| { | |
| "best_metric": 0.2740105390548706, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.06143764079459349, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00040958427196395656, | |
| "grad_norm": 5.032626152038574, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 4.0382, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040958427196395656, | |
| "eval_loss": 5.339817047119141, | |
| "eval_runtime": 6.9343, | |
| "eval_samples_per_second": 7.21, | |
| "eval_steps_per_second": 1.009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008191685439279131, | |
| "grad_norm": 5.231523036956787, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.3188, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012287528158918697, | |
| "grad_norm": 5.883774280548096, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016383370878558263, | |
| "grad_norm": 4.877133846282959, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 3.6963, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020479213598197828, | |
| "grad_norm": 7.621021747589111, | |
| "learning_rate": 0.00015, | |
| "loss": 4.4737, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0024575056317837395, | |
| "grad_norm": 7.185449123382568, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 3.2811, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028670899037476962, | |
| "grad_norm": 6.503012180328369, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.059, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0032766741757116525, | |
| "grad_norm": 4.8399810791015625, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.9927, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0036862584476756092, | |
| "grad_norm": 11.872732162475586, | |
| "learning_rate": 0.00027, | |
| "loss": 1.1176, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0040958427196395655, | |
| "grad_norm": 5.976637363433838, | |
| "learning_rate": 0.0003, | |
| "loss": 0.944, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004505426991603522, | |
| "grad_norm": 4.395268440246582, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.8581, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004915011263567479, | |
| "grad_norm": 3.741900682449341, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.7349, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005324595535531436, | |
| "grad_norm": 2.950590133666992, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.4204, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0057341798074953924, | |
| "grad_norm": 2.196455955505371, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.3694, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006143764079459349, | |
| "grad_norm": 2.7689871788024902, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.4119, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006553348351423305, | |
| "grad_norm": 3.9493329524993896, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.6404, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006962932623387262, | |
| "grad_norm": 2.9368627071380615, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.4964, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0073725168953512185, | |
| "grad_norm": 2.873953342437744, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.467, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007782101167315175, | |
| "grad_norm": 4.046209812164307, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.591, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008191685439279131, | |
| "grad_norm": 2.7434680461883545, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.5402, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008601269711243089, | |
| "grad_norm": 2.1096296310424805, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.3771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009010853983207045, | |
| "grad_norm": 1.6251838207244873, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.3872, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009420438255171002, | |
| "grad_norm": 2.345319986343384, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.4481, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009830022527134958, | |
| "grad_norm": 2.1055288314819336, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.4142, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010239606799098914, | |
| "grad_norm": 2.2987918853759766, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.4101, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010239606799098914, | |
| "eval_loss": 0.391013503074646, | |
| "eval_runtime": 7.0436, | |
| "eval_samples_per_second": 7.099, | |
| "eval_steps_per_second": 0.994, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010649191071062871, | |
| "grad_norm": 1.5232685804367065, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.3703, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011058775343026827, | |
| "grad_norm": 2.0562989711761475, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.3834, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011468359614990785, | |
| "grad_norm": 1.3030779361724854, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.2305, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01187794388695474, | |
| "grad_norm": 1.9921797513961792, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.3723, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.012287528158918698, | |
| "grad_norm": 1.2121187448501587, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012697112430882654, | |
| "grad_norm": 2.0275485515594482, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.4247, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01310669670284661, | |
| "grad_norm": 1.6529933214187622, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.2814, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013516280974810568, | |
| "grad_norm": 1.8799407482147217, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.3434, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.013925865246774524, | |
| "grad_norm": 1.9642513990402222, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.4427, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014335449518738481, | |
| "grad_norm": 1.1001381874084473, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.3256, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014745033790702437, | |
| "grad_norm": 0.934917688369751, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.2164, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015154618062666393, | |
| "grad_norm": 1.091238260269165, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.3009, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01556420233463035, | |
| "grad_norm": 1.2641563415527344, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.289, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.015973786606594306, | |
| "grad_norm": 1.184543251991272, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.3097, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016383370878558262, | |
| "grad_norm": 1.7306755781173706, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.2913, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01679295515052222, | |
| "grad_norm": 1.6884584426879883, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.3326, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.017202539422486177, | |
| "grad_norm": 1.2175815105438232, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.3437, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.017612123694450133, | |
| "grad_norm": 1.8150399923324585, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.3872, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01802170796641409, | |
| "grad_norm": 1.13820219039917, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.2204, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018431292238378045, | |
| "grad_norm": 1.012037992477417, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.2499, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018840876510342004, | |
| "grad_norm": 1.1927300691604614, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.2392, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01925046078230596, | |
| "grad_norm": 1.3892017602920532, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.3714, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.019660045054269916, | |
| "grad_norm": 1.2792326211929321, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.3209, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.020069629326233872, | |
| "grad_norm": 0.9809417128562927, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.2435, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.020479213598197828, | |
| "grad_norm": 1.2792021036148071, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.276, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020479213598197828, | |
| "eval_loss": 0.3750147223472595, | |
| "eval_runtime": 7.0572, | |
| "eval_samples_per_second": 7.085, | |
| "eval_steps_per_second": 0.992, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020888797870161787, | |
| "grad_norm": 1.9061239957809448, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.3689, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.021298382142125743, | |
| "grad_norm": 1.625785231590271, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.3729, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0217079664140897, | |
| "grad_norm": 1.5701191425323486, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.3479, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.022117550686053655, | |
| "grad_norm": 1.1037153005599976, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.2747, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.02252713495801761, | |
| "grad_norm": 1.2575494050979614, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.2879, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02293671922998157, | |
| "grad_norm": 1.5166040658950806, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.3112, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.023346303501945526, | |
| "grad_norm": 1.4540307521820068, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.4235, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.02375588777390948, | |
| "grad_norm": 1.4702589511871338, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.3107, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.024165472045873437, | |
| "grad_norm": 2.018094539642334, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.3377, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.024575056317837397, | |
| "grad_norm": 1.072698950767517, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.2737, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.024984640589801353, | |
| "grad_norm": 2.5592000484466553, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.2333, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.02539422486176531, | |
| "grad_norm": 1.2713217735290527, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.3628, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.025803809133729264, | |
| "grad_norm": 0.9973049163818359, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.2947, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02621339340569322, | |
| "grad_norm": 1.593890905380249, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.3915, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.02662297767765718, | |
| "grad_norm": 2.379255533218384, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.3678, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.027032561949621135, | |
| "grad_norm": 1.0315568447113037, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.265, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02744214622158509, | |
| "grad_norm": 1.6524887084960938, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.3766, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.027851730493549047, | |
| "grad_norm": 1.5630675554275513, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.3315, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.028261314765513003, | |
| "grad_norm": 2.2701518535614014, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.3104, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.028670899037476962, | |
| "grad_norm": 1.7529304027557373, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.4427, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.029080483309440918, | |
| "grad_norm": 1.255183458328247, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.2884, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.029490067581404874, | |
| "grad_norm": 1.3396148681640625, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.3427, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02989965185336883, | |
| "grad_norm": 1.2909964323043823, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.3006, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.030309236125332786, | |
| "grad_norm": 1.2211729288101196, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.2923, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.030718820397296745, | |
| "grad_norm": 1.8062753677368164, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.4641, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.030718820397296745, | |
| "eval_loss": 0.34614190459251404, | |
| "eval_runtime": 7.0556, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 0.992, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": 1.9081662893295288, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.4002, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.03153798894122466, | |
| "grad_norm": 1.015621304512024, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.2631, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.03194757321318861, | |
| "grad_norm": 0.9762264490127563, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.3077, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.03235715748515257, | |
| "grad_norm": 0.9308927059173584, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.317, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.032766741757116524, | |
| "grad_norm": 1.0790940523147583, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.3218, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03317632602908048, | |
| "grad_norm": 0.8803948163986206, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.2791, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.03358591030104444, | |
| "grad_norm": 0.9842001795768738, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.2876, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0339954945730084, | |
| "grad_norm": 1.2645741701126099, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.3469, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.034405078844972355, | |
| "grad_norm": 1.3563826084136963, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.2817, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.03481466311693631, | |
| "grad_norm": 1.3064996004104614, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.4047, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.035224247388900266, | |
| "grad_norm": 1.1984425783157349, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.2203, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.03563383166086422, | |
| "grad_norm": 1.6247293949127197, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.3285, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.03604341593282818, | |
| "grad_norm": 1.0864574909210205, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.3267, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.036453000204792134, | |
| "grad_norm": 1.6605820655822754, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.2532, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.03686258447675609, | |
| "grad_norm": 1.0407780408859253, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.27, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03727216874872005, | |
| "grad_norm": 1.0968496799468994, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.3515, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.03768175302068401, | |
| "grad_norm": 1.1806151866912842, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.2406, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.038091337292647964, | |
| "grad_norm": 1.2452479600906372, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.4016, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.03850092156461192, | |
| "grad_norm": 0.8575266599655151, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.2095, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.038910505836575876, | |
| "grad_norm": 0.912777841091156, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.2773, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.03932009010853983, | |
| "grad_norm": 0.8512354493141174, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.3243, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.03972967438050379, | |
| "grad_norm": 0.9844990968704224, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.2411, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.040139258652467744, | |
| "grad_norm": 1.317114233970642, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.2255, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0405488429244317, | |
| "grad_norm": 1.6339136362075806, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.2351, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.040958427196395655, | |
| "grad_norm": 0.9930921196937561, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.2448, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.040958427196395655, | |
| "eval_loss": 0.31713107228279114, | |
| "eval_runtime": 7.0547, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 0.992, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04136801146835962, | |
| "grad_norm": 0.9509855508804321, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.2413, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.041777595740323574, | |
| "grad_norm": 1.002145767211914, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.2644, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.04218718001228753, | |
| "grad_norm": 1.1608006954193115, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.2308, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.042596764284251486, | |
| "grad_norm": 1.313498616218567, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.3244, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.04300634855621544, | |
| "grad_norm": 1.3625378608703613, | |
| "learning_rate": 0.00015, | |
| "loss": 0.3126, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.0434159328281794, | |
| "grad_norm": 0.931500256061554, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.2741, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.04382551710014335, | |
| "grad_norm": 1.7665846347808838, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.332, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.04423510137210731, | |
| "grad_norm": 1.2403225898742676, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.3456, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.044644685644071265, | |
| "grad_norm": 1.3050745725631714, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.3015, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.04505426991603522, | |
| "grad_norm": 1.056707501411438, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.3497, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.045463854187999184, | |
| "grad_norm": 1.468729019165039, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.3546, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.04587343845996314, | |
| "grad_norm": 1.686792254447937, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.3862, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.046283022731927095, | |
| "grad_norm": 1.143621563911438, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.3013, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.04669260700389105, | |
| "grad_norm": 1.3882373571395874, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.3389, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.04710219127585501, | |
| "grad_norm": 1.0089846849441528, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.3643, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.04751177554781896, | |
| "grad_norm": 1.1870588064193726, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.3509, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.04792135981978292, | |
| "grad_norm": 0.859807014465332, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.2182, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.048330944091746875, | |
| "grad_norm": 1.7744337320327759, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.4168, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.04874052836371083, | |
| "grad_norm": 1.268139123916626, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.3958, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.04915011263567479, | |
| "grad_norm": 1.4337314367294312, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.4177, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04955969690763875, | |
| "grad_norm": 1.177187204360962, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.2095, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.049969281179602705, | |
| "grad_norm": 1.257442831993103, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.3648, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.05037886545156666, | |
| "grad_norm": 1.1356306076049805, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.2471, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.05078844972353062, | |
| "grad_norm": 1.0337142944335938, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.2465, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.05119803399549457, | |
| "grad_norm": 1.0032552480697632, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.2275, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.05119803399549457, | |
| "eval_loss": 0.27536189556121826, | |
| "eval_runtime": 7.0469, | |
| "eval_samples_per_second": 7.095, | |
| "eval_steps_per_second": 0.993, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.05160761826745853, | |
| "grad_norm": 1.302047848701477, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.3416, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.052017202539422484, | |
| "grad_norm": 0.766473650932312, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.2151, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.05242678681138644, | |
| "grad_norm": 0.8692076802253723, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.1766, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.052836371083350396, | |
| "grad_norm": 1.3593523502349854, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.3038, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.05324595535531436, | |
| "grad_norm": 1.0448229312896729, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.2512, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.053655539627278315, | |
| "grad_norm": 1.5594054460525513, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.2915, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.05406512389924227, | |
| "grad_norm": 1.2313745021820068, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.2394, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.054474708171206226, | |
| "grad_norm": 1.4682273864746094, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.3008, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.05488429244317018, | |
| "grad_norm": 0.9318922758102417, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.2269, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.05529387671513414, | |
| "grad_norm": 1.0974271297454834, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.3247, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.055703460987098094, | |
| "grad_norm": 3.1087758541107178, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.3786, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.05611304525906205, | |
| "grad_norm": 0.9446348547935486, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.252, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.056522629531026006, | |
| "grad_norm": 1.5979207754135132, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.2715, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.05693221380298997, | |
| "grad_norm": 2.039667844772339, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.3273, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.057341798074953924, | |
| "grad_norm": 1.4651241302490234, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.3456, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05775138234691788, | |
| "grad_norm": 0.962695300579071, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.2002, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.058160966618881836, | |
| "grad_norm": 0.79236900806427, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.275, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.05857055089084579, | |
| "grad_norm": 1.0277087688446045, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.2996, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.05898013516280975, | |
| "grad_norm": 0.698850154876709, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.2285, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.059389719434773704, | |
| "grad_norm": 1.2999036312103271, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.2599, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.05979930370673766, | |
| "grad_norm": 1.0272763967514038, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.3243, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.060208887978701615, | |
| "grad_norm": 0.919711172580719, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.2842, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.06061847225066557, | |
| "grad_norm": 0.9950523972511292, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.2792, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.061028056522629534, | |
| "grad_norm": 0.7421355843544006, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.2375, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.06143764079459349, | |
| "grad_norm": 0.952510416507721, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.3047, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06143764079459349, | |
| "eval_loss": 0.2740105390548706, | |
| "eval_runtime": 7.0485, | |
| "eval_samples_per_second": 7.094, | |
| "eval_steps_per_second": 0.993, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.625264977707008e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |