Instructions to use nttx/85705d21-720e-4c2c-9421-77cd1613371f with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nttx/85705d21-720e-4c2c-9421-77cd1613371f with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("lcw99/zephykor-ko-7b-chang") model = PeftModel.from_pretrained(base_model, "nttx/85705d21-720e-4c2c-9421-77cd1613371f") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 1.2786811590194702, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.12961762799740764, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006480881399870382, | |
| "grad_norm": 32.42519760131836, | |
| "learning_rate": 1e-05, | |
| "loss": 10.2522, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006480881399870382, | |
| "eval_loss": 3.3373067378997803, | |
| "eval_runtime": 366.4364, | |
| "eval_samples_per_second": 7.093, | |
| "eval_steps_per_second": 1.774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012961762799740765, | |
| "grad_norm": 34.10329055786133, | |
| "learning_rate": 2e-05, | |
| "loss": 10.4056, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019442644199611147, | |
| "grad_norm": 22.09769630432129, | |
| "learning_rate": 3e-05, | |
| "loss": 10.2769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002592352559948153, | |
| "grad_norm": 17.111722946166992, | |
| "learning_rate": 4e-05, | |
| "loss": 9.8817, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0032404406999351912, | |
| "grad_norm": 19.90062141418457, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3269, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0038885288399222295, | |
| "grad_norm": 19.764968872070312, | |
| "learning_rate": 6e-05, | |
| "loss": 9.7497, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004536616979909268, | |
| "grad_norm": 16.849136352539062, | |
| "learning_rate": 7e-05, | |
| "loss": 9.4637, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005184705119896306, | |
| "grad_norm": 15.267022132873535, | |
| "learning_rate": 8e-05, | |
| "loss": 9.3715, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005832793259883344, | |
| "grad_norm": 15.293052673339844, | |
| "learning_rate": 9e-05, | |
| "loss": 8.884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0064808813998703824, | |
| "grad_norm": 14.610129356384277, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6526, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007128969539857421, | |
| "grad_norm": 14.223299026489258, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 8.3602, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007777057679844459, | |
| "grad_norm": 13.844172477722168, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 7.8496, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008425145819831496, | |
| "grad_norm": 13.581099510192871, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 7.6224, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009073233959818535, | |
| "grad_norm": 12.845854759216309, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 7.4729, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009721322099805573, | |
| "grad_norm": 12.738224029541016, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 7.0143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010369410239792612, | |
| "grad_norm": 12.772802352905273, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 7.3166, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01101749837977965, | |
| "grad_norm": 11.514303207397461, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 6.9592, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011665586519766688, | |
| "grad_norm": 11.541314125061035, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 6.9952, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012313674659753726, | |
| "grad_norm": 11.420286178588867, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 6.7441, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012961762799740765, | |
| "grad_norm": 10.901569366455078, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 7.1352, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013609850939727802, | |
| "grad_norm": 11.525110244750977, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 6.895, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014257939079714841, | |
| "grad_norm": 11.956829071044922, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 6.8886, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014906027219701879, | |
| "grad_norm": 11.175165176391602, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 6.2842, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015554115359688918, | |
| "grad_norm": 11.768041610717773, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 7.0381, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016202203499675955, | |
| "grad_norm": 11.069051742553711, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 5.9566, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016850291639662993, | |
| "grad_norm": 11.710158348083496, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 6.3801, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017498379779650033, | |
| "grad_norm": 12.592041969299316, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 6.5622, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01814646791963707, | |
| "grad_norm": 11.391824722290039, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 6.3206, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.018794556059624108, | |
| "grad_norm": 11.525542259216309, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 6.4097, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.019442644199611146, | |
| "grad_norm": 10.853957176208496, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 6.1766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020090732339598186, | |
| "grad_norm": 11.40859317779541, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 6.1226, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.020738820479585224, | |
| "grad_norm": 12.139171600341797, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 6.3555, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02138690861957226, | |
| "grad_norm": 12.078801155090332, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 5.9679, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0220349967595593, | |
| "grad_norm": 13.672163963317871, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 6.0283, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02268308489954634, | |
| "grad_norm": 13.25695514678955, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 6.6222, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023331173039533377, | |
| "grad_norm": 13.72711181640625, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 6.0205, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.023979261179520414, | |
| "grad_norm": 13.88613510131836, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 6.1468, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02462734931950745, | |
| "grad_norm": 15.013215065002441, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 6.3245, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025275437459494492, | |
| "grad_norm": 16.2659854888916, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 6.7021, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02592352559948153, | |
| "grad_norm": 14.23939323425293, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 6.4616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026571613739468567, | |
| "grad_norm": 17.28889274597168, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 7.7787, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027219701879455604, | |
| "grad_norm": 18.503110885620117, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 7.6753, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.027867790019442645, | |
| "grad_norm": 18.613170623779297, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 6.9204, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.028515878159429683, | |
| "grad_norm": 31.382518768310547, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 9.831, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02916396629941672, | |
| "grad_norm": 17.905912399291992, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 5.667, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.029812054439403757, | |
| "grad_norm": 14.090008735656738, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 5.0193, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0304601425793908, | |
| "grad_norm": 10.025882720947266, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 4.6628, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.031108230719377836, | |
| "grad_norm": 10.740228652954102, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.7435, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.031756318859364877, | |
| "grad_norm": 13.310742378234863, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 4.6157, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03240440699935191, | |
| "grad_norm": 9.965121269226074, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 3.9062, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03240440699935191, | |
| "eval_loss": 1.5974934101104736, | |
| "eval_runtime": 369.5459, | |
| "eval_samples_per_second": 7.033, | |
| "eval_steps_per_second": 1.759, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03305249513933895, | |
| "grad_norm": 7.065499305725098, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 6.8925, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.033700583279325985, | |
| "grad_norm": 6.965680122375488, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 6.6026, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.034348671419313026, | |
| "grad_norm": 6.074826717376709, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 6.7384, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.03499675955930007, | |
| "grad_norm": 6.347430229187012, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 6.4046, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0356448476992871, | |
| "grad_norm": 6.753992557525635, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 6.6039, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03629293583927414, | |
| "grad_norm": 6.799598217010498, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 6.2998, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03694102397926118, | |
| "grad_norm": 6.8841938972473145, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 6.148, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.037589112119248216, | |
| "grad_norm": 7.427107334136963, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 6.2598, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03823720025923526, | |
| "grad_norm": 7.565087795257568, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 5.8072, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03888528839922229, | |
| "grad_norm": 7.869139194488525, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 5.9755, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03953337653920933, | |
| "grad_norm": 7.597141742706299, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 5.7743, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.04018146467919637, | |
| "grad_norm": 7.840945243835449, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 5.5691, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.04082955281918341, | |
| "grad_norm": 8.199173927307129, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 6.0614, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.04147764095917045, | |
| "grad_norm": 7.544084072113037, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 5.9541, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.04212572909915749, | |
| "grad_norm": 8.054306983947754, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 5.2729, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.04277381723914452, | |
| "grad_norm": 8.135971069335938, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 5.3806, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.04342190537913156, | |
| "grad_norm": 8.077417373657227, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 5.5062, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0440699935191186, | |
| "grad_norm": 9.035508155822754, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 6.0228, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04471808165910564, | |
| "grad_norm": 8.84268856048584, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 5.5147, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04536616979909268, | |
| "grad_norm": 8.633135795593262, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 5.7103, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04601425793907971, | |
| "grad_norm": 8.999127388000488, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 5.2027, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.046662346079066754, | |
| "grad_norm": 9.32126522064209, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 5.864, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.047310434219053794, | |
| "grad_norm": 9.201434135437012, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 6.0594, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.04795852235904083, | |
| "grad_norm": 9.365532875061035, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 5.7664, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04860661049902787, | |
| "grad_norm": 9.258264541625977, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 5.7479, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0492546986390149, | |
| "grad_norm": 10.26109790802002, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 5.6195, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.049902786779001944, | |
| "grad_norm": 9.954758644104004, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 5.444, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.050550874918988985, | |
| "grad_norm": 9.513286590576172, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 5.1052, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.05119896305897602, | |
| "grad_norm": 9.602066993713379, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 5.1671, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.05184705119896306, | |
| "grad_norm": 10.098516464233398, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 5.3764, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0524951393389501, | |
| "grad_norm": 9.690994262695312, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 5.6407, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.053143227478937134, | |
| "grad_norm": 8.880331993103027, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 5.0537, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.053791315618924175, | |
| "grad_norm": 11.067152976989746, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 6.104, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.05443940375891121, | |
| "grad_norm": 10.420937538146973, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 5.5524, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.05508749189889825, | |
| "grad_norm": 10.208189010620117, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 5.5095, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.05573558003888529, | |
| "grad_norm": 11.656957626342773, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.6347, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.056383668178872325, | |
| "grad_norm": 11.358654022216797, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 5.6918, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.057031756318859365, | |
| "grad_norm": 12.047012329101562, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 6.0127, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.057679844458846406, | |
| "grad_norm": 13.1541109085083, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 6.0023, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.05832793259883344, | |
| "grad_norm": 12.222508430480957, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 5.9762, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05897602073882048, | |
| "grad_norm": 13.239960670471191, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 5.8003, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.059624108878807515, | |
| "grad_norm": 14.097587585449219, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 6.1751, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.060272197018794556, | |
| "grad_norm": 16.177494049072266, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 6.962, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0609202851587816, | |
| "grad_norm": 15.140183448791504, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 5.8179, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.06156837329876863, | |
| "grad_norm": 11.55969524383545, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 4.6251, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.06221646143875567, | |
| "grad_norm": 11.030327796936035, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 4.1549, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.06286454957874271, | |
| "grad_norm": 9.813619613647461, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 4.9202, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.06351263771872975, | |
| "grad_norm": 7.902237415313721, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 4.3541, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.06416072585871678, | |
| "grad_norm": 9.533426284790039, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 4.5985, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.06480881399870382, | |
| "grad_norm": 9.340726852416992, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 4.3479, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06480881399870382, | |
| "eval_loss": 1.4217678308486938, | |
| "eval_runtime": 369.5915, | |
| "eval_samples_per_second": 7.032, | |
| "eval_steps_per_second": 1.759, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06545690213869086, | |
| "grad_norm": 4.824896335601807, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 5.9567, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.0661049902786779, | |
| "grad_norm": 4.737966537475586, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 5.5482, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.06675307841866494, | |
| "grad_norm": 4.824122905731201, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 5.5792, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.06740116655865197, | |
| "grad_norm": 5.279732704162598, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 5.7576, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.06804925469863901, | |
| "grad_norm": 5.975471019744873, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9659, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06869734283862605, | |
| "grad_norm": 6.185173511505127, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 5.5892, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.06934543097861309, | |
| "grad_norm": 6.316420078277588, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 5.2877, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.06999351911860013, | |
| "grad_norm": 6.84273099899292, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 5.6124, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.07064160725858717, | |
| "grad_norm": 7.118045330047607, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 5.5017, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.0712896953985742, | |
| "grad_norm": 7.058719158172607, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 5.5852, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07193778353856124, | |
| "grad_norm": 7.048069000244141, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 5.4123, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.07258587167854828, | |
| "grad_norm": 6.4715094566345215, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 5.0733, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.07323395981853532, | |
| "grad_norm": 7.225956916809082, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 5.3827, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.07388204795852236, | |
| "grad_norm": 7.291068077087402, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 5.667, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.07453013609850939, | |
| "grad_norm": 6.970168113708496, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 5.1527, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.07517822423849643, | |
| "grad_norm": 8.03061580657959, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 5.8739, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.07582631237848347, | |
| "grad_norm": 8.623993873596191, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 5.2747, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.07647440051847051, | |
| "grad_norm": 7.966943264007568, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 5.6577, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.07712248865845756, | |
| "grad_norm": 7.65449333190918, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 5.0632, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.07777057679844458, | |
| "grad_norm": 8.131715774536133, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 5.5256, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07841866493843162, | |
| "grad_norm": 8.38886833190918, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 5.0285, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.07906675307841866, | |
| "grad_norm": 8.168731689453125, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 5.5781, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.0797148412184057, | |
| "grad_norm": 8.660725593566895, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 5.446, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.08036292935839275, | |
| "grad_norm": 8.180733680725098, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 5.1427, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.08101101749837979, | |
| "grad_norm": 7.9701828956604, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 4.6504, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.08165910563836681, | |
| "grad_norm": 8.84539794921875, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 5.3533, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.08230719377835385, | |
| "grad_norm": 8.574117660522461, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 5.6761, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.0829552819183409, | |
| "grad_norm": 8.8590726852417, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 5.7317, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.08360337005832794, | |
| "grad_norm": 8.957681655883789, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 5.2844, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.08425145819831498, | |
| "grad_norm": 9.867990493774414, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 5.4611, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.084899546338302, | |
| "grad_norm": 8.609209060668945, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 5.078, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.08554763447828904, | |
| "grad_norm": 9.531466484069824, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 4.523, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.08619572261827609, | |
| "grad_norm": 9.875545501708984, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 5.6699, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.08684381075826313, | |
| "grad_norm": 9.542217254638672, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 4.7123, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.08749189889825017, | |
| "grad_norm": 9.753568649291992, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 4.2363, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0881399870382372, | |
| "grad_norm": 10.80831527709961, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 5.5241, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.08878807517822424, | |
| "grad_norm": 11.769923210144043, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 5.8018, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.08943616331821128, | |
| "grad_norm": 11.233729362487793, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 4.7832, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.09008425145819832, | |
| "grad_norm": 10.597397804260254, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 4.6093, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.09073233959818536, | |
| "grad_norm": 13.578731536865234, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 5.65, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09138042773817238, | |
| "grad_norm": 16.16774559020996, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 6.0857, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.09202851587815943, | |
| "grad_norm": 14.04427719116211, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 5.4805, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.09267660401814647, | |
| "grad_norm": 19.81171989440918, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 7.049, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.09332469215813351, | |
| "grad_norm": 11.414923667907715, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 5.179, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.09397278029812055, | |
| "grad_norm": 10.083847045898438, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 4.6427, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.09462086843810759, | |
| "grad_norm": 7.28787899017334, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 3.4962, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.09526895657809462, | |
| "grad_norm": 8.137825012207031, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 3.8576, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.09591704471808166, | |
| "grad_norm": 7.965475559234619, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 3.5012, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.0965651328580687, | |
| "grad_norm": 7.481436729431152, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 3.2691, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.09721322099805574, | |
| "grad_norm": 9.343503952026367, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 4.0093, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09721322099805574, | |
| "eval_loss": 1.3234578371047974, | |
| "eval_runtime": 368.809, | |
| "eval_samples_per_second": 7.047, | |
| "eval_steps_per_second": 1.762, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09786130913804278, | |
| "grad_norm": 6.150128364562988, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 5.4909, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.0985093972780298, | |
| "grad_norm": 6.098457336425781, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 5.6214, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.09915748541801685, | |
| "grad_norm": 6.064051628112793, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 5.6911, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.09980557355800389, | |
| "grad_norm": 5.61346435546875, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 5.4218, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.10045366169799093, | |
| "grad_norm": 5.486062526702881, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 5.099, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.10110174983797797, | |
| "grad_norm": 5.618807792663574, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 5.1658, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.101749837977965, | |
| "grad_norm": 6.510883808135986, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 5.5689, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.10239792611795204, | |
| "grad_norm": 6.064540863037109, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 5.3983, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.10304601425793908, | |
| "grad_norm": 6.274316787719727, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 5.529, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.10369410239792612, | |
| "grad_norm": 6.463152885437012, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 5.1448, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10434219053791316, | |
| "grad_norm": 6.518610954284668, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 5.1364, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.1049902786779002, | |
| "grad_norm": 6.675931930541992, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 4.9385, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.10563836681788723, | |
| "grad_norm": 6.833399295806885, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 5.3592, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.10628645495787427, | |
| "grad_norm": 6.469447135925293, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 4.7478, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.10693454309786131, | |
| "grad_norm": 7.158629894256592, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 4.8979, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.10758263123784835, | |
| "grad_norm": 7.534177303314209, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 5.3418, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.10823071937783539, | |
| "grad_norm": 7.45398473739624, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 5.6196, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.10887880751782242, | |
| "grad_norm": 7.560189247131348, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 5.6854, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.10952689565780946, | |
| "grad_norm": 7.284002304077148, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 4.944, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.1101749837977965, | |
| "grad_norm": 7.783074378967285, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 5.3393, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11082307193778354, | |
| "grad_norm": 8.003946304321289, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 5.2522, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.11147116007777058, | |
| "grad_norm": 8.379652976989746, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 5.8552, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.11211924821775761, | |
| "grad_norm": 7.882482528686523, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 4.9849, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.11276733635774465, | |
| "grad_norm": 7.535508632659912, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 4.6377, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.11341542449773169, | |
| "grad_norm": 8.180285453796387, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 5.2924, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.11406351263771873, | |
| "grad_norm": 9.168655395507812, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 5.5962, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.11471160077770577, | |
| "grad_norm": 8.54617977142334, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 5.1917, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.11535968891769281, | |
| "grad_norm": 9.063509941101074, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 5.4326, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.11600777705767984, | |
| "grad_norm": 9.060470581054688, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 5.1408, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.11665586519766688, | |
| "grad_norm": 9.62983512878418, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 5.5681, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.11730395333765392, | |
| "grad_norm": 8.481123924255371, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 4.7449, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.11795204147764096, | |
| "grad_norm": 9.108993530273438, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 5.5554, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.118600129617628, | |
| "grad_norm": 9.262886047363281, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 4.9859, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.11924821775761503, | |
| "grad_norm": 9.577231407165527, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 5.4744, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.11989630589760207, | |
| "grad_norm": 9.803349494934082, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 5.3457, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.12054439403758911, | |
| "grad_norm": 9.43097972869873, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 4.7066, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.12119248217757615, | |
| "grad_norm": 10.22635555267334, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 5.2126, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.1218405703175632, | |
| "grad_norm": 11.419977188110352, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 5.0455, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.12248865845755022, | |
| "grad_norm": 10.00339126586914, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 4.697, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.12313674659753726, | |
| "grad_norm": 12.351414680480957, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 5.8105, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1237848347375243, | |
| "grad_norm": 12.884258270263672, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 5.4671, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.12443292287751134, | |
| "grad_norm": 13.02153205871582, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 5.5333, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.12508101101749838, | |
| "grad_norm": 17.072534561157227, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 6.6621, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.12572909915748542, | |
| "grad_norm": 23.91162109375, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 7.2746, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.12637718729747247, | |
| "grad_norm": 24.72917938232422, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 7.6982, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.1270252754374595, | |
| "grad_norm": 8.144952774047852, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 3.9139, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.12767336357744652, | |
| "grad_norm": 6.427740097045898, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 3.3741, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.12832145171743356, | |
| "grad_norm": 7.9929609298706055, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 3.5547, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.1289695398574206, | |
| "grad_norm": 8.236010551452637, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 3.2099, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.12961762799740764, | |
| "grad_norm": 7.7174201011657715, | |
| "learning_rate": 0.0, | |
| "loss": 3.2533, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12961762799740764, | |
| "eval_loss": 1.2786811590194702, | |
| "eval_runtime": 369.8757, | |
| "eval_samples_per_second": 7.027, | |
| "eval_steps_per_second": 1.757, | |
| "step": 200 | |
| } | |
| ], | |
| "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": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.442746364859515e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |