| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8090614886731392, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008090614886731391, | |
| "grad_norm": 7.823570251464844, | |
| "learning_rate": 6e-06, | |
| "loss": 0.8903, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016181229773462782, | |
| "grad_norm": 2.272317886352539, | |
| "learning_rate": 1.2666666666666668e-05, | |
| "loss": 0.4601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024271844660194174, | |
| "grad_norm": 1.5555341243743896, | |
| "learning_rate": 1.9333333333333333e-05, | |
| "loss": 0.276, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.032362459546925564, | |
| "grad_norm": 1.7244459390640259, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.1865, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.040453074433656956, | |
| "grad_norm": 1.4668376445770264, | |
| "learning_rate": 3.266666666666667e-05, | |
| "loss": 0.1422, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04854368932038835, | |
| "grad_norm": 2.02225661277771, | |
| "learning_rate": 3.933333333333333e-05, | |
| "loss": 0.1238, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05663430420711974, | |
| "grad_norm": 1.1487993001937866, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.0791, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06472491909385113, | |
| "grad_norm": 0.5569996237754822, | |
| "learning_rate": 5.266666666666666e-05, | |
| "loss": 0.0819, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07281553398058252, | |
| "grad_norm": 1.194751262664795, | |
| "learning_rate": 5.9333333333333343e-05, | |
| "loss": 0.0698, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08090614886731391, | |
| "grad_norm": 0.8545956015586853, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0732, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0889967637540453, | |
| "grad_norm": 0.6914941072463989, | |
| "learning_rate": 7.266666666666667e-05, | |
| "loss": 0.0641, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0970873786407767, | |
| "grad_norm": 0.4049356281757355, | |
| "learning_rate": 7.933333333333334e-05, | |
| "loss": 0.0565, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10517799352750809, | |
| "grad_norm": 0.7143370509147644, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.0555, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11326860841423948, | |
| "grad_norm": 0.9746547937393188, | |
| "learning_rate": 9.266666666666666e-05, | |
| "loss": 0.0523, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12135922330097088, | |
| "grad_norm": 0.6225072145462036, | |
| "learning_rate": 9.933333333333334e-05, | |
| "loss": 0.0492, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12944983818770225, | |
| "grad_norm": 0.6568852066993713, | |
| "learning_rate": 9.999753945398704e-05, | |
| "loss": 0.0478, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13754045307443366, | |
| "grad_norm": 0.345377653837204, | |
| "learning_rate": 9.998903417374228e-05, | |
| "loss": 0.0465, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.14563106796116504, | |
| "grad_norm": 0.756610095500946, | |
| "learning_rate": 9.997445481536973e-05, | |
| "loss": 0.0467, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.15372168284789645, | |
| "grad_norm": 0.494722843170166, | |
| "learning_rate": 9.995380315038119e-05, | |
| "loss": 0.0407, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.16181229773462782, | |
| "grad_norm": 0.7570058107376099, | |
| "learning_rate": 9.99270816881235e-05, | |
| "loss": 0.042, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16990291262135923, | |
| "grad_norm": 0.3776613473892212, | |
| "learning_rate": 9.989429367547377e-05, | |
| "loss": 0.0429, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1779935275080906, | |
| "grad_norm": 0.5018635988235474, | |
| "learning_rate": 9.985544309644475e-05, | |
| "loss": 0.0367, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.18608414239482202, | |
| "grad_norm": 0.3979959487915039, | |
| "learning_rate": 9.98105346717008e-05, | |
| "loss": 0.0341, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1941747572815534, | |
| "grad_norm": 0.5319691300392151, | |
| "learning_rate": 9.97595738579843e-05, | |
| "loss": 0.0347, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2022653721682848, | |
| "grad_norm": 0.5348716974258423, | |
| "learning_rate": 9.970256684745258e-05, | |
| "loss": 0.0308, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21035598705501618, | |
| "grad_norm": 0.6536835432052612, | |
| "learning_rate": 9.963952056692549e-05, | |
| "loss": 0.0301, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.21844660194174756, | |
| "grad_norm": 0.5518924593925476, | |
| "learning_rate": 9.957044267704384e-05, | |
| "loss": 0.0364, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.22653721682847897, | |
| "grad_norm": 0.40961554646492004, | |
| "learning_rate": 9.949534157133844e-05, | |
| "loss": 0.0293, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.23462783171521034, | |
| "grad_norm": 0.7217941880226135, | |
| "learning_rate": 9.941422637521035e-05, | |
| "loss": 0.0363, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.24271844660194175, | |
| "grad_norm": 0.5057093501091003, | |
| "learning_rate": 9.932710694482191e-05, | |
| "loss": 0.0295, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.25080906148867316, | |
| "grad_norm": 0.75019770860672, | |
| "learning_rate": 9.923399386589933e-05, | |
| "loss": 0.033, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 0.48032259941101074, | |
| "learning_rate": 9.913489845244626e-05, | |
| "loss": 0.0277, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2669902912621359, | |
| "grad_norm": 0.5418844223022461, | |
| "learning_rate": 9.902983274536912e-05, | |
| "loss": 0.0264, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.2750809061488673, | |
| "grad_norm": 0.5400299429893494, | |
| "learning_rate": 9.891880951101407e-05, | |
| "loss": 0.028, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.28317152103559873, | |
| "grad_norm": 0.7953261733055115, | |
| "learning_rate": 9.880184223961573e-05, | |
| "loss": 0.0245, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2912621359223301, | |
| "grad_norm": 0.47858819365501404, | |
| "learning_rate": 9.867894514365802e-05, | |
| "loss": 0.0272, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2993527508090615, | |
| "grad_norm": 0.3962852954864502, | |
| "learning_rate": 9.855013315614725e-05, | |
| "loss": 0.0262, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3074433656957929, | |
| "grad_norm": 0.840124785900116, | |
| "learning_rate": 9.841542192879762e-05, | |
| "loss": 0.0249, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3155339805825243, | |
| "grad_norm": 0.6563257575035095, | |
| "learning_rate": 9.82748278301294e-05, | |
| "loss": 0.0268, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.32362459546925565, | |
| "grad_norm": 0.4959515929222107, | |
| "learning_rate": 9.812836794348004e-05, | |
| "loss": 0.0241, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.33171521035598706, | |
| "grad_norm": 0.5108354091644287, | |
| "learning_rate": 9.797606006492841e-05, | |
| "loss": 0.0329, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.33980582524271846, | |
| "grad_norm": 0.5321593880653381, | |
| "learning_rate": 9.781792270113241e-05, | |
| "loss": 0.0248, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3478964401294498, | |
| "grad_norm": 0.7112411856651306, | |
| "learning_rate": 9.765397506708023e-05, | |
| "loss": 0.0266, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3559870550161812, | |
| "grad_norm": 0.4580034911632538, | |
| "learning_rate": 9.748423708375563e-05, | |
| "loss": 0.0228, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3640776699029126, | |
| "grad_norm": 0.43798476457595825, | |
| "learning_rate": 9.730872937571739e-05, | |
| "loss": 0.0239, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.37216828478964403, | |
| "grad_norm": 0.5347399711608887, | |
| "learning_rate": 9.712747326859315e-05, | |
| "loss": 0.0265, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3802588996763754, | |
| "grad_norm": 0.5635089874267578, | |
| "learning_rate": 9.69404907864883e-05, | |
| "loss": 0.027, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3883495145631068, | |
| "grad_norm": 0.3755838871002197, | |
| "learning_rate": 9.674780464930979e-05, | |
| "loss": 0.0234, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3964401294498382, | |
| "grad_norm": 0.522113561630249, | |
| "learning_rate": 9.654943827000548e-05, | |
| "loss": 0.021, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4045307443365696, | |
| "grad_norm": 0.43958115577697754, | |
| "learning_rate": 9.634541575171929e-05, | |
| "loss": 0.0214, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.41262135922330095, | |
| "grad_norm": 0.4480895698070526, | |
| "learning_rate": 9.613576188486253e-05, | |
| "loss": 0.0258, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.42071197411003236, | |
| "grad_norm": 0.410576730966568, | |
| "learning_rate": 9.59205021441015e-05, | |
| "loss": 0.0226, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.42880258899676377, | |
| "grad_norm": 0.45604780316352844, | |
| "learning_rate": 9.569966268526232e-05, | |
| "loss": 0.0256, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.4368932038834951, | |
| "grad_norm": 0.30307430028915405, | |
| "learning_rate": 9.54732703421526e-05, | |
| "loss": 0.0204, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.4449838187702265, | |
| "grad_norm": 0.29722708463668823, | |
| "learning_rate": 9.524135262330098e-05, | |
| "loss": 0.0198, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.45307443365695793, | |
| "grad_norm": 0.38580235838890076, | |
| "learning_rate": 9.50039377086147e-05, | |
| "loss": 0.0168, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.46116504854368934, | |
| "grad_norm": 0.39507967233657837, | |
| "learning_rate": 9.476105444595534e-05, | |
| "loss": 0.0157, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.4692556634304207, | |
| "grad_norm": 0.34573355317115784, | |
| "learning_rate": 9.451273234763371e-05, | |
| "loss": 0.0176, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.4773462783171521, | |
| "grad_norm": 0.2983342111110687, | |
| "learning_rate": 9.425900158682385e-05, | |
| "loss": 0.0177, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.4854368932038835, | |
| "grad_norm": 0.38746461272239685, | |
| "learning_rate": 9.399989299389661e-05, | |
| "loss": 0.0216, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4935275080906149, | |
| "grad_norm": 0.39340198040008545, | |
| "learning_rate": 9.373543805267368e-05, | |
| "loss": 0.0221, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5016181229773463, | |
| "grad_norm": 0.47980770468711853, | |
| "learning_rate": 9.346566889660193e-05, | |
| "loss": 0.0172, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5097087378640777, | |
| "grad_norm": 0.421115905046463, | |
| "learning_rate": 9.319061830484898e-05, | |
| "loss": 0.0156, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.517799352750809, | |
| "grad_norm": 0.3385259509086609, | |
| "learning_rate": 9.291031969832026e-05, | |
| "loss": 0.0176, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5258899676375405, | |
| "grad_norm": 0.32277145981788635, | |
| "learning_rate": 9.262480713559808e-05, | |
| "loss": 0.0169, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5339805825242718, | |
| "grad_norm": 0.32181084156036377, | |
| "learning_rate": 9.233411530880326e-05, | |
| "loss": 0.0187, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5420711974110033, | |
| "grad_norm": 0.5838663578033447, | |
| "learning_rate": 9.20382795393797e-05, | |
| "loss": 0.0228, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5501618122977346, | |
| "grad_norm": 0.30314013361930847, | |
| "learning_rate": 9.173733577380258e-05, | |
| "loss": 0.02, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.558252427184466, | |
| "grad_norm": 0.5964832901954651, | |
| "learning_rate": 9.143132057921058e-05, | |
| "loss": 0.018, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.5663430420711975, | |
| "grad_norm": 0.4126530587673187, | |
| "learning_rate": 9.112027113896262e-05, | |
| "loss": 0.0173, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5744336569579288, | |
| "grad_norm": 0.4253070652484894, | |
| "learning_rate": 9.080422524811982e-05, | |
| "loss": 0.0257, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.5825242718446602, | |
| "grad_norm": 0.5417248606681824, | |
| "learning_rate": 9.048322130885305e-05, | |
| "loss": 0.0177, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5906148867313916, | |
| "grad_norm": 0.3459491431713104, | |
| "learning_rate": 9.015729832577681e-05, | |
| "loss": 0.019, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.598705501618123, | |
| "grad_norm": 0.3335317373275757, | |
| "learning_rate": 8.982649590120982e-05, | |
| "loss": 0.0169, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.6067961165048543, | |
| "grad_norm": 0.6572862267494202, | |
| "learning_rate": 8.949085423036296e-05, | |
| "loss": 0.0198, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6148867313915858, | |
| "grad_norm": 0.540212869644165, | |
| "learning_rate": 8.91504140964553e-05, | |
| "loss": 0.016, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6229773462783171, | |
| "grad_norm": 0.24550016224384308, | |
| "learning_rate": 8.880521686575857e-05, | |
| "loss": 0.0168, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.6310679611650486, | |
| "grad_norm": 0.5790821313858032, | |
| "learning_rate": 8.845530448257085e-05, | |
| "loss": 0.0184, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.63915857605178, | |
| "grad_norm": 0.6583966612815857, | |
| "learning_rate": 8.810071946411989e-05, | |
| "loss": 0.0167, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6472491909385113, | |
| "grad_norm": 0.3252386450767517, | |
| "learning_rate": 8.774150489539707e-05, | |
| "loss": 0.0173, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6553398058252428, | |
| "grad_norm": 0.37483498454093933, | |
| "learning_rate": 8.737770442392212e-05, | |
| "loss": 0.0169, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.6634304207119741, | |
| "grad_norm": 0.29752904176712036, | |
| "learning_rate": 8.700936225443959e-05, | |
| "loss": 0.018, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6715210355987055, | |
| "grad_norm": 0.37370291352272034, | |
| "learning_rate": 8.663652314354765e-05, | |
| "loss": 0.0178, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.6796116504854369, | |
| "grad_norm": 0.24446973204612732, | |
| "learning_rate": 8.625923239425978e-05, | |
| "loss": 0.0132, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.6877022653721683, | |
| "grad_norm": 0.45145106315612793, | |
| "learning_rate": 8.587753585050004e-05, | |
| "loss": 0.0196, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.6957928802588996, | |
| "grad_norm": 0.24976196885108948, | |
| "learning_rate": 8.549147989153276e-05, | |
| "loss": 0.017, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.7038834951456311, | |
| "grad_norm": 0.41941019892692566, | |
| "learning_rate": 8.510111142632698e-05, | |
| "loss": 0.0153, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.7119741100323624, | |
| "grad_norm": 0.3423904776573181, | |
| "learning_rate": 8.470647788785665e-05, | |
| "loss": 0.0143, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.7200647249190939, | |
| "grad_norm": 0.28540822863578796, | |
| "learning_rate": 8.430762722733714e-05, | |
| "loss": 0.0125, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.7281553398058253, | |
| "grad_norm": 0.38557255268096924, | |
| "learning_rate": 8.390460790839882e-05, | |
| "loss": 0.0193, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7362459546925566, | |
| "grad_norm": 0.496142715215683, | |
| "learning_rate": 8.349746890119826e-05, | |
| "loss": 0.0137, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.7443365695792881, | |
| "grad_norm": 0.42488303780555725, | |
| "learning_rate": 8.308625967646795e-05, | |
| "loss": 0.0159, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7524271844660194, | |
| "grad_norm": 0.28551360964775085, | |
| "learning_rate": 8.267103019950529e-05, | |
| "loss": 0.0155, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.7605177993527508, | |
| "grad_norm": 0.3401723802089691, | |
| "learning_rate": 8.225183092410128e-05, | |
| "loss": 0.0133, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.7686084142394822, | |
| "grad_norm": 0.34012413024902344, | |
| "learning_rate": 8.182871278641009e-05, | |
| "loss": 0.0191, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 0.385560005903244, | |
| "learning_rate": 8.140172719875979e-05, | |
| "loss": 0.0108, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7847896440129449, | |
| "grad_norm": 0.3427627980709076, | |
| "learning_rate": 8.097092604340542e-05, | |
| "loss": 0.0121, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.7928802588996764, | |
| "grad_norm": 0.45653820037841797, | |
| "learning_rate": 8.053636166622476e-05, | |
| "loss": 0.0154, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.8009708737864077, | |
| "grad_norm": 0.3446105122566223, | |
| "learning_rate": 8.009808687035798e-05, | |
| "loss": 0.0171, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.8090614886731392, | |
| "grad_norm": 0.25365254282951355, | |
| "learning_rate": 7.965615490979163e-05, | |
| "loss": 0.014, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |