{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.1093443774729135, "eval_steps": 500, "global_step": 15000, "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 } ], "logging_steps": 100, "max_steps": 40563, "num_train_epochs": 3, "save_steps": 5000, "total_flos": 3.3477356574825185e+18, "trial_name": null, "trial_params": null }