| { | |
| "best_metric": 1.41787565, | |
| "best_model_checkpoint": "/fs/clip-projects/geoguesser/vlms/llava/output/llava1_6-vicuna-7b-instruct/v10-20241108-045625/checkpoint-534", | |
| "epoch": 1.9962616822429906, | |
| "eval_steps": 50, | |
| "global_step": 534, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003738317757009346, | |
| "grad_norm": 0.7382091283798218, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 1.75865197, | |
| "memory(GiB)": 21.51, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.03225 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 0.7008568048477173, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 1.8970871, | |
| "memory(GiB)": 21.51, | |
| "step": 5, | |
| "train_speed(iter/s)": 0.107257 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 0.6195642948150635, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.85505066, | |
| "memory(GiB)": 26.65, | |
| "step": 10, | |
| "train_speed(iter/s)": 0.150961 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 0.8053833842277527, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 1.85264435, | |
| "memory(GiB)": 26.65, | |
| "step": 15, | |
| "train_speed(iter/s)": 0.174044 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 0.9945815205574036, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 1.75669136, | |
| "memory(GiB)": 26.65, | |
| "step": 20, | |
| "train_speed(iter/s)": 0.188377 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 1.0137534141540527, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 1.5954113, | |
| "memory(GiB)": 26.65, | |
| "step": 25, | |
| "train_speed(iter/s)": 0.198196 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 1.0105948448181152, | |
| "learning_rate": 9.999136119166803e-05, | |
| "loss": 1.67307549, | |
| "memory(GiB)": 26.65, | |
| "step": 30, | |
| "train_speed(iter/s)": 0.205137 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 1.0798794031143188, | |
| "learning_rate": 9.99385792841537e-05, | |
| "loss": 1.68129864, | |
| "memory(GiB)": 26.65, | |
| "step": 35, | |
| "train_speed(iter/s)": 0.210084 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.0679413080215454, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 1.61183624, | |
| "memory(GiB)": 26.65, | |
| "step": 40, | |
| "train_speed(iter/s)": 0.214094 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 0.9876216053962708, | |
| "learning_rate": 9.968931622637652e-05, | |
| "loss": 1.5409358, | |
| "memory(GiB)": 26.65, | |
| "step": 45, | |
| "train_speed(iter/s)": 0.217302 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 0.979777991771698, | |
| "learning_rate": 9.949307432339625e-05, | |
| "loss": 1.60590649, | |
| "memory(GiB)": 26.65, | |
| "step": 50, | |
| "train_speed(iter/s)": 0.219869 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "eval_loss": 1.543888807296753, | |
| "eval_runtime": 18.3158, | |
| "eval_samples_per_second": 2.73, | |
| "eval_steps_per_second": 2.73, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 1.0606234073638916, | |
| "learning_rate": 9.924932805436949e-05, | |
| "loss": 1.54525614, | |
| "memory(GiB)": 26.65, | |
| "step": 55, | |
| "train_speed(iter/s)": 0.206189 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 1.0801302194595337, | |
| "learning_rate": 9.895831137146318e-05, | |
| "loss": 1.54319582, | |
| "memory(GiB)": 26.65, | |
| "step": 60, | |
| "train_speed(iter/s)": 0.209015 | |
| }, | |
| { | |
| "epoch": 0.24299065420560748, | |
| "grad_norm": 1.0459623336791992, | |
| "learning_rate": 9.862030359785981e-05, | |
| "loss": 1.55986643, | |
| "memory(GiB)": 26.65, | |
| "step": 65, | |
| "train_speed(iter/s)": 0.211483 | |
| }, | |
| { | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 1.0878509283065796, | |
| "learning_rate": 9.82356291596578e-05, | |
| "loss": 1.54775982, | |
| "memory(GiB)": 26.65, | |
| "step": 70, | |
| "train_speed(iter/s)": 0.213594 | |
| }, | |
| { | |
| "epoch": 0.2803738317757009, | |
| "grad_norm": 1.0929535627365112, | |
| "learning_rate": 9.780465727448149e-05, | |
| "loss": 1.60084972, | |
| "memory(GiB)": 26.65, | |
| "step": 75, | |
| "train_speed(iter/s)": 0.215384 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 1.0857256650924683, | |
| "learning_rate": 9.732780159709912e-05, | |
| "loss": 1.53291664, | |
| "memory(GiB)": 26.65, | |
| "step": 80, | |
| "train_speed(iter/s)": 0.217022 | |
| }, | |
| { | |
| "epoch": 0.3177570093457944, | |
| "grad_norm": 1.0876630544662476, | |
| "learning_rate": 9.680551982238942e-05, | |
| "loss": 1.49946527, | |
| "memory(GiB)": 26.65, | |
| "step": 85, | |
| "train_speed(iter/s)": 0.218544 | |
| }, | |
| { | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 1.0945876836776733, | |
| "learning_rate": 9.623831324603754e-05, | |
| "loss": 1.57413607, | |
| "memory(GiB)": 26.65, | |
| "step": 90, | |
| "train_speed(iter/s)": 0.219824 | |
| }, | |
| { | |
| "epoch": 0.35514018691588783, | |
| "grad_norm": 0.9552567601203918, | |
| "learning_rate": 9.562672628338233e-05, | |
| "loss": 1.47238646, | |
| "memory(GiB)": 26.65, | |
| "step": 95, | |
| "train_speed(iter/s)": 0.221014 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 1.0762443542480469, | |
| "learning_rate": 9.497134594687634e-05, | |
| "loss": 1.60602245, | |
| "memory(GiB)": 26.65, | |
| "step": 100, | |
| "train_speed(iter/s)": 0.222132 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "eval_loss": 1.4929084777832031, | |
| "eval_runtime": 14.0965, | |
| "eval_samples_per_second": 3.547, | |
| "eval_steps_per_second": 3.547, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3925233644859813, | |
| "grad_norm": 0.985505998134613, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 1.53017511, | |
| "memory(GiB)": 26.65, | |
| "step": 105, | |
| "train_speed(iter/s)": 0.216155 | |
| }, | |
| { | |
| "epoch": 0.411214953271028, | |
| "grad_norm": 1.0371544361114502, | |
| "learning_rate": 9.353176276679396e-05, | |
| "loss": 1.55461969, | |
| "memory(GiB)": 26.65, | |
| "step": 110, | |
| "train_speed(iter/s)": 0.217382 | |
| }, | |
| { | |
| "epoch": 0.42990654205607476, | |
| "grad_norm": 1.1553157567977905, | |
| "learning_rate": 9.274894166171888e-05, | |
| "loss": 1.53458586, | |
| "memory(GiB)": 26.65, | |
| "step": 115, | |
| "train_speed(iter/s)": 0.218618 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 1.062723994255066, | |
| "learning_rate": 9.192508933357753e-05, | |
| "loss": 1.56342993, | |
| "memory(GiB)": 26.65, | |
| "step": 120, | |
| "train_speed(iter/s)": 0.21963 | |
| }, | |
| { | |
| "epoch": 0.4672897196261682, | |
| "grad_norm": 0.9741066098213196, | |
| "learning_rate": 9.106099653103728e-05, | |
| "loss": 1.46541033, | |
| "memory(GiB)": 26.65, | |
| "step": 125, | |
| "train_speed(iter/s)": 0.220578 | |
| }, | |
| { | |
| "epoch": 0.48598130841121495, | |
| "grad_norm": 1.1155296564102173, | |
| "learning_rate": 9.015749262631536e-05, | |
| "loss": 1.45173082, | |
| "memory(GiB)": 26.65, | |
| "step": 130, | |
| "train_speed(iter/s)": 0.221485 | |
| }, | |
| { | |
| "epoch": 0.5046728971962616, | |
| "grad_norm": 1.3632838726043701, | |
| "learning_rate": 8.921544481913218e-05, | |
| "loss": 1.51770496, | |
| "memory(GiB)": 26.65, | |
| "step": 135, | |
| "train_speed(iter/s)": 0.222401 | |
| }, | |
| { | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 1.165434718132019, | |
| "learning_rate": 8.823575730435693e-05, | |
| "loss": 1.55217724, | |
| "memory(GiB)": 32.07, | |
| "step": 140, | |
| "train_speed(iter/s)": 0.223153 | |
| }, | |
| { | |
| "epoch": 0.5420560747663551, | |
| "grad_norm": 1.1032906770706177, | |
| "learning_rate": 8.721937040414481e-05, | |
| "loss": 1.43740101, | |
| "memory(GiB)": 32.07, | |
| "step": 145, | |
| "train_speed(iter/s)": 0.223845 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "grad_norm": 1.1984739303588867, | |
| "learning_rate": 8.616725966539832e-05, | |
| "loss": 1.58604784, | |
| "memory(GiB)": 32.07, | |
| "step": 150, | |
| "train_speed(iter/s)": 0.224618 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "eval_loss": 1.4658682346343994, | |
| "eval_runtime": 14.0407, | |
| "eval_samples_per_second": 3.561, | |
| "eval_steps_per_second": 3.561, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5794392523364486, | |
| "grad_norm": 1.154517650604248, | |
| "learning_rate": 8.508043492341944e-05, | |
| "loss": 1.49082041, | |
| "memory(GiB)": 32.07, | |
| "step": 155, | |
| "train_speed(iter/s)": 0.220462 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 1.2047632932662964, | |
| "learning_rate": 8.395993933265101e-05, | |
| "loss": 1.53753242, | |
| "memory(GiB)": 32.07, | |
| "step": 160, | |
| "train_speed(iter/s)": 0.221167 | |
| }, | |
| { | |
| "epoch": 0.616822429906542, | |
| "grad_norm": 0.9952251315116882, | |
| "learning_rate": 8.280684836543794e-05, | |
| "loss": 1.49997816, | |
| "memory(GiB)": 32.07, | |
| "step": 165, | |
| "train_speed(iter/s)": 0.22173 | |
| }, | |
| { | |
| "epoch": 0.6355140186915887, | |
| "grad_norm": 1.1730362176895142, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 1.50385504, | |
| "memory(GiB)": 32.07, | |
| "step": 170, | |
| "train_speed(iter/s)": 0.222363 | |
| }, | |
| { | |
| "epoch": 0.6542056074766355, | |
| "grad_norm": 1.066243052482605, | |
| "learning_rate": 8.040733755698955e-05, | |
| "loss": 1.4824049, | |
| "memory(GiB)": 32.07, | |
| "step": 175, | |
| "train_speed(iter/s)": 0.22299 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 1.2189449071884155, | |
| "learning_rate": 7.916322081050709e-05, | |
| "loss": 1.49032326, | |
| "memory(GiB)": 32.07, | |
| "step": 180, | |
| "train_speed(iter/s)": 0.223605 | |
| }, | |
| { | |
| "epoch": 0.6915887850467289, | |
| "grad_norm": 1.07020103931427, | |
| "learning_rate": 7.789111266653285e-05, | |
| "loss": 1.46754303, | |
| "memory(GiB)": 32.07, | |
| "step": 185, | |
| "train_speed(iter/s)": 0.224145 | |
| }, | |
| { | |
| "epoch": 0.7102803738317757, | |
| "grad_norm": 1.226481318473816, | |
| "learning_rate": 7.659223411793798e-05, | |
| "loss": 1.42194347, | |
| "memory(GiB)": 32.07, | |
| "step": 190, | |
| "train_speed(iter/s)": 0.224687 | |
| }, | |
| { | |
| "epoch": 0.7289719626168224, | |
| "grad_norm": 1.111670732498169, | |
| "learning_rate": 7.526783185232207e-05, | |
| "loss": 1.50790215, | |
| "memory(GiB)": 32.07, | |
| "step": 195, | |
| "train_speed(iter/s)": 0.225152 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 1.1171320676803589, | |
| "learning_rate": 7.391917705541927e-05, | |
| "loss": 1.51145458, | |
| "memory(GiB)": 32.07, | |
| "step": 200, | |
| "train_speed(iter/s)": 0.22563 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "eval_loss": 1.4480363130569458, | |
| "eval_runtime": 14.0508, | |
| "eval_samples_per_second": 3.559, | |
| "eval_steps_per_second": 3.559, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7663551401869159, | |
| "grad_norm": 0.9992289543151855, | |
| "learning_rate": 7.254756419099074e-05, | |
| "loss": 1.53672495, | |
| "memory(GiB)": 32.07, | |
| "step": 205, | |
| "train_speed(iter/s)": 0.222373 | |
| }, | |
| { | |
| "epoch": 0.7850467289719626, | |
| "grad_norm": 1.076946496963501, | |
| "learning_rate": 7.115430975837457e-05, | |
| "loss": 1.51113377, | |
| "memory(GiB)": 32.07, | |
| "step": 210, | |
| "train_speed(iter/s)": 0.222912 | |
| }, | |
| { | |
| "epoch": 0.8037383177570093, | |
| "grad_norm": 1.3144261837005615, | |
| "learning_rate": 6.974075102888536e-05, | |
| "loss": 1.51253147, | |
| "memory(GiB)": 32.07, | |
| "step": 215, | |
| "train_speed(iter/s)": 0.223388 | |
| }, | |
| { | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 1.2429286241531372, | |
| "learning_rate": 6.830824476227646e-05, | |
| "loss": 1.49584999, | |
| "memory(GiB)": 32.07, | |
| "step": 220, | |
| "train_speed(iter/s)": 0.22384 | |
| }, | |
| { | |
| "epoch": 0.8411214953271028, | |
| "grad_norm": 1.213188886642456, | |
| "learning_rate": 6.685816590449708e-05, | |
| "loss": 1.4517292, | |
| "memory(GiB)": 32.07, | |
| "step": 225, | |
| "train_speed(iter/s)": 0.224262 | |
| }, | |
| { | |
| "epoch": 0.8598130841121495, | |
| "grad_norm": 1.1008031368255615, | |
| "learning_rate": 6.539190626799366e-05, | |
| "loss": 1.44860907, | |
| "memory(GiB)": 32.07, | |
| "step": 230, | |
| "train_speed(iter/s)": 0.224691 | |
| }, | |
| { | |
| "epoch": 0.8785046728971962, | |
| "grad_norm": 1.105083703994751, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 1.45654058, | |
| "memory(GiB)": 32.07, | |
| "step": 235, | |
| "train_speed(iter/s)": 0.225105 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 1.1485651731491089, | |
| "learning_rate": 6.241648821085666e-05, | |
| "loss": 1.4626853, | |
| "memory(GiB)": 32.07, | |
| "step": 240, | |
| "train_speed(iter/s)": 0.225456 | |
| }, | |
| { | |
| "epoch": 0.9158878504672897, | |
| "grad_norm": 1.2288539409637451, | |
| "learning_rate": 6.0910185651380626e-05, | |
| "loss": 1.41080866, | |
| "memory(GiB)": 32.07, | |
| "step": 245, | |
| "train_speed(iter/s)": 0.225881 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "grad_norm": 1.2186890840530396, | |
| "learning_rate": 5.939341129438739e-05, | |
| "loss": 1.53512402, | |
| "memory(GiB)": 32.07, | |
| "step": 250, | |
| "train_speed(iter/s)": 0.226215 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "eval_loss": 1.438408374786377, | |
| "eval_runtime": 14.1598, | |
| "eval_samples_per_second": 3.531, | |
| "eval_steps_per_second": 3.531, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9532710280373832, | |
| "grad_norm": 1.1940230131149292, | |
| "learning_rate": 5.786762096789431e-05, | |
| "loss": 1.55513544, | |
| "memory(GiB)": 32.07, | |
| "step": 255, | |
| "train_speed(iter/s)": 0.223566 | |
| }, | |
| { | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 1.0835857391357422, | |
| "learning_rate": 5.633427915361261e-05, | |
| "loss": 1.51988029, | |
| "memory(GiB)": 32.07, | |
| "step": 260, | |
| "train_speed(iter/s)": 0.22394 | |
| }, | |
| { | |
| "epoch": 0.9906542056074766, | |
| "grad_norm": 1.170660376548767, | |
| "learning_rate": 5.479485758131089e-05, | |
| "loss": 1.56143446, | |
| "memory(GiB)": 32.07, | |
| "step": 265, | |
| "train_speed(iter/s)": 0.224337 | |
| }, | |
| { | |
| "epoch": 1.0093457943925233, | |
| "grad_norm": 1.0278513431549072, | |
| "learning_rate": 5.325083381622165e-05, | |
| "loss": 1.43758631, | |
| "memory(GiB)": 32.07, | |
| "step": 270, | |
| "train_speed(iter/s)": 0.224666 | |
| }, | |
| { | |
| "epoch": 1.02803738317757, | |
| "grad_norm": 1.13231360912323, | |
| "learning_rate": 5.1703689840846945e-05, | |
| "loss": 1.34864044, | |
| "memory(GiB)": 32.07, | |
| "step": 275, | |
| "train_speed(iter/s)": 0.225034 | |
| }, | |
| { | |
| "epoch": 1.0467289719626167, | |
| "grad_norm": 1.2419425249099731, | |
| "learning_rate": 5.01549106325243e-05, | |
| "loss": 1.38481417, | |
| "memory(GiB)": 32.07, | |
| "step": 280, | |
| "train_speed(iter/s)": 0.225399 | |
| }, | |
| { | |
| "epoch": 1.0654205607476634, | |
| "grad_norm": 1.336288332939148, | |
| "learning_rate": 4.860598273811792e-05, | |
| "loss": 1.24492655, | |
| "memory(GiB)": 32.07, | |
| "step": 285, | |
| "train_speed(iter/s)": 0.225789 | |
| }, | |
| { | |
| "epoch": 1.0841121495327102, | |
| "grad_norm": 1.241809368133545, | |
| "learning_rate": 4.705839284720376e-05, | |
| "loss": 1.36301146, | |
| "memory(GiB)": 32.07, | |
| "step": 290, | |
| "train_speed(iter/s)": 0.226105 | |
| }, | |
| { | |
| "epoch": 1.102803738317757, | |
| "grad_norm": 1.4412420988082886, | |
| "learning_rate": 4.55136263651172e-05, | |
| "loss": 1.39876356, | |
| "memory(GiB)": 32.07, | |
| "step": 295, | |
| "train_speed(iter/s)": 0.226405 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "grad_norm": 1.6165404319763184, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 1.32808571, | |
| "memory(GiB)": 32.07, | |
| "step": 300, | |
| "train_speed(iter/s)": 0.226709 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "eval_loss": 1.4294430017471313, | |
| "eval_runtime": 14.1178, | |
| "eval_samples_per_second": 3.542, | |
| "eval_steps_per_second": 3.542, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1401869158878504, | |
| "grad_norm": 1.4734883308410645, | |
| "learning_rate": 4.243849027585096e-05, | |
| "loss": 1.37022314, | |
| "memory(GiB)": 32.07, | |
| "step": 305, | |
| "train_speed(iter/s)": 0.224508 | |
| }, | |
| { | |
| "epoch": 1.158878504672897, | |
| "grad_norm": 1.5161515474319458, | |
| "learning_rate": 4.0911072241036194e-05, | |
| "loss": 1.40692539, | |
| "memory(GiB)": 32.07, | |
| "step": 310, | |
| "train_speed(iter/s)": 0.224822 | |
| }, | |
| { | |
| "epoch": 1.1775700934579438, | |
| "grad_norm": 1.4354695081710815, | |
| "learning_rate": 3.9392377926805226e-05, | |
| "loss": 1.31709337, | |
| "memory(GiB)": 32.07, | |
| "step": 315, | |
| "train_speed(iter/s)": 0.225147 | |
| }, | |
| { | |
| "epoch": 1.1962616822429906, | |
| "grad_norm": 1.5612841844558716, | |
| "learning_rate": 3.788386500398583e-05, | |
| "loss": 1.38046598, | |
| "memory(GiB)": 32.07, | |
| "step": 320, | |
| "train_speed(iter/s)": 0.225425 | |
| }, | |
| { | |
| "epoch": 1.2149532710280373, | |
| "grad_norm": 1.353385090827942, | |
| "learning_rate": 3.6386981371118355e-05, | |
| "loss": 1.29831305, | |
| "memory(GiB)": 32.07, | |
| "step": 325, | |
| "train_speed(iter/s)": 0.225693 | |
| }, | |
| { | |
| "epoch": 1.233644859813084, | |
| "grad_norm": 1.6214525699615479, | |
| "learning_rate": 3.49031637647361e-05, | |
| "loss": 1.33498459, | |
| "memory(GiB)": 32.07, | |
| "step": 330, | |
| "train_speed(iter/s)": 0.225991 | |
| }, | |
| { | |
| "epoch": 1.2523364485981308, | |
| "grad_norm": 1.441267490386963, | |
| "learning_rate": 3.343383638035902e-05, | |
| "loss": 1.2935997, | |
| "memory(GiB)": 32.07, | |
| "step": 335, | |
| "train_speed(iter/s)": 0.226241 | |
| }, | |
| { | |
| "epoch": 1.2710280373831775, | |
| "grad_norm": 1.5621421337127686, | |
| "learning_rate": 3.1980409505524544e-05, | |
| "loss": 1.32472296, | |
| "memory(GiB)": 32.07, | |
| "step": 340, | |
| "train_speed(iter/s)": 0.226507 | |
| }, | |
| { | |
| "epoch": 1.2897196261682242, | |
| "grad_norm": 1.7050727605819702, | |
| "learning_rate": 3.054427816616773e-05, | |
| "loss": 1.25045223, | |
| "memory(GiB)": 32.07, | |
| "step": 345, | |
| "train_speed(iter/s)": 0.226762 | |
| }, | |
| { | |
| "epoch": 1.308411214953271, | |
| "grad_norm": 1.5206207036972046, | |
| "learning_rate": 2.91268207876494e-05, | |
| "loss": 1.33886337, | |
| "memory(GiB)": 32.07, | |
| "step": 350, | |
| "train_speed(iter/s)": 0.226984 | |
| }, | |
| { | |
| "epoch": 1.308411214953271, | |
| "eval_loss": 1.4251823425292969, | |
| "eval_runtime": 14.0593, | |
| "eval_samples_per_second": 3.556, | |
| "eval_steps_per_second": 3.556, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3271028037383177, | |
| "grad_norm": 1.5205532312393188, | |
| "learning_rate": 2.7729397871718304e-05, | |
| "loss": 1.28512764, | |
| "memory(GiB)": 32.07, | |
| "step": 355, | |
| "train_speed(iter/s)": 0.225063 | |
| }, | |
| { | |
| "epoch": 1.3457943925233644, | |
| "grad_norm": 1.5533926486968994, | |
| "learning_rate": 2.635335069067617e-05, | |
| "loss": 1.30997047, | |
| "memory(GiB)": 32.07, | |
| "step": 360, | |
| "train_speed(iter/s)": 0.225339 | |
| }, | |
| { | |
| "epoch": 1.3644859813084111, | |
| "grad_norm": 1.581883192062378, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.28296366, | |
| "memory(GiB)": 32.07, | |
| "step": 365, | |
| "train_speed(iter/s)": 0.225599 | |
| }, | |
| { | |
| "epoch": 1.3831775700934579, | |
| "grad_norm": 1.4634901285171509, | |
| "learning_rate": 2.367064477065652e-05, | |
| "loss": 1.31434088, | |
| "memory(GiB)": 32.07, | |
| "step": 370, | |
| "train_speed(iter/s)": 0.225861 | |
| }, | |
| { | |
| "epoch": 1.4018691588785046, | |
| "grad_norm": 1.706288456916809, | |
| "learning_rate": 2.2366560942325832e-05, | |
| "loss": 1.30933113, | |
| "memory(GiB)": 32.07, | |
| "step": 375, | |
| "train_speed(iter/s)": 0.226141 | |
| }, | |
| { | |
| "epoch": 1.4205607476635513, | |
| "grad_norm": 1.6696898937225342, | |
| "learning_rate": 2.108900019873103e-05, | |
| "loss": 1.32816324, | |
| "memory(GiB)": 32.07, | |
| "step": 380, | |
| "train_speed(iter/s)": 0.226392 | |
| }, | |
| { | |
| "epoch": 1.439252336448598, | |
| "grad_norm": 1.590394377708435, | |
| "learning_rate": 1.983918876624902e-05, | |
| "loss": 1.26775227, | |
| "memory(GiB)": 32.07, | |
| "step": 385, | |
| "train_speed(iter/s)": 0.226637 | |
| }, | |
| { | |
| "epoch": 1.4579439252336448, | |
| "grad_norm": 1.7391793727874756, | |
| "learning_rate": 1.8618326236955907e-05, | |
| "loss": 1.33946781, | |
| "memory(GiB)": 32.07, | |
| "step": 390, | |
| "train_speed(iter/s)": 0.226874 | |
| }, | |
| { | |
| "epoch": 1.4766355140186915, | |
| "grad_norm": 1.7035928964614868, | |
| "learning_rate": 1.7427584417236194e-05, | |
| "loss": 1.34862604, | |
| "memory(GiB)": 32.07, | |
| "step": 395, | |
| "train_speed(iter/s)": 0.227069 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "grad_norm": 1.5830693244934082, | |
| "learning_rate": 1.626810620306163e-05, | |
| "loss": 1.27288446, | |
| "memory(GiB)": 32.07, | |
| "step": 400, | |
| "train_speed(iter/s)": 0.227266 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "eval_loss": 1.4195191860198975, | |
| "eval_runtime": 14.0879, | |
| "eval_samples_per_second": 3.549, | |
| "eval_steps_per_second": 3.549, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.514018691588785, | |
| "grad_norm": 1.4809561967849731, | |
| "learning_rate": 1.5141004483018323e-05, | |
| "loss": 1.31938076, | |
| "memory(GiB)": 32.07, | |
| "step": 405, | |
| "train_speed(iter/s)": 0.225559 | |
| }, | |
| { | |
| "epoch": 1.5327102803738317, | |
| "grad_norm": 1.8556567430496216, | |
| "learning_rate": 1.4047361070135995e-05, | |
| "loss": 1.33600292, | |
| "memory(GiB)": 32.07, | |
| "step": 410, | |
| "train_speed(iter/s)": 0.225804 | |
| }, | |
| { | |
| "epoch": 1.5514018691588785, | |
| "grad_norm": 1.5470691919326782, | |
| "learning_rate": 1.2988225663543602e-05, | |
| "loss": 1.40292425, | |
| "memory(GiB)": 32.07, | |
| "step": 415, | |
| "train_speed(iter/s)": 0.226027 | |
| }, | |
| { | |
| "epoch": 1.5700934579439252, | |
| "grad_norm": 1.8364381790161133, | |
| "learning_rate": 1.1964614840949002e-05, | |
| "loss": 1.32833939, | |
| "memory(GiB)": 32.07, | |
| "step": 420, | |
| "train_speed(iter/s)": 0.226267 | |
| }, | |
| { | |
| "epoch": 1.588785046728972, | |
| "grad_norm": 1.6938135623931885, | |
| "learning_rate": 1.097751108290867e-05, | |
| "loss": 1.35209036, | |
| "memory(GiB)": 32.07, | |
| "step": 425, | |
| "train_speed(iter/s)": 0.226474 | |
| }, | |
| { | |
| "epoch": 1.6074766355140186, | |
| "grad_norm": 1.7861816883087158, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 1.27312994, | |
| "memory(GiB)": 32.07, | |
| "step": 430, | |
| "train_speed(iter/s)": 0.226695 | |
| }, | |
| { | |
| "epoch": 1.6261682242990654, | |
| "grad_norm": 1.6619056463241577, | |
| "learning_rate": 9.11657857257509e-06, | |
| "loss": 1.35062437, | |
| "memory(GiB)": 32.07, | |
| "step": 435, | |
| "train_speed(iter/s)": 0.22691 | |
| }, | |
| { | |
| "epoch": 1.644859813084112, | |
| "grad_norm": 1.7696343660354614, | |
| "learning_rate": 8.244535977645585e-06, | |
| "loss": 1.32785254, | |
| "memory(GiB)": 32.07, | |
| "step": 440, | |
| "train_speed(iter/s)": 0.227108 | |
| }, | |
| { | |
| "epoch": 1.6635514018691588, | |
| "grad_norm": 1.6938729286193848, | |
| "learning_rate": 7.412571047611155e-06, | |
| "loss": 1.3087183, | |
| "memory(GiB)": 32.07, | |
| "step": 445, | |
| "train_speed(iter/s)": 0.227305 | |
| }, | |
| { | |
| "epoch": 1.6822429906542056, | |
| "grad_norm": 1.7258585691452026, | |
| "learning_rate": 6.621482317764105e-06, | |
| "loss": 1.30971994, | |
| "memory(GiB)": 32.07, | |
| "step": 450, | |
| "train_speed(iter/s)": 0.227507 | |
| }, | |
| { | |
| "epoch": 1.6822429906542056, | |
| "eval_loss": 1.4193787574768066, | |
| "eval_runtime": 17.3944, | |
| "eval_samples_per_second": 2.874, | |
| "eval_steps_per_second": 2.874, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7009345794392523, | |
| "grad_norm": 1.8556472063064575, | |
| "learning_rate": 5.872029089665587e-06, | |
| "loss": 1.26630516, | |
| "memory(GiB)": 32.07, | |
| "step": 455, | |
| "train_speed(iter/s)": 0.225602 | |
| }, | |
| { | |
| "epoch": 1.719626168224299, | |
| "grad_norm": 1.852525234222412, | |
| "learning_rate": 5.164930702353782e-06, | |
| "loss": 1.34138193, | |
| "memory(GiB)": 32.07, | |
| "step": 460, | |
| "train_speed(iter/s)": 0.225826 | |
| }, | |
| { | |
| "epoch": 1.7383177570093458, | |
| "grad_norm": 1.557905673980713, | |
| "learning_rate": 4.500865841909168e-06, | |
| "loss": 1.30747194, | |
| "memory(GiB)": 32.07, | |
| "step": 465, | |
| "train_speed(iter/s)": 0.225996 | |
| }, | |
| { | |
| "epoch": 1.7570093457943925, | |
| "grad_norm": 1.7627642154693604, | |
| "learning_rate": 3.880471890038967e-06, | |
| "loss": 1.34135695, | |
| "memory(GiB)": 32.07, | |
| "step": 470, | |
| "train_speed(iter/s)": 0.226199 | |
| }, | |
| { | |
| "epoch": 1.7757009345794392, | |
| "grad_norm": 1.4336940050125122, | |
| "learning_rate": 3.3043443123065286e-06, | |
| "loss": 1.38070517, | |
| "memory(GiB)": 32.07, | |
| "step": 475, | |
| "train_speed(iter/s)": 0.226358 | |
| }, | |
| { | |
| "epoch": 1.794392523364486, | |
| "grad_norm": 1.906886339187622, | |
| "learning_rate": 2.7730360865923956e-06, | |
| "loss": 1.34674683, | |
| "memory(GiB)": 32.07, | |
| "step": 480, | |
| "train_speed(iter/s)": 0.226536 | |
| }, | |
| { | |
| "epoch": 1.8130841121495327, | |
| "grad_norm": 1.7454955577850342, | |
| "learning_rate": 2.287057172336021e-06, | |
| "loss": 1.38749065, | |
| "memory(GiB)": 32.07, | |
| "step": 485, | |
| "train_speed(iter/s)": 0.226699 | |
| }, | |
| { | |
| "epoch": 1.8317757009345794, | |
| "grad_norm": 1.7366608381271362, | |
| "learning_rate": 1.8468740210672076e-06, | |
| "loss": 1.30795374, | |
| "memory(GiB)": 32.07, | |
| "step": 490, | |
| "train_speed(iter/s)": 0.226882 | |
| }, | |
| { | |
| "epoch": 1.8504672897196262, | |
| "grad_norm": 1.5829346179962158, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 1.32902784, | |
| "memory(GiB)": 32.07, | |
| "step": 495, | |
| "train_speed(iter/s)": 0.227039 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "grad_norm": 1.6908546686172485, | |
| "learning_rate": 1.1055406300002347e-06, | |
| "loss": 1.33979492, | |
| "memory(GiB)": 32.07, | |
| "step": 500, | |
| "train_speed(iter/s)": 0.227213 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "eval_loss": 1.4183509349822998, | |
| "eval_runtime": 14.1519, | |
| "eval_samples_per_second": 3.533, | |
| "eval_steps_per_second": 3.533, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.8878504672897196, | |
| "grad_norm": 1.915726900100708, | |
| "learning_rate": 8.0510193567086e-07, | |
| "loss": 1.30009985, | |
| "memory(GiB)": 32.07, | |
| "step": 505, | |
| "train_speed(iter/s)": 0.225856 | |
| }, | |
| { | |
| "epoch": 1.9065420560747663, | |
| "grad_norm": 1.6646161079406738, | |
| "learning_rate": 5.518814123121885e-07, | |
| "loss": 1.37087755, | |
| "memory(GiB)": 32.07, | |
| "step": 510, | |
| "train_speed(iter/s)": 0.226034 | |
| }, | |
| { | |
| "epoch": 1.925233644859813, | |
| "grad_norm": 1.7108522653579712, | |
| "learning_rate": 3.4612210565528326e-07, | |
| "loss": 1.35631628, | |
| "memory(GiB)": 32.07, | |
| "step": 515, | |
| "train_speed(iter/s)": 0.22621 | |
| }, | |
| { | |
| "epoch": 1.9439252336448598, | |
| "grad_norm": 1.7579667568206787, | |
| "learning_rate": 1.8802150727962876e-07, | |
| "loss": 1.24607553, | |
| "memory(GiB)": 32.07, | |
| "step": 520, | |
| "train_speed(iter/s)": 0.226384 | |
| }, | |
| { | |
| "epoch": 1.9626168224299065, | |
| "grad_norm": 1.634746789932251, | |
| "learning_rate": 7.773136505700995e-08, | |
| "loss": 1.27467356, | |
| "memory(GiB)": 32.07, | |
| "step": 525, | |
| "train_speed(iter/s)": 0.226543 | |
| }, | |
| { | |
| "epoch": 1.9813084112149533, | |
| "grad_norm": 1.620557188987732, | |
| "learning_rate": 1.5357537501159423e-08, | |
| "loss": 1.318472, | |
| "memory(GiB)": 32.07, | |
| "step": 530, | |
| "train_speed(iter/s)": 0.226703 | |
| }, | |
| { | |
| "epoch": 1.9962616822429906, | |
| "eval_loss": 1.4178756475448608, | |
| "eval_runtime": 14.1624, | |
| "eval_samples_per_second": 3.53, | |
| "eval_steps_per_second": 3.53, | |
| "step": 534 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 534, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.73270917085696e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |