pbe-lora
/
gcp_models
/lora-logo_fix_full_deepseek33b_ds33i_epoch3_lr_0.0002_alpha_512_r_512
/checkpoint-656
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.974124809741248, | |
| "eval_steps": 82, | |
| "global_step": 656, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.7475221551527104, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.8824, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 1.9414628744125366, | |
| "eval_runtime": 123.0959, | |
| "eval_samples_per_second": 12.884, | |
| "eval_steps_per_second": 0.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.8394624776128384, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.0085, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.6984030798296843, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.8498, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.7825221575930125, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.8723, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.73042256418369, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7854, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6733873556634701, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.5498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6946126437472295, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.4278, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.671110339065168, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.2551, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.49800965413153925, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.053, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 7.936684874484749, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9503, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.5629347075143941, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.9112, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.46018014531680834, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.8149, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.35908081618853777, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.6816, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.27088029466532165, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.6155, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.19037277153624466, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5704, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.1715533324260692, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.5621, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.18392810406473384, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.553, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.18711703649137867, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.5245, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.1543234186639602, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.5637, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.16522870651514204, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.13144977669695102, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.496, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.1448449776524406, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.5308, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.13210017955637518, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.4794, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.11592269058701615, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.4761, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.12006542982550884, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5421, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.10737446692526477, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 0.5002, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.12953598639614283, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 0.4851, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.09733824929451951, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.4542, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.10613947863207521, | |
| "learning_rate": 0.000116, | |
| "loss": 0.4647, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.1039095257837877, | |
| "learning_rate": 0.00012, | |
| "loss": 0.4758, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.11280125013723542, | |
| "learning_rate": 0.000124, | |
| "loss": 0.5201, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.14509547136556272, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.4212, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.11102309182416367, | |
| "learning_rate": 0.000132, | |
| "loss": 0.4835, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.09425973400966652, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 0.4566, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.12645290568794776, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5062, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.07740443045657154, | |
| "learning_rate": 0.000144, | |
| "loss": 0.4716, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.09250410537211813, | |
| "learning_rate": 0.000148, | |
| "loss": 0.4439, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.07257831428716673, | |
| "learning_rate": 0.000152, | |
| "loss": 0.4399, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.07805211720698581, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 0.4806, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.08219198532883135, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4453, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.06882648615991452, | |
| "learning_rate": 0.000164, | |
| "loss": 0.4194, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.0735185368819627, | |
| "learning_rate": 0.000168, | |
| "loss": 0.4277, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.09000672713443908, | |
| "learning_rate": 0.000172, | |
| "loss": 0.4385, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.07000556817217815, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.4722, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.11198652644330877, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4396, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.06749455543697698, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.4433, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.08016159777806485, | |
| "learning_rate": 0.000188, | |
| "loss": 0.4797, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.08133743274553888, | |
| "learning_rate": 0.000192, | |
| "loss": 0.4274, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.07849569589666384, | |
| "learning_rate": 0.000196, | |
| "loss": 0.475, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.08877299630396968, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4943, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.07204041636288709, | |
| "learning_rate": 0.0001999994343137953, | |
| "loss": 0.424, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.07191654577635086, | |
| "learning_rate": 0.0001999977372615812, | |
| "loss": 0.4632, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.09665265331489309, | |
| "learning_rate": 0.00019999490886255764, | |
| "loss": 0.449, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.07539927390993074, | |
| "learning_rate": 0.00019999094914872442, | |
| "loss": 0.4585, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.08930639055236878, | |
| "learning_rate": 0.00019998585816488062, | |
| "loss": 0.481, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.08469327605615759, | |
| "learning_rate": 0.0001999796359686242, | |
| "loss": 0.4857, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.08332264603192001, | |
| "learning_rate": 0.0001999722826303514, | |
| "loss": 0.4245, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.06709088445464295, | |
| "learning_rate": 0.00019996379823325583, | |
| "loss": 0.4012, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.07596405117507889, | |
| "learning_rate": 0.0001999541828733277, | |
| "loss": 0.3956, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.08559852090605236, | |
| "learning_rate": 0.0001999434366593524, | |
| "loss": 0.4563, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.08127079156633164, | |
| "learning_rate": 0.00019993155971290976, | |
| "loss": 0.4509, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.0701846609647525, | |
| "learning_rate": 0.00019991855216837224, | |
| "loss": 0.4544, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.06398894678511088, | |
| "learning_rate": 0.00019990441417290356, | |
| "loss": 0.4601, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.06591736828565847, | |
| "learning_rate": 0.00019988914588645715, | |
| "loss": 0.4224, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.077828162251494, | |
| "learning_rate": 0.00019987274748177418, | |
| "loss": 0.4254, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.06473706298954258, | |
| "learning_rate": 0.00019985521914438165, | |
| "loss": 0.4372, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.07327554578886969, | |
| "learning_rate": 0.00019983656107259038, | |
| "loss": 0.466, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.06656304949099325, | |
| "learning_rate": 0.0001998167734774926, | |
| "loss": 0.4365, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.06157776538024679, | |
| "learning_rate": 0.00019979585658295974, | |
| "loss": 0.4555, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0836930962506547, | |
| "learning_rate": 0.00019977381062563976, | |
| "loss": 0.4244, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.07327316264971273, | |
| "learning_rate": 0.0001997506358549545, | |
| "loss": 0.4954, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.06347290175225703, | |
| "learning_rate": 0.000199726332533097, | |
| "loss": 0.4453, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.06148942506764839, | |
| "learning_rate": 0.00019970090093502827, | |
| "loss": 0.4351, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.05846342056335503, | |
| "learning_rate": 0.00019967434134847442, | |
| "loss": 0.4636, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.05402066917387748, | |
| "learning_rate": 0.0001996466540739233, | |
| "loss": 0.4184, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.05514037422497162, | |
| "learning_rate": 0.00019961783942462104, | |
| "loss": 0.427, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.05753040850434197, | |
| "learning_rate": 0.00019958789772656869, | |
| "loss": 0.4255, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.060231494908924946, | |
| "learning_rate": 0.00019955682931851833, | |
| "loss": 0.443, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.059410745282337876, | |
| "learning_rate": 0.0001995246345519694, | |
| "loss": 0.4235, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.05661811052288241, | |
| "learning_rate": 0.00019949131379116454, | |
| "loss": 0.4276, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.056858490536323955, | |
| "learning_rate": 0.00019945686741308568, | |
| "loss": 0.4235, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.06450718000142791, | |
| "learning_rate": 0.00019942129580744966, | |
| "loss": 0.4252, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.4346230626106262, | |
| "eval_runtime": 122.4606, | |
| "eval_samples_per_second": 12.951, | |
| "eval_steps_per_second": 0.408, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.054491329870003796, | |
| "learning_rate": 0.00019938459937670377, | |
| "loss": 0.4144, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.0647158829875042, | |
| "learning_rate": 0.00019934677853602133, | |
| "loss": 0.4402, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.05997906629822681, | |
| "learning_rate": 0.00019930783371329685, | |
| "loss": 0.4374, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.0643950511378, | |
| "learning_rate": 0.0001992677653491414, | |
| "loss": 0.423, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.05991997266930331, | |
| "learning_rate": 0.0001992265738968773, | |
| "loss": 0.3974, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.05914964629459615, | |
| "learning_rate": 0.00019918425982253334, | |
| "loss": 0.4107, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.06510073255382776, | |
| "learning_rate": 0.00019914082360483924, | |
| "loss": 0.4321, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.06433418164986907, | |
| "learning_rate": 0.00019909626573522043, | |
| "loss": 0.4243, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.06083722254340274, | |
| "learning_rate": 0.0001990505867177923, | |
| "loss": 0.4155, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.06835823739331394, | |
| "learning_rate": 0.0001990037870693547, | |
| "loss": 0.4552, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.06850859839795252, | |
| "learning_rate": 0.00019895586731938592, | |
| "loss": 0.4272, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.058775257076978386, | |
| "learning_rate": 0.00019890682801003675, | |
| "loss": 0.429, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.06595052692128361, | |
| "learning_rate": 0.00019885666969612448, | |
| "loss": 0.3969, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.07293538367078456, | |
| "learning_rate": 0.00019880539294512637, | |
| "loss": 0.4777, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.07705722317762942, | |
| "learning_rate": 0.00019875299833717347, | |
| "loss": 0.426, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.06535660163367653, | |
| "learning_rate": 0.0001986994864650439, | |
| "loss": 0.4122, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.07061357412073356, | |
| "learning_rate": 0.00019864485793415624, | |
| "loss": 0.3978, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.05885384766666641, | |
| "learning_rate": 0.00019858911336256257, | |
| "loss": 0.3861, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.07048027235127552, | |
| "learning_rate": 0.00019853225338094168, | |
| "loss": 0.4299, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.059940204002353135, | |
| "learning_rate": 0.00019847427863259163, | |
| "loss": 0.4162, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.06915736036297007, | |
| "learning_rate": 0.00019841518977342272, | |
| "loss": 0.4471, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.06559011377893892, | |
| "learning_rate": 0.00019835498747195008, | |
| "loss": 0.437, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.06140173500512075, | |
| "learning_rate": 0.00019829367240928588, | |
| "loss": 0.4336, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.06630596133190944, | |
| "learning_rate": 0.00019823124527913185, | |
| "loss": 0.4607, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.057248721454510335, | |
| "learning_rate": 0.00019816770678777128, | |
| "loss": 0.4275, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.05605115688316942, | |
| "learning_rate": 0.0001981030576540612, | |
| "loss": 0.4348, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.057515171222559995, | |
| "learning_rate": 0.00019803729860942397, | |
| "loss": 0.426, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.058197445560344487, | |
| "learning_rate": 0.00019797043039783936, | |
| "loss": 0.4082, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.05551990447123242, | |
| "learning_rate": 0.00019790245377583583, | |
| "loss": 0.3777, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.06348839429477848, | |
| "learning_rate": 0.0001978333695124821, | |
| "loss": 0.4359, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.06109954298889087, | |
| "learning_rate": 0.00019776317838937857, | |
| "loss": 0.4329, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.06367051131888578, | |
| "learning_rate": 0.00019769188120064812, | |
| "loss": 0.4093, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.06228657880841021, | |
| "learning_rate": 0.00019761947875292753, | |
| "loss": 0.4742, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.07407245522803606, | |
| "learning_rate": 0.00019754597186535814, | |
| "loss": 0.4737, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.06014147327741113, | |
| "learning_rate": 0.00019747136136957652, | |
| "loss": 0.4007, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.05694324532649369, | |
| "learning_rate": 0.0001973956481097053, | |
| "loss": 0.4141, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.05366154914265005, | |
| "learning_rate": 0.0001973188329423434, | |
| "loss": 0.4006, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.052826392724311784, | |
| "learning_rate": 0.0001972409167365564, | |
| "loss": 0.3912, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.058165230992289825, | |
| "learning_rate": 0.0001971619003738668, | |
| "loss": 0.3852, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.06799412286654258, | |
| "learning_rate": 0.0001970817847482439, | |
| "loss": 0.4256, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.061619996939206424, | |
| "learning_rate": 0.00019700057076609378, | |
| "loss": 0.4156, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.06366893887332205, | |
| "learning_rate": 0.000196918259346249, | |
| "loss": 0.4197, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.06330624987253586, | |
| "learning_rate": 0.00019683485141995833, | |
| "loss": 0.4308, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.05525542309385779, | |
| "learning_rate": 0.00019675034793087596, | |
| "loss": 0.4029, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.08192037571257756, | |
| "learning_rate": 0.00019666474983505113, | |
| "loss": 0.4545, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.05994384355769922, | |
| "learning_rate": 0.000196578058100917, | |
| "loss": 0.4123, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.061368899549159646, | |
| "learning_rate": 0.00019649027370927997, | |
| "loss": 0.4031, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.062297089331655016, | |
| "learning_rate": 0.0001964013976533084, | |
| "loss": 0.4145, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.06374572759458035, | |
| "learning_rate": 0.00019631143093852148, | |
| "loss": 0.4311, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.05674494393996287, | |
| "learning_rate": 0.00019622037458277784, | |
| "loss": 0.4082, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.08083252449476908, | |
| "learning_rate": 0.0001961282296162639, | |
| "loss": 0.435, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.059089057283910416, | |
| "learning_rate": 0.00019603499708148244, | |
| "loss": 0.4006, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.0684006974801675, | |
| "learning_rate": 0.0001959406780332406, | |
| "loss": 0.44, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.061168968383140614, | |
| "learning_rate": 0.0001958452735386381, | |
| "loss": 0.4141, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.06361724595787813, | |
| "learning_rate": 0.00019574878467705503, | |
| "loss": 0.3948, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.05299938906981593, | |
| "learning_rate": 0.00019565121254013979, | |
| "loss": 0.4122, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.06358024858629942, | |
| "learning_rate": 0.00019555255823179658, | |
| "loss": 0.4056, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.06621918204973565, | |
| "learning_rate": 0.00019545282286817303, | |
| "loss": 0.3946, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.06653433256367869, | |
| "learning_rate": 0.00019535200757764756, | |
| "loss": 0.394, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.05931156276840698, | |
| "learning_rate": 0.0001952501135008165, | |
| "loss": 0.4428, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.06473119673659994, | |
| "learning_rate": 0.00019514714179048138, | |
| "loss": 0.4479, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.05946771197132229, | |
| "learning_rate": 0.00019504309361163566, | |
| "loss": 0.3878, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.06421662056773203, | |
| "learning_rate": 0.0001949379701414518, | |
| "loss": 0.4103, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.06259022473693858, | |
| "learning_rate": 0.00019483177256926767, | |
| "loss": 0.4044, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.07116337369484337, | |
| "learning_rate": 0.00019472450209657332, | |
| "loss": 0.4341, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.06334925135579976, | |
| "learning_rate": 0.0001946161599369973, | |
| "loss": 0.3974, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.05858942254298656, | |
| "learning_rate": 0.0001945067473162929, | |
| "loss": 0.4064, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.06252218761598552, | |
| "learning_rate": 0.00019439626547232433, | |
| "loss": 0.371, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.05953144540904857, | |
| "learning_rate": 0.00019428471565505266, | |
| "loss": 0.4417, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.06565742216852309, | |
| "learning_rate": 0.0001941720991265218, | |
| "loss": 0.4422, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.05952700228692982, | |
| "learning_rate": 0.00019405841716084403, | |
| "loss": 0.4275, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.05536598151691238, | |
| "learning_rate": 0.00019394367104418576, | |
| "loss": 0.4307, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.059756435750596394, | |
| "learning_rate": 0.00019382786207475293, | |
| "loss": 0.4772, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.05652627006582918, | |
| "learning_rate": 0.0001937109915627762, | |
| "loss": 0.4524, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.057425284446652035, | |
| "learning_rate": 0.00019359306083049636, | |
| "loss": 0.4301, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.06875699750011768, | |
| "learning_rate": 0.00019347407121214914, | |
| "loss": 0.4142, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.06384919537252529, | |
| "learning_rate": 0.00019335402405395028, | |
| "loss": 0.4217, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.06464656066475126, | |
| "learning_rate": 0.00019323292071408017, | |
| "loss": 0.4369, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.05872722959006338, | |
| "learning_rate": 0.00019311076256266864, | |
| "loss": 0.3846, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.0666979420987961, | |
| "learning_rate": 0.00019298755098177926, | |
| "loss": 0.4333, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.05375937531872668, | |
| "learning_rate": 0.00019286328736539386, | |
| "loss": 0.4046, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.06617056169749186, | |
| "learning_rate": 0.00019273797311939673, | |
| "loss": 0.4111, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.4133497178554535, | |
| "eval_runtime": 122.4386, | |
| "eval_samples_per_second": 12.953, | |
| "eval_steps_per_second": 0.408, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.05845411670019977, | |
| "learning_rate": 0.00019261160966155868, | |
| "loss": 0.3684, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.07156290733021581, | |
| "learning_rate": 0.00019248419842152098, | |
| "loss": 0.429, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.06122480682648846, | |
| "learning_rate": 0.00019235574084077928, | |
| "loss": 0.3643, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.06226668544210886, | |
| "learning_rate": 0.0001922262383726672, | |
| "loss": 0.4419, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.060048073335656905, | |
| "learning_rate": 0.00019209569248233993, | |
| "loss": 0.3897, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.05671755934285226, | |
| "learning_rate": 0.00019196410464675766, | |
| "loss": 0.4175, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.06055446161915308, | |
| "learning_rate": 0.0001918314763546688, | |
| "loss": 0.3879, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.06010741676187997, | |
| "learning_rate": 0.00019169780910659333, | |
| "loss": 0.4221, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.060153717213729294, | |
| "learning_rate": 0.0001915631044148056, | |
| "loss": 0.4288, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.06839977160709854, | |
| "learning_rate": 0.00019142736380331726, | |
| "loss": 0.4236, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.06287272151085344, | |
| "learning_rate": 0.00019129058880786024, | |
| "loss": 0.4094, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.06385156559987902, | |
| "learning_rate": 0.00019115278097586903, | |
| "loss": 0.415, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.05656510695487937, | |
| "learning_rate": 0.00019101394186646345, | |
| "loss": 0.3799, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.05890420484850292, | |
| "learning_rate": 0.00019087407305043086, | |
| "loss": 0.4185, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.05568601359498617, | |
| "learning_rate": 0.00019073317611020848, | |
| "loss": 0.4141, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.060027676664883796, | |
| "learning_rate": 0.0001905912526398654, | |
| "loss": 0.3894, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.059308428132035046, | |
| "learning_rate": 0.00019044830424508455, | |
| "loss": 0.4382, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.05618895290987069, | |
| "learning_rate": 0.00019030433254314474, | |
| "loss": 0.3953, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.05421958360319748, | |
| "learning_rate": 0.000190159339162902, | |
| "loss": 0.4039, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.05891205833963261, | |
| "learning_rate": 0.00019001332574477146, | |
| "loss": 0.4121, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.05940851141098443, | |
| "learning_rate": 0.00018986629394070865, | |
| "loss": 0.396, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.0650971595649072, | |
| "learning_rate": 0.00018971824541419083, | |
| "loss": 0.4206, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.05660958302709971, | |
| "learning_rate": 0.00018956918184019817, | |
| "loss": 0.4158, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.059513935004651616, | |
| "learning_rate": 0.0001894191049051948, | |
| "loss": 0.3916, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.06560777157043599, | |
| "learning_rate": 0.00018926801630710983, | |
| "loss": 0.4477, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.05516787489224214, | |
| "learning_rate": 0.0001891159177553179, | |
| "loss": 0.4046, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.056860599378059706, | |
| "learning_rate": 0.0001889628109706201, | |
| "loss": 0.409, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.0629579448836026, | |
| "learning_rate": 0.00018880869768522432, | |
| "loss": 0.3894, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.058754785103797114, | |
| "learning_rate": 0.00018865357964272577, | |
| "loss": 0.407, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.05236468270207464, | |
| "learning_rate": 0.00018849745859808717, | |
| "loss": 0.3657, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.057900739277243374, | |
| "learning_rate": 0.00018834033631761897, | |
| "loss": 0.4249, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.060665222606386494, | |
| "learning_rate": 0.00018818221457895926, | |
| "loss": 0.4255, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.06646810483821156, | |
| "learning_rate": 0.00018802309517105382, | |
| "loss": 0.4221, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.061652424868035016, | |
| "learning_rate": 0.00018786297989413568, | |
| "loss": 0.3872, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.06722167692768409, | |
| "learning_rate": 0.0001877018705597049, | |
| "loss": 0.3926, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.08411461135796866, | |
| "learning_rate": 0.00018753976899050812, | |
| "loss": 0.4165, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.058513284109273346, | |
| "learning_rate": 0.00018737667702051764, | |
| "loss": 0.435, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.0809031011230918, | |
| "learning_rate": 0.00018721259649491113, | |
| "loss": 0.4061, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.06801604839502517, | |
| "learning_rate": 0.00018704752927005034, | |
| "loss": 0.4263, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.06417891665023034, | |
| "learning_rate": 0.0001868814772134603, | |
| "loss": 0.4124, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.06680735595079268, | |
| "learning_rate": 0.00018671444220380817, | |
| "loss": 0.4214, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.05720337065800525, | |
| "learning_rate": 0.00018654642613088194, | |
| "loss": 0.3961, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.10723723235138596, | |
| "learning_rate": 0.00018637743089556914, | |
| "loss": 0.3802, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.0597661037051907, | |
| "learning_rate": 0.0001862074584098352, | |
| "loss": 0.3884, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.06696468350315019, | |
| "learning_rate": 0.00018603651059670198, | |
| "loss": 0.3756, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.06439485950750766, | |
| "learning_rate": 0.00018586458939022586, | |
| "loss": 0.4225, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.062365078955430954, | |
| "learning_rate": 0.0001856916967354759, | |
| "loss": 0.4252, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.05530487630658039, | |
| "learning_rate": 0.00018551783458851189, | |
| "loss": 0.3798, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.06534506891507633, | |
| "learning_rate": 0.00018534300491636222, | |
| "loss": 0.4502, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.05963478156581727, | |
| "learning_rate": 0.0001851672096970016, | |
| "loss": 0.4367, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.07202455546410065, | |
| "learning_rate": 0.00018499045091932854, | |
| "loss": 0.4004, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.05449984062624298, | |
| "learning_rate": 0.00018481273058314316, | |
| "loss": 0.3829, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.06068324490432485, | |
| "learning_rate": 0.00018463405069912427, | |
| "loss": 0.3725, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.062634360908686, | |
| "learning_rate": 0.00018445441328880682, | |
| "loss": 0.405, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.05616313167272405, | |
| "learning_rate": 0.00018427382038455886, | |
| "loss": 0.3731, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.06299877079405979, | |
| "learning_rate": 0.00018409227402955871, | |
| "loss": 0.3979, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.06776500547762239, | |
| "learning_rate": 0.00018390977627777175, | |
| "loss": 0.4104, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.05819900581325518, | |
| "learning_rate": 0.00018372632919392716, | |
| "loss": 0.3828, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.05648685002741242, | |
| "learning_rate": 0.00018354193485349468, | |
| "loss": 0.385, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.0582150279905251, | |
| "learning_rate": 0.00018335659534266094, | |
| "loss": 0.393, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.06579203054634192, | |
| "learning_rate": 0.00018317031275830607, | |
| "loss": 0.4136, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.06483250644020357, | |
| "learning_rate": 0.00018298308920797985, | |
| "loss": 0.3839, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.06418230133283062, | |
| "learning_rate": 0.0001827949268098778, | |
| "loss": 0.4113, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.06253873101836974, | |
| "learning_rate": 0.00018260582769281743, | |
| "loss": 0.3672, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.05785495988592293, | |
| "learning_rate": 0.000182415793996214, | |
| "loss": 0.3724, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.07708888229918744, | |
| "learning_rate": 0.0001822248278700563, | |
| "loss": 0.3965, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.06106196577642292, | |
| "learning_rate": 0.00018203293147488236, | |
| "loss": 0.3815, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.060092116126261585, | |
| "learning_rate": 0.00018184010698175506, | |
| "loss": 0.4005, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.06345557819650693, | |
| "learning_rate": 0.00018164635657223755, | |
| "loss": 0.3977, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.06021928418528313, | |
| "learning_rate": 0.0001814516824383685, | |
| "loss": 0.3827, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.0667091152841576, | |
| "learning_rate": 0.0001812560867826373, | |
| "loss": 0.4036, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.06849631829683184, | |
| "learning_rate": 0.0001810595718179593, | |
| "loss": 0.4382, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.060959771332151746, | |
| "learning_rate": 0.00018086213976765053, | |
| "loss": 0.389, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.0596876259529073, | |
| "learning_rate": 0.00018066379286540277, | |
| "loss": 0.4474, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.05610149818159612, | |
| "learning_rate": 0.00018046453335525815, | |
| "loss": 0.4035, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.0578783408637661, | |
| "learning_rate": 0.00018026436349158378, | |
| "loss": 0.3951, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.06466648881256293, | |
| "learning_rate": 0.00018006328553904627, | |
| "loss": 0.4077, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.060932653185465965, | |
| "learning_rate": 0.00017986130177258608, | |
| "loss": 0.3913, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.06352077924805434, | |
| "learning_rate": 0.00017965841447739185, | |
| "loss": 0.3869, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.06244604009103952, | |
| "learning_rate": 0.00017945462594887445, | |
| "loss": 0.3971, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.061543968347526457, | |
| "learning_rate": 0.00017924993849264103, | |
| "loss": 0.4238, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.06619416407009097, | |
| "learning_rate": 0.000179044354424469, | |
| "loss": 0.4152, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.40517091751098633, | |
| "eval_runtime": 122.882, | |
| "eval_samples_per_second": 12.907, | |
| "eval_steps_per_second": 0.407, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.06614424404477753, | |
| "learning_rate": 0.00017883787607027987, | |
| "loss": 0.4209, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.05819748756770155, | |
| "learning_rate": 0.00017863050576611265, | |
| "loss": 0.4012, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.06303585459009173, | |
| "learning_rate": 0.00017842224585809784, | |
| "loss": 0.4282, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.06428888375552616, | |
| "learning_rate": 0.00017821309870243054, | |
| "loss": 0.4135, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.0622520651315585, | |
| "learning_rate": 0.00017800306666534396, | |
| "loss": 0.4017, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.06586267483409845, | |
| "learning_rate": 0.00017779215212308265, | |
| "loss": 0.3796, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.05849365585927707, | |
| "learning_rate": 0.00017758035746187552, | |
| "loss": 0.3761, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.061047936055243, | |
| "learning_rate": 0.0001773676850779089, | |
| "loss": 0.4218, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.07656024387013258, | |
| "learning_rate": 0.00017715413737729954, | |
| "loss": 0.4289, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.05584299457569571, | |
| "learning_rate": 0.00017693971677606714, | |
| "loss": 0.4233, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.0657544686807761, | |
| "learning_rate": 0.00017672442570010728, | |
| "loss": 0.4134, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.06265622224593083, | |
| "learning_rate": 0.00017650826658516375, | |
| "loss": 0.4313, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.05476907835873057, | |
| "learning_rate": 0.00017629124187680114, | |
| "loss": 0.3902, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.05968988448455504, | |
| "learning_rate": 0.00017607335403037712, | |
| "loss": 0.4289, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.05835583386280491, | |
| "learning_rate": 0.0001758546055110147, | |
| "loss": 0.3873, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.05429594756095897, | |
| "learning_rate": 0.00017563499879357425, | |
| "loss": 0.4158, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.05776386664028014, | |
| "learning_rate": 0.0001754145363626256, | |
| "loss": 0.4186, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.058386156774781824, | |
| "learning_rate": 0.00017519322071241983, | |
| "loss": 0.3765, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.06332267300290681, | |
| "learning_rate": 0.0001749710543468612, | |
| "loss": 0.3643, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.06233449532300784, | |
| "learning_rate": 0.0001747480397794786, | |
| "loss": 0.3784, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.06086949946742818, | |
| "learning_rate": 0.00017452417953339736, | |
| "loss": 0.3918, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.056743930463191955, | |
| "learning_rate": 0.0001742994761413105, | |
| "loss": 0.3911, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.05646165162507521, | |
| "learning_rate": 0.0001740739321454503, | |
| "loss": 0.3631, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.061337124565113255, | |
| "learning_rate": 0.0001738475500975592, | |
| "loss": 0.4166, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.05417880541627281, | |
| "learning_rate": 0.0001736203325588613, | |
| "loss": 0.3915, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.05023628577547998, | |
| "learning_rate": 0.00017339228210003305, | |
| "loss": 0.3851, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.05447472323233125, | |
| "learning_rate": 0.00017316340130117447, | |
| "loss": 0.3936, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.05573041834086647, | |
| "learning_rate": 0.00017293369275177983, | |
| "loss": 0.393, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.056757096045186584, | |
| "learning_rate": 0.00017270315905070822, | |
| "loss": 0.3692, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.05603476321447209, | |
| "learning_rate": 0.0001724718028061543, | |
| "loss": 0.379, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.06474846667260976, | |
| "learning_rate": 0.00017223962663561883, | |
| "loss": 0.3761, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.05979236467417292, | |
| "learning_rate": 0.00017200663316587896, | |
| "loss": 0.3948, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.06311444282182939, | |
| "learning_rate": 0.00017177282503295848, | |
| "loss": 0.3863, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.07223823066795879, | |
| "learning_rate": 0.0001715382048820981, | |
| "loss": 0.3842, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.06043719925578775, | |
| "learning_rate": 0.00017130277536772553, | |
| "loss": 0.4047, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.10079632210213979, | |
| "learning_rate": 0.00017106653915342527, | |
| "loss": 0.398, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.060059047325096274, | |
| "learning_rate": 0.00017082949891190872, | |
| "loss": 0.4005, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.06127248779401347, | |
| "learning_rate": 0.00017059165732498372, | |
| "loss": 0.425, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.0635283442344994, | |
| "learning_rate": 0.00017035301708352441, | |
| "loss": 0.3842, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.06029663557030777, | |
| "learning_rate": 0.0001701135808874406, | |
| "loss": 0.4856, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.054272323141467925, | |
| "learning_rate": 0.00016987335144564742, | |
| "loss": 0.4237, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.05837934725809568, | |
| "learning_rate": 0.0001696323314760344, | |
| "loss": 0.39, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.062434200951597935, | |
| "learning_rate": 0.00016939052370543506, | |
| "loss": 0.4155, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.055375007460805724, | |
| "learning_rate": 0.00016914793086959576, | |
| "loss": 0.374, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.061252515951613996, | |
| "learning_rate": 0.0001689045557131449, | |
| "loss": 0.3787, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.07143926799831636, | |
| "learning_rate": 0.00016866040098956187, | |
| "loss": 0.3956, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.06058144159501697, | |
| "learning_rate": 0.00016841546946114587, | |
| "loss": 0.3997, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.059909439571496644, | |
| "learning_rate": 0.0001681697638989846, | |
| "loss": 0.4012, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.05583463642875068, | |
| "learning_rate": 0.000167923287082923, | |
| "loss": 0.3891, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.052492112858005695, | |
| "learning_rate": 0.00016767604180153178, | |
| "loss": 0.3985, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.06353023900523744, | |
| "learning_rate": 0.00016742803085207581, | |
| "loss": 0.4179, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.05310601173830385, | |
| "learning_rate": 0.00016717925704048256, | |
| "loss": 0.3476, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.057810988841411254, | |
| "learning_rate": 0.00016692972318131031, | |
| "loss": 0.3988, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.05455508550099681, | |
| "learning_rate": 0.00016667943209771634, | |
| "loss": 0.3715, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.05605723370275242, | |
| "learning_rate": 0.0001664283866214248, | |
| "loss": 0.3659, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.06863162120008814, | |
| "learning_rate": 0.00016617658959269504, | |
| "loss": 0.4313, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.06136349862118656, | |
| "learning_rate": 0.0001659240438602891, | |
| "loss": 0.4453, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.06251238908761675, | |
| "learning_rate": 0.00016567075228143976, | |
| "loss": 0.3573, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.06271153653054647, | |
| "learning_rate": 0.00016541671772181803, | |
| "loss": 0.3963, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.06582036032519314, | |
| "learning_rate": 0.0001651619430555009, | |
| "loss": 0.4147, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.05784343893620808, | |
| "learning_rate": 0.00016490643116493856, | |
| "loss": 0.3891, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.07278738595625053, | |
| "learning_rate": 0.0001646501849409221, | |
| "loss": 0.4066, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.059873020926217754, | |
| "learning_rate": 0.00016439320728255056, | |
| "loss": 0.3825, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.0617696795652661, | |
| "learning_rate": 0.00016413550109719828, | |
| "loss": 0.4029, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.05914414112543636, | |
| "learning_rate": 0.00016387706930048196, | |
| "loss": 0.3743, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.05849103666936063, | |
| "learning_rate": 0.00016361791481622762, | |
| "loss": 0.396, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.056423952588653806, | |
| "learning_rate": 0.0001633580405764376, | |
| "loss": 0.3941, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.061866308171347806, | |
| "learning_rate": 0.00016309744952125736, | |
| "loss": 0.4081, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.049255127652120916, | |
| "learning_rate": 0.0001628361445989422, | |
| "loss": 0.384, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.054652903461596215, | |
| "learning_rate": 0.00016257412876582387, | |
| "loss": 0.3627, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.05358580621827581, | |
| "learning_rate": 0.0001623114049862773, | |
| "loss": 0.3839, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.05037936179014346, | |
| "learning_rate": 0.00016204797623268675, | |
| "loss": 0.34, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.05563729253169197, | |
| "learning_rate": 0.0001617838454854125, | |
| "loss": 0.4003, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.05541668895080723, | |
| "learning_rate": 0.00016151901573275694, | |
| "loss": 0.3428, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.05698552846407976, | |
| "learning_rate": 0.00016125348997093086, | |
| "loss": 0.3201, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.05949651336722312, | |
| "learning_rate": 0.00016098727120401944, | |
| "loss": 0.3739, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.0554215330150185, | |
| "learning_rate": 0.00016072036244394835, | |
| "loss": 0.3782, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.05587316439560869, | |
| "learning_rate": 0.00016045276671044966, | |
| "loss": 0.3465, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.05823554977558024, | |
| "learning_rate": 0.0001601844870310277, | |
| "loss": 0.3807, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.06011187701909386, | |
| "learning_rate": 0.0001599155264409247, | |
| "loss": 0.4043, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.05496167739242709, | |
| "learning_rate": 0.00015964588798308662, | |
| "loss": 0.3819, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.05400395013969528, | |
| "learning_rate": 0.0001593755747081285, | |
| "loss": 0.3872, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.39384254813194275, | |
| "eval_runtime": 122.5782, | |
| "eval_samples_per_second": 12.939, | |
| "eval_steps_per_second": 0.408, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.06156478355379309, | |
| "learning_rate": 0.00015910458967430025, | |
| "loss": 0.4201, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.05277696408531988, | |
| "learning_rate": 0.00015883293594745168, | |
| "loss": 0.4031, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.05138744464290521, | |
| "learning_rate": 0.00015856061660099818, | |
| "loss": 0.3592, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.05259902237691423, | |
| "learning_rate": 0.00015828763471588563, | |
| "loss": 0.3472, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.05024827202437227, | |
| "learning_rate": 0.00015801399338055583, | |
| "loss": 0.3505, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.05664032492064864, | |
| "learning_rate": 0.00015773969569091132, | |
| "loss": 0.3603, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.057505426474741, | |
| "learning_rate": 0.00015746474475028047, | |
| "loss": 0.379, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.053679090508355995, | |
| "learning_rate": 0.00015718914366938237, | |
| "loss": 0.3932, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.05036497054465667, | |
| "learning_rate": 0.00015691289556629166, | |
| "loss": 0.3228, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.05750205571125401, | |
| "learning_rate": 0.00015663600356640304, | |
| "loss": 0.3783, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.05129309748403285, | |
| "learning_rate": 0.0001563584708023963, | |
| "loss": 0.3431, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.05527705207706242, | |
| "learning_rate": 0.00015608030041420055, | |
| "loss": 0.376, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.06026072911749153, | |
| "learning_rate": 0.00015580149554895876, | |
| "loss": 0.3502, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.06338653048370231, | |
| "learning_rate": 0.0001555220593609923, | |
| "loss": 0.3604, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.054025125559915115, | |
| "learning_rate": 0.0001552419950117651, | |
| "loss": 0.3371, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.05941416059168657, | |
| "learning_rate": 0.00015496130566984792, | |
| "loss": 0.3542, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.06804897134313131, | |
| "learning_rate": 0.00015467999451088251, | |
| "loss": 0.3474, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.05923257123580075, | |
| "learning_rate": 0.00015439806471754576, | |
| "loss": 0.3692, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.05708537521779728, | |
| "learning_rate": 0.0001541155194795135, | |
| "loss": 0.3287, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.0628614738679565, | |
| "learning_rate": 0.00015383236199342467, | |
| "loss": 0.3373, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.05995015107904655, | |
| "learning_rate": 0.00015354859546284493, | |
| "loss": 0.3676, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.07007125689001649, | |
| "learning_rate": 0.00015326422309823044, | |
| "loss": 0.3616, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.06468916068502349, | |
| "learning_rate": 0.00015297924811689172, | |
| "loss": 0.3753, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.06319536131952319, | |
| "learning_rate": 0.00015269367374295715, | |
| "loss": 0.3642, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.05727809800418403, | |
| "learning_rate": 0.0001524075032073363, | |
| "loss": 0.2973, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.06566079091846679, | |
| "learning_rate": 0.00015212073974768368, | |
| "loss": 0.359, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.06234032006616298, | |
| "learning_rate": 0.000151833386608362, | |
| "loss": 0.3676, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.06038139402253696, | |
| "learning_rate": 0.00015154544704040537, | |
| "loss": 0.3499, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.05860092794639025, | |
| "learning_rate": 0.00015125692430148258, | |
| "loss": 0.3591, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.05932490618262185, | |
| "learning_rate": 0.00015096782165586035, | |
| "loss": 0.3393, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.06781375301539468, | |
| "learning_rate": 0.0001506781423743662, | |
| "loss": 0.3624, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.061950927884226244, | |
| "learning_rate": 0.00015038788973435166, | |
| "loss": 0.3726, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.06104150739050668, | |
| "learning_rate": 0.00015009706701965493, | |
| "loss": 0.3914, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.0640573415191276, | |
| "learning_rate": 0.00014980567752056405, | |
| "loss": 0.3585, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.0648486651143408, | |
| "learning_rate": 0.0001495137245337794, | |
| "loss": 0.3511, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.061625541626235895, | |
| "learning_rate": 0.00014922121136237644, | |
| "loss": 0.3699, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.06269600799507528, | |
| "learning_rate": 0.00014892814131576854, | |
| "loss": 0.3293, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.07263716349577137, | |
| "learning_rate": 0.00014863451770966938, | |
| "loss": 0.3829, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.06593060902094908, | |
| "learning_rate": 0.00014834034386605537, | |
| "loss": 0.3909, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.06596234911558371, | |
| "learning_rate": 0.00014804562311312828, | |
| "loss": 0.3706, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.06590323106825134, | |
| "learning_rate": 0.00014775035878527735, | |
| "loss": 0.381, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.06866645979876648, | |
| "learning_rate": 0.00014745455422304174, | |
| "loss": 0.3423, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.06212448957358757, | |
| "learning_rate": 0.0001471582127730726, | |
| "loss": 0.3426, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.06723052244254629, | |
| "learning_rate": 0.00014686133778809538, | |
| "loss": 0.3624, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.06654908092543575, | |
| "learning_rate": 0.00014656393262687173, | |
| "loss": 0.3648, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.06699563829414978, | |
| "learning_rate": 0.0001462660006541616, | |
| "loss": 0.3539, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.07190768092350996, | |
| "learning_rate": 0.00014596754524068514, | |
| "loss": 0.3707, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.06989126054695284, | |
| "learning_rate": 0.00014566856976308453, | |
| "loss": 0.3806, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.06455457895508253, | |
| "learning_rate": 0.00014536907760388584, | |
| "loss": 0.3704, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.07448733194426341, | |
| "learning_rate": 0.00014506907215146075, | |
| "loss": 0.3746, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.061939839884512474, | |
| "learning_rate": 0.00014476855679998818, | |
| "loss": 0.3397, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.06405099134462497, | |
| "learning_rate": 0.00014446753494941583, | |
| "loss": 0.3685, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.10211884815837752, | |
| "learning_rate": 0.00014416601000542193, | |
| "loss": 0.3498, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.060349859133388487, | |
| "learning_rate": 0.0001438639853793765, | |
| "loss": 0.3348, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.07243736261460916, | |
| "learning_rate": 0.00014356146448830278, | |
| "loss": 0.361, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.06833421721058826, | |
| "learning_rate": 0.00014325845075483873, | |
| "loss": 0.3543, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.06523564374569349, | |
| "learning_rate": 0.0001429549476071981, | |
| "loss": 0.3694, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.07301152465306324, | |
| "learning_rate": 0.00014265095847913175, | |
| "loss": 0.3916, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.07668463808073094, | |
| "learning_rate": 0.0001423464868098888, | |
| "loss": 0.3536, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.0660169247211518, | |
| "learning_rate": 0.00014204153604417775, | |
| "loss": 0.3768, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.0717765327978709, | |
| "learning_rate": 0.0001417361096321274, | |
| "loss": 0.4069, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.05920990787624589, | |
| "learning_rate": 0.0001414302110292479, | |
| "loss": 0.3491, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.06397793541223692, | |
| "learning_rate": 0.00014112384369639164, | |
| "loss": 0.3653, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.06446686872699675, | |
| "learning_rate": 0.00014081701109971411, | |
| "loss": 0.3519, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.06599816636022793, | |
| "learning_rate": 0.00014050971671063464, | |
| "loss": 0.3839, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.0671748185387976, | |
| "learning_rate": 0.00014020196400579718, | |
| "loss": 0.3546, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.06499812868524021, | |
| "learning_rate": 0.00013989375646703093, | |
| "loss": 0.36, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.06689087655880699, | |
| "learning_rate": 0.00013958509758131094, | |
| "loss": 0.37, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.06565843990383205, | |
| "learning_rate": 0.00013927599084071865, | |
| "loss": 0.3794, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.06533783543325292, | |
| "learning_rate": 0.00013896643974240246, | |
| "loss": 0.363, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.06489973595655309, | |
| "learning_rate": 0.00013865644778853807, | |
| "loss": 0.3745, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.0655078563337458, | |
| "learning_rate": 0.00013834601848628896, | |
| "loss": 0.3467, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.0678239699960418, | |
| "learning_rate": 0.0001380351553477666, | |
| "loss": 0.386, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.06884773065008377, | |
| "learning_rate": 0.00013772386188999074, | |
| "loss": 0.3651, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.06517480911796501, | |
| "learning_rate": 0.0001374121416348497, | |
| "loss": 0.3301, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.0593587801449866, | |
| "learning_rate": 0.00013709999810906042, | |
| "loss": 0.3328, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.0669147154714388, | |
| "learning_rate": 0.00013678743484412864, | |
| "loss": 0.3828, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.06349130605989597, | |
| "learning_rate": 0.0001364744553763089, | |
| "loss": 0.3459, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.06379628357833858, | |
| "learning_rate": 0.00013616106324656455, | |
| "loss": 0.3523, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.06042269886085037, | |
| "learning_rate": 0.00013584726200052767, | |
| "loss": 0.3475, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.07060345743145212, | |
| "learning_rate": 0.000135533055188459, | |
| "loss": 0.3833, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.06777964063394054, | |
| "learning_rate": 0.00013521844636520767, | |
| "loss": 0.3697, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.39136308431625366, | |
| "eval_runtime": 122.7206, | |
| "eval_samples_per_second": 12.924, | |
| "eval_steps_per_second": 0.407, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.06145097423631168, | |
| "learning_rate": 0.00013490343909017117, | |
| "loss": 0.3637, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.056699875966756165, | |
| "learning_rate": 0.00013458803692725487, | |
| "loss": 0.3264, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.06127294758278969, | |
| "learning_rate": 0.0001342722434448318, | |
| "loss": 0.3598, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.06159667923390936, | |
| "learning_rate": 0.0001339560622157023, | |
| "loss": 0.3684, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.058977890447668525, | |
| "learning_rate": 0.00013363949681705355, | |
| "loss": 0.3501, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.06932673258862988, | |
| "learning_rate": 0.00013332255083041915, | |
| "loss": 0.3884, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.06555116109736263, | |
| "learning_rate": 0.00013300522784163857, | |
| "loss": 0.3456, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.06336684281169956, | |
| "learning_rate": 0.00013268753144081652, | |
| "loss": 0.3342, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.06627308592859903, | |
| "learning_rate": 0.00013236946522228243, | |
| "loss": 0.3541, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.06533098604880103, | |
| "learning_rate": 0.0001320510327845497, | |
| "loss": 0.3326, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.06323579462549002, | |
| "learning_rate": 0.00013173223773027513, | |
| "loss": 0.319, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.07181274423400011, | |
| "learning_rate": 0.000131413083666218, | |
| "loss": 0.3878, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.06303413333855953, | |
| "learning_rate": 0.00013109357420319932, | |
| "loss": 0.3393, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.06742991653105594, | |
| "learning_rate": 0.00013077371295606099, | |
| "loss": 0.3684, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.07557122286908097, | |
| "learning_rate": 0.00013045350354362495, | |
| "loss": 0.3671, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.06856529352140062, | |
| "learning_rate": 0.00013013294958865208, | |
| "loss": 0.3669, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.06745229124491038, | |
| "learning_rate": 0.00012981205471780143, | |
| "loss": 0.3415, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.06091479450038953, | |
| "learning_rate": 0.00012949082256158905, | |
| "loss": 0.355, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.06056310643774801, | |
| "learning_rate": 0.00012916925675434686, | |
| "loss": 0.3484, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.06649681885382276, | |
| "learning_rate": 0.00012884736093418173, | |
| "loss": 0.4195, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.05713734605183639, | |
| "learning_rate": 0.00012852513874293413, | |
| "loss": 0.3376, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.05866468824290877, | |
| "learning_rate": 0.00012820259382613708, | |
| "loss": 0.3535, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.06625387999131105, | |
| "learning_rate": 0.00012787972983297472, | |
| "loss": 0.4006, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.062107888314909765, | |
| "learning_rate": 0.00012755655041624123, | |
| "loss": 0.3549, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.056918017856057566, | |
| "learning_rate": 0.0001272330592322993, | |
| "loss": 0.3125, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.061191777503052935, | |
| "learning_rate": 0.000126909259941039, | |
| "loss": 0.3308, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.06599845564206697, | |
| "learning_rate": 0.00012658515620583613, | |
| "loss": 0.3671, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.06906754300532772, | |
| "learning_rate": 0.00012626075169351099, | |
| "loss": 0.3345, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.061605000170190154, | |
| "learning_rate": 0.00012593605007428667, | |
| "loss": 0.3475, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.06361856715605814, | |
| "learning_rate": 0.00012561105502174768, | |
| "loss": 0.344, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.07037298925209551, | |
| "learning_rate": 0.00012528577021279842, | |
| "loss": 0.3306, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.06770728947984116, | |
| "learning_rate": 0.0001249601993276215, | |
| "loss": 0.3614, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.06304082600978436, | |
| "learning_rate": 0.000124634346049636, | |
| "loss": 0.3541, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.06918463182039399, | |
| "learning_rate": 0.0001243082140654561, | |
| "loss": 0.3494, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.06799726627925741, | |
| "learning_rate": 0.00012398180706484904, | |
| "loss": 0.3655, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.061333077983939055, | |
| "learning_rate": 0.00012365512874069353, | |
| "loss": 0.3223, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.06447411325490386, | |
| "learning_rate": 0.00012332818278893806, | |
| "loss": 0.3696, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.06531438346820978, | |
| "learning_rate": 0.00012300097290855887, | |
| "loss": 0.3723, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.05834884722862323, | |
| "learning_rate": 0.0001226735028015183, | |
| "loss": 0.3523, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.05981203969640804, | |
| "learning_rate": 0.00012234577617272282, | |
| "loss": 0.3563, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.06705791471556063, | |
| "learning_rate": 0.00012201779672998104, | |
| "loss": 0.3607, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.060886117167286924, | |
| "learning_rate": 0.00012168956818396191, | |
| "loss": 0.3664, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.06552628958318901, | |
| "learning_rate": 0.00012136109424815258, | |
| "loss": 0.399, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.06176377084932394, | |
| "learning_rate": 0.0001210323786388166, | |
| "loss": 0.3803, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.06236352212920891, | |
| "learning_rate": 0.00012070342507495166, | |
| "loss": 0.3579, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.059894498476758255, | |
| "learning_rate": 0.00012037423727824761, | |
| "loss": 0.338, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.059582607376293346, | |
| "learning_rate": 0.00012004481897304436, | |
| "loss": 0.3063, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.06115559901281837, | |
| "learning_rate": 0.00011971517388628973, | |
| "loss": 0.3472, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.06219559726103642, | |
| "learning_rate": 0.00011938530574749732, | |
| "loss": 0.35, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.05914045629263112, | |
| "learning_rate": 0.00011905521828870413, | |
| "loss": 0.3182, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.0640204493690558, | |
| "learning_rate": 0.00011872491524442873, | |
| "loss": 0.3544, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.06095682267272818, | |
| "learning_rate": 0.00011839440035162854, | |
| "loss": 0.3619, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.060373261171233164, | |
| "learning_rate": 0.00011806367734965789, | |
| "loss": 0.3621, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.05948639845594211, | |
| "learning_rate": 0.00011773274998022556, | |
| "loss": 0.3587, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.05818981172003461, | |
| "learning_rate": 0.00011740162198735256, | |
| "loss": 0.3648, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.06463525067128013, | |
| "learning_rate": 0.00011707029711732962, | |
| "loss": 0.3632, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.06189982012767264, | |
| "learning_rate": 0.00011673877911867486, | |
| "loss": 0.365, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.060798587097760766, | |
| "learning_rate": 0.00011640707174209147, | |
| "loss": 0.3433, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.058220684999650406, | |
| "learning_rate": 0.0001160751787404252, | |
| "loss": 0.3466, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.06333954768974756, | |
| "learning_rate": 0.00011574310386862188, | |
| "loss": 0.3253, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.06375174661422169, | |
| "learning_rate": 0.00011541085088368504, | |
| "loss": 0.3293, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.07332724400772853, | |
| "learning_rate": 0.0001150784235446332, | |
| "loss": 0.3667, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.07033713227184892, | |
| "learning_rate": 0.00011474582561245766, | |
| "loss": 0.3654, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.06249371325643619, | |
| "learning_rate": 0.00011441306085007956, | |
| "loss": 0.3362, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.06690129016227697, | |
| "learning_rate": 0.00011408013302230764, | |
| "loss": 0.3801, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.060589052706821266, | |
| "learning_rate": 0.00011374704589579553, | |
| "loss": 0.3511, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.061941615977283766, | |
| "learning_rate": 0.00011341380323899904, | |
| "loss": 0.3523, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.05962699983612403, | |
| "learning_rate": 0.00011308040882213363, | |
| "loss": 0.3778, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.0625935056205984, | |
| "learning_rate": 0.00011274686641713177, | |
| "loss": 0.3986, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.0676091683754652, | |
| "learning_rate": 0.00011241317979760023, | |
| "loss": 0.3816, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.058311539764333016, | |
| "learning_rate": 0.00011207935273877728, | |
| "loss": 0.329, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.06030825346428143, | |
| "learning_rate": 0.00011174538901749025, | |
| "loss": 0.3355, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.061034862517603754, | |
| "learning_rate": 0.00011141129241211246, | |
| "loss": 0.3662, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.06657581558823812, | |
| "learning_rate": 0.00011107706670252078, | |
| "loss": 0.369, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.05991184907653025, | |
| "learning_rate": 0.00011074271567005266, | |
| "loss": 0.3469, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.0569909398299895, | |
| "learning_rate": 0.0001104082430974634, | |
| "loss": 0.3202, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.060093078947263165, | |
| "learning_rate": 0.00011007365276888346, | |
| "loss": 0.3584, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.06663275055575502, | |
| "learning_rate": 0.00010973894846977548, | |
| "loss": 0.373, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.06389005307109276, | |
| "learning_rate": 0.00010940413398689153, | |
| "loss": 0.3694, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.05521415751516212, | |
| "learning_rate": 0.0001090692131082303, | |
| "loss": 0.2988, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.0640981682477927, | |
| "learning_rate": 0.00010873418962299419, | |
| "loss": 0.3888, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.05742561691444382, | |
| "learning_rate": 0.00010839906732154655, | |
| "loss": 0.3583, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.38707229495048523, | |
| "eval_runtime": 122.749, | |
| "eval_samples_per_second": 12.921, | |
| "eval_steps_per_second": 0.407, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.0594599847338834, | |
| "learning_rate": 0.00010806384999536856, | |
| "loss": 0.3431, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.06363275458284649, | |
| "learning_rate": 0.00010772854143701661, | |
| "loss": 0.3719, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.061977457734531484, | |
| "learning_rate": 0.00010739314544007916, | |
| "loss": 0.3313, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.06877022304907418, | |
| "learning_rate": 0.00010705766579913401, | |
| "loss": 0.3775, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.06511578416484967, | |
| "learning_rate": 0.00010672210630970527, | |
| "loss": 0.3426, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.06554582238630897, | |
| "learning_rate": 0.00010638647076822042, | |
| "loss": 0.3621, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.06409311173761505, | |
| "learning_rate": 0.00010605076297196735, | |
| "loss": 0.3355, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.06512296008019687, | |
| "learning_rate": 0.00010571498671905146, | |
| "loss": 0.3676, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.05680525015181284, | |
| "learning_rate": 0.00010537914580835264, | |
| "loss": 0.3156, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.06335940185809713, | |
| "learning_rate": 0.00010504324403948224, | |
| "loss": 0.3744, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.05695976176138704, | |
| "learning_rate": 0.00010470728521274026, | |
| "loss": 0.3528, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.05725873963647292, | |
| "learning_rate": 0.00010437127312907218, | |
| "loss": 0.3279, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.062372944627053596, | |
| "learning_rate": 0.00010403521159002597, | |
| "loss": 0.3342, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.055997259099946815, | |
| "learning_rate": 0.00010369910439770913, | |
| "loss": 0.3395, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.05467876935137051, | |
| "learning_rate": 0.00010336295535474578, | |
| "loss": 0.3281, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.06183986053143678, | |
| "learning_rate": 0.00010302676826423338, | |
| "loss": 0.3321, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.06112400264148152, | |
| "learning_rate": 0.00010269054692969994, | |
| "loss": 0.345, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.06681220007098458, | |
| "learning_rate": 0.0001023542951550609, | |
| "loss": 0.3573, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.06525114594815253, | |
| "learning_rate": 0.00010201801674457603, | |
| "loss": 0.3332, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.06788643313724864, | |
| "learning_rate": 0.00010168171550280648, | |
| "loss": 0.3496, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.06327555448309126, | |
| "learning_rate": 0.00010134539523457171, | |
| "loss": 0.3253, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.06553550248726209, | |
| "learning_rate": 0.00010100905974490651, | |
| "loss": 0.3693, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.06034606658577186, | |
| "learning_rate": 0.00010067271283901774, | |
| "loss": 0.3446, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.06485477922469712, | |
| "learning_rate": 0.0001003363583222415, | |
| "loss": 0.4044, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.06248215331143603, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3435, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.05901354177556271, | |
| "learning_rate": 9.96636416777585e-05, | |
| "loss": 0.3368, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.05811290132444931, | |
| "learning_rate": 9.932728716098227e-05, | |
| "loss": 0.332, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.06262940927076384, | |
| "learning_rate": 9.899094025509352e-05, | |
| "loss": 0.3511, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.06739587933545162, | |
| "learning_rate": 9.865460476542828e-05, | |
| "loss": 0.3592, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.058317263268630376, | |
| "learning_rate": 9.831828449719353e-05, | |
| "loss": 0.3687, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.06234669323178603, | |
| "learning_rate": 9.798198325542398e-05, | |
| "loss": 0.3506, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.065550219839229, | |
| "learning_rate": 9.764570484493915e-05, | |
| "loss": 0.3858, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.054920704070804634, | |
| "learning_rate": 9.730945307030008e-05, | |
| "loss": 0.3397, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.05536099801038294, | |
| "learning_rate": 9.697323173576667e-05, | |
| "loss": 0.3341, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.06171321738470161, | |
| "learning_rate": 9.663704464525427e-05, | |
| "loss": 0.3594, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.06163151270568915, | |
| "learning_rate": 9.630089560229088e-05, | |
| "loss": 0.3507, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.059013464840669896, | |
| "learning_rate": 9.596478840997407e-05, | |
| "loss": 0.3203, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.05875213990727573, | |
| "learning_rate": 9.562872687092783e-05, | |
| "loss": 0.3164, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.06349972522387039, | |
| "learning_rate": 9.529271478725976e-05, | |
| "loss": 0.3351, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.06252471613932024, | |
| "learning_rate": 9.495675596051777e-05, | |
| "loss": 0.3552, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.060220088386979724, | |
| "learning_rate": 9.462085419164739e-05, | |
| "loss": 0.336, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.059786132024399655, | |
| "learning_rate": 9.428501328094855e-05, | |
| "loss": 0.3337, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.06415374540934582, | |
| "learning_rate": 9.394923702803265e-05, | |
| "loss": 0.3817, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.06278123019119869, | |
| "learning_rate": 9.36135292317796e-05, | |
| "loss": 0.3407, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.05922532045468198, | |
| "learning_rate": 9.327789369029474e-05, | |
| "loss": 0.3465, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.06636442592391917, | |
| "learning_rate": 9.294233420086603e-05, | |
| "loss": 0.3466, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.05880482326140683, | |
| "learning_rate": 9.260685455992089e-05, | |
| "loss": 0.3302, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.06435055952782932, | |
| "learning_rate": 9.227145856298344e-05, | |
| "loss": 0.3564, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.060808885774335776, | |
| "learning_rate": 9.193615000463146e-05, | |
| "loss": 0.3448, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.059730051788861545, | |
| "learning_rate": 9.160093267845349e-05, | |
| "loss": 0.3348, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.07303786706716316, | |
| "learning_rate": 9.126581037700582e-05, | |
| "loss": 0.3606, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.0614073183577058, | |
| "learning_rate": 9.093078689176972e-05, | |
| "loss": 0.3316, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.06047394998441829, | |
| "learning_rate": 9.05958660131085e-05, | |
| "loss": 0.3803, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.0646755865950851, | |
| "learning_rate": 9.026105153022454e-05, | |
| "loss": 0.3522, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.06311438748645716, | |
| "learning_rate": 8.992634723111656e-05, | |
| "loss": 0.3303, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.061253857746570925, | |
| "learning_rate": 8.95917569025366e-05, | |
| "loss": 0.341, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.06127726410917572, | |
| "learning_rate": 8.925728432994735e-05, | |
| "loss": 0.3341, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.06595872043212175, | |
| "learning_rate": 8.892293329747922e-05, | |
| "loss": 0.3423, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.06593222993653503, | |
| "learning_rate": 8.858870758788753e-05, | |
| "loss": 0.3474, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.06387191311680056, | |
| "learning_rate": 8.82546109825098e-05, | |
| "loss": 0.322, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.05957966285552092, | |
| "learning_rate": 8.792064726122274e-05, | |
| "loss": 0.3464, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.058530278398802066, | |
| "learning_rate": 8.758682020239984e-05, | |
| "loss": 0.3277, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.0673682155555019, | |
| "learning_rate": 8.725313358286826e-05, | |
| "loss": 0.3545, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.06586813986027207, | |
| "learning_rate": 8.69195911778664e-05, | |
| "loss": 0.3514, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.0575609761357647, | |
| "learning_rate": 8.6586196761001e-05, | |
| "loss": 0.3551, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.06288173817107735, | |
| "learning_rate": 8.625295410420451e-05, | |
| "loss": 0.3692, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.06343728831213598, | |
| "learning_rate": 8.591986697769237e-05, | |
| "loss": 0.3365, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.06420189488365828, | |
| "learning_rate": 8.558693914992046e-05, | |
| "loss": 0.336, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.056807147842380334, | |
| "learning_rate": 8.525417438754236e-05, | |
| "loss": 0.3336, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.05578730141649025, | |
| "learning_rate": 8.492157645536678e-05, | |
| "loss": 0.2954, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.07170924375108692, | |
| "learning_rate": 8.4589149116315e-05, | |
| "loss": 0.3606, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.0660529661659269, | |
| "learning_rate": 8.425689613137813e-05, | |
| "loss": 0.3676, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.06272113318850159, | |
| "learning_rate": 8.392482125957481e-05, | |
| "loss": 0.3432, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.05879669607225473, | |
| "learning_rate": 8.359292825790859e-05, | |
| "loss": 0.3435, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.06663498333599296, | |
| "learning_rate": 8.32612208813252e-05, | |
| "loss": 0.3853, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.06238700293080394, | |
| "learning_rate": 8.292970288267042e-05, | |
| "loss": 0.345, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.060990511778978386, | |
| "learning_rate": 8.259837801264745e-05, | |
| "loss": 0.3578, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.060962754222013436, | |
| "learning_rate": 8.226725001977445e-05, | |
| "loss": 0.3226, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.05303135886543622, | |
| "learning_rate": 8.193632265034215e-05, | |
| "loss": 0.313, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.058130465267872945, | |
| "learning_rate": 8.160559964837149e-05, | |
| "loss": 0.3324, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.06151701878564283, | |
| "learning_rate": 8.127508475557129e-05, | |
| "loss": 0.3804, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.0619730509701243, | |
| "learning_rate": 8.094478171129588e-05, | |
| "loss": 0.3836, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.3798465132713318, | |
| "eval_runtime": 123.8964, | |
| "eval_samples_per_second": 12.801, | |
| "eval_steps_per_second": 0.404, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.06321550017648203, | |
| "learning_rate": 8.061469425250272e-05, | |
| "loss": 0.3889, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.06103355787091665, | |
| "learning_rate": 8.028482611371028e-05, | |
| "loss": 0.3477, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.0606094294854126, | |
| "learning_rate": 7.995518102695564e-05, | |
| "loss": 0.346, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.06214027708163376, | |
| "learning_rate": 7.96257627217524e-05, | |
| "loss": 0.3531, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.05837993552001579, | |
| "learning_rate": 7.929657492504837e-05, | |
| "loss": 0.3633, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.06024584422591306, | |
| "learning_rate": 7.896762136118342e-05, | |
| "loss": 0.3288, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.06180374119720931, | |
| "learning_rate": 7.863890575184744e-05, | |
| "loss": 0.3462, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.05876735558987968, | |
| "learning_rate": 7.831043181603814e-05, | |
| "loss": 0.3169, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.062251476058733345, | |
| "learning_rate": 7.798220327001897e-05, | |
| "loss": 0.3538, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.06549539753777106, | |
| "learning_rate": 7.765422382727719e-05, | |
| "loss": 0.3578, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.06272080651790497, | |
| "learning_rate": 7.73264971984817e-05, | |
| "loss": 0.3364, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.06974825361395898, | |
| "learning_rate": 7.699902709144114e-05, | |
| "loss": 0.3278, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.06798281496687084, | |
| "learning_rate": 7.667181721106196e-05, | |
| "loss": 0.3511, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.05840273358098389, | |
| "learning_rate": 7.634487125930648e-05, | |
| "loss": 0.3168, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.06223850382316937, | |
| "learning_rate": 7.601819293515099e-05, | |
| "loss": 0.3468, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.05888308573977418, | |
| "learning_rate": 7.569178593454392e-05, | |
| "loss": 0.327, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.058087614666314805, | |
| "learning_rate": 7.5365653950364e-05, | |
| "loss": 0.33, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.061717770967082225, | |
| "learning_rate": 7.503980067237852e-05, | |
| "loss": 0.3323, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.06217774183723521, | |
| "learning_rate": 7.471422978720161e-05, | |
| "loss": 0.3651, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.05870222739306866, | |
| "learning_rate": 7.438894497825235e-05, | |
| "loss": 0.3399, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.05687322622326134, | |
| "learning_rate": 7.406394992571338e-05, | |
| "loss": 0.3136, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.06266672650291139, | |
| "learning_rate": 7.373924830648904e-05, | |
| "loss": 0.3657, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.07015704812422112, | |
| "learning_rate": 7.341484379416389e-05, | |
| "loss": 0.3504, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.059274321138093646, | |
| "learning_rate": 7.309074005896103e-05, | |
| "loss": 0.3443, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.0599849101614325, | |
| "learning_rate": 7.276694076770072e-05, | |
| "loss": 0.3301, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.06234977967877989, | |
| "learning_rate": 7.244344958375881e-05, | |
| "loss": 0.334, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.06561602562326362, | |
| "learning_rate": 7.21202701670253e-05, | |
| "loss": 0.3723, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.061029071504559676, | |
| "learning_rate": 7.179740617386295e-05, | |
| "loss": 0.3535, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.06320803772301996, | |
| "learning_rate": 7.147486125706586e-05, | |
| "loss": 0.3685, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.06481282691817938, | |
| "learning_rate": 7.115263906581829e-05, | |
| "loss": 0.3769, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.06140550785247152, | |
| "learning_rate": 7.083074324565314e-05, | |
| "loss": 0.3323, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.059941283850795044, | |
| "learning_rate": 7.0509177438411e-05, | |
| "loss": 0.3129, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.06635328242041132, | |
| "learning_rate": 7.018794528219858e-05, | |
| "loss": 0.3652, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.0604245137679678, | |
| "learning_rate": 6.986705041134796e-05, | |
| "loss": 0.3534, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.05858937485572938, | |
| "learning_rate": 6.95464964563751e-05, | |
| "loss": 0.3665, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.05866990901698358, | |
| "learning_rate": 6.922628704393904e-05, | |
| "loss": 0.351, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.05335654688624973, | |
| "learning_rate": 6.890642579680071e-05, | |
| "loss": 0.2945, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.055762012367343995, | |
| "learning_rate": 6.858691633378202e-05, | |
| "loss": 0.3227, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.057901326369948214, | |
| "learning_rate": 6.826776226972488e-05, | |
| "loss": 0.3315, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.05917989098164541, | |
| "learning_rate": 6.794896721545032e-05, | |
| "loss": 0.3532, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.0635119156323232, | |
| "learning_rate": 6.763053477771761e-05, | |
| "loss": 0.3263, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.05979977836430764, | |
| "learning_rate": 6.73124685591835e-05, | |
| "loss": 0.328, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.06308136575035883, | |
| "learning_rate": 6.699477215836145e-05, | |
| "loss": 0.3335, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.059864185055728825, | |
| "learning_rate": 6.667744916958085e-05, | |
| "loss": 0.3422, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.061228567760106684, | |
| "learning_rate": 6.636050318294645e-05, | |
| "loss": 0.3519, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.06647632211670186, | |
| "learning_rate": 6.604393778429772e-05, | |
| "loss": 0.3703, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.06196628054761635, | |
| "learning_rate": 6.572775655516825e-05, | |
| "loss": 0.3481, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.05672599672624562, | |
| "learning_rate": 6.541196307274517e-05, | |
| "loss": 0.3361, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.05568541987089787, | |
| "learning_rate": 6.509656090982885e-05, | |
| "loss": 0.2913, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.057547945912044984, | |
| "learning_rate": 6.478155363479236e-05, | |
| "loss": 0.3287, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.061580396957803755, | |
| "learning_rate": 6.446694481154105e-05, | |
| "loss": 0.3436, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.062263148012036286, | |
| "learning_rate": 6.415273799947234e-05, | |
| "loss": 0.3312, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.06505591114139912, | |
| "learning_rate": 6.383893675343546e-05, | |
| "loss": 0.3882, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.06336870566924423, | |
| "learning_rate": 6.352554462369112e-05, | |
| "loss": 0.3366, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.06244165521010667, | |
| "learning_rate": 6.321256515587138e-05, | |
| "loss": 0.3617, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.061356755805084894, | |
| "learning_rate": 6.290000189093959e-05, | |
| "loss": 0.3404, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.061258301044691155, | |
| "learning_rate": 6.258785836515031e-05, | |
| "loss": 0.3524, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.057116405227860025, | |
| "learning_rate": 6.227613811000925e-05, | |
| "loss": 0.3049, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.0646667660492192, | |
| "learning_rate": 6.196484465223343e-05, | |
| "loss": 0.3482, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.0618872237624025, | |
| "learning_rate": 6.165398151371106e-05, | |
| "loss": 0.3616, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.059399306582954524, | |
| "learning_rate": 6.134355221146197e-05, | |
| "loss": 0.3033, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.05813715375393937, | |
| "learning_rate": 6.103356025759759e-05, | |
| "loss": 0.3122, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.059432746387249054, | |
| "learning_rate": 6.07240091592814e-05, | |
| "loss": 0.3652, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.06133581875571065, | |
| "learning_rate": 6.04149024186891e-05, | |
| "loss": 0.3744, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.0585758917138099, | |
| "learning_rate": 6.0106243532969077e-05, | |
| "loss": 0.3192, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.06000540673276071, | |
| "learning_rate": 5.9798035994202836e-05, | |
| "loss": 0.3085, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.0634090357845784, | |
| "learning_rate": 5.949028328936537e-05, | |
| "loss": 0.3749, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.061483947629424836, | |
| "learning_rate": 5.918298890028591e-05, | |
| "loss": 0.3466, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.058584609908248875, | |
| "learning_rate": 5.8876156303608365e-05, | |
| "loss": 0.3273, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.062283072414331016, | |
| "learning_rate": 5.8569788970752114e-05, | |
| "loss": 0.3266, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.06066237861202388, | |
| "learning_rate": 5.826389036787263e-05, | |
| "loss": 0.3348, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.05951486023366219, | |
| "learning_rate": 5.795846395582225e-05, | |
| "loss": 0.3262, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.058108538057701165, | |
| "learning_rate": 5.765351319011119e-05, | |
| "loss": 0.327, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.06502513578879043, | |
| "learning_rate": 5.734904152086828e-05, | |
| "loss": 0.324, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.062166422759693855, | |
| "learning_rate": 5.7045052392801937e-05, | |
| "loss": 0.3287, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.06134230767100337, | |
| "learning_rate": 5.6741549245161285e-05, | |
| "loss": 0.3313, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.06531107884439685, | |
| "learning_rate": 5.643853551169722e-05, | |
| "loss": 0.3628, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.06770835549403097, | |
| "learning_rate": 5.6136014620623525e-05, | |
| "loss": 0.3765, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.06685814250622198, | |
| "learning_rate": 5.5833989994578115e-05, | |
| "loss": 0.366, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.05925712177676217, | |
| "learning_rate": 5.5532465050584206e-05, | |
| "loss": 0.3043, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.06319108001837946, | |
| "learning_rate": 5.523144320001188e-05, | |
| "loss": 0.3333, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.06582708451272495, | |
| "learning_rate": 5.4930927848539256e-05, | |
| "loss": 0.3363, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.3752548396587372, | |
| "eval_runtime": 122.9572, | |
| "eval_samples_per_second": 12.899, | |
| "eval_steps_per_second": 0.407, | |
| "step": 656 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 984, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 328, | |
| "total_flos": 1.7323584218562822e+19, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |