{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9991416309012876, "eval_steps": 500, "global_step": 582, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0017167381974248926, "grad_norm": 148.37953017406076, "learning_rate": 3.3898305084745763e-06, "loss": 1.4925, "step": 1 }, { "epoch": 0.008583690987124463, "grad_norm": 226.53531287893435, "learning_rate": 1.694915254237288e-05, "loss": 1.8304, "step": 5 }, { "epoch": 0.017167381974248927, "grad_norm": 122.60255331663019, "learning_rate": 3.389830508474576e-05, "loss": 1.6337, "step": 10 }, { "epoch": 0.02575107296137339, "grad_norm": 27.57943216063738, "learning_rate": 5.0847457627118643e-05, "loss": 1.4564, "step": 15 }, { "epoch": 0.034334763948497854, "grad_norm": 68.31876381825991, "learning_rate": 6.779661016949152e-05, "loss": 1.6491, "step": 20 }, { "epoch": 0.04291845493562232, "grad_norm": 34.24629194904229, "learning_rate": 8.474576271186441e-05, "loss": 1.6714, "step": 25 }, { "epoch": 0.05150214592274678, "grad_norm": 392.0670273900377, "learning_rate": 0.00010169491525423729, "loss": 2.8097, "step": 30 }, { "epoch": 0.060085836909871244, "grad_norm": 1460.2154288260613, "learning_rate": 0.00011864406779661017, "loss": 2.2112, "step": 35 }, { "epoch": 0.06866952789699571, "grad_norm": 152.24800163036767, "learning_rate": 0.00013559322033898305, "loss": 1.5475, "step": 40 }, { "epoch": 0.07725321888412018, "grad_norm": 529.4349457912397, "learning_rate": 0.00015254237288135592, "loss": 3.2178, "step": 45 }, { "epoch": 0.08583690987124463, "grad_norm": 740.2750714071109, "learning_rate": 0.00016949152542372882, "loss": 3.7609, "step": 50 }, { "epoch": 0.0944206008583691, "grad_norm": 501.75647987784066, "learning_rate": 0.0001864406779661017, "loss": 5.1663, "step": 55 }, { "epoch": 0.10300429184549356, "grad_norm": 552.7605592699055, "learning_rate": 0.0001999981958814743, "loss": 12.807, "step": 60 }, { "epoch": 0.11158798283261803, "grad_norm": 79.39978511676262, "learning_rate": 0.00019993505856798243, "loss": 15.5599, "step": 65 }, { "epoch": 0.12017167381974249, "grad_norm": 56.78553117050131, "learning_rate": 0.00019978178041451998, "loss": 16.703, "step": 70 }, { "epoch": 0.12875536480686695, "grad_norm": 112.72908285826135, "learning_rate": 0.0001995384996770874, "loss": 15.425, "step": 75 }, { "epoch": 0.13733905579399142, "grad_norm": 442.5710003227928, "learning_rate": 0.000199205435793491, "loss": 31.9561, "step": 80 }, { "epoch": 0.1459227467811159, "grad_norm": 184.54596876342316, "learning_rate": 0.00019878288918541114, "loss": 15.8809, "step": 85 }, { "epoch": 0.15450643776824036, "grad_norm": 347.24694919273804, "learning_rate": 0.00019827124098742394, "loss": 14.7386, "step": 90 }, { "epoch": 0.1630901287553648, "grad_norm": 48.28938306214246, "learning_rate": 0.0001976709527032198, "loss": 17.4369, "step": 95 }, { "epoch": 0.17167381974248927, "grad_norm": 111.82743394628322, "learning_rate": 0.00019698256578933005, "loss": 13.2218, "step": 100 }, { "epoch": 0.18025751072961374, "grad_norm": 266.4352235029355, "learning_rate": 0.00019620670116673604, "loss": 10.8569, "step": 105 }, { "epoch": 0.1888412017167382, "grad_norm": 42.96800119266756, "learning_rate": 0.0001953440586608022, "loss": 9.8788, "step": 110 }, { "epoch": 0.19742489270386265, "grad_norm": 37.647763231857866, "learning_rate": 0.00019439541637003772, "loss": 8.9958, "step": 115 }, { "epoch": 0.20600858369098712, "grad_norm": 20.454288165244996, "learning_rate": 0.00019336162996425597, "loss": 8.1835, "step": 120 }, { "epoch": 0.2145922746781116, "grad_norm": 59.141650986938025, "learning_rate": 0.00019224363191276559, "loss": 8.2297, "step": 125 }, { "epoch": 0.22317596566523606, "grad_norm": 39.88230197372808, "learning_rate": 0.00019104243064328838, "loss": 8.0509, "step": 130 }, { "epoch": 0.2317596566523605, "grad_norm": 27.87553480349785, "learning_rate": 0.00018975910963236366, "loss": 7.7919, "step": 135 }, { "epoch": 0.24034334763948498, "grad_norm": 33.29528319809458, "learning_rate": 0.00018839482642805843, "loss": 7.4218, "step": 140 }, { "epoch": 0.24892703862660945, "grad_norm": 28.706620751101852, "learning_rate": 0.000186950811605866, "loss": 7.3135, "step": 145 }, { "epoch": 0.2575107296137339, "grad_norm": 77.97848200082751, "learning_rate": 0.00018542836765873396, "loss": 7.3272, "step": 150 }, { "epoch": 0.26609442060085836, "grad_norm": 12.617065010078097, "learning_rate": 0.00018382886782222313, "loss": 7.1705, "step": 155 }, { "epoch": 0.27467811158798283, "grad_norm": 9.66255057469759, "learning_rate": 0.00018215375483585726, "loss": 7.152, "step": 160 }, { "epoch": 0.2832618025751073, "grad_norm": 13.81795039749584, "learning_rate": 0.0001804045396417801, "loss": 7.0384, "step": 165 }, { "epoch": 0.2918454935622318, "grad_norm": 10.65607302408338, "learning_rate": 0.0001785828000218947, "loss": 7.1945, "step": 170 }, { "epoch": 0.30042918454935624, "grad_norm": 15.782661016430529, "learning_rate": 0.00017669017917471314, "loss": 7.7122, "step": 175 }, { "epoch": 0.3090128755364807, "grad_norm": 73.67344007196424, "learning_rate": 0.00017472838423320108, "loss": 7.3337, "step": 180 }, { "epoch": 0.31759656652360513, "grad_norm": 14.634220899220917, "learning_rate": 0.0001726991847249539, "loss": 7.6728, "step": 185 }, { "epoch": 0.3261802575107296, "grad_norm": 13.23535439972109, "learning_rate": 0.000170604410976093, "loss": 7.1979, "step": 190 }, { "epoch": 0.33476394849785407, "grad_norm": 15.490178591732896, "learning_rate": 0.00016844595246032234, "loss": 7.4718, "step": 195 }, { "epoch": 0.34334763948497854, "grad_norm": 14.166388152902138, "learning_rate": 0.00016622575609463432, "loss": 7.0926, "step": 200 }, { "epoch": 0.351931330472103, "grad_norm": 7.921484195688758, "learning_rate": 0.00016394582448320163, "loss": 6.9988, "step": 205 }, { "epoch": 0.3605150214592275, "grad_norm": 9.205119757022215, "learning_rate": 0.00016160821411104057, "loss": 6.9226, "step": 210 }, { "epoch": 0.36909871244635195, "grad_norm": 35.99180735659732, "learning_rate": 0.00015921503348907288, "loss": 7.1323, "step": 215 }, { "epoch": 0.3776824034334764, "grad_norm": 11.336602821015093, "learning_rate": 0.00015676844125226178, "loss": 7.1202, "step": 220 }, { "epoch": 0.38626609442060084, "grad_norm": 13.20625274633718, "learning_rate": 0.00015427064421253542, "loss": 7.2282, "step": 225 }, { "epoch": 0.3948497854077253, "grad_norm": 67.29081123770837, "learning_rate": 0.00015172389536825554, "loss": 7.0692, "step": 230 }, { "epoch": 0.4034334763948498, "grad_norm": 11.16921203935729, "learning_rate": 0.00014913049187202613, "loss": 7.0129, "step": 235 }, { "epoch": 0.41201716738197425, "grad_norm": 11.356355094966165, "learning_rate": 0.0001464927729586751, "loss": 6.9715, "step": 240 }, { "epoch": 0.4206008583690987, "grad_norm": 65.02533863066004, "learning_rate": 0.0001438131178352782, "loss": 7.0428, "step": 245 }, { "epoch": 0.4291845493562232, "grad_norm": 8.021375841934983, "learning_rate": 0.000141093943535128, "loss": 6.9865, "step": 250 }, { "epoch": 0.43776824034334766, "grad_norm": 8.30393736182492, "learning_rate": 0.00013833770273758396, "loss": 6.9422, "step": 255 }, { "epoch": 0.44635193133047213, "grad_norm": 10.60254104247866, "learning_rate": 0.00013554688155577012, "loss": 7.0097, "step": 260 }, { "epoch": 0.45493562231759654, "grad_norm": 31.605073666129307, "learning_rate": 0.0001327239972941153, "loss": 6.9863, "step": 265 }, { "epoch": 0.463519313304721, "grad_norm": 8.23597721842936, "learning_rate": 0.00012987159617775952, "loss": 6.9908, "step": 270 }, { "epoch": 0.4721030042918455, "grad_norm": 9.868400148345003, "learning_rate": 0.0001269922510558735, "loss": 6.9117, "step": 275 }, { "epoch": 0.48068669527896996, "grad_norm": 5.852530780039747, "learning_rate": 0.00012408855908096372, "loss": 6.9009, "step": 280 }, { "epoch": 0.4892703862660944, "grad_norm": 5.3374729678346275, "learning_rate": 0.00012116313936625616, "loss": 6.8528, "step": 285 }, { "epoch": 0.4978540772532189, "grad_norm": 5.313298088617677, "learning_rate": 0.00011821863062327142, "loss": 6.8808, "step": 290 }, { "epoch": 0.5064377682403434, "grad_norm": 4.656345284326436, "learning_rate": 0.00011525768878172217, "loss": 6.8471, "step": 295 }, { "epoch": 0.5150214592274678, "grad_norm": 6.2217899411236415, "learning_rate": 0.0001122829845938802, "loss": 6.8989, "step": 300 }, { "epoch": 0.5236051502145923, "grad_norm": 5.068468710318732, "learning_rate": 0.00010929720122557346, "loss": 6.8636, "step": 305 }, { "epoch": 0.5321888412017167, "grad_norm": 4.8062734001678304, "learning_rate": 0.00010630303183598586, "loss": 6.8643, "step": 310 }, { "epoch": 0.5407725321888412, "grad_norm": 4.222058731948505, "learning_rate": 0.00010330317714844382, "loss": 6.8366, "step": 315 }, { "epoch": 0.5493562231759657, "grad_norm": 5.498653200897768, "learning_rate": 0.0001003003430143792, "loss": 6.8438, "step": 320 }, { "epoch": 0.5579399141630901, "grad_norm": 4.606293074529594, "learning_rate": 9.729723797266733e-05, "loss": 6.8435, "step": 325 }, { "epoch": 0.5665236051502146, "grad_norm": 4.094114687291011, "learning_rate": 9.429657080654066e-05, "loss": 6.8383, "step": 330 }, { "epoch": 0.575107296137339, "grad_norm": 4.850653416958559, "learning_rate": 9.130104810028196e-05, "loss": 6.8403, "step": 335 }, { "epoch": 0.5836909871244635, "grad_norm": 3.5962933581788943, "learning_rate": 8.831337179790135e-05, "loss": 6.7696, "step": 340 }, { "epoch": 0.592274678111588, "grad_norm": 4.211863063848454, "learning_rate": 8.533623676599832e-05, "loss": 6.7095, "step": 345 }, { "epoch": 0.6008583690987125, "grad_norm": 2.860326437620046, "learning_rate": 8.237232836300797e-05, "loss": 6.6912, "step": 350 }, { "epoch": 0.6094420600858369, "grad_norm": 8.77242613923949, "learning_rate": 7.94243200170232e-05, "loss": 6.5853, "step": 355 }, { "epoch": 0.6180257510729614, "grad_norm": 6.659382197081032, "learning_rate": 7.649487081437818e-05, "loss": 6.5642, "step": 360 }, { "epoch": 0.6266094420600858, "grad_norm": 10.44433874556097, "learning_rate": 7.358662310116808e-05, "loss": 6.4968, "step": 365 }, { "epoch": 0.6351931330472103, "grad_norm": 6.1233526664383024, "learning_rate": 7.070220009986828e-05, "loss": 6.4142, "step": 370 }, { "epoch": 0.6437768240343348, "grad_norm": 4.045999079298666, "learning_rate": 6.784420354320295e-05, "loss": 6.3996, "step": 375 }, { "epoch": 0.6523605150214592, "grad_norm": 12.756102691389257, "learning_rate": 6.501521132739727e-05, "loss": 6.3766, "step": 380 }, { "epoch": 0.6609442060085837, "grad_norm": 5.067389209546529, "learning_rate": 6.221777518693023e-05, "loss": 6.3331, "step": 385 }, { "epoch": 0.6695278969957081, "grad_norm": 4.587232017547203, "learning_rate": 5.945441839288487e-05, "loss": 6.2912, "step": 390 }, { "epoch": 0.6781115879828327, "grad_norm": 10.154786306342054, "learning_rate": 5.672763347697252e-05, "loss": 6.1986, "step": 395 }, { "epoch": 0.6866952789699571, "grad_norm": 6.356244711188396, "learning_rate": 5.403987998328364e-05, "loss": 6.0784, "step": 400 }, { "epoch": 0.6952789699570815, "grad_norm": 6.256029497303041, "learning_rate": 5.139358224979368e-05, "loss": 6.0875, "step": 405 }, { "epoch": 0.703862660944206, "grad_norm": 6.392716409081631, "learning_rate": 4.8791127221624e-05, "loss": 6.0507, "step": 410 }, { "epoch": 0.7124463519313304, "grad_norm": 4.093689165851618, "learning_rate": 4.62348622980316e-05, "loss": 6.0207, "step": 415 }, { "epoch": 0.721030042918455, "grad_norm": 6.227286133335013, "learning_rate": 4.372709321506848e-05, "loss": 5.9235, "step": 420 }, { "epoch": 0.7296137339055794, "grad_norm": 9.976130870929332, "learning_rate": 4.12700819658212e-05, "loss": 5.8749, "step": 425 }, { "epoch": 0.7381974248927039, "grad_norm": 4.604304131370468, "learning_rate": 3.8866044760106446e-05, "loss": 5.817, "step": 430 }, { "epoch": 0.7467811158798283, "grad_norm": 8.368202258449207, "learning_rate": 3.651715002546251e-05, "loss": 5.7823, "step": 435 }, { "epoch": 0.7553648068669528, "grad_norm": 4.346337001686645, "learning_rate": 3.422551645124048e-05, "loss": 5.7372, "step": 440 }, { "epoch": 0.7639484978540773, "grad_norm": 6.8350119997138306, "learning_rate": 3.199321107755863e-05, "loss": 5.6973, "step": 445 }, { "epoch": 0.7725321888412017, "grad_norm": 4.355909578299472, "learning_rate": 2.9822247430844375e-05, "loss": 5.6349, "step": 450 }, { "epoch": 0.7811158798283262, "grad_norm": 6.751775629287182, "learning_rate": 2.7714583707645247e-05, "loss": 5.5923, "step": 455 }, { "epoch": 0.7896995708154506, "grad_norm": 7.749784220705869, "learning_rate": 2.5672121008346895e-05, "loss": 5.5167, "step": 460 }, { "epoch": 0.7982832618025751, "grad_norm": 10.122654499906968, "learning_rate": 2.369670162239166e-05, "loss": 5.5233, "step": 465 }, { "epoch": 0.8068669527896996, "grad_norm": 13.541428912986023, "learning_rate": 2.1790107366544366e-05, "loss": 5.4574, "step": 470 }, { "epoch": 0.8154506437768241, "grad_norm": 8.344136937270687, "learning_rate": 1.9954057977703776e-05, "loss": 5.4293, "step": 475 }, { "epoch": 0.8240343347639485, "grad_norm": 10.023341035964107, "learning_rate": 1.819020956171017e-05, "loss": 5.4132, "step": 480 }, { "epoch": 0.8326180257510729, "grad_norm": 8.637492625567376, "learning_rate": 1.6500153099547344e-05, "loss": 5.3985, "step": 485 }, { "epoch": 0.8412017167381974, "grad_norm": 7.593060990876112, "learning_rate": 1.4885413012287098e-05, "loss": 5.3591, "step": 490 }, { "epoch": 0.8497854077253219, "grad_norm": 7.293323409290838, "learning_rate": 1.3347445786070456e-05, "loss": 5.3058, "step": 495 }, { "epoch": 0.8583690987124464, "grad_norm": 8.58872146900946, "learning_rate": 1.1887638658365452e-05, "loss": 5.2812, "step": 500 }, { "epoch": 0.8669527896995708, "grad_norm": 10.579607337148637, "learning_rate": 1.0507308366687141e-05, "loss": 5.2935, "step": 505 }, { "epoch": 0.8755364806866953, "grad_norm": 7.796765987218623, "learning_rate": 9.207699960908012e-06, "loss": 5.3239, "step": 510 }, { "epoch": 0.8841201716738197, "grad_norm": 3.845171755230648, "learning_rate": 7.989985680230305e-06, "loss": 5.284, "step": 515 }, { "epoch": 0.8927038626609443, "grad_norm": 3.8997169411441335, "learning_rate": 6.855263895833064e-06, "loss": 5.2478, "step": 520 }, { "epoch": 0.9012875536480687, "grad_norm": 5.516395205208524, "learning_rate": 5.804558120147674e-06, "loss": 5.2356, "step": 525 }, { "epoch": 0.9098712446351931, "grad_norm": 5.160825401670845, "learning_rate": 4.838816083655695e-06, "loss": 5.2529, "step": 530 }, { "epoch": 0.9184549356223176, "grad_norm": 4.170530336706607, "learning_rate": 3.95890888004149e-06, "loss": 5.2019, "step": 535 }, { "epoch": 0.927038626609442, "grad_norm": 4.729325573447989, "learning_rate": 3.165630180470802e-06, "loss": 5.1868, "step": 540 }, { "epoch": 0.9356223175965666, "grad_norm": 4.8268274620539655, "learning_rate": 2.459695517703919e-06, "loss": 5.194, "step": 545 }, { "epoch": 0.944206008583691, "grad_norm": 3.373642611401382, "learning_rate": 1.8417416406894094e-06, "loss": 5.1408, "step": 550 }, { "epoch": 0.9527896995708155, "grad_norm": 2.9560576217055554, "learning_rate": 1.3123259402202048e-06, "loss": 5.1733, "step": 555 }, { "epoch": 0.9613733905579399, "grad_norm": 3.364514157359552, "learning_rate": 8.71925946170371e-07, "loss": 5.1221, "step": 560 }, { "epoch": 0.9699570815450643, "grad_norm": 2.8157940718449845, "learning_rate": 5.209388967659768e-07, "loss": 5.1479, "step": 565 }, { "epoch": 0.9785407725321889, "grad_norm": 3.778011781318662, "learning_rate": 2.596813802785092e-07, "loss": 5.1574, "step": 570 }, { "epoch": 0.9871244635193133, "grad_norm": 3.0834295680511814, "learning_rate": 8.838904946407711e-08, "loss": 5.1232, "step": 575 }, { "epoch": 0.9957081545064378, "grad_norm": 3.298741897550586, "learning_rate": 7.216409006038927e-09, "loss": 5.1634, "step": 580 }, { "epoch": 0.9991416309012876, "eval_loss": 6.949496746063232, "eval_runtime": 2.3831, "eval_samples_per_second": 2.518, "eval_steps_per_second": 0.42, "step": 582 }, { "epoch": 0.9991416309012876, "step": 582, "total_flos": 30438567444480.0, "train_loss": 6.936546556728402, "train_runtime": 8521.4757, "train_samples_per_second": 2.186, "train_steps_per_second": 0.068 } ], "logging_steps": 5, "max_steps": 582, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 30438567444480.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }