning_rate": 7.874260930810151e-06,
"loss": 2.0289,
"step": 85000
},
{
"epoch": 0.79,
"learning_rate": 7.920504883880416e-06,
"loss": 2.0229,
"step": 85500
},
{
"epoch": 0.8,
"learning_rate": 7.966841510203327e-06,
"loss": 2.0106,
"step": 86000
},
{
"epoch": 0.8,
"learning_rate": 8.013178136526235e-06,
"loss": 2.0004,
"step": 86500
},
{
"epoch": 0.81,
"learning_rate": 8.059514762849148e-06,
"loss": 2.0236,
"step": 87000
},
{
"epoch": 0.81,
"learning_rate": 8.105851389172058e-06,
"loss": 2.0163,
"step": 87500
},
{
"epoch": 0.82,
"learning_rate": 8.152188015494969e-06,
"loss": 2.0182,
"step": 88000
},
{
"epoch": 0.82,
"learning_rate": 8.19852464181788e-06,
"loss": 2.004,
"step": 88500
},
{
"epoch": 0.82,
"learning_rate": 8.24486126814079e-06,
"loss": 1.9984,
"step": 89000
},
{
"epoch": 0.83,
"learning_rate": 8.291105221211055e-06,
"loss": 2.0159,
"step": 89500
},
{
"epoch": 0.83,
"learning_rate": 8.33734917428132e-06,
"loss": 2.0023,
"step": 90000
},
{
"epoch": 0.83,
"eval_loss": 1.929675817489624,
"eval_runtime": 1996.5508,
"eval_samples_per_second": 384.328,
"eval_steps_per_second": 6.005,
"step": 90000
},
{
"epoch": 0.84,
"learning_rate": 8.38368580060423e-06,
"loss": 2.0087,
"step": 90500
},
{
"epoch": 0.84,
"learning_rate": 8.43002242692714e-06,
"loss": 1.9971,
"step": 91000
},
{
"epoch": 0.85,
"learning_rate": 8.476359053250051e-06,
"loss": 2.002,
"step": 91500
},
{
"epoch": 0.85,
"learning_rate": 8.522695679572962e-06,
"loss": 2.0124,
"step": 92000
},
{
"epoch": 0.86,
"learning_rate": 8.569032305895874e-06,
"loss": 1.988,
"step": 92500
},
{
"epoch": 0.86,
"learning_rate": 8.615276258966137e-06,
"loss": 1.9868,
"step": 93000
},
{
"epoch": 0.87,
"learning_rate": 8.66161288528905e-06,
"loss": 1.9977,
"step": 93500
},
{
"epoch": 0.87,
"learning_rate": 8.70794951161196e-06,
"loss": 1.991,
"step": 94000
},
{
"epoch": 0.88,
"learning_rate": 8.75428613793487e-06,
"loss": 1.994,
"step": 94500
},
{
"epoch": 0.88,
"learning_rate": 8.800622764257781e-06,
"loss": 1.9881,
"step": 95000
},
{
"epoch": 0.89,
"learning_rate": 8.846866717328046e-06,
"loss": 1.9797,
"step": 95500
},
{
"epoch": 0.89,
"learning_rate": 8.893203343650956e-06,
"loss": 1.99,
"step": 96000
},
{
"epoch": 0.89,
"learning_rate": 8.939447296721221e-06,
"loss": 1.9877,
"step": 96500
},
{
"epoch": 0.9,
"learning_rate": 8.985783923044132e-06,
"loss": 1.9802,
"step": 97000
},
{
"epoch": 0.9,
"learning_rate": 9.032120549367042e-06,
"loss": 1.9736,
"step": 97500
},
{
"epoch": 0.91,
"learning_rate": 9.078457175689953e-06,
"loss": 1.9711,
"step": 98000
},
{
"epoch": 0.91,
"learning_rate": 9.124793802012864e-06,
"loss": 1.9787,
"step": 98500
},
{
"epoch": 0.92,
"learning_rate": 9.171130428335776e-06,
"loss": 1.9906,
"step": 99000
},
{
"epoch": 0.92,
"learning_rate": 9.217467054658685e-06,
"loss": 1.9624,
"step": 99500
},
{
"epoch": 0.93,
"learning_rate": 9.263803680981595e-06,
"loss": 1.9813,
"step": 100000
},
{
"epoch": 0.93,
"eval_loss": 1.8921247720718384,
"eval_runtime": 1996.249,
"eval_samples_per_second": 384.386,
"eval_steps_per_second": 6.006,
"step": 100000
},
{
"epoch": 0.93,
"learning_rate": 9.310140307304506e-06,
"loss": 1.9625,
"step": 100500
},
{
"epoch": 0.94,
"learning_rate": 9.356476933627418e-06,
"loss": 1.9669,
"step": 101000
},
{
"epoch": 0.94,
"learning_rate": 9.402813559950328e-06,
"loss": 1.9549,
"step": 101500
},
{
"epoch": 0.95,
"learning_rate": 9.449150186273239e-06,
"loss": 1.9611,
"step": 102000
},
{
"epoch": 0.95,
"learning_rate": 9.49548681259615e-06,
"loss": 1.9778,
"step": 102500
},
{
"epoch": 0.95,
"learning_rate": 9.54182343891906e-06,
"loss": 1.9671,
"step": 103000
},
{
"epoch": 0.96,
"learning_rate": 9.588067391989325e-06,
"loss": 1.9659,
"step": 103500
},
{
"epoch": 0.96,
"learning_rate": 9.634404018312235e-06,
"loss": 1.9483,
"step": 104000
},
{
"epoch": 0.97,
"learning_rate": 9.680740644635146e-06,
"loss": 1.9568,
"step": 104500
},
{
"epoch": 0.97,
"learning_rate": 9.727077270958058e-06,
"loss": 1.9614,
"step": 105000
},
{
"epoch": 0.98,
"learning_rate": 9.773413897280967e-06,
"loss": 1.9544,
"step": 105500
},
{
"epoch": 0.98,
"learning_rate": 9.819750523603878e-06,
"loss": 1.9554,
"step": 106000
},
{
"epoch": 0.99,
"learning_rate": 9.866087149926788e-06,
"loss": 1.9518,
"step": 106500
},
{
"epoch": 0.99,
"learning_rate": 9.9124237762497e-06,
"loss": 1.9448,
"step": 107000
},
{
"epoch": 1.0,
"learning_rate": 9.958667729319963e-06,
"loss": 1.9569,
"step": 107500
},
{
"epoch": 1.0,
"learning_rate": 1.0005004355642876e-05,
"loss": 1.9459,
"step": 108000
},
{
"epoch": 1.01,
"learning_rate": 1.0051340981965785e-05,
"loss": 1.9293,
"step": 108500
},
{
"epoch": 1.01,
"learning_rate": 1.0097584935036051e-05,
"loss": 1.9362,
"step": 109000
},
{
"epoch": 1.01,
"learning_rate": 1.014392156135896e-05,
"loss": 1.9315,
"step": 109500
},
{
"epoch": 1.02,
"learning_rate": 1.0190165514429227e-05,
"loss": 1.9296,
"step": 110000
},
{
"epoch": 1.02,
"eval_loss": 1.8574298620224,
"eval_runtime": 1996.3161,
"eval_samples_per_second": 384.373,
"eval_steps_per_second": 6.006,
"step": 110000
},
{
"epoch": 1.02,
"learning_rate": 1.0236502140752135e-05,
"loss": 1.9272,
"step": 110500
},
{
"epoch": 1.03,
"learning_rate": 1.0282838767075048e-05,
"loss": 1.9293,
"step": 111000
},
{
"epoch": 1.03,
"learning_rate": 1.0329175393397958e-05,
"loss": 1.9249,
"step": 111500
},
{
"epoch": 1.04,
"learning_rate": 1.0375512019720869e-05,
"loss": 1.9238,
"step": 112000
},
{
"epoch": 1.04,
"learning_rate": 1.042184864604378e-05,
"loss": 1.9118,
"step": 112500
},
{
"epoch": 1.05,
"learning_rate": 1.0468185272366692e-05,
"loss": 1.9259,
"step": 113000
},
{
"epoch": 1.05,
"learning_rate": 1.0514429225436955e-05,
"loss": 1.9308,
"step": 113500
},
{
"epoch": 1.06,
"learning_rate": 1.0560765851759867e-05,
"loss": 1.9365,
"step": 114000
},
{
"epoch": 1.06,
"learning_rate": 1.0607102478082776e-05,
"loss": 1.9232,
"step": 114500
},
{
"epoch": 1.07,
"learning_rate": 1.0653439104405688e-05,
"loss": 1.9329,
"step": 115000
},
{
"epoch": 1.07,
"learning_rate": 1.0699775730728599e-05,
"loss": 1.915,
"step": 115500
},
{
"epoch": 1.08,
"learning_rate": 1.0746112357051507e-05,
"loss": 1.911,
"step": 116000
},
{
"epoch": 1.08,
"learning_rate": 1.079244898337442e-05,
"loss": 1.9226,
"step": 116500
},
{
"epoch": 1.08,
"learning_rate": 1.083878560969733e-05,
"loss": 1.9158,
"step": 117000
},
{
"epoch": 1.09,
"learning_rate": 1.088512223602024e-05,
"loss": 1.9064,
"step": 117500
},
{
"epoch": 1.09,
"learning_rate": 1.0931366189090507e-05,
"loss": 1.8931,
"step": 118000
},
{
"epoch": 1.1,
"learning_rate": 1.0977702815413416e-05,
"loss": 1.9101,
"step": 118500
},
{
"epoch": 1.1,
"learning_rate": 1.1023946768483683e-05,
"loss": 1.9017,
"step": 119000
},
{
"epoch": 1.11,
"learning_rate": 1.1070283394806592e-05,
"loss": 1.9065,
"step": 119500
},
{
"epoch": 1.11,
"learning_rate": 1.1116620021129502e-05,
"loss": 1.8988,
"step": 120000
},
{
"epoch": 1.11,
"eval_loss": 1.82962965965271,
"eval_runtime": 1996.8658,
"eval_samples_per_second": 384.267,
"eval_steps_per_second": 6.004,
"step": 120000
},
{
"epoch": 1.12,
"learning_rate": 1.1162956647452414e-05,
"loss": 1.8876,
"step": 120500
},
{
"epoch": 1.12,
"learning_rate": 1.1209293273775323e-05,
"loss": 1.8863,
"step": 121000
},
{
"epoch": 1.13,
"learning_rate": 1.1255629900098235e-05,
"loss": 1.9032,
"step": 121500
},
{
"epoch": 1.13,
"learning_rate": 1.1301966526421144e-05,
"loss": 1.8953,
"step": 122000
},
{
"epoch": 1.14,
"learning_rate": 1.1348303152744056e-05,
"loss": 1.9121,
"step": 122500
},
{
"epoch": 1.14,
"learning_rate": 1.1394639779066967e-05,
"loss": 1.8789,
"step": 123000
},
{
"epoch": 1.14,
"learning_rate": 1.1440883732137232e-05,
"loss": 1.9,
"step": 123500
},
{
"epoch": 1.15,
"learning_rate": 1.1487220358460142e-05,
"loss": 1.9142,
"step": 124000
},
{
"epoch": 1.15,
"learning_rate": 1.1533556984783051e-05,
"loss": 1.8923,
"step": 124500
},
{
"epoch": 1.16,
"learning_rate": 1.1579893611105963e-05,
"loss": 1.8924,
"step": 125000
},
{
"epoch": 1.16,
"learning_rate": 1.1626230237428876e-05,
"loss": 1.8799,
"step": 125500
},
{
"epoch": 1.17,
"learning_rate": 1.1672474190499139e-05,
"loss": 1.9024,
"step": 126000
},
{
"epoch": 1.17,
"learning_rate": 1.1718810816822051e-05,
"loss": 1.8829,
"step": 126500
},
{
"epoch": 1.18,
"learning_rate": 1.176514744314496e-05,
"loss": 1.8899,
"step": 127000
},
{
"epoch": 1.18,
"learning_rate": 1.181148406946787e-05,
"loss": 1.8889,
"step": 127500
},
{
"epoch": 1.19,
"learning_rate": 1.1857820695790783e-05,
"loss": 1.8689,
"step": 128000
},
{
"epoch": 1.19,
"learning_rate": 1.1904157322113692e-05,
"loss": 1.8771,
"step": 128500
},
{
"epoch": 1.2,
"learning_rate": 1.1950493948436604e-05,
"loss": 1.878,
"step": 129000
},
{
"epoch": 1.2,
"learning_rate": 1.1996737901506867e-05,
"loss": 1.87,
"step": 129500
},
{
"epoch": 1.2,
"learning_rate": 1.204307452782978e-05,
"loss": 1.8782,
"step": 130000
},
{
"epoch": 1.2,
"eval_loss": 1.8040884733200073,
"eval_runtime": 1998.185,
"eval_samples_per_second": 384.013,
"eval_steps_per_second": 6.0,
"step": 130000
},
{
"epoch": 1.21,
"learning_rate": 1.208941115415269e-05,
"loss": 1.8846,
"step": 130500
},
{
"epoch": 1.21,
"learning_rate": 1.21357477804756e-05,
"loss": 1.8777,
"step": 131000
},
{
"epoch": 1.22,
"learning_rate": 1.2182084406798511e-05,
"loss": 1.864,
"step": 131500
},
{
"epoch": 1.22,
"learning_rate": 1.2228421033121423e-05,
"loss": 1.8863,
"step": 132000
},
{
"epoch": 1.23,
"learning_rate": 1.2274757659444332e-05,
"loss": 1.8696,
"step": 132500
},
{
"epoch": 1.23,
"learning_rate": 1.2321001612514599e-05,
"loss": 1.8779,
"step": 133000
},
{
"epoch": 1.24,
"learning_rate": 1.2367338238837507e-05,
"loss": 1.8691,
"step": 133500
},
{
"epoch": 1.24,
"learning_rate": 1.241367486516042e-05,
"loss": 1.8591,
"step": 134000
},
{
"epoch": 1.25,
"learning_rate": 1.2460011491483328e-05,
"loss": 1.8745,
"step": 134500
},
{
"epoch": 1.25,
"learning_rate": 1.2506348117806239e-05,
"loss": 1.862,
"step": 135000
},
{
"epoch": 1.26,
"learning_rate": 1.2552592070876504e-05,
"loss": 1.8724,
"step": 135500
},
{
"epoch": 1.26,
"learning_rate": 1.2598928697199414e-05,
"loss": 1.8419,
"step": 136000
},
{
"epoch": 1.26,
"learning_rate": 1.2645265323522327e-05,
"loss": 1.8655,
"step": 136500
},
{
"epoch": 1.27,
"learning_rate": 1.2691601949845235e-05,
"loss": 1.8508,
"step": 137000
},
{
"epoch": 1.27,
"learning_rate": 1.2737938576168148e-05,
"loss": 1.8545,
"step": 137500
},
{
"epoch": 1.28,
"learning_rate": 1.2784275202491058e-05,
"loss": 1.8548,
"step": 138000
},
{
"epoch": 1.28,
"learning_rate": 1.2830519155561323e-05,
"loss": 1.8709,
"step": 138500
},
{
"epoch": 1.29,
"learning_rate": 1.2876763108631586e-05,
"loss": 1.8505,
"step": 139000
},
{
"epoch": 1.29,
"learning_rate": 1.2923099734954499e-05,
"loss": 1.8545,
"step": 139500
},
{
"epoch": 1.3,
"learning_rate": 1.296943636127741e-05,
"loss": 1.8615,
"step": 140000
},
{
"epoch": 1.3,
"eval_loss": 1.7783693075180054,
"eval_runtime": 2000.1733,
"eval_samples_per_second": 383.632,
"eval_steps_per_second": 5.994,
"step": 140000
},
{
"epoch": 1.3,
"learning_rate": 1.301577298760032e-05,
"loss": 1.8708,
"step": 140500
},
{
"epoch": 1.31,
"learning_rate": 1.306210961392323e-05,
"loss": 1.8444,
"step": 141000
},
{
"epoch": 1.31,
"learning_rate": 1.3108446240246142e-05,
"loss": 1.8495,
"step": 141500
},
{
"epoch": 1.32,
"learning_rate": 1.3154782866569051e-05,
"loss": 1.8504,
"step": 142000
},
{
"epoch": 1.32,
"learning_rate": 1.3201119492891963e-05,
"loss": 1.854,
"step": 142500
},
{
"epoch": 1.33,
"learning_rate": 1.3247363445962227e-05,
"loss": 1.866,
"step": 143000
},
{
"epoch": 1.33,
"learning_rate": 1.3293700072285139e-05,
"loss": 1.8604,
"step": 143500
},
{
"epoch": 1.33,
"learning_rate": 1.3339944025355402e-05,
"loss": 1.845,
"step": 144000
},
{
"epoch": 1.34,
"learning_rate": 1.3386280651678314e-05,
"loss": 1.8431,
"step": 144500
},
{
"epoch": 1.34,
"learning_rate": 1.3432617278001225e-05,
"loss": 1.832,
"step": 145000
},
{
"epoch": 1.35,
"learning_rate": 1.3478953904324135e-05,
"loss": 1.855,
"step": 145500
},
{
"epoch": 1.35,
"learning_rate": 1.3525290530647046e-05,
"loss": 1.8432,
"step": 146000
},
{
"epoch": 1.36,
"learning_rate": 1.3571627156969955e-05,
"loss": 1.8284,
"step": 146500
},
{
"epoch": 1.36,
"learning_rate": 1.3617871110040221e-05,
"loss": 1.8375,
"step": 147000
},
{
"epoch": 1.37,
"learning_rate": 1.366420773636313e-05,
"loss": 1.8344,
"step": 147500
},
{
"epoch": 1.37,
"learning_rate": 1.3710544362686043e-05,
"loss": 1.8501,
"step": 148000
},
{
"epoch": 1.38,
"learning_rate": 1.3756880989008953e-05,
"loss": 1.841,
"step": 148500
},
{
"epoch": 1.38,
"learning_rate": 1.3803217615331864e-05,
"loss": 1.8415,
"step": 149000
},
{
"epoch": 1.39,
"learning_rate": 1.384946156840213e-05,
"loss": 1.8427,
"step": 149500
},
{
"epoch": 1.39,
"learning_rate": 1.3895798194725039e-05,
"loss": 1.8251,
"step": 150000
},
{
"epoch": 1.39,
"eval_loss": 1.7617018222808838,
"eval_runtime": 1996.728,
"eval_samples_per_second": 384.294,
"eval_steps_per_second": 6.005,
"step": 150000
},
{
"epoch": 1.39,
"learning_rate": 1.394213482104795e-05,
"loss": 1.8429,
"step": 150500
},
{
"epoch": 1.4,
"learning_rate": 1.3988471447370862e-05,
"loss": 1.8312,
"step": 151000
},
{
"epoch": 1.4,
"learning_rate": 1.403480807369377e-05,
"loss": 1.8323,
"step": 151500
},
{
"epoch": 1.41,
"learning_rate": 1.4081052026764037e-05,
"loss": 1.8371,
"step": 152000
},
{
"epoch": 1.41,
"learning_rate": 1.4127388653086946e-05,
"loss": 1.8385,
"step": 152500
},
{
"epoch": 1.42,
"learning_rate": 1.4173725279409858e-05,
"loss": 1.828,
"step": 153000
},
{
"epoch": 1.42,
"learning_rate": 1.4220061905732769e-05,
"loss": 1.8061,
"step": 153500
},
{
"epoch": 1.43,
"learning_rate": 1.4266305858803034e-05,
"loss": 1.8361,
"step": 154000
},
{
"epoch": 1.43,
"learning_rate": 1.4312642485125944e-05,
"loss": 1.8316,
"step": 154500
},
{
"epoch": 1.44,
"learning_rate": 1.4358979111448855e-05,
"loss": 1.8474,
"step": 155000
},
{
"epoch": 1.44,
"learning_rate": 1.4405315737771765e-05,
"loss": 1.8241,
"step": 155500
},
{
"epoch": 1.45,
"learning_rate": 1.4451652364094678e-05,
"loss": 1.8317,
"step": 156000
},
{
"epoch": 1.45,
"learning_rate": 1.4497988990417586e-05,
"loss": 1.8092,
"step": 156500
},
{
"epoch": 1.45,
"learning_rate": 1.4544325616740499e-05,
"loss": 1.829,
"step": 157000
},
{
"epoch": 1.46,
"learning_rate": 1.459066224306341e-05,
"loss": 1.8245,
"step": 157500
},
{
"epoch": 1.46,
"learning_rate": 1.4636906196133674e-05,
"loss": 1.8124,
"step": 158000
},
{
"epoch": 1.47,
"learning_rate": 1.4683242822456585e-05,
"loss": 1.8135,
"step": 158500
},
{
"epoch": 1.47,
"learning_rate": 1.4729579448779493e-05,
"loss": 1.8187,
"step": 159000
},
{
"epoch": 1.48,
"learning_rate": 1.4775916075102406e-05,
"loss": 1.8112,
"step": 159500
},
{
"epoch": 1.48,
"learning_rate": 1.4822252701425315e-05,
"loss": 1.8082,
"step": 160000
},
{
"epoch": 1.48,
"eval_loss": 1.7383992671966553,
"eval_runtime": 2000.0796,
"eval_samples_per_second": 383.65,
"eval_steps_per_second": 5.995,
"step": 160000
},
{
"epoch": 1.49,
"learning_rate": 1.4868589327748227e-05,
"loss": 1.8139,
"step": 160500
},
{
"epoch": 1.49,
"learning_rate": 1.4914925954071137e-05,
"loss": 1.8123,
"step": 161000
},
{
"epoch": 1.5,
"learning_rate": 1.4961262580394048e-05,
"loss": 1.8093,
"step": 161500
},
{
"epoch": 1.5,
"learning_rate": 1.5007599206716958e-05,
"loss": 1.8205,
"step": 162000
},
{
"epoch": 1.51,
"learning_rate": 1.505393583303987e-05,
"loss": 1.8207,
"step": 162500
},
{
"epoch": 1.51,
"learning_rate": 1.510027245936278e-05,
"loss": 1.8149,
"step": 163000
},
{
"epoch": 1.52,
"learning_rate": 1.5146516412433046e-05,
"loss": 1.8062,
"step": 163500
},
{
"epoch": 1.52,
"learning_rate": 1.5192853038755955e-05,
"loss": 1.7985,
"step": 164000
},
{
"epoch": 1.52,
"learning_rate": 1.5239189665078867e-05,
"loss": 1.8007,
"step": 164500
},
{
"epoch": 1.53,
"learning_rate": 1.528552629140178e-05,
"loss": 1.8018,
"step": 165000
},
{
"epoch": 1.53,
"learning_rate": 1.5331862917724688e-05,
"loss": 1.8267,
"step": 165500
},
{
"epoch": 1.54,
"learning_rate": 1.5378199544047597e-05,
"loss": 1.8243,
"step": 166000
},
{
"epoch": 1.54,
"learning_rate": 1.542453617037051e-05,
"loss": 1.805,
"step": 166500
},
{
"epoch": 1.55,
"learning_rate": 1.5470780123440774e-05,
"loss": 1.8084,
"step": 167000
},
{
"epoch": 1.55,
"learning_rate": 1.551702407651104e-05,
"loss": 1.8184,
"step": 167500
},
{
"epoch": 1.56,
"learning_rate": 1.5563360702833948e-05,
"loss": 1.797,
"step": 168000
},
{
"epoch": 1.56,
"learning_rate": 1.560969732915686e-05,
"loss": 1.8042,
"step": 168500
},
{
"epoch": 1.57,
"learning_rate": 1.565603395547977e-05,
"loss": 1.787,
"step": 169000
},
{
"epoch": 1.57,
"learning_rate": 1.570237058180268e-05,
"loss": 1.807,
"step": 169500
},
{
"epoch": 1.58,
"learning_rate": 1.5748614534872946e-05,
"loss": 1.7944,
"step": 170000
},
{
"epoch": 1.58,
"eval_loss": 1.722644567489624,
"eval_runtime": 1998.3002,
"eval_samples_per_second": 383.991,
"eval_steps_per_second": 6.0,
"step": 170000
},
{
"epoch": 1.58,
"learning_rate": 1.579495116119586e-05,
"loss": 1.8119,
"step": 170500
},
{
"epoch": 1.58,
"learning_rate": 1.5841287787518767e-05,
"loss": 1.8045,
"step": 171000
},
{
"epoch": 1.59,
"learning_rate": 1.588762441384168e-05,
"loss": 1.8002,
"step": 171500
},
{
"epoch": 1.59,
"learning_rate": 1.5933961040164588e-05,
"loss": 1.7977,
"step": 172000
},
{
"epoch": 1.6,
"learning_rate": 1.5980297666487497e-05,
"loss": 1.7874,
"step": 172500
},
{
"epoch": 1.6,
"learning_rate": 1.602663429281041e-05,
"loss": 1.7918,
"step": 173000
},
{
"epoch": 1.61,
"learning_rate": 1.607297091913332e-05,
"loss": 1.784,
"step": 173500
},
{
"epoch": 1.61,
"learning_rate": 1.611930754545623e-05,
"loss": 1.7943,
"step": 174000
},
{
"epoch": 1.62,
"learning_rate": 1.6165644171779143e-05,
"loss": 1.7977,
"step": 174500
},
{
"epoch": 1.62,
"learning_rate": 1.6211980798102055e-05,
"loss": 1.7964,
"step": 175000
},
{
"epoch": 1.63,
"learning_rate": 1.6258317424424964e-05,
"loss": 1.7822,
"step": 175500
},
{
"epoch": 1.63,
"learning_rate": 1.630456137749523e-05,
"loss": 1.7907,
"step": 176000
},
{
"epoch": 1.64,
"learning_rate": 1.6350898003818137e-05,
"loss": 1.7921,
"step": 176500
},
{
"epoch": 1.64,
"learning_rate": 1.639723463014105e-05,
"loss": 1.8039,
"step": 177000
},
{
"epoch": 1.64,
"learning_rate": 1.6443478583211315e-05,
"loss": 1.7823,
"step": 177500
},
{
"epoch": 1.65,
"learning_rate": 1.6489815209534227e-05,
"loss": 1.7861,
"step": 178000
},
{
"epoch": 1.65,
"learning_rate": 1.6536151835857136e-05,
"loss": 1.779,
"step": 178500
},
{
"epoch": 1.66,
"learning_rate": 1.65823957889274e-05,
"loss": 1.78,
"step": 179000
},
{
"epoch": 1.66,
"learning_rate": 1.6628732415250313e-05,
"loss": 1.7872,
"step": 179500
},
{
"epoch": 1.67,
"learning_rate": 1.667506904157322e-05,
"loss": 1.7997,
"step": 180000
},
{
"epoch": 1.67,
"eval_loss": 1.713136911392212,
"eval_runtime": 1997.6917,
"eval_samples_per_second": 384.108,
"eval_steps_per_second": 6.002,
"step": 180000
},
{
"epoch": 1.67,
"learning_rate": 1.6721405667896134e-05,
"loss": 1.7725,
"step": 180500
},
{
"epoch": 1.68,
"learning_rate": 1.6767742294219046e-05,
"loss": 1.7893,
"step": 181000
},
{
"epoch": 1.68,
"learning_rate": 1.6814078920541955e-05,
"loss": 1.7707,
"step": 181500
},
{
"epoch": 1.69,
"learning_rate": 1.686032287361222e-05,
"loss": 1.7799,
"step": 182000
},
{
"epoch": 1.69,
"learning_rate": 1.690665949993513e-05,
"loss": 1.7857,
"step": 182500
},
{
"epoch": 1.7,
"learning_rate": 1.695299612625804e-05,
"loss": 1.7788,
"step": 183000
},
{
"epoch": 1.7,
"learning_rate": 1.699933275258095e-05,
"loss": 1.7698,
"step": 183500
},
{
"epoch": 1.71,
"learning_rate": 1.7045669378903862e-05,
"loss": 1.7777,
"step": 184000
},
{
"epoch": 1.71,
"learning_rate": 1.7092006005226774e-05,
"loss": 1.7687,
"step": 184500
},
{
"epoch": 1.71,
"learning_rate": 1.7138342631549683e-05,
"loss": 1.7793,
"step": 185000
},
{
"epoch": 1.72,
"learning_rate": 1.7184679257872595e-05,
"loss": 1.7963,
"step": 185500
},
{
"epoch": 1.72,
"learning_rate": 1.7230923210942857e-05,
"loss": 1.79,
"step": 186000
},
{
"epoch": 1.73,
"learning_rate": 1.727725983726577e-05,
"loss": 1.7856,
"step": 186500
},
{
"epoch": 1.73,
"learning_rate": 1.732359646358868e-05,
"loss": 1.7866,
"step": 187000
},
{
"epoch": 1.74,
"learning_rate": 1.736993308991159e-05,
"loss": 1.771,
"step": 187500
},
{
"epoch": 1.74,
"learning_rate": 1.7416177042981858e-05,
"loss": 1.7822,
"step": 188000
},
{
"epoch": 1.75,
"learning_rate": 1.7462513669304767e-05,
"loss": 1.7572,
"step": 188500
},
{
"epoch": 1.75,
"learning_rate": 1.7508850295627676e-05,
"loss": 1.7631,
"step": 189000
},
{
"epoch": 1.76,
"learning_rate": 1.7555186921950588e-05,
"loss": 1.7828,
"step": 189500
},
{
"epoch": 1.76,
"learning_rate": 1.7601523548273497e-05,
"loss": 1.7687,
"step": 190000
},
{
"epoch": 1.76,
"eval_loss": 1.698320984840393,
"eval_runtime": 1996.7628,
"eval_samples_per_second": 384.287,
"eval_steps_per_second": 6.005,
"step": 190000
},
{
"epoch": 1.77,
"learning_rate": 1.764786017459641e-05,
"loss": 1.7606,
"step": 190500
},
{
"epoch": 1.77,
"learning_rate": 1.769419680091932e-05,
"loss": 1.7755,
"step": 191000
},
{
"epoch": 1.77,
"learning_rate": 1.774053342724223e-05,
"loss": 1.7604,
"step": 191500
},
{
"epoch": 1.78,
"learning_rate": 1.7786870053565143e-05,
"loss": 1.7701,
"step": 192000
},
{
"epoch": 1.78,
"learning_rate": 1.7833114006635407e-05,
"loss": 1.7692,
"step": 192500
},
{
"epoch": 1.79,
"learning_rate": 1.7879450632958316e-05,
"loss": 1.7596,
"step": 193000
},
{
"epoch": 1.79,
"learning_rate": 1.792578725928123e-05,
"loss": 1.76,
"step": 193500
},
{
"epoch": 1.8,
"learning_rate": 1.7972123885604137e-05,
"loss": 1.7672,
"step": 194000
},
{
"epoch": 1.8,
"learning_rate": 1.8018367838674406e-05,
"loss": 1.7607,
"step": 194500
},
{
"epoch": 1.81,
"learning_rate": 1.8064704464997315e-05,
"loss": 1.7571,
"step": 195000
},
{
"epoch": 1.81,
"learning_rate": 1.8111041091320227e-05,
"loss": 1.7651,
"step": 195500
},
{
"epoch": 1.82,
"learning_rate": 1.8157377717643136e-05,
"loss": 1.7537,
"step": 196000
},
{
"epoch": 1.82,
"learning_rate": 1.8203714343966044e-05,
"loss": 1.7628,
"step": 196500
},
{
"epoch": 1.83,
"learning_rate": 1.8250050970288957e-05,
"loss": 1.7656,
"step": 197000
},
{
"epoch": 1.83,
"learning_rate": 1.829629492335922e-05,
"loss": 1.7492,
"step": 197500
},
{
"epoch": 1.83,
"learning_rate": 1.8342631549682134e-05,
"loss": 1.7513,
"step": 198000
},
{
"epoch": 1.84,
"learning_rate": 1.8388875502752395e-05,
"loss": 1.7711,
"step": 198500
},
{
"epoch": 1.84,
"learning_rate": 1.8435212129075308e-05,
"loss": 1.7646,
"step": 199000
},
{
"epoch": 1.85,
"learning_rate": 1.8481548755398216e-05,
"loss": 1.7544,
"step": 199500
},
{
"epoch": 1.85,
"learning_rate": 1.852788538172113e-05,
"loss": 1.7681,
"step": 200000
},
{
"epoch": 1.85,
"eval_loss": 1.6830523014068604,
"eval_runtime": 1997.1692,
"eval_samples_per_second": 384.209,
"eval_steps_per_second": 6.003,
"step": 200000
},
{
"epoch": 1.86,
"learning_rate": 1.857422200804404e-05,
"loss": 1.7521,
"step": 200500
},
{
"epoch": 1.86,
"learning_rate": 1.862055863436695e-05,
"loss": 1.7614,
"step": 201000
},
{
"epoch": 1.87,
"learning_rate": 1.8666802587437215e-05,
"loss": 1.7513,
"step": 201500
},
{
"epoch": 1.87,
"learning_rate": 1.8713139213760127e-05,
"loss": 1.7524,
"step": 202000
},
{
"epoch": 1.88,
"learning_rate": 1.8759475840083036e-05,
"loss": 1.754,
"step": 202500
},
{
"epoch": 1.88,
"learning_rate": 1.8805812466405948e-05,
"loss": 1.7509,
"step": 203000
},
{
"epoch": 1.89,
"learning_rate": 1.8852149092728857e-05,
"loss": 1.7472,
"step": 203500
},
{
"epoch": 1.89,
"learning_rate": 1.889848571905177e-05,
"loss": 1.7594,
"step": 204000
},
{
"epoch": 1.9,
"learning_rate": 1.894482234537468e-05,
"loss": 1.7442,
"step": 204500
},
{
"epoch": 1.9,
"learning_rate": 1.899115897169759e-05,
"loss": 1.7579,
"step": 205000
},
{
"epoch": 1.9,
"learning_rate": 1.9037402924767855e-05,
"loss": 1.7504,
"step": 205500
},
{
"epoch": 1.91,
"learning_rate": 1.9083739551090764e-05,
"loss": 1.7286,
"step": 206000
},
{
"epoch": 1.91,
"learning_rate": 1.9130076177413676e-05,
"loss": 1.7516,
"step": 206500
},
{
"epoch": 1.92,
"learning_rate": 1.9176412803736588e-05,
"loss": 1.7547,
"step": 207000
},
{
"epoch": 1.92,
"learning_rate": 1.9222749430059497e-05,
"loss": 1.7548,
"step": 207500
},
{
"epoch": 1.93,
"learning_rate": 1.926908605638241e-05,
"loss": 1.7707,
"step": 208000
},
{
"epoch": 1.93,
"learning_rate": 1.9315422682705318e-05,
"loss": 1.7551,
"step": 208500
},
{
"epoch": 1.94,
"learning_rate": 1.9361666635775583e-05,
"loss": 1.7542,
"step": 209000
},
{
"epoch": 1.94,
"learning_rate": 1.9408003262098495e-05,
"loss": 1.7281,
"step": 209500
},
{
"epoch": 1.95,
"learning_rate": 1.9454339888421404e-05,
"loss": 1.7539,
"step": 210000
},
{
"epoch": 1.95,
"eval_loss": 1.6725276708602905,
"eval_runtime": 1997.5752,
"eval_samples_per_second": 384.131,
"eval_steps_per_second": 6.002,
"step": 210000
},
{
"epoch": 1.95,
"learning_rate": 1.9500676514744316e-05,
"loss": 1.7359,
"step": 210500
},
{
"epoch": 1.96,
"learning_rate": 1.9547013141067225e-05,
"loss": 1.744,
"step": 211000
},
{
"epoch": 1.96,
"learning_rate": 1.9593257094137493e-05,
"loss": 1.7421,
"step": 211500
},
{
"epoch": 1.96,
"learning_rate": 1.9639593720460402e-05,
"loss": 1.7263,
"step": 212000
},
{
"epoch": 1.97,
"learning_rate": 1.9685837673530667e-05,
"loss": 1.7432,
"step": 212500
},
{
"epoch": 1.97,
"learning_rate": 1.9732174299853576e-05,
"loss": 1.7391,
"step": 213000
},
{
"epoch": 1.98,
"learning_rate": 1.9778418252923844e-05,
"loss": 1.7314,
"step": 213500
},
{
"epoch": 1.98,
"learning_rate": 1.9824754879246753e-05,
"loss": 1.7447,
"step": 214000
},
{
"epoch": 1.99,
"learning_rate": 1.9871091505569665e-05,
"loss": 1.7456,
"step": 214500
},
{
"epoch": 1.99,
"learning_rate": 1.9917428131892574e-05,
"loss": 1.7396,
"step": 215000
},
{
"epoch": 2.0,
"learning_rate": 1.9963764758215483e-05,
"loss": 1.7286,
"step": 215500
},
{
"epoch": 2.0,
"learning_rate": 1.99974746538654e-05,
"loss": 1.7457,
"step": 216000
},
{
"epoch": 2.01,
"learning_rate": 1.9985890497284675e-05,
"loss": 1.7394,
"step": 216500
},
{
"epoch": 2.01,
"learning_rate": 1.997430634070395e-05,
"loss": 1.7259,
"step": 217000
},
{
"epoch": 2.02,
"learning_rate": 1.996272218412322e-05,
"loss": 1.7401,
"step": 217500
},
{
"epoch": 2.02,
"learning_rate": 1.9951138027542493e-05,
"loss": 1.7541,
"step": 218000
},
{
"epoch": 2.02,
"learning_rate": 1.9939553870961766e-05,
"loss": 1.7264,
"step": 218500
},
{
"epoch": 2.03,
"learning_rate": 1.9927969714381037e-05,
"loss": 1.7129,
"step": 219000
},
{
"epoch": 2.03,
"learning_rate": 1.9916385557800307e-05,
"loss": 1.7355,
"step": 219500
},
{
"epoch": 2.04,
"learning_rate": 1.9904824569532745e-05,
"loss": 1.7332,
"step": 220000
},
{
"epoch": 2.04,
"eval_loss": 1.6619489192962646,
"eval_runtime": 1997.741,
"eval_samples_per_second": 384.099,
"eval_steps_per_second": 6.002,
"step": 220000
},
{
"epoch": 2.04,
"learning_rate": 1.9893240412952015e-05,
"loss": 1.714,
"step": 220500
},
{
"epoch": 2.05,
"learning_rate": 1.9881656256371285e-05,
"loss": 1.7385,
"step": 221000
},
{
"epoch": 2.05,
"learning_rate": 1.987007209979056e-05,
"loss": 1.7149,
"step": 221500
},
{
"epoch": 2.06,
"learning_rate": 1.9858511111522994e-05,
"loss": 1.7318,
"step": 222000
},
{
"epoch": 2.06,
"learning_rate": 1.9846926954942267e-05,
"loss": 1.7256,
"step": 222500
},
{
"epoch": 2.07,
"learning_rate": 1.9835342798361537e-05,
"loss": 1.7155,
"step": 223000
},
{
"epoch": 2.07,
"learning_rate": 1.9823781810093972e-05,
"loss": 1.7316,
"step": 223500
},
{
"epoch": 2.08,
"learning_rate": 1.9812197653513246e-05,
"loss": 1.7279,
"step": 224000
},
{
"epoch": 2.08,
"learning_rate": 1.9800613496932516e-05,
"loss": 1.7228,
"step": 224500
},
{
"epoch": 2.09,
"learning_rate": 1.978902934035179e-05,
"loss": 1.7205,
"step": 225000
},
{
"epoch": 2.09,
"learning_rate": 1.9777468352084224e-05,
"loss": 1.7216,
"step": 225500
},
{
"epoch": 2.09,
"learning_rate": 1.9765884195503494e-05,
"loss": 1.7128,
"step": 226000
},
{
"epoch": 2.1,
"learning_rate": 1.9754300038922768e-05,
"loss": 1.7223,
"step": 226500
},
{
"epoch": 2.1,
"learning_rate": 1.9742715882342042e-05,
"loss": 1.7299,
"step": 227000
},
{
"epoch": 2.11,
"learning_rate": 1.9731131725761312e-05,
"loss": 1.7228,
"step": 227500
},
{
"epoch": 2.11,
"learning_rate": 1.9719547569180582e-05,
"loss": 1.7199,
"step": 228000
},
{
"epoch": 2.12,
"learning_rate": 1.9707963412599856e-05,
"loss": 1.7125,
"step": 228500
},
{
"epoch": 2.12,
"learning_rate": 1.969637925601913e-05,
"loss": 1.7159,
"step": 229000
},
{
"epoch": 2.13,
"learning_rate": 1.96847950994384e-05,
"loss": 1.7159,
"step": 229500
},
{
"epoch": 2.13,
"learning_rate": 1.9673234111170834e-05,
"loss": 1.7217,
"step": 230000
},
{
"epoch": 2.13,
"eval_loss": 1.6495946645736694,
"eval_runtime": 2000.9284,
"eval_samples_per_second": 383.487,
"eval_steps_per_second": 5.992,
"step": 230000
},
{
"epoch": 2.14,
"learning_rate": 1.966167312290327e-05,
"loss": 1.7081,
"step": 230500
},
{
"epoch": 2.14,
"learning_rate": 1.9650088966322543e-05,
"loss": 1.7257,
"step": 231000
},
{
"epoch": 2.15,
"learning_rate": 1.9638504809741813e-05,
"loss": 1.7007,
"step": 231500
},
{
"epoch": 2.15,
"learning_rate": 1.9626920653161087e-05,
"loss": 1.7165,
"step": 232000
},
{
"epoch": 2.15,
"learning_rate": 1.961533649658036e-05,
"loss": 1.7122,
"step": 232500
},
{
"epoch": 2.16,
"learning_rate": 1.960375233999963e-05,
"loss": 1.7073,
"step": 233000
},
{
"epoch": 2.16,
"learning_rate": 1.9592168183418904e-05,
"loss": 1.7044,
"step": 233500
},
{
"epoch": 2.17,
"learning_rate": 1.9580584026838178e-05,
"loss": 1.714,
"step": 234000
},
{
"epoch": 2.17,
"learning_rate": 1.956902303857061e-05,
"loss": 1.7063,
"step": 234500
},
{
"epoch": 2.18,
"learning_rate": 1.955743888198988e-05,
"loss": 1.7151,
"step": 235000
},
{
"epoch": 2.18,
"learning_rate": 1.9545854725409156e-05,
"loss": 1.7101,
"step": 235500
},
{
"epoch": 2.19,
"learning_rate": 1.9534270568828426e-05,
"loss": 1.7131,
"step": 236000
},
{
"epoch": 2.19,
"learning_rate": 1.9522686412247697e-05,
"loss": 1.6993,
"step": 236500
},
{
"epoch": 2.2,
"learning_rate": 1.951112542398013e-05,
"loss": 1.714,
"step": 237000
},
{
"epoch": 2.2,
"learning_rate": 1.9499564435712566e-05,
"loss": 1.7024,
"step": 237500
},
{
"epoch": 2.21,
"learning_rate": 1.948798027913184e-05,
"loss": 1.6996,
"step": 238000
},
{
"epoch": 2.21,
"learning_rate": 1.947639612255111e-05,
"loss": 1.7098,
"step": 238500
},
{
"epoch": 2.21,
"learning_rate": 1.9464811965970383e-05,
"loss": 1.6994,
"step": 239000
},
{
"epoch": 2.22,
"learning_rate": 1.9453227809389657e-05,
"loss": 1.7041,
"step": 239500
},
{
"epoch": 2.22,
"learning_rate": 1.9441643652808927e-05,
"loss": 1.7038,
"step": 240000
},
{
"epoch": 2.22,
"eval_loss": 1.6334847211837769,
"eval_runtime": 1997.524,
"eval_samples_per_second": 384.141,
"eval_steps_per_second": 6.002,
"step": 240000
},
{
"epoch": 2.23,
"learning_rate": 1.9430082664541362e-05,
"loss": 1.7067,
"step": 240500
},
{
"epoch": 2.23,
"learning_rate": 1.9418498507960636e-05,
"loss": 1.7112,
"step": 241000
},
{
"epoch": 2.24,
"learning_rate": 1.9406914351379906e-05,
"loss": 1.7015,
"step": 241500
},
{
"epoch": 2.24,
"learning_rate": 1.939533019479918e-05,
"loss": 1.7122,
"step": 242000
},
{
"epoch": 2.25,
"learning_rate": 1.9383769206531614e-05,
"loss": 1.6973,
"step": 242500
},
{
"epoch": 2.25,
"learning_rate": 1.9372185049950884e-05,
"loss": 1.7048,
"step": 243000
},
{
"epoch": 2.26,
"learning_rate": 1.9360600893370155e-05,
"loss": 1.6986,
"step": 243500
},
{
"epoch": 2.26,
"learning_rate": 1.934901673678943e-05,
"loss": 1.7118,
"step": 244000
},
{
"epoch": 2.27,
"learning_rate": 1.9337432580208702e-05,
"loss": 1.7049,
"step": 244500
},
{
"epoch": 2.27,
"learning_rate": 1.9325871591941136e-05,
"loss": 1.6972,
"step": 245000
},
{
"epoch": 2.28,
"learning_rate": 1.9314287435360407e-05,
"loss": 1.6999,
"step": 245500
},
{
"epoch": 2.28,
"learning_rate": 1.930270327877968e-05,
"loss": 1.6854,
"step": 246000
},
{
"epoch": 2.28,
"learning_rate": 1.9291119122198954e-05,
"loss": 1.6981,
"step": 246500
},
{
"epoch": 2.29,
"learning_rate": 1.9279534965618224e-05,
"loss": 1.6865,
"step": 247000
},
{
"epoch": 2.29,
"learning_rate": 1.9267950809037498e-05,
"loss": 1.6989,
"step": 247500
},
{
"epoch": 2.3,
"learning_rate": 1.9256389820769933e-05,
"loss": 1.6857,
"step": 248000
},
{
"epoch": 2.3,
"learning_rate": 1.9244805664189203e-05,
"loss": 1.6911,
"step": 248500
},
{
"epoch": 2.31,
"learning_rate": 1.9233221507608476e-05,
"loss": 1.6828,
"step": 249000
},
{
"epoch": 2.31,
"learning_rate": 1.922163735102775e-05,
"loss": 1.6863,
"step": 249500
},
{
"epoch": 2.32,
"learning_rate": 1.921005319444702e-05,
"loss": 1.6958,
"step": 250000
},
{
"epoch": 2.32,
"eval_loss": 1.6255241632461548,
"eval_runtime": 2000.1822,
"eval_samples_per_second": 383.63,
"eval_steps_per_second": 5.994,
"step": 250000
},
{
"epoch": 2.32,
"learning_rate": 1.919846903786629e-05,
"loss": 1.6883,
"step": 250500
},
{
"epoch": 2.33,
"learning_rate": 1.9186884881285564e-05,
"loss": 1.6986,
"step": 251000
},
{
"epoch": 2.33,
"learning_rate": 1.9175323893018e-05,
"loss": 1.6896,
"step": 251500
},
{
"epoch": 2.34,
"learning_rate": 1.916373973643727e-05,
"loss": 1.7071,
"step": 252000
},
{
"epoch": 2.34,
"learning_rate": 1.9152155579856543e-05,
"loss": 1.7047,
"step": 252500
},
{
"epoch": 2.34,
"learning_rate": 1.9140571423275816e-05,
"loss": 1.6899,
"step": 253000
},
{
"epoch": 2.35,
"learning_rate": 1.9129010435008248e-05,
"loss": 1.6951,
"step": 253500
},
{
"epoch": 2.35,
"learning_rate": 1.911742627842752e-05,
"loss": 1.6779,
"step": 254000
},
{
"epoch": 2.36,
"learning_rate": 1.9105842121846795e-05,
"loss": 1.6799,
"step": 254500
},
{
"epoch": 2.36,
"learning_rate": 1.909425796526607e-05,
"loss": 1.6829,
"step": 255000
},
{
"epoch": 2.37,
"learning_rate": 1.908267380868534e-05,
"loss": 1.688,
"step": 255500
},
{
"epoch": 2.37,
"learning_rate": 1.9071089652104612e-05,
"loss": 1.6716,
"step": 256000
},
{
"epoch": 2.38,
"learning_rate": 1.9059505495523886e-05,
"loss": 1.6786,
"step": 256500
},
{
"epoch": 2.38,
"learning_rate": 1.9047944507256317e-05,
"loss": 1.6914,
"step": 257000
},
{
"epoch": 2.39,
"learning_rate": 1.9036360350675587e-05,
"loss": 1.682,
"step": 257500
},
{
"epoch": 2.39,
"learning_rate": 1.902477619409486e-05,
"loss": 1.675,
"step": 258000
},
{
"epoch": 2.4,
"learning_rate": 1.9013192037514135e-05,
"loss": 1.6829,
"step": 258500
},
{
"epoch": 2.4,
"learning_rate": 1.9001607880933405e-05,
"loss": 1.6896,
"step": 259000
},
{
"epoch": 2.4,
"learning_rate": 1.899002372435268e-05,
"loss": 1.6758,
"step": 259500
},
{
"epoch": 2.41,
"learning_rate": 1.8978439567771952e-05,
"loss": 1.6843,
"step": 260000
},
{
"epoch": 2.41,
"eval_loss": 1.616537094116211,
"eval_runtime": 1997.5771,
"eval_samples_per_second": 384.13,
"eval_steps_per_second": 6.002,
"step": 260000
},
{
"epoch": 2.41,
"learning_rate": 1.8966855411191223e-05,
"loss": 1.6922,
"step": 260500
},
{
"epoch": 2.42,
"learning_rate": 1.8955271254610496e-05,
"loss": 1.6727,
"step": 261000
},
{
"epoch": 2.42,
"learning_rate": 1.894368709802977e-05,
"loss": 1.6769,
"step": 261500
},
{
"epoch": 2.43,
"learning_rate": 1.89321261097622e-05,
"loss": 1.702,
"step": 262000
},
{
"epoch": 2.43,
"learning_rate": 1.8920541953181475e-05,
"loss": 1.6675,
"step": 262500
},
{
"epoch": 2.44,
"learning_rate": 1.8908957796600745e-05,
"loss": 1.6693,
"step": 263000
},
{
"epoch": 2.44,
"learning_rate": 1.889737364002002e-05,
"loss": 1.6872,
"step": 263500
},
{
"epoch": 2.45,
"learning_rate": 1.8885812651752453e-05,
"loss": 1.685,
"step": 264000
},
{
"epoch": 2.45,
"learning_rate": 1.8874228495171723e-05,
"loss": 1.6776,
"step": 264500
},
{
"epoch": 2.46,
"learning_rate": 1.8862644338590997e-05,
"loss": 1.6692,
"step": 265000
},
{
"epoch": 2.46,
"learning_rate": 1.885106018201027e-05,
"loss": 1.6668,
"step": 265500
},
{
"epoch": 2.47,
"learning_rate": 1.883947602542954e-05,
"loss": 1.6646,
"step": 266000
},
{
"epoch": 2.47,
"learning_rate": 1.8827891868848815e-05,
"loss": 1.6947,
"step": 266500
},
{
"epoch": 2.47,
"learning_rate": 1.881633088058125e-05,
"loss": 1.6724,
"step": 267000
},
{
"epoch": 2.48,
"learning_rate": 1.880476989231368e-05,
"loss": 1.6736,
"step": 267500
},
{
"epoch": 2.48,
"learning_rate": 1.8793185735732954e-05,
"loss": 1.6828,
"step": 268000
},
{
"epoch": 2.49,
"learning_rate": 1.8781601579152228e-05,
"loss": 1.6961,
"step": 268500
},
{
"epoch": 2.49,
"learning_rate": 1.8770017422571498e-05,
"loss": 1.6812,
"step": 269000
},
{
"epoch": 2.5,
"learning_rate": 1.875843326599077e-05,
"loss": 1.6814,
"step": 269500
},
{
"epoch": 2.5,
"learning_rate": 1.8746849109410045e-05,
"loss": 1.6701,
"step": 270000
},
{
"epoch": 2.5,
"eval_loss": 1.6026573181152344,
"eval_runtime": 1997.2448,
"eval_samples_per_second": 384.194,
"eval_steps_per_second": 6.003,
"step": 270000
},
{
"epoch": 2.51,
"learning_rate": 1.8735264952829315e-05,
"loss": 1.6781,
"step": 270500
},
{
"epoch": 2.51,
"learning_rate": 1.872370396456175e-05,
"loss": 1.6708,
"step": 271000
},
{
"epoch": 2.52,
"learning_rate": 1.8712142976294185e-05,
"loss": 1.6545,
"step": 271500
},
{
"epoch": 2.52,
"learning_rate": 1.870055881971346e-05,
"loss": 1.6616,
"step": 272000
},
{
"epoch": 2.53,
"learning_rate": 1.868897466313273e-05,
"loss": 1.6714,
"step": 272500
},
{
"epoch": 2.53,
"learning_rate": 1.8677390506552e-05,
"loss": 1.6725,
"step": 273000
},
{
"epoch": 2.53,
"learning_rate": 1.8665806349971272e-05,
"loss": 1.6703,
"step": 273500
},
{
"epoch": 2.54,
"learning_rate": 1.8654222193390546e-05,
"loss": 1.681,
"step": 274000
},
{
"epoch": 2.54,
"learning_rate": 1.8642638036809816e-05,
"loss": 1.6681,
"step": 274500
},
{
"epoch": 2.55,
"learning_rate": 1.863105388022909e-05,
"loss": 1.6694,
"step": 275000
},
{
"epoch": 2.55,
"learning_rate": 1.8619469723648364e-05,
"loss": 1.6652,
"step": 275500
},
{
"epoch": 2.56,
"learning_rate": 1.8607885567067634e-05,
"loss": 1.673,
"step": 276000
},
{
"epoch": 2.56,
"learning_rate": 1.859632457880007e-05,
"loss": 1.6761,
"step": 276500
},
{
"epoch": 2.57,
"learning_rate": 1.8584740422219342e-05,
"loss": 1.6719,
"step": 277000
},
{
"epoch": 2.57,
"learning_rate": 1.8573156265638612e-05,
"loss": 1.6731,
"step": 277500
},
{
"epoch": 2.58,
"learning_rate": 1.8561572109057886e-05,
"loss": 1.6474,
"step": 278000
},
{
"epoch": 2.58,
"learning_rate": 1.8549987952477156e-05,
"loss": 1.6659,
"step": 278500
},
{
"epoch": 2.59,
"learning_rate": 1.853840379589643e-05,
"loss": 1.6774,
"step": 279000
},
{
"epoch": 2.59,
"learning_rate": 1.8526842807628865e-05,
"loss": 1.6502,
"step": 279500
},
{
"epoch": 2.59,
"learning_rate": 1.8515258651048135e-05,
"loss": 1.6713,
"step": 280000
},
{
"epoch": 2.59,
"eval_loss": 1.5932214260101318,
"eval_runtime": 1997.7208,
"eval_samples_per_second": 384.103,
"eval_steps_per_second": 6.002,
"step": 280000
},
{
"epoch": 2.6,
"learning_rate": 1.850367449446741e-05,
"loss": 1.661,
"step": 280500
},
{
"epoch": 2.6,
"learning_rate": 1.8492113506199843e-05,
"loss": 1.6581,
"step": 281000
},
{
"epoch": 2.61,
"learning_rate": 1.8480529349619113e-05,
"loss": 1.6622,
"step": 281500
},
{
"epoch": 2.61,
"learning_rate": 1.8468945193038387e-05,
"loss": 1.6672,
"step": 282000
},
{
"epoch": 2.62,
"learning_rate": 1.845736103645766e-05,
"loss": 1.6534,
"step": 282500
},
{
"epoch": 2.62,
"learning_rate": 1.844577687987693e-05,
"loss": 1.6678,
"step": 283000
},
{
"epoch": 2.63,
"learning_rate": 1.8434192723296204e-05,
"loss": 1.6653,
"step": 283500
},
{
"epoch": 2.63,
"learning_rate": 1.8422608566715475e-05,
"loss": 1.6426,
"step": 284000
},
{
"epoch": 2.64,
"learning_rate": 1.841102441013475e-05,
"loss": 1.6612,
"step": 284500
},
{
"epoch": 2.64,
"learning_rate": 1.8399440253554022e-05,
"loss": 1.67,
"step": 285000
},
{
"epoch": 2.65,
"learning_rate": 1.8387856096973292e-05,
"loss": 1.6558,
"step": 285500
},
{
"epoch": 2.65,
"learning_rate": 1.8376271940392566e-05,
"loss": 1.6729,
"step": 286000
},
{
"epoch": 2.66,
"learning_rate": 1.836468778381184e-05,
"loss": 1.6524,
"step": 286500
},
{
"epoch": 2.66,
"learning_rate": 1.835310362723111e-05,
"loss": 1.6556,
"step": 287000
},
{
"epoch": 2.66,
"learning_rate": 1.8341542638963544e-05,
"loss": 1.666,
"step": 287500
},
{
"epoch": 2.67,
"learning_rate": 1.8329958482382818e-05,
"loss": 1.6636,
"step": 288000
},
{
"epoch": 2.67,
"learning_rate": 1.831842066242841e-05,
"loss": 1.6673,
"step": 288500
},
{
"epoch": 2.68,
"learning_rate": 1.8306836505847684e-05,
"loss": 1.6652,
"step": 289000
},
{
"epoch": 2.68,
"learning_rate": 1.8295252349266957e-05,
"loss": 1.6646,
"step": 289500
},
{
"epoch": 2.69,
"learning_rate": 1.8283668192686228e-05,
"loss": 1.6617,
"step": 290000
},
{
"epoch": 2.69,
"eval_loss": 1.5840277671813965,
"eval_runtime": 1996.9221,
"eval_samples_per_second": 384.256,
"eval_steps_per_second": 6.004,
"step": 290000
},
{
"epoch": 2.69,
"learning_rate": 1.8272084036105498e-05,
"loss": 1.6476,
"step": 290500
},
{
"epoch": 2.7,
"learning_rate": 1.8260499879524775e-05,
"loss": 1.6557,
"step": 291000
},
{
"epoch": 2.7,
"learning_rate": 1.8248915722944045e-05,
"loss": 1.6634,
"step": 291500
},
{
"epoch": 2.71,
"learning_rate": 1.823733156636332e-05,
"loss": 1.6408,
"step": 292000
},
{
"epoch": 2.71,
"learning_rate": 1.822574740978259e-05,
"loss": 1.6589,
"step": 292500
},
{
"epoch": 2.72,
"learning_rate": 1.8214163253201863e-05,
"loss": 1.6692,
"step": 293000
},
{
"epoch": 2.72,
"learning_rate": 1.8202579096621136e-05,
"loss": 1.6518,
"step": 293500
},
{
"epoch": 2.72,
"learning_rate": 1.8190994940040407e-05,
"loss": 1.6536,
"step": 294000
},
{
"epoch": 2.73,
"learning_rate": 1.817941078345968e-05,
"loss": 1.6501,
"step": 294500
},
{
"epoch": 2.73,
"learning_rate": 1.8167849795192115e-05,
"loss": 1.6502,
"step": 295000
},
{
"epoch": 2.74,
"learning_rate": 1.8156265638611385e-05,
"loss": 1.6566,
"step": 295500
},
{
"epoch": 2.74,
"learning_rate": 1.814468148203066e-05,
"loss": 1.6513,
"step": 296000
},
{
"epoch": 2.75,
"learning_rate": 1.8133097325449932e-05,
"loss": 1.6499,
"step": 296500
},
{
"epoch": 2.75,
"learning_rate": 1.8121513168869203e-05,
"loss": 1.657,
"step": 297000
},
{
"epoch": 2.76,
"learning_rate": 1.8109929012288473e-05,
"loss": 1.6651,
"step": 297500
},
{
"epoch": 2.76,
"learning_rate": 1.8098368024020908e-05,
"loss": 1.6461,
"step": 298000
},
{
"epoch": 2.77,
"learning_rate": 1.808678386744018e-05,
"loss": 1.6555,
"step": 298500
},
{
"epoch": 2.77,
"learning_rate": 1.807519971085945e-05,
"loss": 1.6471,
"step": 299000
},
{
"epoch": 2.78,
"learning_rate": 1.8063615554278725e-05,
"loss": 1.6296,
"step": 299500
},
{
"epoch": 2.78,
"learning_rate": 1.8052031397698e-05,
"loss": 1.6454,
"step": 300000
},
{
"epoch": 2.78,
"eval_loss": 1.577728271484375,
"eval_runtime": 2001.1968,
"eval_samples_per_second": 383.436,
"eval_steps_per_second": 5.991,
"step": 300000
},
{
"epoch": 2.78,
"learning_rate": 1.804044724111727e-05,
"loss": 1.6441,
"step": 300500
},
{
"epoch": 2.79,
"learning_rate": 1.8028863084536543e-05,
"loss": 1.672,
"step": 301000
},
{
"epoch": 2.79,
"learning_rate": 1.8017278927955816e-05,
"loss": 1.6422,
"step": 301500
},
{
"epoch": 2.8,
"learning_rate": 1.8005694771375087e-05,
"loss": 1.6455,
"step": 302000
},
{
"epoch": 2.8,
"learning_rate": 1.799413378310752e-05,
"loss": 1.6554,
"step": 302500
},
{
"epoch": 2.81,
"learning_rate": 1.798254962652679e-05,
"loss": 1.6323,
"step": 303000
},
{
"epoch": 2.81,
"learning_rate": 1.797098863825923e-05,
"loss": 1.6464,
"step": 303500
},
{
"epoch": 2.82,
"learning_rate": 1.79594044816785e-05,
"loss": 1.6424,
"step": 304000
},
{
"epoch": 2.82,
"learning_rate": 1.794782032509777e-05,
"loss": 1.6568,
"step": 304500
},
{
"epoch": 2.83,
"learning_rate": 1.7936259336830208e-05,
"loss": 1.6505,
"step": 305000
},
{
"epoch": 2.83,
"learning_rate": 1.792469834856264e-05,
"loss": 1.6481,
"step": 305500
},
{
"epoch": 2.84,
"learning_rate": 1.791311419198191e-05,
"loss": 1.637,
"step": 306000
},
{
"epoch": 2.84,
"learning_rate": 1.7901530035401183e-05,
"loss": 1.6488,
"step": 306500
},
{
"epoch": 2.85,
"learning_rate": 1.7889945878820457e-05,
"loss": 1.6385,
"step": 307000
},
{
"epoch": 2.85,
"learning_rate": 1.7878361722239727e-05,
"loss": 1.6323,
"step": 307500
},
{
"epoch": 2.85,
"learning_rate": 1.7866777565659e-05,
"loss": 1.6303,
"step": 308000
},
{
"epoch": 2.86,
"learning_rate": 1.7855193409078274e-05,
"loss": 1.6324,
"step": 308500
},
{
"epoch": 2.86,
"learning_rate": 1.784363242081071e-05,
"loss": 1.6346,
"step": 309000
},
{
"epoch": 2.87,
"learning_rate": 1.783204826422998e-05,
"loss": 1.6279,
"step": 309500
},
{
"epoch": 2.87,
"learning_rate": 1.7820464107649253e-05,
"loss": 1.6426,
"step": 310000
},
{
"epoch": 2.87,
"eval_loss": 1.57373046875,
"eval_runtime": 2000.3584,
"eval_samples_per_second": 383.596,
"eval_steps_per_second": 5.994,
"step": 310000
},
{
"epoch": 2.88,
"learning_rate": 1.7808879951068526e-05,
"loss": 1.6477,
"step": 310500
},
{
"epoch": 2.88,
"learning_rate": 1.7797295794487797e-05,
"loss": 1.6324,
"step": 311000
},
{
"epoch": 2.89,
"learning_rate": 1.7785711637907067e-05,
"loss": 1.6441,
"step": 311500
},
{
"epoch": 2.89,
"learning_rate": 1.777412748132634e-05,
"loss": 1.6483,
"step": 312000
},
{
"epoch": 2.9,
"learning_rate": 1.7762543324745614e-05,
"loss": 1.6385,
"step": 312500
},
{
"epoch": 2.9,
"learning_rate": 1.7750959168164884e-05,
"loss": 1.6186,
"step": 313000
},
{
"epoch": 2.91,
"learning_rate": 1.7739375011584158e-05,
"loss": 1.6396,
"step": 313500
},
{
"epoch": 2.91,
"learning_rate": 1.772779085500343e-05,
"loss": 1.6401,
"step": 314000
},
{
"epoch": 2.91,
"learning_rate": 1.7716206698422702e-05,
"loss": 1.6149,
"step": 314500
},
{
"epoch": 2.92,
"learning_rate": 1.7704622541841976e-05,
"loss": 1.6177,
"step": 315000
},
{
"epoch": 2.92,
"learning_rate": 1.769308472188757e-05,
"loss": 1.6299,
"step": 315500
},
{
"epoch": 2.93,
"learning_rate": 1.768150056530684e-05,
"loss": 1.6324,
"step": 316000
},
{
"epoch": 2.93,
"learning_rate": 1.7669916408726115e-05,
"loss": 1.6144,
"step": 316500
},
{
"epoch": 2.94,
"learning_rate": 1.765835542045855e-05,
"loss": 1.6338,
"step": 317000
},
{
"epoch": 2.94,
"learning_rate": 1.7646771263877823e-05,
"loss": 1.6424,
"step": 317500
},
{
"epoch": 2.95,
"learning_rate": 1.7635187107297093e-05,
"loss": 1.6261,
"step": 318000
},
{
"epoch": 2.95,
"learning_rate": 1.7623602950716364e-05,
"loss": 1.6242,
"step": 318500
},
{
"epoch": 2.96,
"learning_rate": 1.761201879413564e-05,
"loss": 1.6286,
"step": 319000
},
{
"epoch": 2.96,
"learning_rate": 1.760043463755491e-05,
"loss": 1.6171,
"step": 319500
},
{
"epoch": 2.97,
"learning_rate": 1.758885048097418e-05,
"loss": 1.6296,
"step": 320000
},
{
"epoch": 2.97,
"eval_loss": 1.5615925788879395,
"eval_runtime": 1998.3038,
"eval_samples_per_second": 383.991,
"eval_steps_per_second": 6.0,
"step": 320000
},
{
"epoch": 2.97,
"learning_rate": 1.7577266324393455e-05,
"loss": 1.6205,
"step": 320500
},
{
"epoch": 2.97,
"learning_rate": 1.756570533612589e-05,
"loss": 1.6213,
"step": 321000
},
{
"epoch": 2.98,
"learning_rate": 1.755412117954516e-05,
"loss": 1.6304,
"step": 321500
},
{
"epoch": 2.98,
"learning_rate": 1.7542537022964433e-05,
"loss": 1.6373,
"step": 322000
},
{
"epoch": 2.99,
"learning_rate": 1.7530952866383707e-05,
"loss": 1.6222,
"step": 322500
},
{
"epoch": 2.99,
"learning_rate": 1.7519368709802977e-05,
"loss": 1.6249,
"step": 323000
},
{
"epoch": 3.0,
"learning_rate": 1.750778455322225e-05,
"loss": 1.6233,
"step": 323500
},
{
"epoch": 3.0,
"learning_rate": 1.7496223564954686e-05,
"loss": 1.6251,
"step": 324000
},
{
"epoch": 3.01,
"learning_rate": 1.7484639408373956e-05,
"loss": 1.6391,
"step": 324500
},
{
"epoch": 3.01,
"learning_rate": 1.747305525179323e-05,
"loss": 1.6213,
"step": 325000
},
{
"epoch": 3.02,
"learning_rate": 1.74614710952125e-05,
"loss": 1.623,
"step": 325500
},
{
"epoch": 3.02,
"learning_rate": 1.7449886938631773e-05,
"loss": 1.644,
"step": 326000
},
{
"epoch": 3.03,
"learning_rate": 1.7438302782051047e-05,
"loss": 1.6366,
"step": 326500
},
{
"epoch": 3.03,
"learning_rate": 1.7426718625470317e-05,
"loss": 1.6187,
"step": 327000
},
{
"epoch": 3.04,
"learning_rate": 1.741513446888959e-05,
"loss": 1.6226,
"step": 327500
},
{
"epoch": 3.04,
"learning_rate": 1.7403550312308865e-05,
"loss": 1.6191,
"step": 328000
},
{
"epoch": 3.04,
"learning_rate": 1.7391966155728135e-05,
"loss": 1.6256,
"step": 328500
},
{
"epoch": 3.05,
"learning_rate": 1.7380381999147405e-05,
"loss": 1.6142,
"step": 329000
},
{
"epoch": 3.05,
"learning_rate": 1.736879784256668e-05,
"loss": 1.6139,
"step": 329500
},
{
"epoch": 3.06,
"learning_rate": 1.7357260022612274e-05,
"loss": 1.6098,
"step": 330000
},
{
"epoch": 3.06,
"eval_loss": 1.5585696697235107,
"eval_runtime": 1998.1499,
"eval_samples_per_second": 384.02,
"eval_steps_per_second": 6.001,
"step": 330000
},
{
"epoch": 3.06,
"learning_rate": 1.7345675866031548e-05,
"loss": 1.6283,
"step": 330500
},
{
"epoch": 3.07,
"learning_rate": 1.733409170945082e-05,
"loss": 1.6054,
"step": 331000
},
{
"epoch": 3.07,
"learning_rate": 1.7322507552870092e-05,
"loss": 1.6116,
"step": 331500
},
{
"epoch": 3.08,
"learning_rate": 1.7310923396289365e-05,
"loss": 1.6298,
"step": 332000
},
{
"epoch": 3.08,
"learning_rate": 1.7299362408021797e-05,
"loss": 1.6141,
"step": 332500
},
{
"epoch": 3.09,
"learning_rate": 1.728777825144107e-05,
"loss": 1.6254,
"step": 333000
},
{
"epoch": 3.09,
"learning_rate": 1.7276194094860344e-05,
"loss": 1.6062,
"step": 333500
},
{
"epoch": 3.1,
"learning_rate": 1.7264609938279614e-05,
"loss": 1.6079,
"step": 334000
},
{
"epoch": 3.1,
"learning_rate": 1.725304895001205e-05,
"loss": 1.6256,
"step": 334500
},
{
"epoch": 3.1,
"learning_rate": 1.7241464793431322e-05,
"loss": 1.6222,
"step": 335000
},
{
"epoch": 3.11,
"learning_rate": 1.7229880636850593e-05,
"loss": 1.5983,
"step": 335500
},
{
"epoch": 3.11,
"learning_rate": 1.7218319648583027e-05,
"loss": 1.6127,
"step": 336000
},
{
"epoch": 3.12,
"learning_rate": 1.72067354920023e-05,
"loss": 1.613,
"step": 336500
},
{
"epoch": 3.12,
"learning_rate": 1.719515133542157e-05,
"loss": 1.6204,
"step": 337000
},
{
"epoch": 3.13,
"learning_rate": 1.7183567178840845e-05,
"loss": 1.6106,
"step": 337500
},
{
"epoch": 3.13,
"learning_rate": 1.717198302226012e-05,
"loss": 1.6235,
"step": 338000
},
{
"epoch": 3.14,
"learning_rate": 1.716039886567939e-05,
"loss": 1.6157,
"step": 338500
},
{
"epoch": 3.14,
"learning_rate": 1.7148837877411823e-05,
"loss": 1.593,
"step": 339000
},
{
"epoch": 3.15,
"learning_rate": 1.7137253720831094e-05,
"loss": 1.6152,
"step": 339500
},
{
"epoch": 3.15,
"learning_rate": 1.7125669564250367e-05,
"loss": 1.6159,
"step": 340000
},
{
"epoch": 3.15,
"eval_loss": 1.551076889038086,
"eval_runtime": 2001.8218,
"eval_samples_per_second": 383.316,
"eval_steps_per_second": 5.99,
"step": 340000
},
{
"epoch": 3.16,
"learning_rate": 1.711408540766964e-05,
"loss": 1.6079,
"step": 340500
},
{
"epoch": 3.16,
"learning_rate": 1.710250125108891e-05,
"loss": 1.6252,
"step": 341000
},
{
"epoch": 3.16,
"learning_rate": 1.7090917094508185e-05,
"loss": 1.6198,
"step": 341500
},
{
"epoch": 3.17,
"learning_rate": 1.707933293792746e-05,
"loss": 1.6185,
"step": 342000
},
{
"epoch": 3.17,
"learning_rate": 1.706774878134673e-05,
"loss": 1.6142,
"step": 342500
},
{
"epoch": 3.18,
"learning_rate": 1.7056164624766002e-05,
"loss": 1.6112,
"step": 343000
},
{
"epoch": 3.18,
"learning_rate": 1.7044603636498437e-05,
"loss": 1.6162,
"step": 343500
},
{
"epoch": 3.19,
"learning_rate": 1.7033019479917707e-05,
"loss": 1.6147,
"step": 344000
},
{
"epoch": 3.19,
"learning_rate": 1.7021435323336977e-05,
"loss": 1.6122,
"step": 344500
},
{
"epoch": 3.2,
"learning_rate": 1.7009851166756254e-05,
"loss": 1.6203,
"step": 345000
},
{
"epoch": 3.2,
"learning_rate": 1.6998267010175525e-05,
"loss": 1.6178,
"step": 345500
},
{
"epoch": 3.21,
"learning_rate": 1.698670602190796e-05,
"loss": 1.5984,
"step": 346000
},
{
"epoch": 3.21,
"learning_rate": 1.6975145033640394e-05,
"loss": 1.6133,
"step": 346500
},
{
"epoch": 3.22,
"learning_rate": 1.6963560877059664e-05,
"loss": 1.6158,
"step": 347000
},
{
"epoch": 3.22,
"learning_rate": 1.6951976720478938e-05,
"loss": 1.6129,
"step": 347500
},
{
"epoch": 3.23,
"learning_rate": 1.6940392563898208e-05,
"loss": 1.6149,
"step": 348000
},
{
"epoch": 3.23,
"learning_rate": 1.692880840731748e-05,
"loss": 1.6028,
"step": 348500
},
{
"epoch": 3.23,
"learning_rate": 1.6917224250736755e-05,
"loss": 1.613,
"step": 349000
},
{
"epoch": 3.24,
"learning_rate": 1.6905640094156026e-05,
"loss": 1.6066,
"step": 349500
},
{
"epoch": 3.24,
"learning_rate": 1.68940559375753e-05,
"loss": 1.608,
"step": 350000
},
{
"epoch": 3.24,
"eval_loss": 1.5453064441680908,
"eval_runtime": 1998.9984,
"eval_samples_per_second": 383.857,
"eval_steps_per_second": 5.998,
"step": 350000
},
{
"epoch": 3.25,
"learning_rate": 1.6882471780994573e-05,
"loss": 1.6084,
"step": 350500
},
{
"epoch": 3.25,
"learning_rate": 1.6870887624413843e-05,
"loss": 1.6034,
"step": 351000
},
{
"epoch": 3.26,
"learning_rate": 1.6859326636146274e-05,
"loss": 1.6203,
"step": 351500
},
{
"epoch": 3.26,
"learning_rate": 1.684774247956555e-05,
"loss": 1.6052,
"step": 352000
},
{
"epoch": 3.27,
"learning_rate": 1.683615832298482e-05,
"loss": 1.6071,
"step": 352500
},
{
"epoch": 3.27,
"learning_rate": 1.6824574166404092e-05,
"loss": 1.6057,
"step": 353000
},
{
"epoch": 3.28,
"learning_rate": 1.6812990009823365e-05,
"loss": 1.6187,
"step": 353500
},
{
"epoch": 3.28,
"learning_rate": 1.68014290215558e-05,
"loss": 1.6003,
"step": 354000
},
{
"epoch": 3.29,
"learning_rate": 1.6789844864975074e-05,
"loss": 1.6174,
"step": 354500
},
{
"epoch": 3.29,
"learning_rate": 1.6778283876707505e-05,
"loss": 1.5958,
"step": 355000
},
{
"epoch": 3.29,
"learning_rate": 1.676669972012678e-05,
"loss": 1.6038,
"step": 355500
},
{
"epoch": 3.3,
"learning_rate": 1.6755115563546052e-05,
"loss": 1.6058,
"step": 356000
},
{
"epoch": 3.3,
"learning_rate": 1.6743531406965322e-05,
"loss": 1.6068,
"step": 356500
},
{
"epoch": 3.31,
"learning_rate": 1.6731947250384596e-05,
"loss": 1.6134,
"step": 357000
},
{
"epoch": 3.31,
"learning_rate": 1.672036309380387e-05,
"loss": 1.6029,
"step": 357500
},
{
"epoch": 3.32,
"learning_rate": 1.67088021055363e-05,
"loss": 1.603,
"step": 358000
},
{
"epoch": 3.32,
"learning_rate": 1.6697217948955575e-05,
"loss": 1.596,
"step": 358500
},
{
"epoch": 3.33,
"learning_rate": 1.6685633792374848e-05,
"loss": 1.613,
"step": 359000
},
{
"epoch": 3.33,
"learning_rate": 1.667404963579412e-05,
"loss": 1.6069,
"step": 359500
},
{
"epoch": 3.34,
"learning_rate": 1.666246547921339e-05,
"loss": 1.5935,
"step": 360000
},
{
"epoch": 3.34,
"eval_loss": 1.5372581481933594,
"eval_runtime": 1998.6879,
"eval_samples_per_second": 383.917,
"eval_steps_per_second": 5.999,
"step": 360000
},
{
"epoch": 3.34,
"learning_rate": 1.6650881322632662e-05,
"loss": 1.6009,
"step": 360500
},
{
"epoch": 3.35,
"learning_rate": 1.6639297166051936e-05,
"loss": 1.6133,
"step": 361000
},
{
"epoch": 3.35,
"learning_rate": 1.6627713009471206e-05,
"loss": 1.592,
"step": 361500
},
{
"epoch": 3.35,
"learning_rate": 1.661615202120364e-05,
"loss": 1.6038,
"step": 362000
},
{
"epoch": 3.36,
"learning_rate": 1.6604567864622915e-05,
"loss": 1.6082,
"step": 362500
},
{
"epoch": 3.36,
"learning_rate": 1.6592983708042185e-05,
"loss": 1.6084,
"step": 363000
},
{
"epoch": 3.37,
"learning_rate": 1.658139955146146e-05,
"loss": 1.6006,
"step": 363500
},
{
"epoch": 3.37,
"learning_rate": 1.6569815394880732e-05,
"loss": 1.5974,
"step": 364000
},
{
"epoch": 3.38,
"learning_rate": 1.6558231238300002e-05,
"loss": 1.6028,
"step": 364500
},
{
"epoch": 3.38,
"learning_rate": 1.6546647081719276e-05,
"loss": 1.6085,
"step": 365000
},
{
"epoch": 3.39,
"learning_rate": 1.6535062925138546e-05,
"loss": 1.5808,
"step": 365500
},
{
"epoch": 3.39,
"learning_rate": 1.652347876855782e-05,
"loss": 1.6075,
"step": 366000
},
{
"epoch": 3.4,
"learning_rate": 1.6511917780290254e-05,
"loss": 1.5737,
"step": 366500
},
{
"epoch": 3.4,
"learning_rate": 1.6500356792022686e-05,
"loss": 1.5917,
"step": 367000
},
{
"epoch": 3.41,
"learning_rate": 1.648877263544196e-05,
"loss": 1.6105,
"step": 367500
},
{
"epoch": 3.41,
"learning_rate": 1.6477188478861233e-05,
"loss": 1.5855,
"step": 368000
},
{
"epoch": 3.42,
"learning_rate": 1.6465604322280503e-05,
"loss": 1.5895,
"step": 368500
},
{
"epoch": 3.42,
"learning_rate": 1.6454043334012938e-05,
"loss": 1.6065,
"step": 369000
},
{
"epoch": 3.42,
"learning_rate": 1.644245917743221e-05,
"loss": 1.6047,
"step": 369500
},
{
"epoch": 3.43,
"learning_rate": 1.643087502085148e-05,
"loss": 1.5885,
"step": 370000
},
{
"epoch": 3.43,
"eval_loss": 1.530922770500183,
"eval_runtime": 1999.4946,
"eval_samples_per_second": 383.762,
"eval_steps_per_second": 5.997,
"step": 370000
},
{
"epoch": 3.43,
"learning_rate": 1.6419290864270755e-05,
"loss": 1.5866,
"step": 370500
},
{
"epoch": 3.44,
"learning_rate": 1.640772987600319e-05,
"loss": 1.5859,
"step": 371000
},
{
"epoch": 3.44,
"learning_rate": 1.6396145719422464e-05,
"loss": 1.5933,
"step": 371500
},
{
"epoch": 3.45,
"learning_rate": 1.6384561562841734e-05,
"loss": 1.5854,
"step": 372000
},
{
"epoch": 3.45,
"learning_rate": 1.637300057457417e-05,
"loss": 1.588,
"step": 372500
},
{
"epoch": 3.46,
"learning_rate": 1.6361439586306603e-05,
"loss": 1.5933,
"step": 373000
},
{
"epoch": 3.46,
"learning_rate": 1.6349855429725873e-05,
"loss": 1.5858,
"step": 373500
},
{
"epoch": 3.47,
"learning_rate": 1.6338271273145147e-05,
"loss": 1.6101,
"step": 374000
},
{
"epoch": 3.47,
"learning_rate": 1.632668711656442e-05,
"loss": 1.5954,
"step": 374500
},
{
"epoch": 3.48,
"learning_rate": 1.631510295998369e-05,
"loss": 1.5882,
"step": 375000
},
{
"epoch": 3.48,
"learning_rate": 1.630351880340296e-05,
"loss": 1.5951,
"step": 375500
},
{
"epoch": 3.48,
"learning_rate": 1.6291934646822235e-05,
"loss": 1.586,
"step": 376000
},
{
"epoch": 3.49,
"learning_rate": 1.628035049024151e-05,
"loss": 1.6067,
"step": 376500
},
{
"epoch": 3.49,
"learning_rate": 1.626876633366078e-05,
"loss": 1.5929,
"step": 377000
},
{
"epoch": 3.5,
"learning_rate": 1.6257182177080052e-05,
"loss": 1.5882,
"step": 377500
},
{
"epoch": 3.5,
"learning_rate": 1.6245598020499326e-05,
"loss": 1.5934,
"step": 378000
},
{
"epoch": 3.51,
"learning_rate": 1.6234013863918596e-05,
"loss": 1.5902,
"step": 378500
},
{
"epoch": 3.51,
"learning_rate": 1.622245287565103e-05,
"loss": 1.5941,
"step": 379000
},
{
"epoch": 3.52,
"learning_rate": 1.6210891887383465e-05,
"loss": 1.5874,
"step": 379500
},
{
"epoch": 3.52,
"learning_rate": 1.619930773080274e-05,
"loss": 1.6113,
"step": 380000
},
{
"epoch": 3.52,
"eval_loss": 1.5287482738494873,
"eval_runtime": 1998.1926,
"eval_samples_per_second": 384.012,
"eval_steps_per_second": 6.0,
"step": 380000
},
{
"epoch": 3.53,
"learning_rate": 1.618772357422201e-05,
"loss": 1.5951,
"step": 380500
},
{
"epoch": 3.53,
"learning_rate": 1.617613941764128e-05,
"loss": 1.5844,
"step": 381000
},
{
"epoch": 3.54,
"learning_rate": 1.6164555261060557e-05,
"loss": 1.5849,
"step": 381500
},
{
"epoch": 3.54,
"learning_rate": 1.6152971104479827e-05,
"loss": 1.5853,
"step": 382000
},
{
"epoch": 3.54,
"learning_rate": 1.6141386947899097e-05,
"loss": 1.5878,
"step": 382500
},
{
"epoch": 3.55,
"learning_rate": 1.612980279131837e-05,
"loss": 1.6009,
"step": 383000
},
{
"epoch": 3.55,
"learning_rate": 1.6118241803050805e-05,
"loss": 1.5711,
"step": 383500
},
{
"epoch": 3.56,
"learning_rate": 1.6106657646470076e-05,
"loss": 1.5848,
"step": 384000
},
{
"epoch": 3.56,
"learning_rate": 1.609507348988935e-05,
"loss": 1.5962,
"step": 384500
},
{
"epoch": 3.57,
"learning_rate": 1.6083489333308623e-05,
"loss": 1.5806,
"step": 385000
},
{
"epoch": 3.57,
"learning_rate": 1.6071905176727893e-05,
"loss": 1.5795,
"step": 385500
},
{
"epoch": 3.58,
"learning_rate": 1.6060321020147167e-05,
"loss": 1.5875,
"step": 386000
},
{
"epoch": 3.58,
"learning_rate": 1.604873686356644e-05,
"loss": 1.5808,
"step": 386500
},
{
"epoch": 3.59,
"learning_rate": 1.603717587529887e-05,
"loss": 1.5882,
"step": 387000
},
{
"epoch": 3.59,
"learning_rate": 1.6025591718718145e-05,
"loss": 1.5792,
"step": 387500
},
{
"epoch": 3.6,
"learning_rate": 1.6014007562137415e-05,
"loss": 1.586,
"step": 388000
},
{
"epoch": 3.6,
"learning_rate": 1.600242340555669e-05,
"loss": 1.5861,
"step": 388500
},
{
"epoch": 3.6,
"learning_rate": 1.5990862417289124e-05,
"loss": 1.5798,
"step": 389000
},
{
"epoch": 3.61,
"learning_rate": 1.5979278260708394e-05,
"loss": 1.5888,
"step": 389500
},
{
"epoch": 3.61,
"learning_rate": 1.5967694104127668e-05,
"loss": 1.5923,
"step": 390000
},
{
"epoch": 3.61,
"eval_loss": 1.52175772190094,
"eval_runtime": 1998.4056,
"eval_samples_per_second": 383.971,
"eval_steps_per_second": 6.0,
"step": 390000
},
{
"epoch": 3.62,
"learning_rate": 1.5956133115860102e-05,
"loss": 1.5848,
"step": 390500
},
{
"epoch": 3.62,
"learning_rate": 1.5944548959279372e-05,
"loss": 1.5924,
"step": 391000
},
{
"epoch": 3.63,
"learning_rate": 1.5932964802698646e-05,
"loss": 1.5686,
"step": 391500
},
{
"epoch": 3.63,
"learning_rate": 1.592138064611792e-05,
"loss": 1.5884,
"step": 392000
},
{
"epoch": 3.64,
"learning_rate": 1.590981965785035e-05,
"loss": 1.595,
"step": 392500
},
{
"epoch": 3.64,
"learning_rate": 1.5898235501269625e-05,
"loss": 1.5845,
"step": 393000
},
{
"epoch": 3.65,
"learning_rate": 1.5886651344688898e-05,
"loss": 1.5817,
"step": 393500
},
{
"epoch": 3.65,
"learning_rate": 1.587506718810817e-05,
"loss": 1.5718,
"step": 394000
},
{
"epoch": 3.66,
"learning_rate": 1.5863506199840603e-05,
"loss": 1.5822,
"step": 394500
},
{
"epoch": 3.66,
"learning_rate": 1.5851922043259877e-05,
"loss": 1.5902,
"step": 395000
},
{
"epoch": 3.67,
"learning_rate": 1.584033788667915e-05,
"loss": 1.5927,
"step": 395500
},
{
"epoch": 3.67,
"learning_rate": 1.582875373009842e-05,
"loss": 1.5772,
"step": 396000
},
{
"epoch": 3.67,
"learning_rate": 1.581716957351769e-05,
"loss": 1.5846,
"step": 396500
},
{
"epoch": 3.68,
"learning_rate": 1.5805585416936965e-05,
"loss": 1.5931,
"step": 397000
},
{
"epoch": 3.68,
"learning_rate": 1.5794001260356238e-05,
"loss": 1.5667,
"step": 397500
},
{
"epoch": 3.69,
"learning_rate": 1.578241710377551e-05,
"loss": 1.5941,
"step": 398000
},
{
"epoch": 3.69,
"learning_rate": 1.5770832947194782e-05,
"loss": 1.595,
"step": 398500
},
{
"epoch": 3.7,
"learning_rate": 1.5759248790614056e-05,
"loss": 1.5962,
"step": 399000
},
{
"epoch": 3.7,
"learning_rate": 1.5747664634033326e-05,
"loss": 1.5764,
"step": 399500
},
{
"epoch": 3.71,
"learning_rate": 1.57360804774526e-05,
"loss": 1.579,
"step": 400000
},
{
"epoch": 3.71,
"eval_loss": 1.5175821781158447,
"eval_runtime": 1998.6499,
"eval_samples_per_second": 383.924,
"eval_steps_per_second": 5.999,
"step": 400000
},
{
"epoch": 3.71,
"learning_rate": 1.5724519489185034e-05,
"loss": 1.5755,
"step": 400500
},
{
"epoch": 3.72,
"learning_rate": 1.5712935332604304e-05,
"loss": 1.5805,
"step": 401000
},
{
"epoch": 3.72,
"learning_rate": 1.5701351176023578e-05,
"loss": 1.5796,
"step": 401500
},
{
"epoch": 3.73,
"learning_rate": 1.568976701944285e-05,
"loss": 1.5733,
"step": 402000
},
{
"epoch": 3.73,
"learning_rate": 1.5678182862862122e-05,
"loss": 1.5598,
"step": 402500
},
{
"epoch": 3.73,
"learning_rate": 1.5666621874594557e-05,
"loss": 1.5689,
"step": 403000
},
{
"epoch": 3.74,
"learning_rate": 1.5655037718013827e-05,
"loss": 1.5793,
"step": 403500
},
{
"epoch": 3.74,
"learning_rate": 1.56434535614331e-05,
"loss": 1.5778,
"step": 404000
},
{
"epoch": 3.75,
"learning_rate": 1.5631869404852374e-05,
"loss": 1.5861,
"step": 404500
},
{
"epoch": 3.75,
"learning_rate": 1.5620308416584805e-05,
"loss": 1.5817,
"step": 405000
},
{
"epoch": 3.76,
"learning_rate": 1.560872426000408e-05,
"loss": 1.5649,
"step": 405500
},
{
"epoch": 3.76,
"learning_rate": 1.5597140103423353e-05,
"loss": 1.5851,
"step": 406000
},
{
"epoch": 3.77,
"learning_rate": 1.5585579115155784e-05,
"loss": 1.5665,
"step": 406500
},
{
"epoch": 3.77,
"learning_rate": 1.5573994958575057e-05,
"loss": 1.569,
"step": 407000
},
{
"epoch": 3.78,
"learning_rate": 1.556241080199433e-05,
"loss": 1.5821,
"step": 407500
},
{
"epoch": 3.78,
"learning_rate": 1.55508266454136e-05,
"loss": 1.5693,
"step": 408000
},
{
"epoch": 3.79,
"learning_rate": 1.5539242488832875e-05,
"loss": 1.5843,
"step": 408500
},
{
"epoch": 3.79,
"learning_rate": 1.5527658332252145e-05,
"loss": 1.5877,
"step": 409000
},
{
"epoch": 3.79,
"learning_rate": 1.551607417567142e-05,
"loss": 1.568,
"step": 409500
},
{
"epoch": 3.8,
"learning_rate": 1.5504490019090693e-05,
"loss": 1.5775,
"step": 410000
},
{
"epoch": 3.8,
"eval_loss": 1.5105193853378296,
"eval_runtime": 1997.8257,
"eval_samples_per_second": 384.083,
"eval_steps_per_second": 6.002,
"step": 410000
},
{
"epoch": 3.8,
"learning_rate": 1.5492929030823124e-05,
"loss": 1.5768,
"step": 410500
},
{
"epoch": 3.81,
"learning_rate": 1.5481344874242397e-05,
"loss": 1.5655,
"step": 411000
},
{
"epoch": 3.81,
"learning_rate": 1.546976071766167e-05,
"loss": 1.5734,
"step": 411500
},
{
"epoch": 3.82,
"learning_rate": 1.545817656108094e-05,
"loss": 1.5684,
"step": 412000
},
{
"epoch": 3.82,
"learning_rate": 1.5446592404500215e-05,
"loss": 1.5805,
"step": 412500
},
{
"epoch": 3.83,
"learning_rate": 1.543503141623265e-05,
"loss": 1.5734,
"step": 413000
},
{
"epoch": 3.83,
"learning_rate": 1.542344725965192e-05,
"loss": 1.5735,
"step": 413500
},
{
"epoch": 3.84,
"learning_rate": 1.5411863103071193e-05,
"loss": 1.5752,
"step": 414000
},
{
"epoch": 3.84,
"learning_rate": 1.5400278946490467e-05,
"loss": 1.5717,
"step": 414500
},
{
"epoch": 3.85,
"learning_rate": 1.5388694789909737e-05,
"loss": 1.5703,
"step": 415000
},
{
"epoch": 3.85,
"learning_rate": 1.5377133801642172e-05,
"loss": 1.5783,
"step": 415500
},
{
"epoch": 3.86,
"learning_rate": 1.5365549645061446e-05,
"loss": 1.5777,
"step": 416000
},
{
"epoch": 3.86,
"learning_rate": 1.5353965488480716e-05,
"loss": 1.5749,
"step": 416500
},
{
"epoch": 3.86,
"learning_rate": 1.534238133189999e-05,
"loss": 1.5804,
"step": 417000
},
{
"epoch": 3.87,
"learning_rate": 1.533082034363242e-05,
"loss": 1.5706,
"step": 417500
},
{
"epoch": 3.87,
"learning_rate": 1.5319236187051694e-05,
"loss": 1.5859,
"step": 418000
},
{
"epoch": 3.88,
"learning_rate": 1.5307652030470968e-05,
"loss": 1.557,
"step": 418500
},
{
"epoch": 3.88,
"learning_rate": 1.5296067873890238e-05,
"loss": 1.5684,
"step": 419000
},
{
"epoch": 3.89,
"learning_rate": 1.5284483717309512e-05,
"loss": 1.5805,
"step": 419500
},
{
"epoch": 3.89,
"learning_rate": 1.5272922729041946e-05,
"loss": 1.5615,
"step": 420000
},
{
"epoch": 3.89,
"eval_loss": 1.5067431926727295,
"eval_runtime": 1997.9824,
"eval_samples_per_second": 384.052,
"eval_steps_per_second": 6.001,
"step": 420000
},
{
"epoch": 3.9,
"learning_rate": 1.5261338572461217e-05,
"loss": 1.5702,
"step": 420500
},
{
"epoch": 3.9,
"learning_rate": 1.5249754415880489e-05,
"loss": 1.569,
"step": 421000
},
{
"epoch": 3.91,
"learning_rate": 1.5238170259299762e-05,
"loss": 1.568,
"step": 421500
},
{
"epoch": 3.91,
"learning_rate": 1.5226586102719034e-05,
"loss": 1.5841,
"step": 422000
},
{
"epoch": 3.92,
"learning_rate": 1.5215001946138306e-05,
"loss": 1.5791,
"step": 422500
},
{
"epoch": 3.92,
"learning_rate": 1.520341778955758e-05,
"loss": 1.5619,
"step": 423000
},
{
"epoch": 3.92,
"learning_rate": 1.5191833632976852e-05,
"loss": 1.5795,
"step": 423500
},
{
"epoch": 3.93,
"learning_rate": 1.5180272644709286e-05,
"loss": 1.5809,
"step": 424000
},
{
"epoch": 3.93,
"learning_rate": 1.5168688488128558e-05,
"loss": 1.5645,
"step": 424500
},
{
"epoch": 3.94,
"learning_rate": 1.515710433154783e-05,
"loss": 1.5644,
"step": 425000
},
{
"epoch": 3.94,
"learning_rate": 1.5145520174967104e-05,
"loss": 1.565,
"step": 425500
},
{
"epoch": 3.95,
"learning_rate": 1.5133959186699537e-05,
"loss": 1.5888,
"step": 426000
},
{
"epoch": 3.95,
"learning_rate": 1.5122375030118807e-05,
"loss": 1.5679,
"step": 426500
},
{
"epoch": 3.96,
"learning_rate": 1.511079087353808e-05,
"loss": 1.5626,
"step": 427000
},
{
"epoch": 3.96,
"learning_rate": 1.5099206716957353e-05,
"loss": 1.5731,
"step": 427500
},
{
"epoch": 3.97,
"learning_rate": 1.5087622560376625e-05,
"loss": 1.5644,
"step": 428000
},
{
"epoch": 3.97,
"learning_rate": 1.507606157210906e-05,
"loss": 1.5638,
"step": 428500
},
{
"epoch": 3.98,
"learning_rate": 1.5064477415528331e-05,
"loss": 1.5619,
"step": 429000
},
{
"epoch": 3.98,
"learning_rate": 1.5052916427260764e-05,
"loss": 1.5774,
"step": 429500
},
{
"epoch": 3.98,
"learning_rate": 1.5041332270680038e-05,
"loss": 1.5751,
"step": 430000
},
{
"epoch": 3.98,
"eval_loss": 1.5027018785476685,
"eval_runtime": 2000.1605,
"eval_samples_per_second": 383.634,
"eval_steps_per_second": 5.995,
"step": 430000
},
{
"epoch": 3.99,
"learning_rate": 1.502974811409931e-05,
"loss": 1.5667,
"step": 430500
},
{
"epoch": 3.99,
"learning_rate": 1.5018163957518582e-05,
"loss": 1.5677,
"step": 431000
},
{
"epoch": 4.0,
"learning_rate": 1.5006579800937855e-05,
"loss": 1.5624,
"step": 431500
},
{
"epoch": 4.0,
"learning_rate": 1.4994995644357127e-05,
"loss": 1.5649,
"step": 432000
},
{
"epoch": 4.01,
"learning_rate": 1.49834114877764e-05,
"loss": 1.5632,
"step": 432500
},
{
"epoch": 4.01,
"learning_rate": 1.4971827331195671e-05,
"loss": 1.5674,
"step": 433000
},
{
"epoch": 4.02,
"learning_rate": 1.4960243174614943e-05,
"loss": 1.5571,
"step": 433500
},
{
"epoch": 4.02,
"learning_rate": 1.4948659018034217e-05,
"loss": 1.5595,
"step": 434000
},
{
"epoch": 4.03,
"learning_rate": 1.4937074861453489e-05,
"loss": 1.5655,
"step": 434500
},
{
"epoch": 4.03,
"learning_rate": 1.492549070487276e-05,
"loss": 1.5499,
"step": 435000
},
{
"epoch": 4.04,
"learning_rate": 1.4913906548292034e-05,
"loss": 1.5554,
"step": 435500
},
{
"epoch": 4.04,
"learning_rate": 1.4902345560024467e-05,
"loss": 1.5872,
"step": 436000
},
{
"epoch": 4.05,
"learning_rate": 1.4890761403443739e-05,
"loss": 1.5573,
"step": 436500
},
{
"epoch": 4.05,
"learning_rate": 1.4879177246863013e-05,
"loss": 1.5624,
"step": 437000
},
{
"epoch": 4.05,
"learning_rate": 1.4867593090282285e-05,
"loss": 1.5599,
"step": 437500
},
{
"epoch": 4.06,
"learning_rate": 1.4856008933701555e-05,
"loss": 1.5643,
"step": 438000
},
{
"epoch": 4.06,
"learning_rate": 1.484442477712083e-05,
"loss": 1.5671,
"step": 438500
},
{
"epoch": 4.07,
"learning_rate": 1.4832863788853263e-05,
"loss": 1.551,
"step": 439000
},
{
"epoch": 4.07,
"learning_rate": 1.4821279632272533e-05,
"loss": 1.5572,
"step": 439500
},
{
"epoch": 4.08,
"learning_rate": 1.4809695475691807e-05,
"loss": 1.5659,
"step": 440000
},
{
"epoch": 4.08,
"eval_loss": 1.5023467540740967,
"eval_runtime": 2000.2264,
"eval_samples_per_second": 383.622,
"eval_steps_per_second": 5.994,
"step": 440000
},
{
"epoch": 4.08,
"learning_rate": 1.4798111319111079e-05,
"loss": 1.5507,
"step": 440500
},
{
"epoch": 4.09,
"learning_rate": 1.4786527162530351e-05,
"loss": 1.5562,
"step": 441000
},
{
"epoch": 4.09,
"learning_rate": 1.4774966174262786e-05,
"loss": 1.5578,
"step": 441500
},
{
"epoch": 4.1,
"learning_rate": 1.4763382017682057e-05,
"loss": 1.565,
"step": 442000
},
{
"epoch": 4.1,
"learning_rate": 1.475179786110133e-05,
"loss": 1.5528,
"step": 442500
},
{
"epoch": 4.11,
"learning_rate": 1.4740213704520603e-05,
"loss": 1.5588,
"step": 443000
},
{
"epoch": 4.11,
"learning_rate": 1.4728652716253036e-05,
"loss": 1.5516,
"step": 443500
},
{
"epoch": 4.11,
"learning_rate": 1.471706855967231e-05,
"loss": 1.5727,
"step": 444000
},
{
"epoch": 4.12,
"learning_rate": 1.4705484403091582e-05,
"loss": 1.5583,
"step": 444500
},
{
"epoch": 4.12,
"learning_rate": 1.4693900246510853e-05,
"loss": 1.5475,
"step": 445000
},
{
"epoch": 4.13,
"learning_rate": 1.4682316089930127e-05,
"loss": 1.5435,
"step": 445500
},
{
"epoch": 4.13,
"learning_rate": 1.4670731933349397e-05,
"loss": 1.5477,
"step": 446000
},
{
"epoch": 4.14,
"learning_rate": 1.465914777676867e-05,
"loss": 1.553,
"step": 446500
},
{
"epoch": 4.14,
"learning_rate": 1.4647563620187943e-05,
"loss": 1.5624,
"step": 447000
},
{
"epoch": 4.15,
"learning_rate": 1.4636002631920376e-05,
"loss": 1.5482,
"step": 447500
},
{
"epoch": 4.15,
"learning_rate": 1.4624418475339648e-05,
"loss": 1.5516,
"step": 448000
},
{
"epoch": 4.16,
"learning_rate": 1.4612834318758921e-05,
"loss": 1.5532,
"step": 448500
},
{
"epoch": 4.16,
"learning_rate": 1.4601250162178193e-05,
"loss": 1.5499,
"step": 449000
},
{
"epoch": 4.17,
"learning_rate": 1.4589666005597465e-05,
"loss": 1.5481,
"step": 449500
},
{
"epoch": 4.17,
"learning_rate": 1.45781050173299e-05,
"loss": 1.5573,
"step": 450000
},
{
"epoch": 4.17,
"eval_loss": 1.4936351776123047,
"eval_runtime": 2001.439,
"eval_samples_per_second": 383.389,
"eval_steps_per_second": 5.991,
"step": 450000
},
{
"epoch": 4.17,
"learning_rate": 1.4566520860749172e-05,
"loss": 1.5531,
"step": 450500
},
{
"epoch": 4.18,
"learning_rate": 1.4554959872481607e-05,
"loss": 1.555,
"step": 451000
},
{
"epoch": 4.18,
"learning_rate": 1.4543375715900878e-05,
"loss": 1.5557,
"step": 451500
},
{
"epoch": 4.19,
"learning_rate": 1.4531814727633311e-05,
"loss": 1.5578,
"step": 452000
},
{
"epoch": 4.19,
"learning_rate": 1.4520230571052585e-05,
"loss": 1.5575,
"step": 452500
},
{
"epoch": 4.2,
"learning_rate": 1.4508646414471857e-05,
"loss": 1.5506,
"step": 453000
},
{
"epoch": 4.2,
"learning_rate": 1.4497062257891127e-05,
"loss": 1.5497,
"step": 453500
},
{
"epoch": 4.21,
"learning_rate": 1.4485478101310403e-05,
"loss": 1.5587,
"step": 454000
},
{
"epoch": 4.21,
"learning_rate": 1.4473917113042835e-05,
"loss": 1.5447,
"step": 454500
},
{
"epoch": 4.22,
"learning_rate": 1.4462332956462106e-05,
"loss": 1.5462,
"step": 455000
},
{
"epoch": 4.22,
"learning_rate": 1.445074879988138e-05,
"loss": 1.5574,
"step": 455500
},
{
"epoch": 4.23,
"learning_rate": 1.4439164643300651e-05,
"loss": 1.5467,
"step": 456000
},
{
"epoch": 4.23,
"learning_rate": 1.4427580486719923e-05,
"loss": 1.5487,
"step": 456500
},
{
"epoch": 4.24,
"learning_rate": 1.4415996330139197e-05,
"loss": 1.5651,
"step": 457000
},
{
"epoch": 4.24,
"learning_rate": 1.4404412173558469e-05,
"loss": 1.5435,
"step": 457500
},
{
"epoch": 4.24,
"learning_rate": 1.439282801697774e-05,
"loss": 1.5465,
"step": 458000
},
{
"epoch": 4.25,
"learning_rate": 1.4381243860397014e-05,
"loss": 1.5473,
"step": 458500
},
{
"epoch": 4.25,
"learning_rate": 1.4369659703816285e-05,
"loss": 1.548,
"step": 459000
},
{
"epoch": 4.26,
"learning_rate": 1.4358075547235557e-05,
"loss": 1.5488,
"step": 459500
},
{
"epoch": 4.26,
"learning_rate": 1.4346514558967993e-05,
"loss": 1.5429,
"step": 460000
},
{
"epoch": 4.26,
"eval_loss": 1.4894782304763794,
"eval_runtime": 1998.7971,
"eval_samples_per_second": 383.896,
"eval_steps_per_second": 5.999,
"step": 460000
},
{
"epoch": 4.27,
"learning_rate": 1.4334930402387263e-05,
"loss": 1.547,
"step": 460500
},
{
"epoch": 4.27,
"learning_rate": 1.4323346245806537e-05,
"loss": 1.5471,
"step": 461000
},
{
"epoch": 4.28,
"learning_rate": 1.4311762089225809e-05,
"loss": 1.5421,
"step": 461500
},
{
"epoch": 4.28,
"learning_rate": 1.430017793264508e-05,
"loss": 1.5328,
"step": 462000
},
{
"epoch": 4.29,
"learning_rate": 1.4288593776064354e-05,
"loss": 1.5514,
"step": 462500
},
{
"epoch": 4.29,
"learning_rate": 1.4277032787796787e-05,
"loss": 1.5383,
"step": 463000
},
{
"epoch": 4.3,
"learning_rate": 1.426544863121606e-05,
"loss": 1.5511,
"step": 463500
},
{
"epoch": 4.3,
"learning_rate": 1.4253864474635333e-05,
"loss": 1.5645,
"step": 464000
},
{
"epoch": 4.3,
"learning_rate": 1.4242280318054605e-05,
"loss": 1.5447,
"step": 464500
},
{
"epoch": 4.31,
"learning_rate": 1.4230696161473877e-05,
"loss": 1.56,
"step": 465000
},
{
"epoch": 4.31,
"learning_rate": 1.421911200489315e-05,
"loss": 1.5522,
"step": 465500
},
{
"epoch": 4.32,
"learning_rate": 1.420752784831242e-05,
"loss": 1.549,
"step": 466000
},
{
"epoch": 4.32,
"learning_rate": 1.4195943691731693e-05,
"loss": 1.5538,
"step": 466500
},
{
"epoch": 4.33,
"learning_rate": 1.4184382703464127e-05,
"loss": 1.552,
"step": 467000
},
{
"epoch": 4.33,
"learning_rate": 1.4172798546883399e-05,
"loss": 1.559,
"step": 467500
},
{
"epoch": 4.34,
"learning_rate": 1.4161237558615832e-05,
"loss": 1.5409,
"step": 468000
},
{
"epoch": 4.34,
"learning_rate": 1.4149653402035106e-05,
"loss": 1.5435,
"step": 468500
},
{
"epoch": 4.35,
"learning_rate": 1.4138069245454378e-05,
"loss": 1.5331,
"step": 469000
},
{
"epoch": 4.35,
"learning_rate": 1.4126485088873651e-05,
"loss": 1.5413,
"step": 469500
},
{
"epoch": 4.36,
"learning_rate": 1.4114900932292923e-05,
"loss": 1.5462,
"step": 470000
},
{
"epoch": 4.36,
"eval_loss": 1.4869228601455688,
"eval_runtime": 1997.9766,
"eval_samples_per_second": 384.054,
"eval_steps_per_second": 6.001,
"step": 470000
},
{
"epoch": 4.36,
"learning_rate": 1.4103316775712195e-05,
"loss": 1.5479,
"step": 470500
},
{
"epoch": 4.36,
"learning_rate": 1.4091732619131469e-05,
"loss": 1.5427,
"step": 471000
},
{
"epoch": 4.37,
"learning_rate": 1.408014846255074e-05,
"loss": 1.5539,
"step": 471500
},
{
"epoch": 4.37,
"learning_rate": 1.4068564305970011e-05,
"loss": 1.5543,
"step": 472000
},
{
"epoch": 4.38,
"learning_rate": 1.4057003317702447e-05,
"loss": 1.553,
"step": 472500
},
{
"epoch": 4.38,
"learning_rate": 1.4045419161121718e-05,
"loss": 1.5592,
"step": 473000
},
{
"epoch": 4.39,
"learning_rate": 1.403383500454099e-05,
"loss": 1.5445,
"step": 473500
},
{
"epoch": 4.39,
"learning_rate": 1.4022250847960263e-05,
"loss": 1.544,
"step": 474000
},
{
"epoch": 4.4,
"learning_rate": 1.4010666691379535e-05,
"loss": 1.5354,
"step": 474500
},
{
"epoch": 4.4,
"learning_rate": 1.3999082534798807e-05,
"loss": 1.5322,
"step": 475000
},
{
"epoch": 4.41,
"learning_rate": 1.3987544714844403e-05,
"loss": 1.5421,
"step": 475500
},
{
"epoch": 4.41,
"learning_rate": 1.3975960558263675e-05,
"loss": 1.5483,
"step": 476000
},
{
"epoch": 4.42,
"learning_rate": 1.3964376401682946e-05,
"loss": 1.5266,
"step": 476500
},
{
"epoch": 4.42,
"learning_rate": 1.3952815413415381e-05,
"loss": 1.5302,
"step": 477000
},
{
"epoch": 4.43,
"learning_rate": 1.3941231256834653e-05,
"loss": 1.5295,
"step": 477500
},
{
"epoch": 4.43,
"learning_rate": 1.3929647100253927e-05,
"loss": 1.5415,
"step": 478000
},
{
"epoch": 4.43,
"learning_rate": 1.3918062943673199e-05,
"loss": 1.5448,
"step": 478500
},
{
"epoch": 4.44,
"learning_rate": 1.390647878709247e-05,
"loss": 1.5322,
"step": 479000
},
{
"epoch": 4.44,
"learning_rate": 1.3894894630511744e-05,
"loss": 1.5509,
"step": 479500
},
{
"epoch": 4.45,
"learning_rate": 1.3883310473931016e-05,
"loss": 1.5417,
"step": 480000
},
{
"epoch": 4.45,
"eval_loss": 1.4829367399215698,
"eval_runtime": 1997.9031,
"eval_samples_per_second": 384.068,
"eval_steps_per_second": 6.001,
"step": 480000
},
{
"epoch": 4.45,
"learning_rate": 1.3871726317350286e-05,
"loss": 1.5444,
"step": 480500
},
{
"epoch": 4.46,
"learning_rate": 1.386014216076956e-05,
"loss": 1.5313,
"step": 481000
},
{
"epoch": 4.46,
"learning_rate": 1.3848558004188832e-05,
"loss": 1.5362,
"step": 481500
},
{
"epoch": 4.47,
"learning_rate": 1.3836997015921265e-05,
"loss": 1.5209,
"step": 482000
},
{
"epoch": 4.47,
"learning_rate": 1.3825412859340539e-05,
"loss": 1.5396,
"step": 482500
},
{
"epoch": 4.48,
"learning_rate": 1.381382870275981e-05,
"loss": 1.5433,
"step": 483000
},
{
"epoch": 4.48,
"learning_rate": 1.3802244546179082e-05,
"loss": 1.5279,
"step": 483500
},
{
"epoch": 4.49,
"learning_rate": 1.3790660389598356e-05,
"loss": 1.5396,
"step": 484000
},
{
"epoch": 4.49,
"learning_rate": 1.3779076233017628e-05,
"loss": 1.5437,
"step": 484500
},
{
"epoch": 4.49,
"learning_rate": 1.3767492076436898e-05,
"loss": 1.5359,
"step": 485000
},
{
"epoch": 4.5,
"learning_rate": 1.3755907919856174e-05,
"loss": 1.5416,
"step": 485500
},
{
"epoch": 4.5,
"learning_rate": 1.3744323763275444e-05,
"loss": 1.5272,
"step": 486000
},
{
"epoch": 4.51,
"learning_rate": 1.3732739606694716e-05,
"loss": 1.5326,
"step": 486500
},
{
"epoch": 4.51,
"learning_rate": 1.372117861842715e-05,
"loss": 1.5401,
"step": 487000
},
{
"epoch": 4.52,
"learning_rate": 1.3709617630159583e-05,
"loss": 1.5244,
"step": 487500
},
{
"epoch": 4.52,
"learning_rate": 1.3698033473578859e-05,
"loss": 1.5431,
"step": 488000
},
{
"epoch": 4.53,
"learning_rate": 1.3686449316998129e-05,
"loss": 1.5336,
"step": 488500
},
{
"epoch": 4.53,
"learning_rate": 1.3674865160417401e-05,
"loss": 1.556,
"step": 489000
},
{
"epoch": 4.54,
"learning_rate": 1.3663281003836675e-05,
"loss": 1.5338,
"step": 489500
},
{
"epoch": 4.54,
"learning_rate": 1.3651720015569107e-05,
"loss": 1.5323,
"step": 490000
},
{
"epoch": 4.54,
"eval_loss": 1.4786036014556885,
"eval_runtime": 1998.2754,
"eval_samples_per_second": 383.996,
"eval_steps_per_second": 6.0,
"step": 490000
},
{
"epoch": 4.55,
"learning_rate": 1.364013585898838e-05,
"loss": 1.5298,
"step": 490500
},
{
"epoch": 4.55,
"learning_rate": 1.3628551702407653e-05,
"loss": 1.5347,
"step": 491000
},
{
"epoch": 4.55,
"learning_rate": 1.3616967545826925e-05,
"loss": 1.5355,
"step": 491500
},
{
"epoch": 4.56,
"learning_rate": 1.3605383389246197e-05,
"loss": 1.5312,
"step": 492000
},
{
"epoch": 4.56,
"learning_rate": 1.359379923266547e-05,
"loss": 1.5325,
"step": 492500
},
{
"epoch": 4.57,
"learning_rate": 1.3582238244397903e-05,
"loss": 1.5358,
"step": 493000
},
{
"epoch": 4.57,
"learning_rate": 1.3570654087817174e-05,
"loss": 1.5296,
"step": 493500
},
{
"epoch": 4.58,
"learning_rate": 1.3559069931236449e-05,
"loss": 1.5383,
"step": 494000
},
{
"epoch": 4.58,
"learning_rate": 1.354748577465572e-05,
"loss": 1.5451,
"step": 494500
},
{
"epoch": 4.59,
"learning_rate": 1.3535901618074991e-05,
"loss": 1.5337,
"step": 495000
},
{
"epoch": 4.59,
"learning_rate": 1.3524340629807426e-05,
"loss": 1.5362,
"step": 495500
},
{
"epoch": 4.6,
"learning_rate": 1.3512756473226698e-05,
"loss": 1.5209,
"step": 496000
},
{
"epoch": 4.6,
"learning_rate": 1.3501172316645971e-05,
"loss": 1.5457,
"step": 496500
},
{
"epoch": 4.61,
"learning_rate": 1.3489588160065243e-05,
"loss": 1.5349,
"step": 497000
},
{
"epoch": 4.61,
"learning_rate": 1.3478004003484515e-05,
"loss": 1.54,
"step": 497500
},
{
"epoch": 4.62,
"learning_rate": 1.3466419846903789e-05,
"loss": 1.5432,
"step": 498000
},
{
"epoch": 4.62,
"learning_rate": 1.3454835690323061e-05,
"loss": 1.5437,
"step": 498500
},
{
"epoch": 4.62,
"learning_rate": 1.3443274702055494e-05,
"loss": 1.5251,
"step": 499000
},
{
"epoch": 4.63,
"learning_rate": 1.3431690545474767e-05,
"loss": 1.5419,
"step": 499500
},
{
"epoch": 4.63,
"learning_rate": 1.34201295572072e-05,
"loss": 1.5227,
"step": 500000
},
{
"epoch": 4.63,
"eval_loss": 1.474404215812683,
"eval_runtime": 1998.7036,
"eval_samples_per_second": 383.914,
"eval_steps_per_second": 5.999,
"step": 500000
},
{
"epoch": 4.64,
"learning_rate": 1.3408545400626472e-05,
"loss": 1.5347,
"step": 500500
},
{
"epoch": 4.64,
"learning_rate": 1.3396961244045746e-05,
"loss": 1.5279,
"step": 501000
},
{
"epoch": 4.65,
"learning_rate": 1.3385377087465016e-05,
"loss": 1.5359,
"step": 501500
},
{
"epoch": 4.65,
"learning_rate": 1.3373792930884288e-05,
"loss": 1.5441,
"step": 502000
},
{
"epoch": 4.66,
"learning_rate": 1.3362208774303562e-05,
"loss": 1.5328,
"step": 502500
},
{
"epoch": 4.66,
"learning_rate": 1.3350624617722834e-05,
"loss": 1.5331,
"step": 503000
},
{
"epoch": 4.67,
"learning_rate": 1.3339040461142106e-05,
"loss": 1.5143,
"step": 503500
},
{
"epoch": 4.67,
"learning_rate": 1.332745630456138e-05,
"loss": 1.528,
"step": 504000
},
{
"epoch": 4.68,
"learning_rate": 1.3315872147980651e-05,
"loss": 1.5245,
"step": 504500
},
{
"epoch": 4.68,
"learning_rate": 1.3304287991399922e-05,
"loss": 1.5178,
"step": 505000
},
{
"epoch": 4.68,
"learning_rate": 1.3292703834819197e-05,
"loss": 1.5393,
"step": 505500
},
{
"epoch": 4.69,
"learning_rate": 1.328114284655163e-05,
"loss": 1.532,
"step": 506000
},
{
"epoch": 4.69,
"learning_rate": 1.32695586899709e-05,
"loss": 1.5383,
"step": 506500
},
{
"epoch": 4.7,
"learning_rate": 1.3257974533390174e-05,
"loss": 1.5328,
"step": 507000
},
{
"epoch": 4.7,
"learning_rate": 1.3246390376809446e-05,
"loss": 1.533,
"step": 507500
},
{
"epoch": 4.71,
"learning_rate": 1.323480622022872e-05,
"loss": 1.5164,
"step": 508000
},
{
"epoch": 4.71,
"learning_rate": 1.3223222063647991e-05,
"loss": 1.5429,
"step": 508500
},
{
"epoch": 4.72,
"learning_rate": 1.3211661075380424e-05,
"loss": 1.5477,
"step": 509000
},
{
"epoch": 4.72,
"learning_rate": 1.3200076918799698e-05,
"loss": 1.549,
"step": 509500
},
{
"epoch": 4.73,
"learning_rate": 1.318849276221897e-05,
"loss": 1.5389,
"step": 510000
},
{
"epoch": 4.73,
"eval_loss": 1.4718245267868042,
"eval_runtime": 1998.8873,
"eval_samples_per_second": 383.879,
"eval_steps_per_second": 5.998,
"step": 510000
},
{
"epoch": 4.73,
"learning_rate": 1.3176908605638242e-05,
"loss": 1.5396,
"step": 510500
},
{
"epoch": 4.74,
"learning_rate": 1.3165324449057515e-05,
"loss": 1.5304,
"step": 511000
},
{
"epoch": 4.74,
"learning_rate": 1.3153740292476787e-05,
"loss": 1.5193,
"step": 511500
},
{
"epoch": 4.74,
"learning_rate": 1.3142156135896057e-05,
"loss": 1.5189,
"step": 512000
},
{
"epoch": 4.75,
"learning_rate": 1.3130571979315331e-05,
"loss": 1.5348,
"step": 512500
},
{
"epoch": 4.75,
"learning_rate": 1.3118987822734603e-05,
"loss": 1.5284,
"step": 513000
},
{
"epoch": 4.76,
"learning_rate": 1.3107403666153875e-05,
"loss": 1.5292,
"step": 513500
},
{
"epoch": 4.76,
"learning_rate": 1.3095819509573149e-05,
"loss": 1.5246,
"step": 514000
},
{
"epoch": 4.77,
"learning_rate": 1.308423535299242e-05,
"loss": 1.5415,
"step": 514500
},
{
"epoch": 4.77,
"learning_rate": 1.3072651196411693e-05,
"loss": 1.5306,
"step": 515000
},
{
"epoch": 4.78,
"learning_rate": 1.3061090208144127e-05,
"loss": 1.526,
"step": 515500
},
{
"epoch": 4.78,
"learning_rate": 1.3049506051563399e-05,
"loss": 1.5251,
"step": 516000
},
{
"epoch": 4.79,
"learning_rate": 1.3037945063295832e-05,
"loss": 1.5253,
"step": 516500
},
{
"epoch": 4.79,
"learning_rate": 1.3026360906715106e-05,
"loss": 1.5314,
"step": 517000
},
{
"epoch": 4.8,
"learning_rate": 1.3014776750134378e-05,
"loss": 1.531,
"step": 517500
},
{
"epoch": 4.8,
"learning_rate": 1.3003192593553651e-05,
"loss": 1.5283,
"step": 518000
},
{
"epoch": 4.81,
"learning_rate": 1.2991631605286084e-05,
"loss": 1.5219,
"step": 518500
},
{
"epoch": 4.81,
"learning_rate": 1.2980047448705354e-05,
"loss": 1.5331,
"step": 519000
},
{
"epoch": 4.81,
"learning_rate": 1.296846329212463e-05,
"loss": 1.5348,
"step": 519500
},
{
"epoch": 4.82,
"learning_rate": 1.29568791355439e-05,
"loss": 1.5394,
"step": 520000
},
{
"epoch": 4.82,
"eval_loss": 1.4706006050109863,
"eval_runtime": 1998.7255,
"eval_samples_per_second": 383.91,
"eval_steps_per_second": 5.999,
"step": 520000
},
{
"epoch": 4.82,
"learning_rate": 1.2945318147276333e-05,
"loss": 1.5064,
"step": 520500
},
{
"epoch": 4.83,
"learning_rate": 1.293375715900877e-05,
"loss": 1.5129,
"step": 521000
},
{
"epoch": 4.83,
"learning_rate": 1.292217300242804e-05,
"loss": 1.5204,
"step": 521500
},
{
"epoch": 4.84,
"learning_rate": 1.2910588845847311e-05,
"loss": 1.5225,
"step": 522000
},
{
"epoch": 4.84,
"learning_rate": 1.2899004689266585e-05,
"loss": 1.5261,
"step": 522500
},
{
"epoch": 4.85,
"learning_rate": 1.2887420532685857e-05,
"loss": 1.5275,
"step": 523000
},
{
"epoch": 4.85,
"learning_rate": 1.2875836376105129e-05,
"loss": 1.5301,
"step": 523500
},
{
"epoch": 4.86,
"learning_rate": 1.2864252219524403e-05,
"loss": 1.5202,
"step": 524000
},
{
"epoch": 4.86,
"learning_rate": 1.2852668062943675e-05,
"loss": 1.5295,
"step": 524500
},
{
"epoch": 4.87,
"learning_rate": 1.2841083906362945e-05,
"loss": 1.5149,
"step": 525000
},
{
"epoch": 4.87,
"learning_rate": 1.2829522918095381e-05,
"loss": 1.5159,
"step": 525500
},
{
"epoch": 4.87,
"learning_rate": 1.2817938761514653e-05,
"loss": 1.5224,
"step": 526000
},
{
"epoch": 4.88,
"learning_rate": 1.2806354604933927e-05,
"loss": 1.5322,
"step": 526500
},
{
"epoch": 4.88,
"learning_rate": 1.279479361666636e-05,
"loss": 1.5264,
"step": 527000
},
{
"epoch": 4.89,
"learning_rate": 1.278320946008563e-05,
"loss": 1.5324,
"step": 527500
},
{
"epoch": 4.89,
"learning_rate": 1.2771625303504903e-05,
"loss": 1.5316,
"step": 528000
},
{
"epoch": 4.9,
"learning_rate": 1.2760041146924175e-05,
"loss": 1.5324,
"step": 528500
},
{
"epoch": 4.9,
"learning_rate": 1.2748456990343447e-05,
"loss": 1.5262,
"step": 529000
},
{
"epoch": 4.91,
"learning_rate": 1.2736872833762721e-05,
"loss": 1.5268,
"step": 529500
},
{
"epoch": 4.91,
"learning_rate": 1.2725288677181993e-05,
"loss": 1.5209,
"step": 530000
},
{
"epoch": 4.91,
"eval_loss": 1.4657567739486694,
"eval_runtime": 2001.499,
"eval_samples_per_second": 383.378,
"eval_steps_per_second": 5.991,
"step": 530000
},
{
"epoch": 4.92,
"learning_rate": 1.2713704520601265e-05,
"loss": 1.5229,
"step": 530500
},
{
"epoch": 4.92,
"learning_rate": 1.2702120364020539e-05,
"loss": 1.5327,
"step": 531000
},
{
"epoch": 4.93,
"learning_rate": 1.2690559375752971e-05,
"loss": 1.5233,
"step": 531500
},
{
"epoch": 4.93,
"learning_rate": 1.2678998387485404e-05,
"loss": 1.5367,
"step": 532000
},
{
"epoch": 4.93,
"learning_rate": 1.2667414230904678e-05,
"loss": 1.5202,
"step": 532500
},
{
"epoch": 4.94,
"learning_rate": 1.265583007432395e-05,
"loss": 1.5392,
"step": 533000
},
{
"epoch": 4.94,
"learning_rate": 1.2644245917743224e-05,
"loss": 1.522,
"step": 533500
},
{
"epoch": 4.95,
"learning_rate": 1.2632661761162494e-05,
"loss": 1.5223,
"step": 534000
},
{
"epoch": 4.95,
"learning_rate": 1.2621077604581766e-05,
"loss": 1.5172,
"step": 534500
},
{
"epoch": 4.96,
"learning_rate": 1.260949344800104e-05,
"loss": 1.5137,
"step": 535000
},
{
"epoch": 4.96,
"learning_rate": 1.2597909291420311e-05,
"loss": 1.5356,
"step": 535500
},
{
"epoch": 4.97,
"learning_rate": 1.2586348303152744e-05,
"loss": 1.5263,
"step": 536000
},
{
"epoch": 4.97,
"learning_rate": 1.2574764146572018e-05,
"loss": 1.5194,
"step": 536500
},
{
"epoch": 4.98,
"learning_rate": 1.256317998999129e-05,
"loss": 1.5232,
"step": 537000
},
{
"epoch": 4.98,
"learning_rate": 1.2551595833410562e-05,
"loss": 1.5266,
"step": 537500
},
{
"epoch": 4.99,
"learning_rate": 1.2540011676829835e-05,
"loss": 1.5169,
"step": 538000
},
{
"epoch": 4.99,
"learning_rate": 1.2528427520249107e-05,
"loss": 1.5231,
"step": 538500
},
{
"epoch": 5.0,
"learning_rate": 1.2516843363668378e-05,
"loss": 1.5231,
"step": 539000
},
{
"epoch": 5.0,
"learning_rate": 1.2505259207087653e-05,
"loss": 1.5286,
"step": 539500
},
{
"epoch": 5.0,
"learning_rate": 1.2493675050506923e-05,
"loss": 1.5142,
"step": 540000
},
{
"epoch": 5.0,
"eval_loss": 1.4590072631835938,
"eval_runtime": 2001.8934,
"eval_samples_per_second": 383.302,
"eval_steps_per_second": 5.989,
"step": 540000
},
{
"epoch": 5.01,
"learning_rate": 1.2482090893926195e-05,
"loss": 1.5121,
"step": 540500
},
{
"epoch": 5.01,
"learning_rate": 1.247052990565863e-05,
"loss": 1.5309,
"step": 541000
},
{
"epoch": 5.02,
"learning_rate": 1.2458968917391063e-05,
"loss": 1.5201,
"step": 541500
},
{
"epoch": 5.02,
"learning_rate": 1.2447384760810335e-05,
"loss": 1.5236,
"step": 542000
},
{
"epoch": 5.03,
"learning_rate": 1.2435800604229608e-05,
"loss": 1.525,
"step": 542500
},
{
"epoch": 5.03,
"learning_rate": 1.242421644764888e-05,
"loss": 1.5126,
"step": 543000
},
{
"epoch": 5.04,
"learning_rate": 1.2412632291068152e-05,
"loss": 1.5153,
"step": 543500
},
{
"epoch": 5.04,
"learning_rate": 1.2401048134487426e-05,
"loss": 1.5196,
"step": 544000
},
{
"epoch": 5.05,
"learning_rate": 1.2389463977906698e-05,
"loss": 1.5245,
"step": 544500
},
{
"epoch": 5.05,
"learning_rate": 1.2377879821325971e-05,
"loss": 1.5046,
"step": 545000
},
{
"epoch": 5.06,
"learning_rate": 1.2366295664745243e-05,
"loss": 1.5255,
"step": 545500
},
{
"epoch": 5.06,
"learning_rate": 1.2354711508164514e-05,
"loss": 1.5024,
"step": 546000
},
{
"epoch": 5.06,
"learning_rate": 1.2343127351583787e-05,
"loss": 1.508,
"step": 546500
},
{
"epoch": 5.07,
"learning_rate": 1.233156636331622e-05,
"loss": 1.5105,
"step": 547000
},
{
"epoch": 5.07,
"learning_rate": 1.2319982206735492e-05,
"loss": 1.5232,
"step": 547500
},
{
"epoch": 5.08,
"learning_rate": 1.2308398050154766e-05,
"loss": 1.5244,
"step": 548000
},
{
"epoch": 5.08,
"learning_rate": 1.2296813893574038e-05,
"loss": 1.5163,
"step": 548500
},
{
"epoch": 5.09,
"learning_rate": 1.228522973699331e-05,
"loss": 1.5134,
"step": 549000
},
{
"epoch": 5.09,
"learning_rate": 1.2273645580412583e-05,
"loss": 1.5094,
"step": 549500
},
{
"epoch": 5.1,
"learning_rate": 1.2262061423831855e-05,
"loss": 1.5223,
"step": 550000
},
{
"epoch": 5.1,
"eval_loss": 1.4577363729476929,
"eval_runtime": 1999.2946,
"eval_samples_per_second": 383.8,
"eval_steps_per_second": 5.997,
"step": 550000
},
{
"epoch": 5.1,
"learning_rate": 1.2250500435564288e-05,
"loss": 1.5048,
"step": 550500
},
{
"epoch": 5.11,
"learning_rate": 1.2238916278983562e-05,
"loss": 1.5294,
"step": 551000
},
{
"epoch": 5.11,
"learning_rate": 1.2227332122402834e-05,
"loss": 1.5245,
"step": 551500
},
{
"epoch": 5.12,
"learning_rate": 1.2215771134135267e-05,
"loss": 1.5049,
"step": 552000
},
{
"epoch": 5.12,
"learning_rate": 1.220418697755454e-05,
"loss": 1.5172,
"step": 552500
},
{
"epoch": 5.12,
"learning_rate": 1.219260282097381e-05,
"loss": 1.5119,
"step": 553000
},
{
"epoch": 5.13,
"learning_rate": 1.2181018664393082e-05,
"loss": 1.5112,
"step": 553500
},
{
"epoch": 5.13,
"learning_rate": 1.2169434507812356e-05,
"loss": 1.5214,
"step": 554000
},
{
"epoch": 5.14,
"learning_rate": 1.2157850351231628e-05,
"loss": 1.4996,
"step": 554500
},
{
"epoch": 5.14,
"learning_rate": 1.2146266194650902e-05,
"loss": 1.5152,
"step": 555000
},
{
"epoch": 5.15,
"learning_rate": 1.2134682038070174e-05,
"loss": 1.5083,
"step": 555500
},
{
"epoch": 5.15,
"learning_rate": 1.2123121049802607e-05,
"loss": 1.5157,
"step": 556000
},
{
"epoch": 5.16,
"learning_rate": 1.211153689322188e-05,
"loss": 1.4987,
"step": 556500
},
{
"epoch": 5.16,
"learning_rate": 1.2099952736641152e-05,
"loss": 1.5153,
"step": 557000
},
{
"epoch": 5.17,
"learning_rate": 1.2088368580060424e-05,
"loss": 1.4983,
"step": 557500
},
{
"epoch": 5.17,
"learning_rate": 1.2076807591792859e-05,
"loss": 1.5161,
"step": 558000
},
{
"epoch": 5.18,
"learning_rate": 1.206522343521213e-05,
"loss": 1.5126,
"step": 558500
},
{
"epoch": 5.18,
"learning_rate": 1.2053639278631401e-05,
"loss": 1.5198,
"step": 559000
},
{
"epoch": 5.19,
"learning_rate": 1.2042055122050676e-05,
"loss": 1.5155,
"step": 559500
},
{
"epoch": 5.19,
"learning_rate": 1.2030470965469946e-05,
"loss": 1.5112,
"step": 560000
},
{
"epoch": 5.19,
"eval_loss": 1.4550400972366333,
"eval_runtime": 1999.5313,
"eval_samples_per_second": 383.755,
"eval_steps_per_second": 5.996,
"step": 560000
},
{
"epoch": 5.19,
"learning_rate": 1.201890997720238e-05,
"loss": 1.514,
"step": 560500
},
{
"epoch": 5.2,
"learning_rate": 1.2007325820621653e-05,
"loss": 1.5005,
"step": 561000
},
{
"epoch": 5.2,
"learning_rate": 1.1995741664040925e-05,
"loss": 1.5163,
"step": 561500
},
{
"epoch": 5.21,
"learning_rate": 1.1984157507460197e-05,
"loss": 1.5069,
"step": 562000
},
{
"epoch": 5.21,
"learning_rate": 1.197257335087947e-05,
"loss": 1.5084,
"step": 562500
},
{
"epoch": 5.22,
"learning_rate": 1.1960989194298742e-05,
"loss": 1.515,
"step": 563000
},
{
"epoch": 5.22,
"learning_rate": 1.1949405037718014e-05,
"loss": 1.5047,
"step": 563500
},
{
"epoch": 5.23,
"learning_rate": 1.1937820881137288e-05,
"loss": 1.5244,
"step": 564000
},
{
"epoch": 5.23,
"learning_rate": 1.1926236724556558e-05,
"loss": 1.5034,
"step": 564500
},
{
"epoch": 5.24,
"learning_rate": 1.191465256797583e-05,
"loss": 1.511,
"step": 565000
},
{
"epoch": 5.24,
"learning_rate": 1.1903068411395104e-05,
"loss": 1.5011,
"step": 565500
},
{
"epoch": 5.25,
"learning_rate": 1.1891484254814376e-05,
"loss": 1.5049,
"step": 566000
},
{
"epoch": 5.25,
"learning_rate": 1.187990009823365e-05,
"loss": 1.5193,
"step": 566500
},
{
"epoch": 5.25,
"learning_rate": 1.1868362278279243e-05,
"loss": 1.5102,
"step": 567000
},
{
"epoch": 5.26,
"learning_rate": 1.1856778121698515e-05,
"loss": 1.5217,
"step": 567500
},
{
"epoch": 5.26,
"learning_rate": 1.1845193965117789e-05,
"loss": 1.5099,
"step": 568000
},
{
"epoch": 5.27,
"learning_rate": 1.1833609808537061e-05,
"loss": 1.5024,
"step": 568500
},
{
"epoch": 5.27,
"learning_rate": 1.1822025651956333e-05,
"loss": 1.5157,
"step": 569000
},
{
"epoch": 5.28,
"learning_rate": 1.1810441495375606e-05,
"loss": 1.5071,
"step": 569500
},
{
"epoch": 5.28,
"learning_rate": 1.1798857338794878e-05,
"loss": 1.5033,
"step": 570000
},
{
"epoch": 5.28,
"eval_loss": 1.4514985084533691,
"eval_runtime": 1998.4849,
"eval_samples_per_second": 383.956,
"eval_steps_per_second": 6.0,
"step": 570000
},
{
"epoch": 5.29,
"learning_rate": 1.1787273182214149e-05,
"loss": 1.5088,
"step": 570500
},
{
"epoch": 5.29,
"learning_rate": 1.1775689025633424e-05,
"loss": 1.4955,
"step": 571000
},
{
"epoch": 5.3,
"learning_rate": 1.1764128037365857e-05,
"loss": 1.51,
"step": 571500
},
{
"epoch": 5.3,
"learning_rate": 1.1752543880785127e-05,
"loss": 1.4984,
"step": 572000
},
{
"epoch": 5.31,
"learning_rate": 1.17409597242044e-05,
"loss": 1.517,
"step": 572500
},
{
"epoch": 5.31,
"learning_rate": 1.1729398735936834e-05,
"loss": 1.5041,
"step": 573000
},
{
"epoch": 5.31,
"learning_rate": 1.1717814579356107e-05,
"loss": 1.5057,
"step": 573500
},
{
"epoch": 5.32,
"learning_rate": 1.170623042277538e-05,
"loss": 1.4925,
"step": 574000
},
{
"epoch": 5.32,
"learning_rate": 1.1694646266194651e-05,
"loss": 1.5095,
"step": 574500
},
{
"epoch": 5.33,
"learning_rate": 1.1683062109613925e-05,
"loss": 1.5207,
"step": 575000
},
{
"epoch": 5.33,
"learning_rate": 1.1671501121346358e-05,
"loss": 1.5025,
"step": 575500
},
{
"epoch": 5.34,
"learning_rate": 1.165991696476563e-05,
"loss": 1.5068,
"step": 576000
},
{
"epoch": 5.34,
"learning_rate": 1.1648332808184903e-05,
"loss": 1.5002,
"step": 576500
},
{
"epoch": 5.35,
"learning_rate": 1.1636748651604175e-05,
"loss": 1.509,
"step": 577000
},
{
"epoch": 5.35,
"learning_rate": 1.1625164495023447e-05,
"loss": 1.5018,
"step": 577500
},
{
"epoch": 5.36,
"learning_rate": 1.1613580338442721e-05,
"loss": 1.5174,
"step": 578000
},
{
"epoch": 5.36,
"learning_rate": 1.1602019350175154e-05,
"loss": 1.5065,
"step": 578500
},
{
"epoch": 5.37,
"learning_rate": 1.1590435193594424e-05,
"loss": 1.4875,
"step": 579000
},
{
"epoch": 5.37,
"learning_rate": 1.15788510370137e-05,
"loss": 1.5011,
"step": 579500
},
{
"epoch": 5.38,
"learning_rate": 1.156726688043297e-05,
"loss": 1.5044,
"step": 580000
},
{
"epoch": 5.38,
"eval_loss": 1.444977879524231,
"eval_runtime": 1998.355,
"eval_samples_per_second": 383.981,
"eval_steps_per_second": 6.0,
"step": 580000
},
{
"epoch": 5.38,
"learning_rate": 1.1555705892165403e-05,
"loss": 1.5075,
"step": 580500
},
{
"epoch": 5.38,
"learning_rate": 1.1544121735584676e-05,
"loss": 1.4983,
"step": 581000
},
{
"epoch": 5.39,
"learning_rate": 1.1532537579003948e-05,
"loss": 1.515,
"step": 581500
},
{
"epoch": 5.39,
"learning_rate": 1.1520953422423222e-05,
"loss": 1.5037,
"step": 582000
},
{
"epoch": 5.4,
"learning_rate": 1.1509369265842494e-05,
"loss": 1.5091,
"step": 582500
},
{
"epoch": 5.4,
"learning_rate": 1.1497785109261766e-05,
"loss": 1.4986,
"step": 583000
},
{
"epoch": 5.41,
"learning_rate": 1.14862241209942e-05,
"loss": 1.5166,
"step": 583500
},
{
"epoch": 5.41,
"learning_rate": 1.1474639964413472e-05,
"loss": 1.5026,
"step": 584000
},
{
"epoch": 5.42,
"learning_rate": 1.1463055807832744e-05,
"loss": 1.5031,
"step": 584500
},
{
"epoch": 5.42,
"learning_rate": 1.1451494819565179e-05,
"loss": 1.5044,
"step": 585000
},
{
"epoch": 5.43,
"learning_rate": 1.143991066298445e-05,
"loss": 1.5025,
"step": 585500
},
{
"epoch": 5.43,
"learning_rate": 1.1428326506403721e-05,
"loss": 1.5118,
"step": 586000
},
{
"epoch": 5.44,
"learning_rate": 1.1416742349822996e-05,
"loss": 1.4926,
"step": 586500
},
{
"epoch": 5.44,
"learning_rate": 1.140518136155543e-05,
"loss": 1.5075,
"step": 587000
},
{
"epoch": 5.44,
"learning_rate": 1.13935972049747e-05,
"loss": 1.5144,
"step": 587500
},
{
"epoch": 5.45,
"learning_rate": 1.1382013048393973e-05,
"loss": 1.474,
"step": 588000
},
{
"epoch": 5.45,
"learning_rate": 1.1370452060126406e-05,
"loss": 1.5044,
"step": 588500
},
{
"epoch": 5.46,
"learning_rate": 1.1358867903545681e-05,
"loss": 1.4968,
"step": 589000
},
{
"epoch": 5.46,
"learning_rate": 1.1347283746964952e-05,
"loss": 1.503,
"step": 589500
},
{
"epoch": 5.47,
"learning_rate": 1.1335699590384224e-05,
"loss": 1.4921,
"step": 590000
},
{
"epoch": 5.47,
"eval_loss": 1.4433023929595947,
"eval_runtime": 1999.0257,
"eval_samples_per_second": 383.852,
"eval_steps_per_second": 5.998,
"step": 590000
},
{
"epoch": 5.47,
"learning_rate": 1.1324115433803497e-05,
"loss": 1.507,
"step": 590500
},
{
"epoch": 5.48,
"learning_rate": 1.131253127722277e-05,
"loss": 1.4896,
"step": 591000
},
{
"epoch": 5.48,
"learning_rate": 1.1300947120642041e-05,
"loss": 1.5129,
"step": 591500
},
{
"epoch": 5.49,
"learning_rate": 1.1289362964061315e-05,
"loss": 1.4976,
"step": 592000
},
{
"epoch": 5.49,
"learning_rate": 1.1277778807480587e-05,
"loss": 1.4987,
"step": 592500
},
{
"epoch": 5.5,
"learning_rate": 1.1266194650899857e-05,
"loss": 1.4983,
"step": 593000
},
{
"epoch": 5.5,
"learning_rate": 1.125461049431913e-05,
"loss": 1.4948,
"step": 593500
},
{
"epoch": 5.5,
"learning_rate": 1.1243049506051564e-05,
"loss": 1.5025,
"step": 594000
},
{
"epoch": 5.51,
"learning_rate": 1.1231465349470835e-05,
"loss": 1.5041,
"step": 594500
},
{
"epoch": 5.51,
"learning_rate": 1.1219881192890109e-05,
"loss": 1.5025,
"step": 595000
},
{
"epoch": 5.52,
"learning_rate": 1.1208297036309381e-05,
"loss": 1.4927,
"step": 595500
},
{
"epoch": 5.52,
"learning_rate": 1.1196712879728653e-05,
"loss": 1.5098,
"step": 596000
},
{
"epoch": 5.53,
"learning_rate": 1.1185128723147927e-05,
"loss": 1.5051,
"step": 596500
},
{
"epoch": 5.53,
"learning_rate": 1.1173544566567199e-05,
"loss": 1.5073,
"step": 597000
},
{
"epoch": 5.54,
"learning_rate": 1.116196040998647e-05,
"loss": 1.4951,
"step": 597500
},
{
"epoch": 5.54,
"learning_rate": 1.1150376253405744e-05,
"loss": 1.4864,
"step": 598000
},
{
"epoch": 5.55,
"learning_rate": 1.1138792096825014e-05,
"loss": 1.5081,
"step": 598500
},
{
"epoch": 5.55,
"learning_rate": 1.1127207940244286e-05,
"loss": 1.4943,
"step": 599000
},
{
"epoch": 5.56,
"learning_rate": 1.111562378366356e-05,
"loss": 1.4996,
"step": 599500
},
{
"epoch": 5.56,
"learning_rate": 1.1104039627082832e-05,
"loss": 1.5015,
"step": 600000
},
{
"epoch": 5.56,
"eval_loss": 1.442922592163086,
"eval_runtime": 1999.2552,
"eval_samples_per_second": 383.808,
"eval_steps_per_second": 5.997,
"step": 600000
},
{
"epoch": 5.57,
"learning_rate": 1.1092455470502104e-05,
"loss": 1.5154,
"step": 600500
},
{
"epoch": 5.57,
"learning_rate": 1.10809176505477e-05,
"loss": 1.5069,
"step": 601000
},
{
"epoch": 5.57,
"learning_rate": 1.1069333493966971e-05,
"loss": 1.4989,
"step": 601500
},
{
"epoch": 5.58,
"learning_rate": 1.1057749337386245e-05,
"loss": 1.5132,
"step": 602000
},
{
"epoch": 5.58,
"learning_rate": 1.1046188349118678e-05,
"loss": 1.497,
"step": 602500
},
{
"epoch": 5.59,
"learning_rate": 1.103460419253795e-05,
"loss": 1.4968,
"step": 603000
},
{
"epoch": 5.59,
"learning_rate": 1.1023020035957224e-05,
"loss": 1.4995,
"step": 603500
},
{
"epoch": 5.6,
"learning_rate": 1.1011435879376496e-05,
"loss": 1.4965,
"step": 604000
},
{
"epoch": 5.6,
"learning_rate": 1.0999851722795767e-05,
"loss": 1.493,
"step": 604500
},
{
"epoch": 5.61,
"learning_rate": 1.0988267566215041e-05,
"loss": 1.4923,
"step": 605000
},
{
"epoch": 5.61,
"learning_rate": 1.0976683409634313e-05,
"loss": 1.51,
"step": 605500
},
{
"epoch": 5.62,
"learning_rate": 1.0965122421366744e-05,
"loss": 1.5041,
"step": 606000
},
{
"epoch": 5.62,
"learning_rate": 1.095356143309918e-05,
"loss": 1.5059,
"step": 606500
},
{
"epoch": 5.63,
"learning_rate": 1.0941977276518453e-05,
"loss": 1.4994,
"step": 607000
},
{
"epoch": 5.63,
"learning_rate": 1.0930393119937726e-05,
"loss": 1.4995,
"step": 607500
},
{
"epoch": 5.63,
"learning_rate": 1.0918808963356996e-05,
"loss": 1.503,
"step": 608000
},
{
"epoch": 5.64,
"learning_rate": 1.0907224806776268e-05,
"loss": 1.4992,
"step": 608500
},
{
"epoch": 5.64,
"learning_rate": 1.0895640650195542e-05,
"loss": 1.4959,
"step": 609000
},
{
"epoch": 5.65,
"learning_rate": 1.0884056493614814e-05,
"loss": 1.5005,
"step": 609500
},
{
"epoch": 5.65,
"learning_rate": 1.0872472337034086e-05,
"loss": 1.493,
"step": 610000
},
{
"epoch": 5.65,
"eval_loss": 1.4419279098510742,
"eval_runtime": 2000.9004,
"eval_samples_per_second": 383.492,
"eval_steps_per_second": 5.992,
"step": 610000
},
{
"epoch": 5.66,
"learning_rate": 1.086088818045336e-05,
"loss": 1.5043,
"step": 610500
},
{
"epoch": 5.66,
"learning_rate": 1.0849304023872631e-05,
"loss": 1.4898,
"step": 611000
},
{
"epoch": 5.67,
"learning_rate": 1.0837743035605064e-05,
"loss": 1.4887,
"step": 611500
},
{
"epoch": 5.67,
"learning_rate": 1.0826158879024338e-05,
"loss": 1.4943,
"step": 612000
},
{
"epoch": 5.68,
"learning_rate": 1.081457472244361e-05,
"loss": 1.5013,
"step": 612500
},
{
"epoch": 5.68,
"learning_rate": 1.080299056586288e-05,
"loss": 1.4985,
"step": 613000
},
{
"epoch": 5.69,
"learning_rate": 1.0791429577595317e-05,
"loss": 1.4848,
"step": 613500
},
{
"epoch": 5.69,
"learning_rate": 1.0779845421014587e-05,
"loss": 1.4963,
"step": 614000
},
{
"epoch": 5.69,
"learning_rate": 1.0768261264433859e-05,
"loss": 1.4828,
"step": 614500
},
{
"epoch": 5.7,
"learning_rate": 1.0756677107853132e-05,
"loss": 1.5016,
"step": 615000
},
{
"epoch": 5.7,
"learning_rate": 1.0745092951272404e-05,
"loss": 1.5119,
"step": 615500
},
{
"epoch": 5.71,
"learning_rate": 1.0733508794691676e-05,
"loss": 1.5058,
"step": 616000
},
{
"epoch": 5.71,
"learning_rate": 1.072192463811095e-05,
"loss": 1.4828,
"step": 616500
},
{
"epoch": 5.72,
"learning_rate": 1.0710363649843383e-05,
"loss": 1.4882,
"step": 617000
},
{
"epoch": 5.72,
"learning_rate": 1.0698779493262655e-05,
"loss": 1.4963,
"step": 617500
},
{
"epoch": 5.73,
"learning_rate": 1.0687195336681928e-05,
"loss": 1.4809,
"step": 618000
},
{
"epoch": 5.73,
"learning_rate": 1.0675634348414361e-05,
"loss": 1.4987,
"step": 618500
},
{
"epoch": 5.74,
"learning_rate": 1.0664050191833635e-05,
"loss": 1.4903,
"step": 619000
},
{
"epoch": 5.74,
"learning_rate": 1.0652466035252907e-05,
"loss": 1.4951,
"step": 619500
},
{
"epoch": 5.75,
"learning_rate": 1.0640881878672177e-05,
"loss": 1.4899,
"step": 620000
},
{
"epoch": 5.75,
"eval_loss": 1.4368497133255005,
"eval_runtime": 1999.447,
"eval_samples_per_second": 383.771,
"eval_steps_per_second": 5.997,
"step": 620000
},
{
"epoch": 5.75,
"learning_rate": 1.0629297722091452e-05,
"loss": 1.4936,
"step": 620500
},
{
"epoch": 5.76,
"learning_rate": 1.0617713565510723e-05,
"loss": 1.5063,
"step": 621000
},
{
"epoch": 5.76,
"learning_rate": 1.0606152577243156e-05,
"loss": 1.4969,
"step": 621500
},
{
"epoch": 5.76,
"learning_rate": 1.059456842066243e-05,
"loss": 1.4742,
"step": 622000
},
{
"epoch": 5.77,
"learning_rate": 1.0582984264081701e-05,
"loss": 1.4792,
"step": 622500
},
{
"epoch": 5.77,
"learning_rate": 1.0571400107500973e-05,
"loss": 1.5045,
"step": 623000
},
{
"epoch": 5.78,
"learning_rate": 1.0559815950920247e-05,
"loss": 1.4985,
"step": 623500
},
{
"epoch": 5.78,
"learning_rate": 1.0548231794339519e-05,
"loss": 1.5019,
"step": 624000
},
{
"epoch": 5.79,
"learning_rate": 1.053664763775879e-05,
"loss": 1.5043,
"step": 624500
},
{
"epoch": 5.79,
"learning_rate": 1.0525063481178064e-05,
"loss": 1.5071,
"step": 625000
},
{
"epoch": 5.8,
"learning_rate": 1.0513479324597336e-05,
"loss": 1.494,
"step": 625500
},
{
"epoch": 5.8,
"learning_rate": 1.0501918336329768e-05,
"loss": 1.483,
"step": 626000
},
{
"epoch": 5.81,
"learning_rate": 1.0490334179749043e-05,
"loss": 1.4955,
"step": 626500
},
{
"epoch": 5.81,
"learning_rate": 1.0478750023168313e-05,
"loss": 1.4904,
"step": 627000
},
{
"epoch": 5.82,
"learning_rate": 1.0467165866587585e-05,
"loss": 1.4879,
"step": 627500
},
{
"epoch": 5.82,
"learning_rate": 1.0455581710006859e-05,
"loss": 1.4864,
"step": 628000
},
{
"epoch": 5.82,
"learning_rate": 1.044399755342613e-05,
"loss": 1.4779,
"step": 628500
},
{
"epoch": 5.83,
"learning_rate": 1.0432413396845404e-05,
"loss": 1.4912,
"step": 629000
},
{
"epoch": 5.83,
"learning_rate": 1.0420829240264676e-05,
"loss": 1.4861,
"step": 629500
},
{
"epoch": 5.84,
"learning_rate": 1.0409245083683948e-05,
"loss": 1.5117,
"step": 630000
},
{
"epoch": 5.84,
"eval_loss": 1.4308295249938965,
"eval_runtime": 2000.8874,
"eval_samples_per_second": 383.495,
"eval_steps_per_second": 5.992,
"step": 630000
},
{
"epoch": 5.84,
"learning_rate": 1.0397660927103222e-05,
"loss": 1.4849,
"step": 630500
},
{
"epoch": 5.85,
"learning_rate": 1.0386099938835655e-05,
"loss": 1.4955,
"step": 631000
},
{
"epoch": 5.85,
"learning_rate": 1.0374515782254927e-05,
"loss": 1.4981,
"step": 631500
},
{
"epoch": 5.86,
"learning_rate": 1.0362954793987361e-05,
"loss": 1.4888,
"step": 632000
},
{
"epoch": 5.86,
"learning_rate": 1.0351370637406633e-05,
"loss": 1.4848,
"step": 632500
},
{
"epoch": 5.87,
"learning_rate": 1.0339786480825903e-05,
"loss": 1.5026,
"step": 633000
},
{
"epoch": 5.87,
"learning_rate": 1.0328202324245177e-05,
"loss": 1.4891,
"step": 633500
},
{
"epoch": 5.88,
"learning_rate": 1.0316618167664449e-05,
"loss": 1.4865,
"step": 634000
},
{
"epoch": 5.88,
"learning_rate": 1.0305034011083721e-05,
"loss": 1.4932,
"step": 634500
},
{
"epoch": 5.88,
"learning_rate": 1.0293449854502995e-05,
"loss": 1.5003,
"step": 635000
},
{
"epoch": 5.89,
"learning_rate": 1.0281865697922267e-05,
"loss": 1.4901,
"step": 635500
},
{
"epoch": 5.89,
"learning_rate": 1.02703047096547e-05,
"loss": 1.4941,
"step": 636000
},
{
"epoch": 5.9,
"learning_rate": 1.0258720553073973e-05,
"loss": 1.5047,
"step": 636500
},
{
"epoch": 5.9,
"learning_rate": 1.0247136396493245e-05,
"loss": 1.4788,
"step": 637000
},
{
"epoch": 5.91,
"learning_rate": 1.0235552239912517e-05,
"loss": 1.4992,
"step": 637500
},
{
"epoch": 5.91,
"learning_rate": 1.022396808333179e-05,
"loss": 1.4891,
"step": 638000
},
{
"epoch": 5.92,
"learning_rate": 1.0212383926751061e-05,
"loss": 1.5074,
"step": 638500
},
{
"epoch": 5.92,
"learning_rate": 1.0200799770170333e-05,
"loss": 1.4932,
"step": 639000
},
{
"epoch": 5.93,
"learning_rate": 1.0189215613589606e-05,
"loss": 1.4866,
"step": 639500
},
{
"epoch": 5.93,
"learning_rate": 1.017765462532204e-05,
"loss": 1.4947,
"step": 640000
},
{
"epoch": 5.93,
"eval_loss": 1.4289482831954956,
"eval_runtime": 2001.1567,
"eval_samples_per_second": 383.443,
"eval_steps_per_second": 5.992,
"step": 640000
},
{
"epoch": 5.94,
"learning_rate": 1.0166070468741313e-05,
"loss": 1.494,
"step": 640500
},
{
"epoch": 5.94,
"learning_rate": 1.0154486312160585e-05,
"loss": 1.4925,
"step": 641000
},
{
"epoch": 5.94,
"learning_rate": 1.0142902155579857e-05,
"loss": 1.4897,
"step": 641500
},
{
"epoch": 5.95,
"learning_rate": 1.013131799899913e-05,
"loss": 1.49,
"step": 642000
},
{
"epoch": 5.95,
"learning_rate": 1.0119733842418403e-05,
"loss": 1.492,
"step": 642500
},
{
"epoch": 5.96,
"learning_rate": 1.0108149685837674e-05,
"loss": 1.4734,
"step": 643000
},
{
"epoch": 5.96,
"learning_rate": 1.0096588697570109e-05,
"loss": 1.4924,
"step": 643500
},
{
"epoch": 5.97,
"learning_rate": 1.0085004540989381e-05,
"loss": 1.5033,
"step": 644000
},
{
"epoch": 5.97,
"learning_rate": 1.0073420384408651e-05,
"loss": 1.492,
"step": 644500
},
{
"epoch": 5.98,
"learning_rate": 1.0061836227827927e-05,
"loss": 1.4798,
"step": 645000
},
{
"epoch": 5.98,
"learning_rate": 1.0050252071247197e-05,
"loss": 1.4752,
"step": 645500
},
{
"epoch": 5.99,
"learning_rate": 1.0038667914666469e-05,
"loss": 1.4935,
"step": 646000
},
{
"epoch": 5.99,
"learning_rate": 1.0027083758085742e-05,
"loss": 1.4842,
"step": 646500
},
{
"epoch": 6.0,
"learning_rate": 1.0015522769818175e-05,
"loss": 1.4889,
"step": 647000
},
{
"epoch": 6.0,
"learning_rate": 1.0003938613237447e-05,
"loss": 1.4821,
"step": 647500
},
{
"epoch": 6.01,
"learning_rate": 9.992354456656721e-06,
"loss": 1.4797,
"step": 648000
},
{
"epoch": 6.01,
"learning_rate": 9.980770300075993e-06,
"loss": 1.497,
"step": 648500
},
{
"epoch": 6.01,
"learning_rate": 9.969186143495265e-06,
"loss": 1.4863,
"step": 649000
},
{
"epoch": 6.02,
"learning_rate": 9.957601986914538e-06,
"loss": 1.4906,
"step": 649500
},
{
"epoch": 6.02,
"learning_rate": 9.946017830333809e-06,
"loss": 1.4784,
"step": 650000
},
{
"epoch": 6.02,
"eval_loss": 1.4286057949066162,
"eval_runtime": 2000.2228,
"eval_samples_per_second": 383.622,
"eval_steps_per_second": 5.994,
"step": 650000
},
{
"epoch": 6.03,
"learning_rate": 9.934433673753082e-06,
"loss": 1.4871,
"step": 650500
},
{
"epoch": 6.03,
"learning_rate": 9.922849517172354e-06,
"loss": 1.4699,
"step": 651000
},
{
"epoch": 6.04,
"learning_rate": 9.911288528904787e-06,
"loss": 1.4948,
"step": 651500
},
{
"epoch": 6.04,
"learning_rate": 9.899727540637222e-06,
"loss": 1.4776,
"step": 652000
},
{
"epoch": 6.05,
"learning_rate": 9.888143384056494e-06,
"loss": 1.4765,
"step": 652500
},
{
"epoch": 6.05,
"learning_rate": 9.876559227475767e-06,
"loss": 1.4792,
"step": 653000
},
{
"epoch": 6.06,
"learning_rate": 9.8649982392082e-06,
"loss": 1.4815,
"step": 653500
},
{
"epoch": 6.06,
"learning_rate": 9.853414082627472e-06,
"loss": 1.4779,
"step": 654000
},
{
"epoch": 6.07,
"learning_rate": 9.841829926046746e-06,
"loss": 1.4749,
"step": 654500
},
{
"epoch": 6.07,
"learning_rate": 9.830245769466018e-06,
"loss": 1.4791,
"step": 655000
},
{
"epoch": 6.07,
"learning_rate": 9.81866161288529e-06,
"loss": 1.4742,
"step": 655500
},
{
"epoch": 6.08,
"learning_rate": 9.807077456304562e-06,
"loss": 1.4739,
"step": 656000
},
{
"epoch": 6.08,
"learning_rate": 9.795493299723835e-06,
"loss": 1.4773,
"step": 656500
},
{
"epoch": 6.09,
"learning_rate": 9.783909143143107e-06,
"loss": 1.4937,
"step": 657000
},
{
"epoch": 6.09,
"learning_rate": 9.77232498656238e-06,
"loss": 1.4902,
"step": 657500
},
{
"epoch": 6.1,
"learning_rate": 9.760740829981651e-06,
"loss": 1.4894,
"step": 658000
},
{
"epoch": 6.1,
"learning_rate": 9.749156673400923e-06,
"loss": 1.4871,
"step": 658500
},
{
"epoch": 6.11,
"learning_rate": 9.737572516820197e-06,
"loss": 1.4833,
"step": 659000
},
{
"epoch": 6.11,
"learning_rate": 9.72601152855263e-06,
"loss": 1.4667,
"step": 659500
},
{
"epoch": 6.12,
"learning_rate": 9.714427371971902e-06,
"loss": 1.4747,
"step": 660000
},
{
"epoch": 6.12,
"eval_loss": 1.423827052116394,
"eval_runtime": 2001.0282,
"eval_samples_per_second": 383.468,
"eval_steps_per_second": 5.992,
"step": 660000
},
{
"epoch": 6.12,
"learning_rate": 9.702843215391174e-06,
"loss": 1.4772,
"step": 660500
},
{
"epoch": 6.13,
"learning_rate": 9.691282227123608e-06,
"loss": 1.4894,
"step": 661000
},
{
"epoch": 6.13,
"learning_rate": 9.679698070542882e-06,
"loss": 1.4834,
"step": 661500
},
{
"epoch": 6.13,
"learning_rate": 9.668113913962152e-06,
"loss": 1.4769,
"step": 662000
},
{
"epoch": 6.14,
"learning_rate": 9.656529757381426e-06,
"loss": 1.4708,
"step": 662500
},
{
"epoch": 6.14,
"learning_rate": 9.644945600800698e-06,
"loss": 1.4841,
"step": 663000
},
{
"epoch": 6.15,
"learning_rate": 9.63336144421997e-06,
"loss": 1.4804,
"step": 663500
},
{
"epoch": 6.15,
"learning_rate": 9.621777287639242e-06,
"loss": 1.4649,
"step": 664000
},
{
"epoch": 6.16,
"learning_rate": 9.610193131058515e-06,
"loss": 1.4728,
"step": 664500
},
{
"epoch": 6.16,
"learning_rate": 9.59863214279095e-06,
"loss": 1.4846,
"step": 665000
},
{
"epoch": 6.17,
"learning_rate": 9.58704798621022e-06,
"loss": 1.4817,
"step": 665500
},
{
"epoch": 6.17,
"learning_rate": 9.575463829629494e-06,
"loss": 1.4826,
"step": 666000
},
{
"epoch": 6.18,
"learning_rate": 9.563902841361927e-06,
"loss": 1.4598,
"step": 666500
},
{
"epoch": 6.18,
"learning_rate": 9.552318684781199e-06,
"loss": 1.472,
"step": 667000
},
{
"epoch": 6.19,
"learning_rate": 9.540734528200472e-06,
"loss": 1.4818,
"step": 667500
},
{
"epoch": 6.19,
"learning_rate": 9.529150371619744e-06,
"loss": 1.4819,
"step": 668000
},
{
"epoch": 6.2,
"learning_rate": 9.517566215039016e-06,
"loss": 1.4836,
"step": 668500
},
{
"epoch": 6.2,
"learning_rate": 9.506005226771449e-06,
"loss": 1.4861,
"step": 669000
},
{
"epoch": 6.2,
"learning_rate": 9.494421070190723e-06,
"loss": 1.4761,
"step": 669500
},
{
"epoch": 6.21,
"learning_rate": 9.482836913609995e-06,
"loss": 1.4943,
"step": 670000
},
{
"epoch": 6.21,
"eval_loss": 1.4223008155822754,
"eval_runtime": 1999.8288,
"eval_samples_per_second": 383.698,
"eval_steps_per_second": 5.996,
"step": 670000
},
{
"epoch": 6.21,
"learning_rate": 9.471252757029267e-06,
"loss": 1.484,
"step": 670500
},
{
"epoch": 6.22,
"learning_rate": 9.45966860044854e-06,
"loss": 1.4718,
"step": 671000
},
{
"epoch": 6.22,
"learning_rate": 9.448084443867812e-06,
"loss": 1.4826,
"step": 671500
},
{
"epoch": 6.23,
"learning_rate": 9.436523455600245e-06,
"loss": 1.4746,
"step": 672000
},
{
"epoch": 6.23,
"learning_rate": 9.424939299019517e-06,
"loss": 1.4846,
"step": 672500
},
{
"epoch": 6.24,
"learning_rate": 9.41335514243879e-06,
"loss": 1.4838,
"step": 673000
},
{
"epoch": 6.24,
"learning_rate": 9.401770985858063e-06,
"loss": 1.4615,
"step": 673500
},
{
"epoch": 6.25,
"learning_rate": 9.390186829277335e-06,
"loss": 1.4934,
"step": 674000
},
{
"epoch": 6.25,
"learning_rate": 9.378602672696606e-06,
"loss": 1.4808,
"step": 674500
},
{
"epoch": 6.26,
"learning_rate": 9.367018516115878e-06,
"loss": 1.4837,
"step": 675000
},
{
"epoch": 6.26,
"learning_rate": 9.355434359535152e-06,
"loss": 1.4782,
"step": 675500
},
{
"epoch": 6.26,
"learning_rate": 9.343850202954424e-06,
"loss": 1.4733,
"step": 676000
},
{
"epoch": 6.27,
"learning_rate": 9.332266046373698e-06,
"loss": 1.4845,
"step": 676500
},
{
"epoch": 6.27,
"learning_rate": 9.32070505810613e-06,
"loss": 1.4705,
"step": 677000
},
{
"epoch": 6.28,
"learning_rate": 9.309120901525403e-06,
"loss": 1.4696,
"step": 677500
},
{
"epoch": 6.28,
"learning_rate": 9.297536744944674e-06,
"loss": 1.477,
"step": 678000
},
{
"epoch": 6.29,
"learning_rate": 9.285952588363946e-06,
"loss": 1.4857,
"step": 678500
},
{
"epoch": 6.29,
"learning_rate": 9.27436843178322e-06,
"loss": 1.4872,
"step": 679000
},
{
"epoch": 6.3,
"learning_rate": 9.262784275202492e-06,
"loss": 1.4819,
"step": 679500
},
{
"epoch": 6.3,
"learning_rate": 9.251200118621764e-06,
"loss": 1.4593,
"step": 680000
},
{
"epoch": 6.3,
"eval_loss": 1.4186582565307617,
"eval_runtime": 1999.5782,
"eval_samples_per_second": 383.746,
"eval_steps_per_second": 5.996,
"step": 680000
}
],
"logging_steps": 500,
"max_steps": 1079060,
"num_train_epochs": 10,
"save_steps": 10000,
"total_flos": 1.145470169601572e+19,
"trial_name": null,
"trial_params": null
}