| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 23, | |
| "global_step": 228, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0043859649122807015, | |
| "grad_norm": 0.048455942422151566, | |
| "learning_rate": 5e-06, | |
| "loss": 2.2365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0043859649122807015, | |
| "eval_loss": 2.2304763793945312, | |
| "eval_runtime": 216.9254, | |
| "eval_samples_per_second": 0.369, | |
| "eval_steps_per_second": 0.369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": 0.04205497354269028, | |
| "learning_rate": 1e-05, | |
| "loss": 2.2844, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013157894736842105, | |
| "grad_norm": 0.040102917701005936, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.3425, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 0.03933990001678467, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2561, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021929824561403508, | |
| "grad_norm": 0.042966291308403015, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.2957, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 0.04421572387218475, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3794, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03070175438596491, | |
| "grad_norm": 0.04840295761823654, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.4057, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 0.04756808653473854, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2825, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 0.04309004917740822, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.031, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "grad_norm": 0.0425834022462368, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3098, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04824561403508772, | |
| "grad_norm": 0.03927280381321907, | |
| "learning_rate": 4.99976636830244e-05, | |
| "loss": 2.3039, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 0.03671770170331001, | |
| "learning_rate": 4.999065521728665e-05, | |
| "loss": 2.2635, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05701754385964912, | |
| "grad_norm": 0.043874163180589676, | |
| "learning_rate": 4.9978976058253205e-05, | |
| "loss": 2.3794, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06140350877192982, | |
| "grad_norm": 0.031037230044603348, | |
| "learning_rate": 4.9962628631365625e-05, | |
| "loss": 2.3362, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 0.033785346895456314, | |
| "learning_rate": 4.9941616331536875e-05, | |
| "loss": 2.4863, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.038742709904909134, | |
| "learning_rate": 4.991594352244631e-05, | |
| "loss": 2.3597, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07456140350877193, | |
| "grad_norm": 0.04327031224966049, | |
| "learning_rate": 4.9885615535633464e-05, | |
| "loss": 2.3703, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 0.04216183349490166, | |
| "learning_rate": 4.9850638669390816e-05, | |
| "loss": 2.3208, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 0.04454097896814346, | |
| "learning_rate": 4.981102018745582e-05, | |
| "loss": 2.1064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "grad_norm": 0.041186701506376266, | |
| "learning_rate": 4.976676831750243e-05, | |
| "loss": 2.1267, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09210526315789473, | |
| "grad_norm": 0.033286575227975845, | |
| "learning_rate": 4.971789224943241e-05, | |
| "loss": 2.0027, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09649122807017543, | |
| "grad_norm": 0.031756095588207245, | |
| "learning_rate": 4.9664402133466884e-05, | |
| "loss": 2.2847, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10087719298245613, | |
| "grad_norm": 0.03505243733525276, | |
| "learning_rate": 4.960630907803838e-05, | |
| "loss": 2.045, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10087719298245613, | |
| "eval_loss": 2.201603651046753, | |
| "eval_runtime": 221.2761, | |
| "eval_samples_per_second": 0.362, | |
| "eval_steps_per_second": 0.362, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.03322993218898773, | |
| "learning_rate": 4.954362514748392e-05, | |
| "loss": 2.2481, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10964912280701754, | |
| "grad_norm": 0.029862001538276672, | |
| "learning_rate": 4.94763633595396e-05, | |
| "loss": 2.2409, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11403508771929824, | |
| "grad_norm": 0.032439861446619034, | |
| "learning_rate": 4.940453768263715e-05, | |
| "loss": 2.2443, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11842105263157894, | |
| "grad_norm": 0.02963525988161564, | |
| "learning_rate": 4.9328163033003086e-05, | |
| "loss": 2.2605, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12280701754385964, | |
| "grad_norm": 0.03317798301577568, | |
| "learning_rate": 4.9247255271560994e-05, | |
| "loss": 2.2619, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12719298245614036, | |
| "grad_norm": 0.03550229221582413, | |
| "learning_rate": 4.916183120063769e-05, | |
| "loss": 2.1695, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 0.03996920958161354, | |
| "learning_rate": 4.9071908560473775e-05, | |
| "loss": 2.1766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13596491228070176, | |
| "grad_norm": 0.032255735248327255, | |
| "learning_rate": 4.8977506025539554e-05, | |
| "loss": 2.2302, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.03136478736996651, | |
| "learning_rate": 4.8878643200656793e-05, | |
| "loss": 2.2832, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14473684210526316, | |
| "grad_norm": 0.03207270801067352, | |
| "learning_rate": 4.8775340616927357e-05, | |
| "loss": 2.3316, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14912280701754385, | |
| "grad_norm": 0.031349290162324905, | |
| "learning_rate": 4.866761972746946e-05, | |
| "loss": 2.1679, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15350877192982457, | |
| "grad_norm": 0.030217550694942474, | |
| "learning_rate": 4.855550290296248e-05, | |
| "loss": 2.292, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.032989416271448135, | |
| "learning_rate": 4.8439013427001076e-05, | |
| "loss": 2.2805, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16228070175438597, | |
| "grad_norm": 0.03313658758997917, | |
| "learning_rate": 4.8318175491259945e-05, | |
| "loss": 2.3498, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.03528057411313057, | |
| "learning_rate": 4.8193014190469815e-05, | |
| "loss": 2.0183, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17105263157894737, | |
| "grad_norm": 0.031257182359695435, | |
| "learning_rate": 4.8063555517205936e-05, | |
| "loss": 2.2793, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 0.0320710726082325, | |
| "learning_rate": 4.792982635649019e-05, | |
| "loss": 2.1969, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17982456140350878, | |
| "grad_norm": 0.03237050399184227, | |
| "learning_rate": 4.779185448020774e-05, | |
| "loss": 2.3167, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 0.033470962196588516, | |
| "learning_rate": 4.7649668541339635e-05, | |
| "loss": 2.2394, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18859649122807018, | |
| "grad_norm": 0.03281046077609062, | |
| "learning_rate": 4.750329806801234e-05, | |
| "loss": 2.2975, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19298245614035087, | |
| "grad_norm": 0.035084936767816544, | |
| "learning_rate": 4.735277345736555e-05, | |
| "loss": 2.1174, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 0.0374368391931057, | |
| "learning_rate": 4.7198125969239533e-05, | |
| "loss": 2.3721, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20175438596491227, | |
| "grad_norm": 0.031239116564393044, | |
| "learning_rate": 4.703938771968333e-05, | |
| "loss": 2.2614, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20175438596491227, | |
| "eval_loss": 2.186415910720825, | |
| "eval_runtime": 221.6088, | |
| "eval_samples_per_second": 0.361, | |
| "eval_steps_per_second": 0.361, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20614035087719298, | |
| "grad_norm": 0.03350961580872536, | |
| "learning_rate": 4.6876591674285145e-05, | |
| "loss": 2.3679, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.031444985419511795, | |
| "learning_rate": 4.6709771641326244e-05, | |
| "loss": 2.2733, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2149122807017544, | |
| "grad_norm": 0.03112543374300003, | |
| "learning_rate": 4.6538962264759954e-05, | |
| "loss": 2.1792, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21929824561403508, | |
| "grad_norm": 0.03221912682056427, | |
| "learning_rate": 4.636419901701705e-05, | |
| "loss": 2.2643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2236842105263158, | |
| "grad_norm": 0.031834062188863754, | |
| "learning_rate": 4.618551819163906e-05, | |
| "loss": 2.2191, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.22807017543859648, | |
| "grad_norm": 0.0330105684697628, | |
| "learning_rate": 4.600295689574114e-05, | |
| "loss": 2.1179, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.2324561403508772, | |
| "grad_norm": 0.03336255997419357, | |
| "learning_rate": 4.581655304230596e-05, | |
| "loss": 2.1939, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 0.034072939306497574, | |
| "learning_rate": 4.562634534231012e-05, | |
| "loss": 2.3282, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2412280701754386, | |
| "grad_norm": 0.036779358983039856, | |
| "learning_rate": 4.543237329668504e-05, | |
| "loss": 2.0628, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 0.03245358541607857, | |
| "learning_rate": 4.5234677188113664e-05, | |
| "loss": 2.229, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.032968707382678986, | |
| "learning_rate": 4.503329807266484e-05, | |
| "loss": 2.1244, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2543859649122807, | |
| "grad_norm": 0.03246884047985077, | |
| "learning_rate": 4.482827777126706e-05, | |
| "loss": 2.3287, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.25877192982456143, | |
| "grad_norm": 0.03295806050300598, | |
| "learning_rate": 4.461965886102351e-05, | |
| "loss": 2.313, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 0.03239140287041664, | |
| "learning_rate": 4.440748466636987e-05, | |
| "loss": 2.2437, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2675438596491228, | |
| "grad_norm": 0.03406047448515892, | |
| "learning_rate": 4.419179925007705e-05, | |
| "loss": 2.2797, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2719298245614035, | |
| "grad_norm": 0.03304027020931244, | |
| "learning_rate": 4.397264740410055e-05, | |
| "loss": 2.2423, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.27631578947368424, | |
| "grad_norm": 0.035411059856414795, | |
| "learning_rate": 4.3750074640278414e-05, | |
| "loss": 2.1787, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.03362572193145752, | |
| "learning_rate": 4.352412718087967e-05, | |
| "loss": 2.2556, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2850877192982456, | |
| "grad_norm": 0.035657159984111786, | |
| "learning_rate": 4.32948519490052e-05, | |
| "loss": 2.254, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 0.03446522727608681, | |
| "learning_rate": 4.306229655884312e-05, | |
| "loss": 2.1582, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.29385964912280704, | |
| "grad_norm": 0.03329275920987129, | |
| "learning_rate": 4.282650930578061e-05, | |
| "loss": 2.0713, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2982456140350877, | |
| "grad_norm": 0.036497630178928375, | |
| "learning_rate": 4.2587539156374295e-05, | |
| "loss": 2.2137, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3026315789473684, | |
| "grad_norm": 0.034867726266384125, | |
| "learning_rate": 4.234543573818121e-05, | |
| "loss": 2.3029, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3026315789473684, | |
| "eval_loss": 2.177396059036255, | |
| "eval_runtime": 221.9078, | |
| "eval_samples_per_second": 0.361, | |
| "eval_steps_per_second": 0.361, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.30701754385964913, | |
| "grad_norm": 0.03490519896149635, | |
| "learning_rate": 4.210024932945254e-05, | |
| "loss": 2.2167, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.31140350877192985, | |
| "grad_norm": 0.03391524776816368, | |
| "learning_rate": 4.1852030848692184e-05, | |
| "loss": 2.2559, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.0409424863755703, | |
| "learning_rate": 4.160083184408238e-05, | |
| "loss": 2.1958, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3201754385964912, | |
| "grad_norm": 0.034918639808893204, | |
| "learning_rate": 4.134670448277859e-05, | |
| "loss": 2.179, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.32456140350877194, | |
| "grad_norm": 0.035045966506004333, | |
| "learning_rate": 4.1089701540075746e-05, | |
| "loss": 2.2114, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": 0.03757881000638008, | |
| "learning_rate": 4.0829876388448335e-05, | |
| "loss": 2.2123, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.03646866977214813, | |
| "learning_rate": 4.056728298646634e-05, | |
| "loss": 2.2624, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.33771929824561403, | |
| "grad_norm": 0.037842828780412674, | |
| "learning_rate": 4.0301975867589556e-05, | |
| "loss": 2.1933, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 0.04188080504536629, | |
| "learning_rate": 4.0034010128842484e-05, | |
| "loss": 2.2684, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.34649122807017546, | |
| "grad_norm": 0.03659341111779213, | |
| "learning_rate": 3.9763441419372184e-05, | |
| "loss": 2.3599, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 0.035152070224285126, | |
| "learning_rate": 3.949032592889144e-05, | |
| "loss": 2.2093, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.35526315789473684, | |
| "grad_norm": 0.04070575535297394, | |
| "learning_rate": 3.9214720376009754e-05, | |
| "loss": 2.2219, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.35964912280701755, | |
| "grad_norm": 0.03422649949789047, | |
| "learning_rate": 3.893668199645438e-05, | |
| "loss": 2.3257, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.36403508771929827, | |
| "grad_norm": 0.03752286732196808, | |
| "learning_rate": 3.865626853118409e-05, | |
| "loss": 2.3327, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 0.03680169954895973, | |
| "learning_rate": 3.8373538214397895e-05, | |
| "loss": 2.0797, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.37280701754385964, | |
| "grad_norm": 0.03573755919933319, | |
| "learning_rate": 3.808854976144147e-05, | |
| "loss": 2.3888, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.37719298245614036, | |
| "grad_norm": 0.03731301426887512, | |
| "learning_rate": 3.7801362356613505e-05, | |
| "loss": 2.2343, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.3815789473684211, | |
| "grad_norm": 0.035398200154304504, | |
| "learning_rate": 3.751203564087484e-05, | |
| "loss": 2.3215, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 0.03954707086086273, | |
| "learning_rate": 3.722062969946254e-05, | |
| "loss": 2.0028, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.39035087719298245, | |
| "grad_norm": 0.03811151161789894, | |
| "learning_rate": 3.6927205049412e-05, | |
| "loss": 2.2696, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 0.03738315403461456, | |
| "learning_rate": 3.663182262698905e-05, | |
| "loss": 2.2021, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3991228070175439, | |
| "grad_norm": 0.03729921206831932, | |
| "learning_rate": 3.63345437750353e-05, | |
| "loss": 2.287, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.40350877192982454, | |
| "grad_norm": 0.037670135498046875, | |
| "learning_rate": 3.6035430230228806e-05, | |
| "loss": 2.2515, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.40350877192982454, | |
| "eval_loss": 2.171975612640381, | |
| "eval_runtime": 221.318, | |
| "eval_samples_per_second": 0.361, | |
| "eval_steps_per_second": 0.361, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.40789473684210525, | |
| "grad_norm": 0.039739374071359634, | |
| "learning_rate": 3.573454411026311e-05, | |
| "loss": 2.4027, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.41228070175438597, | |
| "grad_norm": 0.036624688655138016, | |
| "learning_rate": 3.5431947900947086e-05, | |
| "loss": 2.2523, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 0.03838134929537773, | |
| "learning_rate": 3.512770444322836e-05, | |
| "loss": 2.0867, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.04036020487546921, | |
| "learning_rate": 3.4821876920142896e-05, | |
| "loss": 2.0927, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.42543859649122806, | |
| "grad_norm": 0.03726624324917793, | |
| "learning_rate": 3.4514528843693726e-05, | |
| "loss": 2.1346, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.4298245614035088, | |
| "grad_norm": 0.040338750928640366, | |
| "learning_rate": 3.4205724041661135e-05, | |
| "loss": 2.279, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4342105263157895, | |
| "grad_norm": 0.03956661745905876, | |
| "learning_rate": 3.389552664434746e-05, | |
| "loss": 2.2589, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "grad_norm": 0.040090542286634445, | |
| "learning_rate": 3.358400107125892e-05, | |
| "loss": 2.2241, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44298245614035087, | |
| "grad_norm": 0.038386132568120956, | |
| "learning_rate": 3.327121201772752e-05, | |
| "loss": 2.1874, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 0.03814141824841499, | |
| "learning_rate": 3.2957224441475506e-05, | |
| "loss": 2.1831, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4517543859649123, | |
| "grad_norm": 0.03928579390048981, | |
| "learning_rate": 3.264210354912551e-05, | |
| "loss": 2.2175, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 0.04026209935545921, | |
| "learning_rate": 3.232591478265887e-05, | |
| "loss": 2.2436, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": 0.0390322245657444, | |
| "learning_rate": 3.2008723805825174e-05, | |
| "loss": 2.1753, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4649122807017544, | |
| "grad_norm": 0.038063932210206985, | |
| "learning_rate": 3.169059649050561e-05, | |
| "loss": 2.3489, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.4692982456140351, | |
| "grad_norm": 0.03953162208199501, | |
| "learning_rate": 3.137159890303329e-05, | |
| "loss": 2.3278, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 0.03997305780649185, | |
| "learning_rate": 3.1051797290472966e-05, | |
| "loss": 2.0943, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.4780701754385965, | |
| "grad_norm": 0.03778674080967903, | |
| "learning_rate": 3.073125806686343e-05, | |
| "loss": 2.384, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.4824561403508772, | |
| "grad_norm": 0.038230303674936295, | |
| "learning_rate": 3.0410047799425095e-05, | |
| "loss": 2.2288, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4868421052631579, | |
| "grad_norm": 0.03927282989025116, | |
| "learning_rate": 3.0088233194735756e-05, | |
| "loss": 2.3347, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 0.03646494820713997, | |
| "learning_rate": 2.9765881084877567e-05, | |
| "loss": 2.1844, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.4956140350877193, | |
| "grad_norm": 0.040188323706388474, | |
| "learning_rate": 2.9443058413557746e-05, | |
| "loss": 2.2538, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.03920644521713257, | |
| "learning_rate": 2.9119832222206262e-05, | |
| "loss": 2.2415, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5043859649122807, | |
| "grad_norm": 0.037783924490213394, | |
| "learning_rate": 2.8796269636053147e-05, | |
| "loss": 2.2141, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5043859649122807, | |
| "eval_loss": 2.168910026550293, | |
| "eval_runtime": 222.2719, | |
| "eval_samples_per_second": 0.36, | |
| "eval_steps_per_second": 0.36, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5087719298245614, | |
| "grad_norm": 0.041254762560129166, | |
| "learning_rate": 2.8472437850188416e-05, | |
| "loss": 2.1322, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5131578947368421, | |
| "grad_norm": 0.04002700001001358, | |
| "learning_rate": 2.8148404115607496e-05, | |
| "loss": 2.1348, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5175438596491229, | |
| "grad_norm": 0.04018218815326691, | |
| "learning_rate": 2.7824235725245042e-05, | |
| "loss": 2.1397, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5219298245614035, | |
| "grad_norm": 0.03979986160993576, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 2.1661, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.03741481155157089, | |
| "learning_rate": 2.7175764274754967e-05, | |
| "loss": 2.0629, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5307017543859649, | |
| "grad_norm": 0.04032299295067787, | |
| "learning_rate": 2.685159588439251e-05, | |
| "loss": 2.2347, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5350877192982456, | |
| "grad_norm": 0.042785074561834335, | |
| "learning_rate": 2.6527562149811586e-05, | |
| "loss": 2.1792, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5394736842105263, | |
| "grad_norm": 0.040340930223464966, | |
| "learning_rate": 2.6203730363946855e-05, | |
| "loss": 2.4248, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.543859649122807, | |
| "grad_norm": 0.04094316065311432, | |
| "learning_rate": 2.5880167777793746e-05, | |
| "loss": 2.1152, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5482456140350878, | |
| "grad_norm": 0.04053365811705589, | |
| "learning_rate": 2.5556941586442263e-05, | |
| "loss": 2.247, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5526315789473685, | |
| "grad_norm": 0.04444659873843193, | |
| "learning_rate": 2.523411891512244e-05, | |
| "loss": 2.0332, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5570175438596491, | |
| "grad_norm": 0.04211907461285591, | |
| "learning_rate": 2.4911766805264246e-05, | |
| "loss": 2.2871, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.039295535534620285, | |
| "learning_rate": 2.458995220057491e-05, | |
| "loss": 2.0771, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5657894736842105, | |
| "grad_norm": 0.04139047861099243, | |
| "learning_rate": 2.426874193313657e-05, | |
| "loss": 2.3538, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5701754385964912, | |
| "grad_norm": 0.04222600907087326, | |
| "learning_rate": 2.394820270952704e-05, | |
| "loss": 2.2202, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5745614035087719, | |
| "grad_norm": 0.04055177420377731, | |
| "learning_rate": 2.3628401096966717e-05, | |
| "loss": 2.1976, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 0.040084317326545715, | |
| "learning_rate": 2.3309403509494393e-05, | |
| "loss": 2.1939, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5833333333333334, | |
| "grad_norm": 0.04429348185658455, | |
| "learning_rate": 2.2991276194174838e-05, | |
| "loss": 2.367, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.5877192982456141, | |
| "grad_norm": 0.04366152733564377, | |
| "learning_rate": 2.267408521734113e-05, | |
| "loss": 2.2848, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.5921052631578947, | |
| "grad_norm": 0.04157907888293266, | |
| "learning_rate": 2.23578964508745e-05, | |
| "loss": 2.3166, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 0.045395560562610626, | |
| "learning_rate": 2.2042775558524503e-05, | |
| "loss": 2.2021, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6008771929824561, | |
| "grad_norm": 0.04491296038031578, | |
| "learning_rate": 2.1728787982272493e-05, | |
| "loss": 2.1836, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "grad_norm": 0.04048113152384758, | |
| "learning_rate": 2.141599892874107e-05, | |
| "loss": 2.2104, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "eval_loss": 2.166778087615967, | |
| "eval_runtime": 219.3317, | |
| "eval_samples_per_second": 0.365, | |
| "eval_steps_per_second": 0.365, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6096491228070176, | |
| "grad_norm": 0.04249032586812973, | |
| "learning_rate": 2.1104473355652543e-05, | |
| "loss": 2.1101, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6140350877192983, | |
| "grad_norm": 0.0415317639708519, | |
| "learning_rate": 2.079427595833887e-05, | |
| "loss": 2.2474, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.618421052631579, | |
| "grad_norm": 0.04562680423259735, | |
| "learning_rate": 2.0485471156306286e-05, | |
| "loss": 2.278, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6228070175438597, | |
| "grad_norm": 0.04500352591276169, | |
| "learning_rate": 2.017812307985711e-05, | |
| "loss": 2.1393, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6271929824561403, | |
| "grad_norm": 0.03962068632245064, | |
| "learning_rate": 1.9872295556771652e-05, | |
| "loss": 2.1795, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.044582221657037735, | |
| "learning_rate": 1.9568052099052912e-05, | |
| "loss": 2.0925, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6359649122807017, | |
| "grad_norm": 0.04261946305632591, | |
| "learning_rate": 1.9265455889736893e-05, | |
| "loss": 2.265, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6403508771929824, | |
| "grad_norm": 0.04217216372489929, | |
| "learning_rate": 1.89645697697712e-05, | |
| "loss": 1.9885, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6447368421052632, | |
| "grad_norm": 0.04785408079624176, | |
| "learning_rate": 1.8665456224964706e-05, | |
| "loss": 1.947, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6491228070175439, | |
| "grad_norm": 0.04387756809592247, | |
| "learning_rate": 1.8368177373010954e-05, | |
| "loss": 2.2214, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.6535087719298246, | |
| "grad_norm": 0.04180494323372841, | |
| "learning_rate": 1.807279495058801e-05, | |
| "loss": 2.2836, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 0.043545372784137726, | |
| "learning_rate": 1.7779370300537463e-05, | |
| "loss": 2.2564, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6622807017543859, | |
| "grad_norm": 0.04130139574408531, | |
| "learning_rate": 1.7487964359125172e-05, | |
| "loss": 2.2876, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.04039989784359932, | |
| "learning_rate": 1.71986376433865e-05, | |
| "loss": 2.2178, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6710526315789473, | |
| "grad_norm": 0.044490255415439606, | |
| "learning_rate": 1.6911450238558544e-05, | |
| "loss": 2.2864, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6754385964912281, | |
| "grad_norm": 0.044686999171972275, | |
| "learning_rate": 1.6626461785602114e-05, | |
| "loss": 2.2928, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.6798245614035088, | |
| "grad_norm": 0.04130301997065544, | |
| "learning_rate": 1.634373146881592e-05, | |
| "loss": 2.3054, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 0.04189175367355347, | |
| "learning_rate": 1.606331800354563e-05, | |
| "loss": 2.2446, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6885964912280702, | |
| "grad_norm": 0.04377526417374611, | |
| "learning_rate": 1.578527962399025e-05, | |
| "loss": 2.3201, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.6929824561403509, | |
| "grad_norm": 0.043845128268003464, | |
| "learning_rate": 1.550967407110856e-05, | |
| "loss": 2.2915, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.6973684210526315, | |
| "grad_norm": 0.040581248700618744, | |
| "learning_rate": 1.5236558580627818e-05, | |
| "loss": 2.2255, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.043707672506570816, | |
| "learning_rate": 1.4965989871157523e-05, | |
| "loss": 2.1187, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.706140350877193, | |
| "grad_norm": 0.04184063524007797, | |
| "learning_rate": 1.4698024132410453e-05, | |
| "loss": 2.0291, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.706140350877193, | |
| "eval_loss": 2.165196418762207, | |
| "eval_runtime": 218.8267, | |
| "eval_samples_per_second": 0.366, | |
| "eval_steps_per_second": 0.366, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7105263157894737, | |
| "grad_norm": 0.045050691813230515, | |
| "learning_rate": 1.443271701353367e-05, | |
| "loss": 2.0026, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7149122807017544, | |
| "grad_norm": 0.04285702109336853, | |
| "learning_rate": 1.4170123611551672e-05, | |
| "loss": 2.0858, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.7192982456140351, | |
| "grad_norm": 0.04647679999470711, | |
| "learning_rate": 1.391029845992426e-05, | |
| "loss": 2.2815, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7236842105263158, | |
| "grad_norm": 0.04479655995965004, | |
| "learning_rate": 1.3653295517221414e-05, | |
| "loss": 2.2331, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7280701754385965, | |
| "grad_norm": 0.04288294166326523, | |
| "learning_rate": 1.3399168155917618e-05, | |
| "loss": 2.2517, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.7324561403508771, | |
| "grad_norm": 0.040452826768159866, | |
| "learning_rate": 1.3147969151307832e-05, | |
| "loss": 2.0543, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.041480351239442825, | |
| "learning_rate": 1.2899750670547473e-05, | |
| "loss": 2.184, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7412280701754386, | |
| "grad_norm": 0.04393285885453224, | |
| "learning_rate": 1.2654564261818803e-05, | |
| "loss": 2.265, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.7456140350877193, | |
| "grad_norm": 0.04307292774319649, | |
| "learning_rate": 1.2412460843625707e-05, | |
| "loss": 2.0731, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.04109564423561096, | |
| "learning_rate": 1.2173490694219395e-05, | |
| "loss": 2.3338, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7543859649122807, | |
| "grad_norm": 0.04446297138929367, | |
| "learning_rate": 1.1937703441156884e-05, | |
| "loss": 2.183, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.7587719298245614, | |
| "grad_norm": 0.04082484543323517, | |
| "learning_rate": 1.170514805099481e-05, | |
| "loss": 2.1772, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.7631578947368421, | |
| "grad_norm": 0.04336797446012497, | |
| "learning_rate": 1.1475872819120328e-05, | |
| "loss": 2.3144, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7675438596491229, | |
| "grad_norm": 0.0429406575858593, | |
| "learning_rate": 1.1249925359721588e-05, | |
| "loss": 2.1344, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 0.04397052899003029, | |
| "learning_rate": 1.1027352595899456e-05, | |
| "loss": 2.1452, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.7763157894736842, | |
| "grad_norm": 0.04313274472951889, | |
| "learning_rate": 1.0808200749922962e-05, | |
| "loss": 2.2194, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.7807017543859649, | |
| "grad_norm": 0.04726535826921463, | |
| "learning_rate": 1.0592515333630128e-05, | |
| "loss": 1.9798, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.7850877192982456, | |
| "grad_norm": 0.04374031722545624, | |
| "learning_rate": 1.038034113897649e-05, | |
| "loss": 2.0765, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.04320162534713745, | |
| "learning_rate": 1.0171722228732938e-05, | |
| "loss": 2.1935, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.793859649122807, | |
| "grad_norm": 0.046704404056072235, | |
| "learning_rate": 9.966701927335172e-06, | |
| "loss": 2.18, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.7982456140350878, | |
| "grad_norm": 0.04343089088797569, | |
| "learning_rate": 9.765322811886333e-06, | |
| "loss": 2.1722, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.8026315789473685, | |
| "grad_norm": 0.04284314066171646, | |
| "learning_rate": 9.567626703314955e-06, | |
| "loss": 2.2947, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "grad_norm": 0.04306797310709953, | |
| "learning_rate": 9.373654657689884e-06, | |
| "loss": 2.3129, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "eval_loss": 2.1641502380371094, | |
| "eval_runtime": 219.0202, | |
| "eval_samples_per_second": 0.365, | |
| "eval_steps_per_second": 0.365, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8114035087719298, | |
| "grad_norm": 0.04292619228363037, | |
| "learning_rate": 9.183446957694048e-06, | |
| "loss": 2.225, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8157894736842105, | |
| "grad_norm": 0.04302488639950752, | |
| "learning_rate": 8.997043104258856e-06, | |
| "loss": 2.0675, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8201754385964912, | |
| "grad_norm": 0.04218915104866028, | |
| "learning_rate": 8.814481808360945e-06, | |
| "loss": 2.1778, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8245614035087719, | |
| "grad_norm": 0.04348418116569519, | |
| "learning_rate": 8.635800982982958e-06, | |
| "loss": 2.2598, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.8289473684210527, | |
| "grad_norm": 0.04379533231258392, | |
| "learning_rate": 8.461037735240047e-06, | |
| "loss": 2.223, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.04641556367278099, | |
| "learning_rate": 8.290228358673758e-06, | |
| "loss": 2.1633, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8377192982456141, | |
| "grad_norm": 0.04623427614569664, | |
| "learning_rate": 8.123408325714857e-06, | |
| "loss": 2.2546, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.04348750412464142, | |
| "learning_rate": 7.960612280316673e-06, | |
| "loss": 2.2283, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.8464912280701754, | |
| "grad_norm": 0.04299633204936981, | |
| "learning_rate": 7.801874030760472e-06, | |
| "loss": 2.2155, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.8508771929824561, | |
| "grad_norm": 0.04249183461070061, | |
| "learning_rate": 7.647226542634454e-06, | |
| "loss": 2.2647, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.8552631578947368, | |
| "grad_norm": 0.04467320442199707, | |
| "learning_rate": 7.49670193198766e-06, | |
| "loss": 2.3202, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8596491228070176, | |
| "grad_norm": 0.04538441821932793, | |
| "learning_rate": 7.350331458660367e-06, | |
| "loss": 2.0542, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.8640350877192983, | |
| "grad_norm": 0.04282210022211075, | |
| "learning_rate": 7.208145519792266e-06, | |
| "loss": 2.3344, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.868421052631579, | |
| "grad_norm": 0.042627353221178055, | |
| "learning_rate": 7.0701736435098155e-06, | |
| "loss": 2.3739, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.8728070175438597, | |
| "grad_norm": 0.04885130748152733, | |
| "learning_rate": 6.936444482794065e-06, | |
| "loss": 2.2614, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.04192091524600983, | |
| "learning_rate": 6.806985809530189e-06, | |
| "loss": 2.0821, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.881578947368421, | |
| "grad_norm": 0.04542316868901253, | |
| "learning_rate": 6.6818245087400574e-06, | |
| "loss": 2.3226, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.8859649122807017, | |
| "grad_norm": 0.0446937195956707, | |
| "learning_rate": 6.56098657299893e-06, | |
| "loss": 2.342, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.8903508771929824, | |
| "grad_norm": 0.04320209473371506, | |
| "learning_rate": 6.444497097037532e-06, | |
| "loss": 2.1945, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 0.04684532806277275, | |
| "learning_rate": 6.332380272530536e-06, | |
| "loss": 2.2744, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.8991228070175439, | |
| "grad_norm": 0.04657423868775368, | |
| "learning_rate": 6.224659383072649e-06, | |
| "loss": 2.1249, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.9035087719298246, | |
| "grad_norm": 0.04765097796916962, | |
| "learning_rate": 6.1213567993432085e-06, | |
| "loss": 2.1456, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.9078947368421053, | |
| "grad_norm": 0.047186579555273056, | |
| "learning_rate": 6.022493974460447e-06, | |
| "loss": 2.2972, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.9078947368421053, | |
| "eval_loss": 2.163572311401367, | |
| "eval_runtime": 218.9467, | |
| "eval_samples_per_second": 0.365, | |
| "eval_steps_per_second": 0.365, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 0.04384492337703705, | |
| "learning_rate": 5.928091439526226e-06, | |
| "loss": 2.2382, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.9166666666666666, | |
| "grad_norm": 0.044699691236019135, | |
| "learning_rate": 5.838168799362318e-06, | |
| "loss": 2.1484, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 0.043975383043289185, | |
| "learning_rate": 5.752744728439006e-06, | |
| "loss": 2.208, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9254385964912281, | |
| "grad_norm": 0.0446508526802063, | |
| "learning_rate": 5.671836966996916e-06, | |
| "loss": 2.0749, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.9298245614035088, | |
| "grad_norm": 0.04373237490653992, | |
| "learning_rate": 5.595462317362849e-06, | |
| "loss": 2.372, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.9342105263157895, | |
| "grad_norm": 0.04464460536837578, | |
| "learning_rate": 5.523636640460405e-06, | |
| "loss": 2.2327, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.9385964912280702, | |
| "grad_norm": 0.05024990811944008, | |
| "learning_rate": 5.456374852516083e-06, | |
| "loss": 2.1838, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.9429824561403509, | |
| "grad_norm": 0.044989317655563354, | |
| "learning_rate": 5.3936909219616205e-06, | |
| "loss": 2.373, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.04446178302168846, | |
| "learning_rate": 5.335597866533116e-06, | |
| "loss": 2.0206, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.9517543859649122, | |
| "grad_norm": 0.0473959781229496, | |
| "learning_rate": 5.282107750567588e-06, | |
| "loss": 2.0744, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.956140350877193, | |
| "grad_norm": 0.046764299273490906, | |
| "learning_rate": 5.233231682497572e-06, | |
| "loss": 2.0287, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.9605263157894737, | |
| "grad_norm": 0.042999010533094406, | |
| "learning_rate": 5.1889798125441795e-06, | |
| "loss": 2.3255, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.9649122807017544, | |
| "grad_norm": 0.04476455599069595, | |
| "learning_rate": 5.149361330609188e-06, | |
| "loss": 2.3038, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9692982456140351, | |
| "grad_norm": 0.04403753951191902, | |
| "learning_rate": 5.114384464366541e-06, | |
| "loss": 2.2972, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.9736842105263158, | |
| "grad_norm": 0.04389164224267006, | |
| "learning_rate": 5.084056477553695e-06, | |
| "loss": 2.2914, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.9780701754385965, | |
| "grad_norm": 0.044895585626363754, | |
| "learning_rate": 5.058383668463131e-06, | |
| "loss": 2.2486, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.04405970871448517, | |
| "learning_rate": 5.0373713686343774e-06, | |
| "loss": 2.1718, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.9868421052631579, | |
| "grad_norm": 0.04554829001426697, | |
| "learning_rate": 5.021023941746794e-06, | |
| "loss": 2.1137, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9912280701754386, | |
| "grad_norm": 0.041737962514162064, | |
| "learning_rate": 5.009344782713349e-06, | |
| "loss": 2.2621, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.9956140350877193, | |
| "grad_norm": 0.04512747749686241, | |
| "learning_rate": 5.0023363169756045e-06, | |
| "loss": 2.3551, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.04331080988049507, | |
| "learning_rate": 5e-06, | |
| "loss": 2.2325, | |
| "step": 228 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 228, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 23, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2790575338430136e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |