{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9998890655622525, "eval_steps": 500, "global_step": 40563, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.999925019651876e-05, "loss": 3.2124, "step": 100 }, { "epoch": 0.01, "learning_rate": 4.9997000831051485e-05, "loss": 0.2834, "step": 200 }, { "epoch": 0.02, "learning_rate": 4.999325203852471e-05, "loss": 0.2178, "step": 300 }, { "epoch": 0.03, "learning_rate": 4.998800404380707e-05, "loss": 0.1782, "step": 400 }, { "epoch": 0.04, "learning_rate": 4.9981257161695735e-05, "loss": 0.1501, "step": 500 }, { "epoch": 0.04, "learning_rate": 4.997301179689756e-05, "loss": 0.1376, "step": 600 }, { "epoch": 0.05, "learning_rate": 4.996326844400481e-05, "loss": 0.1161, "step": 700 }, { "epoch": 0.06, "learning_rate": 4.9952027687465465e-05, "loss": 0.1163, "step": 800 }, { "epoch": 0.07, "learning_rate": 4.9939290201548214e-05, "loss": 0.1157, "step": 900 }, { "epoch": 0.07, "learning_rate": 4.992505675030195e-05, "loss": 0.1048, "step": 1000 }, { "epoch": 0.08, "learning_rate": 4.9909328187509964e-05, "loss": 0.1073, "step": 1100 }, { "epoch": 0.09, "learning_rate": 4.989210545663877e-05, "loss": 0.1047, "step": 1200 }, { "epoch": 0.1, "learning_rate": 4.987338959078144e-05, "loss": 0.1066, "step": 1300 }, { "epoch": 0.1, "learning_rate": 4.9853181712595686e-05, "loss": 0.1011, "step": 1400 }, { "epoch": 0.11, "learning_rate": 4.98314830342365e-05, "loss": 0.0947, "step": 1500 }, { "epoch": 0.12, "learning_rate": 4.9808294857283454e-05, "loss": 0.0916, "step": 1600 }, { "epoch": 0.13, "learning_rate": 4.97836185726626e-05, "loss": 0.0933, "step": 1700 }, { "epoch": 0.13, "learning_rate": 4.9757455660563085e-05, "loss": 0.089, "step": 1800 }, { "epoch": 0.14, "learning_rate": 4.9729807690348297e-05, "loss": 0.0872, "step": 1900 }, { "epoch": 0.15, "learning_rate": 4.9700676320461794e-05, "loss": 0.0898, "step": 2000 }, { "epoch": 0.16, "learning_rate": 4.9670376756771875e-05, "loss": 0.0894, "step": 2100 }, { "epoch": 0.16, "learning_rate": 4.963829870746861e-05, "loss": 0.0859, "step": 2200 }, { "epoch": 0.17, "learning_rate": 4.960474274759395e-05, "loss": 0.0826, "step": 2300 }, { "epoch": 0.18, "learning_rate": 4.956971088997792e-05, "loss": 0.0816, "step": 2400 }, { "epoch": 0.18, "learning_rate": 4.953320523598123e-05, "loss": 0.074, "step": 2500 }, { "epoch": 0.19, "learning_rate": 4.9495227975369186e-05, "loss": 0.0896, "step": 2600 }, { "epoch": 0.2, "learning_rate": 4.945578138618039e-05, "loss": 0.0768, "step": 2700 }, { "epoch": 0.21, "learning_rate": 4.941486783459001e-05, "loss": 0.0779, "step": 2800 }, { "epoch": 0.21, "learning_rate": 4.937248977476793e-05, "loss": 0.0814, "step": 2900 }, { "epoch": 0.22, "learning_rate": 4.9328649748731495e-05, "loss": 0.0727, "step": 3000 }, { "epoch": 0.23, "learning_rate": 4.928335038619302e-05, "loss": 0.0806, "step": 3100 }, { "epoch": 0.24, "learning_rate": 4.9236594404402104e-05, "loss": 0.0709, "step": 3200 }, { "epoch": 0.24, "learning_rate": 4.9188384607982565e-05, "loss": 0.0746, "step": 3300 }, { "epoch": 0.25, "learning_rate": 4.913872388876427e-05, "loss": 0.0805, "step": 3400 }, { "epoch": 0.26, "learning_rate": 4.908761522560962e-05, "loss": 0.0726, "step": 3500 }, { "epoch": 0.27, "learning_rate": 4.903506168423491e-05, "loss": 0.0715, "step": 3600 }, { "epoch": 0.27, "learning_rate": 4.898106641702639e-05, "loss": 0.0751, "step": 3700 }, { "epoch": 0.28, "learning_rate": 4.892563266285121e-05, "loss": 0.0818, "step": 3800 }, { "epoch": 0.29, "learning_rate": 4.886876374686313e-05, "loss": 0.0651, "step": 3900 }, { "epoch": 0.3, "learning_rate": 4.881046308030303e-05, "loss": 0.0806, "step": 4000 }, { "epoch": 0.3, "learning_rate": 4.87513385076558e-05, "loss": 0.0803, "step": 4100 }, { "epoch": 0.31, "learning_rate": 4.869019914568559e-05, "loss": 0.0717, "step": 4200 }, { "epoch": 0.32, "learning_rate": 4.8627638744212125e-05, "loss": 0.0678, "step": 4300 }, { "epoch": 0.33, "learning_rate": 4.8563661055875955e-05, "loss": 0.0681, "step": 4400 }, { "epoch": 0.33, "learning_rate": 4.849826991833256e-05, "loss": 0.0668, "step": 4500 }, { "epoch": 0.34, "learning_rate": 4.8431469254022146e-05, "loss": 0.0717, "step": 4600 }, { "epoch": 0.35, "learning_rate": 4.8363263069934364e-05, "loss": 0.0681, "step": 4700 }, { "epoch": 0.35, "learning_rate": 4.829365545736794e-05, "loss": 0.0703, "step": 4800 }, { "epoch": 0.36, "learning_rate": 4.8222650591685316e-05, "loss": 0.0625, "step": 4900 }, { "epoch": 0.37, "learning_rate": 4.815025273206212e-05, "loss": 0.066, "step": 5000 }, { "epoch": 0.38, "learning_rate": 4.807646622123172e-05, "loss": 0.0707, "step": 5100 }, { "epoch": 0.38, "learning_rate": 4.800129548522474e-05, "loss": 0.061, "step": 5200 }, { "epoch": 0.39, "learning_rate": 4.7924745033103533e-05, "loss": 0.0645, "step": 5300 }, { "epoch": 0.4, "learning_rate": 4.784681945669176e-05, "loss": 0.0669, "step": 5400 }, { "epoch": 0.41, "learning_rate": 4.776752343029888e-05, "loss": 0.059, "step": 5500 }, { "epoch": 0.41, "learning_rate": 4.768686171043982e-05, "loss": 0.0641, "step": 5600 }, { "epoch": 0.42, "learning_rate": 4.760483913554966e-05, "loss": 0.0619, "step": 5700 }, { "epoch": 0.43, "learning_rate": 4.7522301106315205e-05, "loss": 0.0616, "step": 5800 }, { "epoch": 0.44, "learning_rate": 4.7437585147204955e-05, "loss": 0.0625, "step": 5900 }, { "epoch": 0.44, "learning_rate": 4.7351523285738384e-05, "loss": 0.0594, "step": 6000 }, { "epoch": 0.45, "learning_rate": 4.726412068427418e-05, "loss": 0.0616, "step": 6100 }, { "epoch": 0.46, "learning_rate": 4.717538258559431e-05, "loss": 0.0657, "step": 6200 }, { "epoch": 0.47, "learning_rate": 4.7085314312589614e-05, "loss": 0.0631, "step": 6300 }, { "epoch": 0.47, "learning_rate": 4.699392126794045e-05, "loss": 0.0503, "step": 6400 }, { "epoch": 0.48, "learning_rate": 4.6901208933792675e-05, "loss": 0.0652, "step": 6500 }, { "epoch": 0.49, "learning_rate": 4.680718287142875e-05, "loss": 0.0571, "step": 6600 }, { "epoch": 0.5, "learning_rate": 4.671184872093419e-05, "loss": 0.054, "step": 6700 }, { "epoch": 0.5, "learning_rate": 4.661521220085923e-05, "loss": 0.0628, "step": 6800 }, { "epoch": 0.51, "learning_rate": 4.65172791078758e-05, "loss": 0.0554, "step": 6900 }, { "epoch": 0.52, "learning_rate": 4.641805531642983e-05, "loss": 0.059, "step": 7000 }, { "epoch": 0.53, "learning_rate": 4.631754677838885e-05, "loss": 0.0557, "step": 7100 }, { "epoch": 0.53, "learning_rate": 4.621575952268501e-05, "loss": 0.0579, "step": 7200 }, { "epoch": 0.54, "learning_rate": 4.6112699654953394e-05, "loss": 0.0594, "step": 7300 }, { "epoch": 0.55, "learning_rate": 4.600837335716581e-05, "loss": 0.0652, "step": 7400 }, { "epoch": 0.55, "learning_rate": 4.590278688725998e-05, "loss": 0.0509, "step": 7500 }, { "epoch": 0.56, "learning_rate": 4.579594657876408e-05, "loss": 0.0658, "step": 7600 }, { "epoch": 0.57, "learning_rate": 4.568785884041696e-05, "loss": 0.054, "step": 7700 }, { "epoch": 0.58, "learning_rate": 4.557853015578361e-05, "loss": 0.0543, "step": 7800 }, { "epoch": 0.58, "learning_rate": 4.5467967082866306e-05, "loss": 0.0552, "step": 7900 }, { "epoch": 0.59, "learning_rate": 4.535730021743883e-05, "loss": 0.0615, "step": 8000 }, { "epoch": 0.6, "learning_rate": 4.52443005148096e-05, "loss": 0.0567, "step": 8100 }, { "epoch": 0.61, "learning_rate": 4.5130086472420265e-05, "loss": 0.0519, "step": 8200 }, { "epoch": 0.61, "learning_rate": 4.5014664941317766e-05, "loss": 0.0573, "step": 8300 }, { "epoch": 0.62, "learning_rate": 4.489804284497936e-05, "loss": 0.053, "step": 8400 }, { "epoch": 0.63, "learning_rate": 4.4780227178897366e-05, "loss": 0.0658, "step": 8500 }, { "epoch": 0.64, "learning_rate": 4.46612250101595e-05, "loss": 0.0574, "step": 8600 }, { "epoch": 0.64, "learning_rate": 4.4541043477025e-05, "loss": 0.0608, "step": 8700 }, { "epoch": 0.65, "learning_rate": 4.441968978849641e-05, "loss": 0.0471, "step": 8800 }, { "epoch": 0.66, "learning_rate": 4.4297171223887194e-05, "loss": 0.0598, "step": 8900 }, { "epoch": 0.67, "learning_rate": 4.4173495132385035e-05, "loss": 0.0549, "step": 9000 }, { "epoch": 0.67, "learning_rate": 4.404866893261106e-05, "loss": 0.0529, "step": 9100 }, { "epoch": 0.68, "learning_rate": 4.39227001121748e-05, "loss": 0.0529, "step": 9200 }, { "epoch": 0.69, "learning_rate": 4.3795596227225066e-05, "loss": 0.0568, "step": 9300 }, { "epoch": 0.7, "learning_rate": 4.366736490199668e-05, "loss": 0.0602, "step": 9400 }, { "epoch": 0.7, "learning_rate": 4.353801382835318e-05, "loss": 0.053, "step": 9500 }, { "epoch": 0.71, "learning_rate": 4.340755076532538e-05, "loss": 0.0498, "step": 9600 }, { "epoch": 0.72, "learning_rate": 4.3275983538645995e-05, "loss": 0.0509, "step": 9700 }, { "epoch": 0.72, "learning_rate": 4.314332004028019e-05, "loss": 0.0552, "step": 9800 }, { "epoch": 0.73, "learning_rate": 4.3009568227952194e-05, "loss": 0.0565, "step": 9900 }, { "epoch": 0.74, "learning_rate": 4.287473612466796e-05, "loss": 0.0573, "step": 10000 }, { "epoch": 0.75, "learning_rate": 4.273883181823394e-05, "loss": 0.0477, "step": 10100 }, { "epoch": 0.75, "learning_rate": 4.2603238384474695e-05, "loss": 0.0522, "step": 10200 }, { "epoch": 0.76, "learning_rate": 4.24652247094062e-05, "loss": 0.0515, "step": 10300 }, { "epoch": 0.77, "learning_rate": 4.23261633954347e-05, "loss": 0.0478, "step": 10400 }, { "epoch": 0.78, "learning_rate": 4.218606278405277e-05, "loss": 0.0535, "step": 10500 }, { "epoch": 0.78, "learning_rate": 4.20449312790945e-05, "loss": 0.0481, "step": 10600 }, { "epoch": 0.79, "learning_rate": 4.1902777346231383e-05, "loss": 0.0487, "step": 10700 }, { "epoch": 0.8, "learning_rate": 4.175960951246454e-05, "loss": 0.0429, "step": 10800 }, { "epoch": 0.81, "learning_rate": 4.161543636561316e-05, "loss": 0.0485, "step": 10900 }, { "epoch": 0.81, "learning_rate": 4.147026655379945e-05, "loss": 0.0486, "step": 11000 }, { "epoch": 0.82, "learning_rate": 4.132410878492983e-05, "loss": 0.0484, "step": 11100 }, { "epoch": 0.83, "learning_rate": 4.1176971826172596e-05, "loss": 0.0485, "step": 11200 }, { "epoch": 0.84, "learning_rate": 4.1028864503432085e-05, "loss": 0.0545, "step": 11300 }, { "epoch": 0.84, "learning_rate": 4.087979570081917e-05, "loss": 0.0436, "step": 11400 }, { "epoch": 0.85, "learning_rate": 4.072977436011844e-05, "loss": 0.0492, "step": 11500 }, { "epoch": 0.86, "learning_rate": 4.057880948025177e-05, "loss": 0.0534, "step": 11600 }, { "epoch": 0.87, "learning_rate": 4.042691011673855e-05, "loss": 0.0551, "step": 11700 }, { "epoch": 0.87, "learning_rate": 4.027408538115252e-05, "loss": 0.0488, "step": 11800 }, { "epoch": 0.88, "learning_rate": 4.0120344440575165e-05, "loss": 0.0525, "step": 11900 }, { "epoch": 0.89, "learning_rate": 3.996569651704589e-05, "loss": 0.0458, "step": 12000 }, { "epoch": 0.89, "learning_rate": 3.9810150887008806e-05, "loss": 0.0492, "step": 12100 }, { "epoch": 0.9, "learning_rate": 3.965528558751401e-05, "loss": 0.0489, "step": 12200 }, { "epoch": 0.91, "learning_rate": 3.949798133193112e-05, "loss": 0.0465, "step": 12300 }, { "epoch": 0.92, "learning_rate": 3.933980742539834e-05, "loss": 0.0502, "step": 12400 }, { "epoch": 0.92, "learning_rate": 3.9180773355863344e-05, "loss": 0.0506, "step": 12500 }, { "epoch": 0.93, "learning_rate": 3.902088866287004e-05, "loss": 0.0525, "step": 12600 }, { "epoch": 0.94, "learning_rate": 3.886016293698637e-05, "loss": 0.0472, "step": 12700 }, { "epoch": 0.95, "learning_rate": 3.869860581922905e-05, "loss": 0.0443, "step": 12800 }, { "epoch": 0.95, "learning_rate": 3.8536227000485234e-05, "loss": 0.042, "step": 12900 }, { "epoch": 0.96, "learning_rate": 3.837303622093119e-05, "loss": 0.0447, "step": 13000 }, { "epoch": 0.97, "learning_rate": 3.8209043269448096e-05, "loss": 0.046, "step": 13100 }, { "epoch": 0.98, "learning_rate": 3.804425798303483e-05, "loss": 0.0434, "step": 13200 }, { "epoch": 0.98, "learning_rate": 3.787869024621789e-05, "loss": 0.0479, "step": 13300 }, { "epoch": 0.99, "learning_rate": 3.7712349990458524e-05, "loss": 0.0484, "step": 13400 }, { "epoch": 1.0, "learning_rate": 3.754524719355695e-05, "loss": 0.0506, "step": 13500 }, { "epoch": 1.01, "learning_rate": 3.737739187905389e-05, "loss": 0.0449, "step": 13600 }, { "epoch": 1.01, "learning_rate": 3.7208794115629266e-05, "loss": 0.0419, "step": 13700 }, { "epoch": 1.02, "learning_rate": 3.703946401649827e-05, "loss": 0.0356, "step": 13800 }, { "epoch": 1.03, "learning_rate": 3.6869411738804735e-05, "loss": 0.0433, "step": 13900 }, { "epoch": 1.04, "learning_rate": 3.669864748301185e-05, "loss": 0.0408, "step": 14000 }, { "epoch": 1.04, "learning_rate": 3.6527181492290277e-05, "loss": 0.0435, "step": 14100 }, { "epoch": 1.05, "learning_rate": 3.635502405190375e-05, "loss": 0.0394, "step": 14200 }, { "epoch": 1.06, "learning_rate": 3.618391721177532e-05, "loss": 0.0442, "step": 14300 }, { "epoch": 1.06, "learning_rate": 3.601041454923619e-05, "loss": 0.0448, "step": 14400 }, { "epoch": 1.07, "learning_rate": 3.583625143492436e-05, "loss": 0.047, "step": 14500 }, { "epoch": 1.08, "learning_rate": 3.5661438315888565e-05, "loss": 0.0374, "step": 14600 }, { "epoch": 1.09, "learning_rate": 3.5485985678167643e-05, "loss": 0.0397, "step": 14700 }, { "epoch": 1.09, "learning_rate": 3.530990404616147e-05, "loss": 0.0398, "step": 14800 }, { "epoch": 1.1, "learning_rate": 3.5133203981999684e-05, "loss": 0.0461, "step": 14900 }, { "epoch": 1.11, "learning_rate": 3.4955896084908166e-05, "loss": 0.0374, "step": 15000 }, { "epoch": 1.12, "learning_rate": 3.4777990990573174e-05, "loss": 0.0415, "step": 15100 }, { "epoch": 1.12, "learning_rate": 3.459949937050345e-05, "loss": 0.0378, "step": 15200 }, { "epoch": 1.13, "learning_rate": 3.442043193139005e-05, "loss": 0.0434, "step": 15300 }, { "epoch": 1.14, "learning_rate": 3.424079941446407e-05, "loss": 0.0409, "step": 15400 }, { "epoch": 1.15, "learning_rate": 3.4060612594852486e-05, "loss": 0.0384, "step": 15500 }, { "epoch": 1.15, "learning_rate": 3.387988228093163e-05, "loss": 0.0394, "step": 15600 }, { "epoch": 1.16, "learning_rate": 3.3698619313679e-05, "loss": 0.0343, "step": 15700 }, { "epoch": 1.17, "learning_rate": 3.3516834566022906e-05, "loss": 0.0371, "step": 15800 }, { "epoch": 1.18, "learning_rate": 3.333453894219027e-05, "loss": 0.0364, "step": 15900 }, { "epoch": 1.18, "learning_rate": 3.315174337705257e-05, "loss": 0.04, "step": 16000 }, { "epoch": 1.19, "learning_rate": 3.296845883546988e-05, "loss": 0.0422, "step": 16100 }, { "epoch": 1.2, "learning_rate": 3.2784696311633213e-05, "loss": 0.0343, "step": 16200 }, { "epoch": 1.21, "learning_rate": 3.260046682840495e-05, "loss": 0.0381, "step": 16300 }, { "epoch": 1.21, "learning_rate": 3.241578143665773e-05, "loss": 0.041, "step": 16400 }, { "epoch": 1.22, "learning_rate": 3.223250468230082e-05, "loss": 0.0336, "step": 16500 }, { "epoch": 1.23, "learning_rate": 3.204694501705715e-05, "loss": 0.0364, "step": 16600 }, { "epoch": 1.24, "learning_rate": 3.186096264590101e-05, "loss": 0.0328, "step": 16700 }, { "epoch": 1.24, "learning_rate": 3.1674568724850744e-05, "loss": 0.0403, "step": 16800 }, { "epoch": 1.25, "learning_rate": 3.148777443461123e-05, "loss": 0.0425, "step": 16900 }, { "epoch": 1.26, "learning_rate": 3.13005909799032e-05, "loss": 0.0432, "step": 17000 }, { "epoch": 1.26, "learning_rate": 3.111302958879111e-05, "loss": 0.0423, "step": 17100 }, { "epoch": 1.27, "learning_rate": 3.0925101512009715e-05, "loss": 0.0328, "step": 17200 }, { "epoch": 1.28, "learning_rate": 3.073681802228907e-05, "loss": 0.0385, "step": 17300 }, { "epoch": 1.29, "learning_rate": 3.054819041367849e-05, "loss": 0.0378, "step": 17400 }, { "epoch": 1.29, "learning_rate": 3.035923000086896e-05, "loss": 0.0461, "step": 17500 }, { "epoch": 1.3, "learning_rate": 3.016994811851453e-05, "loss": 0.0332, "step": 17600 }, { "epoch": 1.31, "learning_rate": 2.9980356120552333e-05, "loss": 0.0343, "step": 17700 }, { "epoch": 1.32, "learning_rate": 2.9790465379521572e-05, "loss": 0.0413, "step": 17800 }, { "epoch": 1.32, "learning_rate": 2.960028728588135e-05, "loss": 0.0363, "step": 17900 }, { "epoch": 1.33, "learning_rate": 2.94098332473274e-05, "loss": 0.0486, "step": 18000 }, { "epoch": 1.34, "learning_rate": 2.9219114688107802e-05, "loss": 0.0388, "step": 18100 }, { "epoch": 1.35, "learning_rate": 2.9028143048337736e-05, "loss": 0.0389, "step": 18200 }, { "epoch": 1.35, "learning_rate": 2.8836929783313228e-05, "loss": 0.0424, "step": 18300 }, { "epoch": 1.36, "learning_rate": 2.8645486362824016e-05, "loss": 0.04, "step": 18400 }, { "epoch": 1.37, "learning_rate": 2.845574193607597e-05, "loss": 0.0414, "step": 18500 }, { "epoch": 1.38, "learning_rate": 2.826387468336204e-05, "loss": 0.0421, "step": 18600 }, { "epoch": 1.38, "learning_rate": 2.807181164948013e-05, "loss": 0.0387, "step": 18700 }, { "epoch": 1.39, "learning_rate": 2.7879564355192734e-05, "loss": 0.0342, "step": 18800 }, { "epoch": 1.4, "learning_rate": 2.7687144332315106e-05, "loss": 0.0377, "step": 18900 }, { "epoch": 1.41, "learning_rate": 2.749456312302348e-05, "loss": 0.0394, "step": 19000 }, { "epoch": 1.41, "learning_rate": 2.7301832279162748e-05, "loss": 0.0343, "step": 19100 }, { "epoch": 1.42, "learning_rate": 2.7108963361553523e-05, "loss": 0.0383, "step": 19200 }, { "epoch": 1.43, "learning_rate": 2.6915967939298682e-05, "loss": 0.0399, "step": 19300 }, { "epoch": 1.43, "learning_rate": 2.672285758908937e-05, "loss": 0.0394, "step": 19400 }, { "epoch": 1.44, "learning_rate": 2.6529643894510626e-05, "loss": 0.0379, "step": 19500 }, { "epoch": 1.45, "learning_rate": 2.63363384453465e-05, "loss": 0.0353, "step": 19600 }, { "epoch": 1.46, "learning_rate": 2.6142952836884905e-05, "loss": 0.0335, "step": 19700 }, { "epoch": 1.46, "learning_rate": 2.5949498669222026e-05, "loss": 0.0324, "step": 19800 }, { "epoch": 1.47, "learning_rate": 2.5755987546566546e-05, "loss": 0.0392, "step": 19900 }, { "epoch": 1.48, "learning_rate": 2.556243107654353e-05, "loss": 0.0391, "step": 20000 }, { "epoch": 1.49, "learning_rate": 2.5368840869498178e-05, "loss": 0.0321, "step": 20100 }, { "epoch": 1.49, "learning_rate": 2.5175228537799395e-05, "loss": 0.0417, "step": 20200 }, { "epoch": 1.5, "learning_rate": 2.498160569514319e-05, "loss": 0.0368, "step": 20300 }, { "epoch": 1.51, "learning_rate": 2.4787983955856092e-05, "loss": 0.038, "step": 20400 }, { "epoch": 1.52, "learning_rate": 2.4594374934198443e-05, "loss": 0.0394, "step": 20500 }, { "epoch": 1.52, "learning_rate": 2.4400790243667697e-05, "loss": 0.0351, "step": 20600 }, { "epoch": 1.53, "learning_rate": 2.4209176767733668e-05, "loss": 0.0372, "step": 20700 }, { "epoch": 1.54, "learning_rate": 2.4015675040424098e-05, "loss": 0.0355, "step": 20800 }, { "epoch": 1.55, "learning_rate": 2.3822232357137047e-05, "loss": 0.0336, "step": 20900 }, { "epoch": 1.55, "learning_rate": 2.3628860321392283e-05, "loss": 0.0329, "step": 21000 }, { "epoch": 1.56, "learning_rate": 2.3435570532471857e-05, "loss": 0.0343, "step": 21100 }, { "epoch": 1.57, "learning_rate": 2.3242374584724318e-05, "loss": 0.04, "step": 21200 }, { "epoch": 1.58, "learning_rate": 2.304928406686917e-05, "loss": 0.0318, "step": 21300 }, { "epoch": 1.58, "learning_rate": 2.285631056130183e-05, "loss": 0.045, "step": 21400 }, { "epoch": 1.59, "learning_rate": 2.2663465643398795e-05, "loss": 0.0327, "step": 21500 }, { "epoch": 1.6, "learning_rate": 2.2470760880823344e-05, "loss": 0.0402, "step": 21600 }, { "epoch": 1.6, "learning_rate": 2.227820783283159e-05, "loss": 0.0343, "step": 21700 }, { "epoch": 1.61, "learning_rate": 2.2085818049579214e-05, "loss": 0.0379, "step": 21800 }, { "epoch": 1.62, "learning_rate": 2.1893603071428552e-05, "loss": 0.0339, "step": 21900 }, { "epoch": 1.63, "learning_rate": 2.1701574428256376e-05, "loss": 0.0358, "step": 22000 }, { "epoch": 1.63, "learning_rate": 2.1509743638762304e-05, "loss": 0.0341, "step": 22100 }, { "epoch": 1.64, "learning_rate": 2.1318122209777842e-05, "loss": 0.0329, "step": 22200 }, { "epoch": 1.65, "learning_rate": 2.1126721635576142e-05, "loss": 0.0324, "step": 22300 }, { "epoch": 1.66, "learning_rate": 2.0935553397182553e-05, "loss": 0.0347, "step": 22400 }, { "epoch": 1.66, "learning_rate": 2.0744628961685932e-05, "loss": 0.0358, "step": 22500 }, { "epoch": 1.67, "learning_rate": 2.0553959781550803e-05, "loss": 0.0385, "step": 22600 }, { "epoch": 1.68, "learning_rate": 2.036355729393034e-05, "loss": 0.036, "step": 22700 }, { "epoch": 1.69, "learning_rate": 2.0173432919980404e-05, "loss": 0.0337, "step": 22800 }, { "epoch": 1.69, "learning_rate": 1.99835980641744e-05, "loss": 0.0346, "step": 22900 }, { "epoch": 1.7, "learning_rate": 1.9794064113619162e-05, "loss": 0.0394, "step": 23000 }, { "epoch": 1.71, "learning_rate": 1.9604842437371985e-05, "loss": 0.032, "step": 23100 }, { "epoch": 1.72, "learning_rate": 1.94178317271113e-05, "loss": 0.0308, "step": 23200 }, { "epoch": 1.72, "learning_rate": 1.9229265225466943e-05, "loss": 0.0405, "step": 23300 }, { "epoch": 1.73, "learning_rate": 1.904104487718444e-05, "loss": 0.0336, "step": 23400 }, { "epoch": 1.74, "learning_rate": 1.885318197252559e-05, "loss": 0.0342, "step": 23500 }, { "epoch": 1.75, "learning_rate": 1.8665687780311184e-05, "loss": 0.035, "step": 23600 }, { "epoch": 1.75, "learning_rate": 1.8478573547245055e-05, "loss": 0.0358, "step": 23700 }, { "epoch": 1.76, "learning_rate": 1.8291850497239484e-05, "loss": 0.0343, "step": 23800 }, { "epoch": 1.77, "learning_rate": 1.8105529830741892e-05, "loss": 0.0387, "step": 23900 }, { "epoch": 1.77, "learning_rate": 1.791962272406304e-05, "loss": 0.0363, "step": 24000 }, { "epoch": 1.78, "learning_rate": 1.7734140328706585e-05, "loss": 0.0372, "step": 24100 }, { "epoch": 1.79, "learning_rate": 1.754909377070018e-05, "loss": 0.0361, "step": 24200 }, { "epoch": 1.8, "learning_rate": 1.7364494149928108e-05, "loss": 0.0309, "step": 24300 }, { "epoch": 1.8, "learning_rate": 1.7180352539465422e-05, "loss": 0.0347, "step": 24400 }, { "epoch": 1.81, "learning_rate": 1.6996679984913775e-05, "loss": 0.0337, "step": 24500 }, { "epoch": 1.82, "learning_rate": 1.6813487503738824e-05, "loss": 0.0321, "step": 24600 }, { "epoch": 1.83, "learning_rate": 1.663078608460939e-05, "loss": 0.0363, "step": 24700 }, { "epoch": 1.83, "learning_rate": 1.644858668673827e-05, "loss": 0.0394, "step": 24800 }, { "epoch": 1.84, "learning_rate": 1.6266900239224884e-05, "loss": 0.0311, "step": 24900 }, { "epoch": 1.85, "learning_rate": 1.6085737640399716e-05, "loss": 0.0396, "step": 25000 }, { "epoch": 1.86, "learning_rate": 1.590510975717054e-05, "loss": 0.0364, "step": 25100 }, { "epoch": 1.86, "learning_rate": 1.5725027424370598e-05, "loss": 0.0371, "step": 25200 }, { "epoch": 1.87, "learning_rate": 1.554729391457912e-05, "loss": 0.0356, "step": 25300 }, { "epoch": 1.88, "learning_rate": 1.5368329331184854e-05, "loss": 0.0367, "step": 25400 }, { "epoch": 1.89, "learning_rate": 1.5189942496606382e-05, "loss": 0.0366, "step": 25500 }, { "epoch": 1.89, "learning_rate": 1.5012144111249285e-05, "loss": 0.0384, "step": 25600 }, { "epoch": 1.9, "learning_rate": 1.4834944840221435e-05, "loss": 0.0282, "step": 25700 }, { "epoch": 1.91, "learning_rate": 1.4658355312693234e-05, "loss": 0.0329, "step": 25800 }, { "epoch": 1.92, "learning_rate": 1.4482386121260094e-05, "loss": 0.0314, "step": 25900 }, { "epoch": 1.92, "learning_rate": 1.4307047821306999e-05, "loss": 0.032, "step": 26000 }, { "epoch": 1.93, "learning_rate": 1.4132350930375377e-05, "loss": 0.0358, "step": 26100 }, { "epoch": 1.94, "learning_rate": 1.3958305927532162e-05, "loss": 0.0308, "step": 26200 }, { "epoch": 1.95, "learning_rate": 1.378492325274129e-05, "loss": 0.032, "step": 26300 }, { "epoch": 1.95, "learning_rate": 1.361221330623742e-05, "loss": 0.0381, "step": 26400 }, { "epoch": 1.96, "learning_rate": 1.3440186447902067e-05, "loss": 0.0304, "step": 26500 }, { "epoch": 1.97, "learning_rate": 1.3268852996642216e-05, "loss": 0.0331, "step": 26600 }, { "epoch": 1.97, "learning_rate": 1.3098223229771328e-05, "loss": 0.0343, "step": 26700 }, { "epoch": 1.98, "learning_rate": 1.2928307382392862e-05, "loss": 0.0282, "step": 26800 }, { "epoch": 1.99, "learning_rate": 1.2759115646786316e-05, "loss": 0.0362, "step": 26900 }, { "epoch": 2.0, "learning_rate": 1.2590658171795883e-05, "loss": 0.0333, "step": 27000 }, { "epoch": 2.0, "learning_rate": 1.2422945062221672e-05, "loss": 0.0282, "step": 27100 }, { "epoch": 2.01, "learning_rate": 1.2255986378213532e-05, "loss": 0.0265, "step": 27200 }, { "epoch": 2.02, "learning_rate": 1.209145026035119e-05, "loss": 0.0243, "step": 27300 }, { "epoch": 2.03, "learning_rate": 1.1926022633019637e-05, "loss": 0.0244, "step": 27400 }, { "epoch": 2.03, "learning_rate": 1.1761379238787568e-05, "loss": 0.0283, "step": 27500 }, { "epoch": 2.04, "learning_rate": 1.1597529953670167e-05, "loss": 0.0326, "step": 27600 }, { "epoch": 2.05, "learning_rate": 1.1434484606048597e-05, "loss": 0.0293, "step": 27700 }, { "epoch": 2.06, "learning_rate": 1.1272252976080408e-05, "loss": 0.0239, "step": 27800 }, { "epoch": 2.06, "learning_rate": 1.1110844795112854e-05, "loss": 0.0229, "step": 27900 }, { "epoch": 2.07, "learning_rate": 1.0950269745099226e-05, "loss": 0.0319, "step": 28000 }, { "epoch": 2.08, "learning_rate": 1.0790537458018037e-05, "loss": 0.0274, "step": 28100 }, { "epoch": 2.09, "learning_rate": 1.0631657515295298e-05, "loss": 0.0272, "step": 28200 }, { "epoch": 2.09, "learning_rate": 1.0473639447229716e-05, "loss": 0.0336, "step": 28300 }, { "epoch": 2.1, "learning_rate": 1.0316492732421109e-05, "loss": 0.03, "step": 28400 }, { "epoch": 2.11, "learning_rate": 1.0160226797201788e-05, "loss": 0.024, "step": 28500 }, { "epoch": 2.12, "learning_rate": 1.0004851015071116e-05, "loss": 0.03, "step": 28600 }, { "epoch": 2.12, "learning_rate": 9.850374706133284e-06, "loss": 0.0242, "step": 28700 }, { "epoch": 2.13, "learning_rate": 9.696807136538232e-06, "loss": 0.027, "step": 28800 }, { "epoch": 2.14, "learning_rate": 9.544157517925836e-06, "loss": 0.0293, "step": 28900 }, { "epoch": 2.14, "learning_rate": 9.392435006873307e-06, "loss": 0.0305, "step": 29000 }, { "epoch": 2.15, "learning_rate": 9.241648704346015e-06, "loss": 0.0275, "step": 29100 }, { "epoch": 2.16, "learning_rate": 9.091807655151535e-06, "loss": 0.0289, "step": 29200 }, { "epoch": 2.17, "learning_rate": 8.942920847397072e-06, "loss": 0.026, "step": 29300 }, { "epoch": 2.17, "learning_rate": 8.796471651418955e-06, "loss": 0.0295, "step": 29400 }, { "epoch": 2.18, "learning_rate": 8.649510297187774e-06, "loss": 0.0193, "step": 29500 }, { "epoch": 2.19, "learning_rate": 8.503529715284528e-06, "loss": 0.0235, "step": 29600 }, { "epoch": 2.2, "learning_rate": 8.358538662249076e-06, "loss": 0.0267, "step": 29700 }, { "epoch": 2.2, "learning_rate": 8.21454583526514e-06, "loss": 0.0214, "step": 29800 }, { "epoch": 2.21, "learning_rate": 8.071559871638553e-06, "loss": 0.0322, "step": 29900 }, { "epoch": 2.22, "learning_rate": 7.929589348279173e-06, "loss": 0.028, "step": 30000 }, { "epoch": 2.23, "learning_rate": 7.788642781186414e-06, "loss": 0.0336, "step": 30100 }, { "epoch": 2.23, "learning_rate": 7.648728624938411e-06, "loss": 0.0256, "step": 30200 }, { "epoch": 2.24, "learning_rate": 7.509855272184891e-06, "loss": 0.0272, "step": 30300 }, { "epoch": 2.25, "learning_rate": 7.373404074924179e-06, "loss": 0.0229, "step": 30400 }, { "epoch": 2.26, "learning_rate": 7.236626642156463e-06, "loss": 0.024, "step": 30500 }, { "epoch": 2.26, "learning_rate": 7.100914732523323e-06, "loss": 0.0296, "step": 30600 }, { "epoch": 2.27, "learning_rate": 6.966276486605741e-06, "loss": 0.0283, "step": 30700 }, { "epoch": 2.28, "learning_rate": 6.832719980581764e-06, "loss": 0.0205, "step": 30800 }, { "epoch": 2.29, "learning_rate": 6.700253225742034e-06, "loss": 0.0272, "step": 30900 }, { "epoch": 2.29, "learning_rate": 6.5688841680092675e-06, "loss": 0.0253, "step": 31000 }, { "epoch": 2.3, "learning_rate": 6.438620687461619e-06, "loss": 0.024, "step": 31100 }, { "epoch": 2.31, "learning_rate": 6.3094705978599674e-06, "loss": 0.025, "step": 31200 }, { "epoch": 2.31, "learning_rate": 6.181441646179267e-06, "loss": 0.0262, "step": 31300 }, { "epoch": 2.32, "learning_rate": 6.054541512143816e-06, "loss": 0.0316, "step": 31400 }, { "epoch": 2.33, "learning_rate": 5.9287778077665804e-06, "loss": 0.0306, "step": 31500 }, { "epoch": 2.34, "learning_rate": 5.804158076892635e-06, "loss": 0.0261, "step": 31600 }, { "epoch": 2.34, "learning_rate": 5.6806897947466355e-06, "loss": 0.0253, "step": 31700 }, { "epoch": 2.35, "learning_rate": 5.558380367484384e-06, "loss": 0.0251, "step": 31800 }, { "epoch": 2.36, "learning_rate": 5.43723713174864e-06, "loss": 0.0271, "step": 31900 }, { "epoch": 2.37, "learning_rate": 5.3172673542289884e-06, "loss": 0.0362, "step": 32000 }, { "epoch": 2.37, "learning_rate": 5.198478231225989e-06, "loss": 0.0248, "step": 32100 }, { "epoch": 2.38, "learning_rate": 5.08087688821946e-06, "loss": 0.032, "step": 32200 }, { "epoch": 2.39, "learning_rate": 4.964470379441122e-06, "loss": 0.0254, "step": 32300 }, { "epoch": 2.4, "learning_rate": 4.849265687451421e-06, "loss": 0.0292, "step": 32400 }, { "epoch": 2.4, "learning_rate": 4.735269722720675e-06, "loss": 0.0352, "step": 32500 }, { "epoch": 2.41, "learning_rate": 4.622489323214582e-06, "loss": 0.0238, "step": 32600 }, { "epoch": 2.42, "learning_rate": 4.5109312539840465e-06, "loss": 0.0279, "step": 32700 }, { "epoch": 2.43, "learning_rate": 4.400602206759349e-06, "loss": 0.0251, "step": 32800 }, { "epoch": 2.43, "learning_rate": 4.291508799548788e-06, "loss": 0.0214, "step": 32900 }, { "epoch": 2.44, "learning_rate": 4.1836575762416845e-06, "loss": 0.0283, "step": 33000 }, { "epoch": 2.45, "learning_rate": 4.077055006215863e-06, "loss": 0.0262, "step": 33100 }, { "epoch": 2.46, "learning_rate": 3.9717074839495576e-06, "loss": 0.0246, "step": 33200 }, { "epoch": 2.46, "learning_rate": 3.867621328637891e-06, "loss": 0.0252, "step": 33300 }, { "epoch": 2.47, "learning_rate": 3.764802783813795e-06, "loss": 0.0294, "step": 33400 }, { "epoch": 2.48, "learning_rate": 3.6632580169734864e-06, "loss": 0.0244, "step": 33500 }, { "epoch": 2.48, "learning_rate": 3.5629931192065453e-06, "loss": 0.027, "step": 33600 }, { "epoch": 2.49, "learning_rate": 3.464014104830529e-06, "loss": 0.0307, "step": 33700 }, { "epoch": 2.5, "learning_rate": 3.3663269110301905e-06, "loss": 0.0298, "step": 33800 }, { "epoch": 2.51, "learning_rate": 3.2699373975013743e-06, "loss": 0.0288, "step": 33900 }, { "epoch": 2.51, "learning_rate": 3.174851346099503e-06, "loss": 0.0252, "step": 34000 }, { "epoch": 2.52, "learning_rate": 3.081074460492769e-06, "loss": 0.0233, "step": 34100 }, { "epoch": 2.53, "learning_rate": 2.98861236581999e-06, "loss": 0.029, "step": 34200 }, { "epoch": 2.54, "learning_rate": 2.8974706083532033e-06, "loss": 0.0242, "step": 34300 }, { "epoch": 2.54, "learning_rate": 2.80854623420958e-06, "loss": 0.0241, "step": 34400 }, { "epoch": 2.55, "learning_rate": 2.7200481345203947e-06, "loss": 0.0277, "step": 34500 }, { "epoch": 2.56, "learning_rate": 2.632886481668853e-06, "loss": 0.0227, "step": 34600 }, { "epoch": 2.57, "learning_rate": 2.547066503983811e-06, "loss": 0.0207, "step": 34700 }, { "epoch": 2.57, "learning_rate": 2.462593349314707e-06, "loss": 0.0274, "step": 34800 }, { "epoch": 2.58, "learning_rate": 2.3794720847227806e-06, "loss": 0.0292, "step": 34900 }, { "epoch": 2.59, "learning_rate": 2.297707696177112e-06, "loss": 0.0239, "step": 35000 }, { "epoch": 2.6, "learning_rate": 2.217305088255564e-06, "loss": 0.0184, "step": 35100 }, { "epoch": 2.6, "learning_rate": 2.1382690838505525e-06, "loss": 0.0249, "step": 35200 }, { "epoch": 2.61, "learning_rate": 2.060604423879781e-06, "loss": 0.0226, "step": 35300 }, { "epoch": 2.62, "learning_rate": 1.984315767001846e-06, "loss": 0.027, "step": 35400 }, { "epoch": 2.63, "learning_rate": 1.9094076893367783e-06, "loss": 0.0237, "step": 35500 }, { "epoch": 2.63, "learning_rate": 1.8358846841915772e-06, "loss": 0.0257, "step": 35600 }, { "epoch": 2.64, "learning_rate": 1.7637511617906639e-06, "loss": 0.0293, "step": 35700 }, { "epoch": 2.65, "learning_rate": 1.693011449011328e-06, "loss": 0.0248, "step": 35800 }, { "epoch": 2.66, "learning_rate": 1.6236697891241992e-06, "loss": 0.0253, "step": 35900 }, { "epoch": 2.66, "learning_rate": 1.5557303415387276e-06, "loss": 0.0263, "step": 36000 }, { "epoch": 2.67, "learning_rate": 1.4891971815536448e-06, "loss": 0.0213, "step": 36100 }, { "epoch": 2.68, "learning_rate": 1.4240743001125573e-06, "loss": 0.0321, "step": 36200 }, { "epoch": 2.68, "learning_rate": 1.3603656035645201e-06, "loss": 0.0221, "step": 36300 }, { "epoch": 2.69, "learning_rate": 1.298074913429731e-06, "loss": 0.0258, "step": 36400 }, { "epoch": 2.7, "learning_rate": 1.2372059661702907e-06, "loss": 0.0249, "step": 36500 }, { "epoch": 2.71, "learning_rate": 1.1777624129660853e-06, "loss": 0.0196, "step": 36600 }, { "epoch": 2.71, "learning_rate": 1.1203208805821596e-06, "loss": 0.0304, "step": 36700 }, { "epoch": 2.72, "learning_rate": 1.0637243854684231e-06, "loss": 0.0276, "step": 36800 }, { "epoch": 2.73, "learning_rate": 1.00856369057738e-06, "loss": 0.029, "step": 36900 }, { "epoch": 2.74, "learning_rate": 9.548421046835037e-07, "loss": 0.0263, "step": 37000 }, { "epoch": 2.74, "learning_rate": 9.025628502373707e-07, "loss": 0.0245, "step": 37100 }, { "epoch": 2.75, "learning_rate": 8.517290631723351e-07, "loss": 0.0259, "step": 37200 }, { "epoch": 2.76, "learning_rate": 8.023437927164451e-07, "loss": 0.0276, "step": 37300 }, { "epoch": 2.77, "learning_rate": 7.544100012095073e-07, "loss": 0.025, "step": 37400 }, { "epoch": 2.77, "learning_rate": 7.079305639254241e-07, "loss": 0.0274, "step": 37500 }, { "epoch": 2.78, "learning_rate": 6.629082688997118e-07, "loss": 0.0268, "step": 37600 }, { "epoch": 2.79, "learning_rate": 6.193458167622457e-07, "loss": 0.0238, "step": 37700 }, { "epoch": 2.8, "learning_rate": 5.772458205752923e-07, "loss": 0.0269, "step": 37800 }, { "epoch": 2.8, "learning_rate": 5.366108056767488e-07, "loss": 0.0234, "step": 37900 }, { "epoch": 2.81, "learning_rate": 4.974432095286614e-07, "loss": 0.0231, "step": 38000 }, { "epoch": 2.82, "learning_rate": 4.597453815710251e-07, "loss": 0.0266, "step": 38100 }, { "epoch": 2.83, "learning_rate": 4.2351958308085305e-07, "loss": 0.0303, "step": 38200 }, { "epoch": 2.83, "learning_rate": 3.887679870365341e-07, "loss": 0.0234, "step": 38300 }, { "epoch": 2.84, "learning_rate": 3.554926779874762e-07, "loss": 0.0274, "step": 38400 }, { "epoch": 2.85, "learning_rate": 3.2369565192909013e-07, "loss": 0.0237, "step": 38500 }, { "epoch": 2.85, "learning_rate": 2.9337881618304307e-07, "loss": 0.0231, "step": 38600 }, { "epoch": 2.86, "learning_rate": 2.6454398928284773e-07, "loss": 0.0205, "step": 38700 }, { "epoch": 2.87, "learning_rate": 2.3745906178262723e-07, "loss": 0.0266, "step": 38800 }, { "epoch": 2.88, "learning_rate": 2.1157849086218263e-07, "loss": 0.0299, "step": 38900 }, { "epoch": 2.88, "learning_rate": 1.8718483552108977e-07, "loss": 0.0231, "step": 39000 }, { "epoch": 2.89, "learning_rate": 1.6427955899516178e-07, "loss": 0.0277, "step": 39100 }, { "epoch": 2.9, "learning_rate": 1.428640352408861e-07, "loss": 0.0257, "step": 39200 }, { "epoch": 2.91, "learning_rate": 1.229395488530072e-07, "loss": 0.0316, "step": 39300 }, { "epoch": 2.91, "learning_rate": 1.0450729498746037e-07, "loss": 0.0269, "step": 39400 }, { "epoch": 2.92, "learning_rate": 8.756837928969586e-08, "loss": 0.0232, "step": 39500 }, { "epoch": 2.93, "learning_rate": 7.21238178283512e-08, "loss": 0.0242, "step": 39600 }, { "epoch": 2.94, "learning_rate": 5.8174537034305646e-08, "loss": 0.0253, "step": 39700 }, { "epoch": 2.94, "learning_rate": 4.5721373645096765e-08, "loss": 0.0191, "step": 39800 }, { "epoch": 2.95, "learning_rate": 3.4765074654749544e-08, "loss": 0.0351, "step": 39900 }, { "epoch": 2.96, "learning_rate": 2.530629726895384e-08, "loss": 0.0214, "step": 40000 }, { "epoch": 2.97, "learning_rate": 1.734560886564318e-08, "loss": 0.0259, "step": 40100 }, { "epoch": 2.97, "learning_rate": 1.0883486960974742e-08, "loss": 0.0216, "step": 40200 }, { "epoch": 2.98, "learning_rate": 5.920319180660605e-09, "loss": 0.0224, "step": 40300 }, { "epoch": 2.99, "learning_rate": 2.4564032367446752e-09, "loss": 0.0282, "step": 40400 }, { "epoch": 3.0, "learning_rate": 4.919469097225404e-10, "loss": 0.0267, "step": 40500 }, { "epoch": 3.0, "step": 40563, "total_flos": 9.051629520354902e+18, "train_loss": 0.05192308982466081, "train_runtime": 264704.0502, "train_samples_per_second": 4.904, "train_steps_per_second": 0.153 } ], "logging_steps": 100, "max_steps": 40563, "num_train_epochs": 3, "save_steps": 5000, "total_flos": 9.051629520354902e+18, "trial_name": null, "trial_params": null }