| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9996105008958479, | |
| "eval_steps": 25, | |
| "global_step": 401, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009971177066292747, | |
| "grad_norm": 7.652912616729736, | |
| "learning_rate": 1.9512195121951222e-05, | |
| "loss": 2.2965, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019942354132585494, | |
| "grad_norm": 25.198680877685547, | |
| "learning_rate": 3.9024390243902444e-05, | |
| "loss": 2.1832, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029913531198878244, | |
| "grad_norm": 1.633164405822754, | |
| "learning_rate": 5.853658536585366e-05, | |
| "loss": 2.0435, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03988470826517099, | |
| "grad_norm": 1.5140329599380493, | |
| "learning_rate": 7.804878048780489e-05, | |
| "loss": 1.7848, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04985588533146374, | |
| "grad_norm": 2.636758804321289, | |
| "learning_rate": 9.75609756097561e-05, | |
| "loss": 1.5732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05982706239775649, | |
| "grad_norm": 1.3496147394180298, | |
| "learning_rate": 0.00011707317073170732, | |
| "loss": 1.4785, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.062319856664329674, | |
| "eval_loss": 1.4366233348846436, | |
| "eval_runtime": 140.1422, | |
| "eval_samples_per_second": 29.227, | |
| "eval_steps_per_second": 1.827, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06979823946404923, | |
| "grad_norm": 0.6696961522102356, | |
| "learning_rate": 0.00013658536585365856, | |
| "loss": 1.4621, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07976941653034197, | |
| "grad_norm": 0.5544710159301758, | |
| "learning_rate": 0.00015609756097560978, | |
| "loss": 1.4146, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08974059359663472, | |
| "grad_norm": 0.5817800760269165, | |
| "learning_rate": 0.000175609756097561, | |
| "loss": 1.3902, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09971177066292748, | |
| "grad_norm": 0.49702659249305725, | |
| "learning_rate": 0.0001951219512195122, | |
| "loss": 1.3624, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10968294772922023, | |
| "grad_norm": 0.5360238552093506, | |
| "learning_rate": 0.00019833333333333335, | |
| "loss": 1.4103, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11965412479551298, | |
| "grad_norm": 0.6442453265190125, | |
| "learning_rate": 0.00019611111111111112, | |
| "loss": 1.3618, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12463971332865935, | |
| "eval_loss": 1.3544318675994873, | |
| "eval_runtime": 137.5844, | |
| "eval_samples_per_second": 29.771, | |
| "eval_steps_per_second": 1.861, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1296253018618057, | |
| "grad_norm": 0.46826621890068054, | |
| "learning_rate": 0.0001938888888888889, | |
| "loss": 1.3712, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13959647892809846, | |
| "grad_norm": 0.47624409198760986, | |
| "learning_rate": 0.00019166666666666667, | |
| "loss": 1.3469, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1495676559943912, | |
| "grad_norm": 0.449796587228775, | |
| "learning_rate": 0.00018944444444444445, | |
| "loss": 1.3431, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15953883306068395, | |
| "grad_norm": 0.5890815258026123, | |
| "learning_rate": 0.00018722222222222222, | |
| "loss": 1.3511, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1695100101269767, | |
| "grad_norm": 0.429056316614151, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 1.342, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17948118719326944, | |
| "grad_norm": 0.4640163481235504, | |
| "learning_rate": 0.00018277777777777777, | |
| "loss": 1.3353, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18695956999298902, | |
| "eval_loss": 1.3305575847625732, | |
| "eval_runtime": 137.0065, | |
| "eval_samples_per_second": 29.896, | |
| "eval_steps_per_second": 1.869, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1894523642595622, | |
| "grad_norm": 0.4788176715373993, | |
| "learning_rate": 0.00018055555555555557, | |
| "loss": 1.3255, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.19942354132585496, | |
| "grad_norm": 0.43469157814979553, | |
| "learning_rate": 0.00017833333333333335, | |
| "loss": 1.324, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2093947183921477, | |
| "grad_norm": 0.4492317736148834, | |
| "learning_rate": 0.00017611111111111112, | |
| "loss": 1.3325, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21936589545844046, | |
| "grad_norm": 0.4481510519981384, | |
| "learning_rate": 0.0001738888888888889, | |
| "loss": 1.3575, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2293370725247332, | |
| "grad_norm": 0.4316515624523163, | |
| "learning_rate": 0.00017166666666666667, | |
| "loss": 1.3247, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.23930824959102595, | |
| "grad_norm": 0.48252755403518677, | |
| "learning_rate": 0.00016944444444444445, | |
| "loss": 1.3314, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2492794266573187, | |
| "grad_norm": 0.49299389123916626, | |
| "learning_rate": 0.00016722222222222222, | |
| "loss": 1.3422, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2492794266573187, | |
| "eval_loss": 1.319018840789795, | |
| "eval_runtime": 137.544, | |
| "eval_samples_per_second": 29.78, | |
| "eval_steps_per_second": 1.861, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2592506037236114, | |
| "grad_norm": 0.4329146444797516, | |
| "learning_rate": 0.000165, | |
| "loss": 1.3041, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.26922178078990416, | |
| "grad_norm": 0.42452341318130493, | |
| "learning_rate": 0.00016277777777777777, | |
| "loss": 1.3334, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2791929578561969, | |
| "grad_norm": 0.482371985912323, | |
| "learning_rate": 0.00016055555555555558, | |
| "loss": 1.3352, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.28916413492248966, | |
| "grad_norm": 0.4965856075286865, | |
| "learning_rate": 0.00015833333333333332, | |
| "loss": 1.3361, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.2991353119887824, | |
| "grad_norm": 0.4086521863937378, | |
| "learning_rate": 0.00015611111111111113, | |
| "loss": 1.3238, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.30910648905507515, | |
| "grad_norm": 0.5104921460151672, | |
| "learning_rate": 0.0001538888888888889, | |
| "loss": 1.3064, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3115992833216484, | |
| "eval_loss": 1.3116130828857422, | |
| "eval_runtime": 142.0878, | |
| "eval_samples_per_second": 28.827, | |
| "eval_steps_per_second": 1.802, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3190776661213679, | |
| "grad_norm": 0.4384579658508301, | |
| "learning_rate": 0.00015166666666666668, | |
| "loss": 1.3192, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.32904884318766064, | |
| "grad_norm": 0.41889750957489014, | |
| "learning_rate": 0.00014944444444444445, | |
| "loss": 1.326, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3390200202539534, | |
| "grad_norm": 0.44409337639808655, | |
| "learning_rate": 0.00014722222222222223, | |
| "loss": 1.3291, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.34899119732024614, | |
| "grad_norm": 0.4266604483127594, | |
| "learning_rate": 0.000145, | |
| "loss": 1.3114, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3589623743865389, | |
| "grad_norm": 0.4299560785293579, | |
| "learning_rate": 0.00014277777777777778, | |
| "loss": 1.2829, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.36893355145283163, | |
| "grad_norm": 0.4503760039806366, | |
| "learning_rate": 0.00014055555555555555, | |
| "loss": 1.3061, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.37391913998597803, | |
| "eval_loss": 1.3071435689926147, | |
| "eval_runtime": 138.362, | |
| "eval_samples_per_second": 29.604, | |
| "eval_steps_per_second": 1.85, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3789047285191244, | |
| "grad_norm": 0.42756497859954834, | |
| "learning_rate": 0.00013833333333333333, | |
| "loss": 1.3165, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3888759055854172, | |
| "grad_norm": 0.4549823999404907, | |
| "learning_rate": 0.00013611111111111113, | |
| "loss": 1.3283, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3988470826517099, | |
| "grad_norm": 0.43239399790763855, | |
| "learning_rate": 0.00013388888888888888, | |
| "loss": 1.3074, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4088182597180027, | |
| "grad_norm": 0.4290738105773926, | |
| "learning_rate": 0.00013166666666666668, | |
| "loss": 1.2981, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4187894367842954, | |
| "grad_norm": 0.6137893795967102, | |
| "learning_rate": 0.00012944444444444445, | |
| "loss": 1.3113, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.42876061385058817, | |
| "grad_norm": 0.4174145460128784, | |
| "learning_rate": 0.00012722222222222223, | |
| "loss": 1.2837, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.4362389966503077, | |
| "eval_loss": 1.3025227785110474, | |
| "eval_runtime": 138.018, | |
| "eval_samples_per_second": 29.677, | |
| "eval_steps_per_second": 1.855, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4387317909168809, | |
| "grad_norm": 0.4010506272315979, | |
| "learning_rate": 0.000125, | |
| "loss": 1.31, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.44870296798317366, | |
| "grad_norm": 0.42004135251045227, | |
| "learning_rate": 0.0001227777777777778, | |
| "loss": 1.3001, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4586741450494664, | |
| "grad_norm": 0.434986412525177, | |
| "learning_rate": 0.00012055555555555555, | |
| "loss": 1.3285, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.46864532211575916, | |
| "grad_norm": 0.4850348234176636, | |
| "learning_rate": 0.00011833333333333334, | |
| "loss": 1.3145, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.4786164991820519, | |
| "grad_norm": 0.42585763335227966, | |
| "learning_rate": 0.00011611111111111113, | |
| "loss": 1.288, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.48858767624834465, | |
| "grad_norm": 0.5526877045631409, | |
| "learning_rate": 0.00011388888888888889, | |
| "loss": 1.3069, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.4985588533146374, | |
| "grad_norm": 0.44904306530952454, | |
| "learning_rate": 0.00011166666666666668, | |
| "loss": 1.3299, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4985588533146374, | |
| "eval_loss": 1.2983635663986206, | |
| "eval_runtime": 137.4814, | |
| "eval_samples_per_second": 29.793, | |
| "eval_steps_per_second": 1.862, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5085300303809301, | |
| "grad_norm": 0.43869510293006897, | |
| "learning_rate": 0.00010944444444444445, | |
| "loss": 1.3097, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.5185012074472228, | |
| "grad_norm": 0.4270603060722351, | |
| "learning_rate": 0.00010722222222222223, | |
| "loss": 1.3294, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.5284723845135156, | |
| "grad_norm": 0.43747490644454956, | |
| "learning_rate": 0.000105, | |
| "loss": 1.317, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.5384435615798083, | |
| "grad_norm": 0.4406147301197052, | |
| "learning_rate": 0.00010277777777777778, | |
| "loss": 1.2965, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.5484147386461011, | |
| "grad_norm": 0.4331868290901184, | |
| "learning_rate": 0.00010055555555555555, | |
| "loss": 1.2863, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5583859157123938, | |
| "grad_norm": 0.42832815647125244, | |
| "learning_rate": 9.833333333333333e-05, | |
| "loss": 1.2968, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.560878709978967, | |
| "eval_loss": 1.2944072484970093, | |
| "eval_runtime": 137.7551, | |
| "eval_samples_per_second": 29.734, | |
| "eval_steps_per_second": 1.858, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5683570927786866, | |
| "grad_norm": 0.43270131945610046, | |
| "learning_rate": 9.611111111111112e-05, | |
| "loss": 1.2904, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.5783282698449793, | |
| "grad_norm": 0.4404992461204529, | |
| "learning_rate": 9.388888888888889e-05, | |
| "loss": 1.31, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.5882994469112721, | |
| "grad_norm": 0.44887053966522217, | |
| "learning_rate": 9.166666666666667e-05, | |
| "loss": 1.3015, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.5982706239775648, | |
| "grad_norm": 0.42438870668411255, | |
| "learning_rate": 8.944444444444446e-05, | |
| "loss": 1.3053, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6082418010438576, | |
| "grad_norm": 0.4337781071662903, | |
| "learning_rate": 8.722222222222223e-05, | |
| "loss": 1.278, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.6182129781101503, | |
| "grad_norm": 0.4185997247695923, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.2979, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.6231985666432968, | |
| "eval_loss": 1.290996789932251, | |
| "eval_runtime": 137.572, | |
| "eval_samples_per_second": 29.773, | |
| "eval_steps_per_second": 1.861, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6281841551764431, | |
| "grad_norm": 0.4232589900493622, | |
| "learning_rate": 8.277777777777778e-05, | |
| "loss": 1.2937, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.6381553322427358, | |
| "grad_norm": 0.44364941120147705, | |
| "learning_rate": 8.055555555555556e-05, | |
| "loss": 1.3272, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.6481265093090286, | |
| "grad_norm": 0.4201723635196686, | |
| "learning_rate": 7.833333333333333e-05, | |
| "loss": 1.311, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6580976863753213, | |
| "grad_norm": 0.4404850900173187, | |
| "learning_rate": 7.61111111111111e-05, | |
| "loss": 1.312, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.6680688634416141, | |
| "grad_norm": 0.42794689536094666, | |
| "learning_rate": 7.38888888888889e-05, | |
| "loss": 1.2697, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.6780400405079068, | |
| "grad_norm": 0.45072466135025024, | |
| "learning_rate": 7.166666666666667e-05, | |
| "loss": 1.2878, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.6855184233076264, | |
| "eval_loss": 1.2891337871551514, | |
| "eval_runtime": 137.4053, | |
| "eval_samples_per_second": 29.81, | |
| "eval_steps_per_second": 1.863, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6880112175741996, | |
| "grad_norm": 0.42994165420532227, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 1.2823, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.6979823946404923, | |
| "grad_norm": 0.44423794746398926, | |
| "learning_rate": 6.722222222222223e-05, | |
| "loss": 1.2828, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7079535717067851, | |
| "grad_norm": 0.4406779110431671, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.2836, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.7179247487730778, | |
| "grad_norm": 0.4179854094982147, | |
| "learning_rate": 6.277777777777778e-05, | |
| "loss": 1.3222, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.7278959258393706, | |
| "grad_norm": 0.42552730441093445, | |
| "learning_rate": 6.055555555555555e-05, | |
| "loss": 1.3059, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.7378671029056633, | |
| "grad_norm": 0.45751523971557617, | |
| "learning_rate": 5.833333333333334e-05, | |
| "loss": 1.2756, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.7478382799719561, | |
| "grad_norm": 0.4325704276561737, | |
| "learning_rate": 5.6111111111111114e-05, | |
| "loss": 1.2734, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7478382799719561, | |
| "eval_loss": 1.2868282794952393, | |
| "eval_runtime": 137.7011, | |
| "eval_samples_per_second": 29.746, | |
| "eval_steps_per_second": 1.859, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7578094570382488, | |
| "grad_norm": 0.4315655529499054, | |
| "learning_rate": 5.388888888888889e-05, | |
| "loss": 1.3283, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.7677806341045416, | |
| "grad_norm": 0.4370616376399994, | |
| "learning_rate": 5.166666666666667e-05, | |
| "loss": 1.2928, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.7777518111708344, | |
| "grad_norm": 0.46377331018447876, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 1.2502, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.787722988237127, | |
| "grad_norm": 0.42414504289627075, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.2988, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.7976941653034199, | |
| "grad_norm": 0.42951062321662903, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.2756, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8076653423697125, | |
| "grad_norm": 0.44111117720603943, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 1.2826, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.8101581366362858, | |
| "eval_loss": 1.2843713760375977, | |
| "eval_runtime": 136.8431, | |
| "eval_samples_per_second": 29.932, | |
| "eval_steps_per_second": 1.871, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8176365194360053, | |
| "grad_norm": 0.453071266412735, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 1.3157, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.827607696502298, | |
| "grad_norm": 0.4466659426689148, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 1.3015, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.8375788735685908, | |
| "grad_norm": 0.47975486516952515, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.2719, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.8475500506348835, | |
| "grad_norm": 0.4295012056827545, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 1.2761, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8575212277011763, | |
| "grad_norm": 0.4600393772125244, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 1.3026, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.867492404767469, | |
| "grad_norm": 0.4381970167160034, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 1.2989, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.8724779933006154, | |
| "eval_loss": 1.283011794090271, | |
| "eval_runtime": 136.5997, | |
| "eval_samples_per_second": 29.985, | |
| "eval_steps_per_second": 1.874, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8774635818337618, | |
| "grad_norm": 0.4486907720565796, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 1.2821, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.8874347589000545, | |
| "grad_norm": 0.4515422582626343, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.3049, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.8974059359663473, | |
| "grad_norm": 0.430318146944046, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 1.2848, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.90737711303264, | |
| "grad_norm": 0.4484976828098297, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 1.3249, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.9173482900989328, | |
| "grad_norm": 0.43680936098098755, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 1.2724, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.9273194671652255, | |
| "grad_norm": 0.45802849531173706, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 1.3046, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.9347978499649451, | |
| "eval_loss": 1.2813191413879395, | |
| "eval_runtime": 137.1907, | |
| "eval_samples_per_second": 29.856, | |
| "eval_steps_per_second": 1.866, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9372906442315183, | |
| "grad_norm": 0.4513862133026123, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 1.2824, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.947261821297811, | |
| "grad_norm": 0.43908172845840454, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 1.2946, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9572329983641038, | |
| "grad_norm": 0.4305504858493805, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 1.2842, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.9672041754303965, | |
| "grad_norm": 0.4479218125343323, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 1.3138, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.9771753524966893, | |
| "grad_norm": 0.43993687629699707, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3092, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.987146529562982, | |
| "grad_norm": 0.438343346118927, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 1.2904, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.9971177066292748, | |
| "grad_norm": 0.4632357954978943, | |
| "learning_rate": 5.555555555555556e-07, | |
| "loss": 1.2978, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9971177066292748, | |
| "eval_loss": 1.2806103229522705, | |
| "eval_runtime": 137.0794, | |
| "eval_samples_per_second": 29.88, | |
| "eval_steps_per_second": 1.868, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 401, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 512, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5348543338753556e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |