| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 10178, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.039300451955197484, | |
| "grad_norm": 0.5243114233016968, | |
| "learning_rate": 7.861635220125787e-07, | |
| "loss": 1.9595, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07860090391039497, | |
| "grad_norm": 0.5634641051292419, | |
| "learning_rate": 1.5723270440251573e-06, | |
| "loss": 1.9417, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11790135586559246, | |
| "grad_norm": 0.5528621077537537, | |
| "learning_rate": 2.358490566037736e-06, | |
| "loss": 1.9052, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15720180782078993, | |
| "grad_norm": 0.5267557501792908, | |
| "learning_rate": 3.1446540880503146e-06, | |
| "loss": 1.8587, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.19650225977598743, | |
| "grad_norm": 0.4375621974468231, | |
| "learning_rate": 3.930817610062894e-06, | |
| "loss": 1.802, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23580271173118492, | |
| "grad_norm": 0.44920215010643005, | |
| "learning_rate": 4.716981132075472e-06, | |
| "loss": 1.7458, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2751031636863824, | |
| "grad_norm": 0.5727487802505493, | |
| "learning_rate": 5.503144654088051e-06, | |
| "loss": 1.6559, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.31440361564157987, | |
| "grad_norm": 0.5727925300598145, | |
| "learning_rate": 6.289308176100629e-06, | |
| "loss": 1.5392, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.35370406759677736, | |
| "grad_norm": 0.5609890818595886, | |
| "learning_rate": 7.0754716981132075e-06, | |
| "loss": 1.3973, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.39300451955197485, | |
| "grad_norm": 0.5241280794143677, | |
| "learning_rate": 7.861635220125787e-06, | |
| "loss": 1.3599, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.43230497150717234, | |
| "grad_norm": 0.4475036859512329, | |
| "learning_rate": 8.647798742138366e-06, | |
| "loss": 1.3509, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.47160542346236983, | |
| "grad_norm": 0.46985116600990295, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 1.3268, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5109058754175673, | |
| "grad_norm": 0.49204403162002563, | |
| "learning_rate": 1.0220125786163524e-05, | |
| "loss": 1.3113, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5502063273727648, | |
| "grad_norm": 0.5724858045578003, | |
| "learning_rate": 1.1006289308176102e-05, | |
| "loss": 1.3017, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5895067793279622, | |
| "grad_norm": 0.6059098839759827, | |
| "learning_rate": 1.179245283018868e-05, | |
| "loss": 1.3185, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6288072312831597, | |
| "grad_norm": 0.6029092669487, | |
| "learning_rate": 1.2578616352201259e-05, | |
| "loss": 1.3167, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6681076832383572, | |
| "grad_norm": 0.5854910612106323, | |
| "learning_rate": 1.3364779874213839e-05, | |
| "loss": 1.3188, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7074081351935547, | |
| "grad_norm": 0.7484495043754578, | |
| "learning_rate": 1.4150943396226415e-05, | |
| "loss": 1.3073, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7467085871487522, | |
| "grad_norm": 0.5744655132293701, | |
| "learning_rate": 1.4937106918238995e-05, | |
| "loss": 1.3014, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7860090391039497, | |
| "grad_norm": 0.6052381992340088, | |
| "learning_rate": 1.5723270440251575e-05, | |
| "loss": 1.2955, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8253094910591472, | |
| "grad_norm": 0.7050319910049438, | |
| "learning_rate": 1.650943396226415e-05, | |
| "loss": 1.3033, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.8646099430143447, | |
| "grad_norm": 0.596123456954956, | |
| "learning_rate": 1.729559748427673e-05, | |
| "loss": 1.3067, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.9039103949695422, | |
| "grad_norm": 0.618027925491333, | |
| "learning_rate": 1.8081761006289308e-05, | |
| "loss": 1.2855, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.9432108469247397, | |
| "grad_norm": 0.7311336994171143, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 1.278, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.9825112988799372, | |
| "grad_norm": 0.6211506128311157, | |
| "learning_rate": 1.9654088050314464e-05, | |
| "loss": 1.3028, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.999803497740224, | |
| "eval_loss": 1.2847634553909302, | |
| "eval_runtime": 874.8058, | |
| "eval_samples_per_second": 4.363, | |
| "eval_steps_per_second": 0.728, | |
| "step": 2544 | |
| }, | |
| { | |
| "epoch": 1.0218117508351345, | |
| "grad_norm": 0.7327952980995178, | |
| "learning_rate": 1.9999704794507125e-05, | |
| "loss": 1.2766, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.0611122027903321, | |
| "grad_norm": 0.6698949337005615, | |
| "learning_rate": 1.9997709221324418e-05, | |
| "loss": 1.2867, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.1004126547455295, | |
| "grad_norm": 0.6375765204429626, | |
| "learning_rate": 1.9993831411601573e-05, | |
| "loss": 1.2934, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.1397131067007271, | |
| "grad_norm": 0.7647634148597717, | |
| "learning_rate": 1.998807209540135e-05, | |
| "loss": 1.2868, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.1790135586559245, | |
| "grad_norm": 0.722791314125061, | |
| "learning_rate": 1.9980432357011672e-05, | |
| "loss": 1.2833, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.218314010611122, | |
| "grad_norm": 0.6894689202308655, | |
| "learning_rate": 1.9970913634741498e-05, | |
| "loss": 1.2675, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.2576144625663195, | |
| "grad_norm": 0.8223153352737427, | |
| "learning_rate": 1.995951772065004e-05, | |
| "loss": 1.2946, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.2969149145215169, | |
| "grad_norm": 0.7805577516555786, | |
| "learning_rate": 1.994624676020936e-05, | |
| "loss": 1.2843, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.3362153664767145, | |
| "grad_norm": 0.8491411209106445, | |
| "learning_rate": 1.9931103251900485e-05, | |
| "loss": 1.2665, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.375515818431912, | |
| "grad_norm": 0.700754702091217, | |
| "learning_rate": 1.9914090046742984e-05, | |
| "loss": 1.2724, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.4148162703871094, | |
| "grad_norm": 0.7429256439208984, | |
| "learning_rate": 1.9895210347758233e-05, | |
| "loss": 1.2818, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.4541167223423068, | |
| "grad_norm": 0.7554534077644348, | |
| "learning_rate": 1.9874467709366408e-05, | |
| "loss": 1.2717, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.4934171742975044, | |
| "grad_norm": 0.6377087831497192, | |
| "learning_rate": 1.985186603671728e-05, | |
| "loss": 1.2817, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.532717626252702, | |
| "grad_norm": 0.6828142404556274, | |
| "learning_rate": 1.9827409584955025e-05, | |
| "loss": 1.2666, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.5720180782078994, | |
| "grad_norm": 0.7497674822807312, | |
| "learning_rate": 1.9801102958417107e-05, | |
| "loss": 1.2774, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.6113185301630968, | |
| "grad_norm": 0.6864811778068542, | |
| "learning_rate": 1.977295110976744e-05, | |
| "loss": 1.2754, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.6506189821182944, | |
| "grad_norm": 0.6789698004722595, | |
| "learning_rate": 1.9742959339063977e-05, | |
| "loss": 1.2786, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.689919434073492, | |
| "grad_norm": 0.7490926384925842, | |
| "learning_rate": 1.971113329276087e-05, | |
| "loss": 1.2809, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.7292198860286894, | |
| "grad_norm": 0.7881296873092651, | |
| "learning_rate": 1.9677478962645422e-05, | |
| "loss": 1.2621, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.7685203379838867, | |
| "grad_norm": 0.7230281829833984, | |
| "learning_rate": 1.9642002684710065e-05, | |
| "loss": 1.2852, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.8078207899390843, | |
| "grad_norm": 0.7554972767829895, | |
| "learning_rate": 1.960471113795947e-05, | |
| "loss": 1.2721, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.8471212418942817, | |
| "grad_norm": 0.734038770198822, | |
| "learning_rate": 1.9565611343153133e-05, | |
| "loss": 1.2814, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.886421693849479, | |
| "grad_norm": 0.7878260016441345, | |
| "learning_rate": 1.9524710661483594e-05, | |
| "loss": 1.2678, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.9257221458046767, | |
| "grad_norm": 0.6968903541564941, | |
| "learning_rate": 1.9482016793190554e-05, | |
| "loss": 1.2728, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.9650225977598743, | |
| "grad_norm": 0.6642516851425171, | |
| "learning_rate": 1.9437537776111207e-05, | |
| "loss": 1.2597, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2640804052352905, | |
| "eval_runtime": 870.1498, | |
| "eval_samples_per_second": 4.387, | |
| "eval_steps_per_second": 0.732, | |
| "step": 5089 | |
| }, | |
| { | |
| "epoch": 2.004323049715072, | |
| "grad_norm": 0.7448713183403015, | |
| "learning_rate": 1.9391281984166944e-05, | |
| "loss": 1.28, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.043623501670269, | |
| "grad_norm": 0.7270140647888184, | |
| "learning_rate": 1.9343258125786866e-05, | |
| "loss": 1.2702, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.0829239536254667, | |
| "grad_norm": 0.7596098184585571, | |
| "learning_rate": 1.9293475242268224e-05, | |
| "loss": 1.2719, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.1222244055806643, | |
| "grad_norm": 0.64553302526474, | |
| "learning_rate": 1.92419427060743e-05, | |
| "loss": 1.2817, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.161524857535862, | |
| "grad_norm": 0.7140522003173828, | |
| "learning_rate": 1.9188670219069825e-05, | |
| "loss": 1.2781, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.200825309491059, | |
| "grad_norm": 0.7687891721725464, | |
| "learning_rate": 1.913366781069449e-05, | |
| "loss": 1.2616, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.2401257614462566, | |
| "grad_norm": 0.7907755374908447, | |
| "learning_rate": 1.9076945836074716e-05, | |
| "loss": 1.2526, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.2794262134014542, | |
| "grad_norm": 0.9397710561752319, | |
| "learning_rate": 1.901851497407411e-05, | |
| "loss": 1.256, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.3187266653566514, | |
| "grad_norm": 0.7789448499679565, | |
| "learning_rate": 1.8958386225283018e-05, | |
| "loss": 1.2759, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.358027117311849, | |
| "grad_norm": 0.8291410207748413, | |
| "learning_rate": 1.8896570909947477e-05, | |
| "loss": 1.2546, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.3973275692670466, | |
| "grad_norm": 0.8539474606513977, | |
| "learning_rate": 1.8833080665837956e-05, | |
| "loss": 1.2643, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.436628021222244, | |
| "grad_norm": 0.7579149007797241, | |
| "learning_rate": 1.876792744605839e-05, | |
| "loss": 1.2425, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.4759284731774414, | |
| "grad_norm": 0.7331416606903076, | |
| "learning_rate": 1.8701123516795797e-05, | |
| "loss": 1.2541, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.515228925132639, | |
| "grad_norm": 0.9984397888183594, | |
| "learning_rate": 1.8632681455010937e-05, | |
| "loss": 1.2564, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.5545293770878366, | |
| "grad_norm": 0.8411275744438171, | |
| "learning_rate": 1.856261414607053e-05, | |
| "loss": 1.2519, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.5938298290430337, | |
| "grad_norm": 0.8506852388381958, | |
| "learning_rate": 1.849093478132133e-05, | |
| "loss": 1.2384, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.6331302809982313, | |
| "grad_norm": 0.821840226650238, | |
| "learning_rate": 1.841765685560666e-05, | |
| "loss": 1.2591, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 2.672430732953429, | |
| "grad_norm": 0.8434679508209229, | |
| "learning_rate": 1.834279416472577e-05, | |
| "loss": 1.2414, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.7117311849086265, | |
| "grad_norm": 0.7219915986061096, | |
| "learning_rate": 1.8266360802836542e-05, | |
| "loss": 1.2632, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.751031636863824, | |
| "grad_norm": 0.7417508363723755, | |
| "learning_rate": 1.8188371159802046e-05, | |
| "loss": 1.2247, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.7903320888190213, | |
| "grad_norm": 0.9285396337509155, | |
| "learning_rate": 1.8108839918481384e-05, | |
| "loss": 1.2532, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.829632540774219, | |
| "grad_norm": 0.8321588039398193, | |
| "learning_rate": 1.8027782051965408e-05, | |
| "loss": 1.2465, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.8689329927294165, | |
| "grad_norm": 0.9930406808853149, | |
| "learning_rate": 1.794521282075778e-05, | |
| "loss": 1.2382, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.9082334446846136, | |
| "grad_norm": 0.8240166306495667, | |
| "learning_rate": 1.786114776990194e-05, | |
| "loss": 1.2632, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.9475338966398112, | |
| "grad_norm": 0.8060221672058105, | |
| "learning_rate": 1.777560272605447e-05, | |
| "loss": 1.2625, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.986834348595009, | |
| "grad_norm": 0.9597970843315125, | |
| "learning_rate": 1.7688593794505466e-05, | |
| "loss": 1.2472, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.999803497740224, | |
| "eval_loss": 1.2436127662658691, | |
| "eval_runtime": 871.1991, | |
| "eval_samples_per_second": 4.381, | |
| "eval_steps_per_second": 0.731, | |
| "step": 7633 | |
| }, | |
| { | |
| "epoch": 3.0261348005502064, | |
| "grad_norm": 0.7766150236129761, | |
| "learning_rate": 1.760013735614646e-05, | |
| "loss": 1.252, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 3.0654352525054036, | |
| "grad_norm": 0.7692065834999084, | |
| "learning_rate": 1.751025006438643e-05, | |
| "loss": 1.2421, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 3.104735704460601, | |
| "grad_norm": 0.86983722448349, | |
| "learning_rate": 1.7418948842016515e-05, | |
| "loss": 1.2405, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 3.144036156415799, | |
| "grad_norm": 0.8825920820236206, | |
| "learning_rate": 1.732625087802402e-05, | |
| "loss": 1.2511, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.1833366083709964, | |
| "grad_norm": 0.7962430119514465, | |
| "learning_rate": 1.7232173624356307e-05, | |
| "loss": 1.2397, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 3.2226370603261936, | |
| "grad_norm": 0.8126371502876282, | |
| "learning_rate": 1.7136734792635154e-05, | |
| "loss": 1.2465, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 3.261937512281391, | |
| "grad_norm": 1.0476093292236328, | |
| "learning_rate": 1.7039952350822275e-05, | |
| "loss": 1.2414, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 3.3012379642365888, | |
| "grad_norm": 0.868041455745697, | |
| "learning_rate": 1.694184451983651e-05, | |
| "loss": 1.2318, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 3.3405384161917864, | |
| "grad_norm": 1.0523380041122437, | |
| "learning_rate": 1.6842429770123476e-05, | |
| "loss": 1.2439, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.3798388681469835, | |
| "grad_norm": 0.8371441960334778, | |
| "learning_rate": 1.6741726818178154e-05, | |
| "loss": 1.2219, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 3.419139320102181, | |
| "grad_norm": 0.9032717943191528, | |
| "learning_rate": 1.6639754623021227e-05, | |
| "loss": 1.2496, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 3.4584397720573787, | |
| "grad_norm": 0.8264920115470886, | |
| "learning_rate": 1.6536532382629696e-05, | |
| "loss": 1.2527, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 3.4977402240125763, | |
| "grad_norm": 0.87635737657547, | |
| "learning_rate": 1.643207953032258e-05, | |
| "loss": 1.2295, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 3.5370406759677735, | |
| "grad_norm": 0.9072712063789368, | |
| "learning_rate": 1.6326415731102226e-05, | |
| "loss": 1.2424, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.576341127922971, | |
| "grad_norm": 0.8442856073379517, | |
| "learning_rate": 1.6219560877952052e-05, | |
| "loss": 1.2437, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 3.6156415798781687, | |
| "grad_norm": 0.8766356706619263, | |
| "learning_rate": 1.6111535088091388e-05, | |
| "loss": 1.2538, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 3.6549420318333663, | |
| "grad_norm": 1.021742820739746, | |
| "learning_rate": 1.6002358699188035e-05, | |
| "loss": 1.247, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 3.6942424837885635, | |
| "grad_norm": 0.8045344352722168, | |
| "learning_rate": 1.5892052265529378e-05, | |
| "loss": 1.2459, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 3.733542935743761, | |
| "grad_norm": 0.8662866950035095, | |
| "learning_rate": 1.5780636554152682e-05, | |
| "loss": 1.2381, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.7728433876989587, | |
| "grad_norm": 1.0202692747116089, | |
| "learning_rate": 1.566813254093538e-05, | |
| "loss": 1.2382, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 3.812143839654156, | |
| "grad_norm": 0.8142303228378296, | |
| "learning_rate": 1.5554561406645964e-05, | |
| "loss": 1.2332, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 3.8514442916093534, | |
| "grad_norm": 0.9972567558288574, | |
| "learning_rate": 1.5439944532956398e-05, | |
| "loss": 1.2392, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 3.890744743564551, | |
| "grad_norm": 0.8277762532234192, | |
| "learning_rate": 1.5324303498416622e-05, | |
| "loss": 1.2476, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 3.9300451955197486, | |
| "grad_norm": 0.6960517168045044, | |
| "learning_rate": 1.520766007439205e-05, | |
| "loss": 1.2556, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.9693456474749462, | |
| "grad_norm": 0.9125708937644958, | |
| "learning_rate": 1.509003622096474e-05, | |
| "loss": 1.2438, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.2373554706573486, | |
| "eval_runtime": 870.4282, | |
| "eval_samples_per_second": 4.385, | |
| "eval_steps_per_second": 0.732, | |
| "step": 10178 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 25440, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2731866625592525e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |