Instructions to use aleegis10/63737358-4804-47f9-8e79-51357ac71efb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aleegis10/63737358-4804-47f9-8e79-51357ac71efb with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("MLP-KTLim/llama-3-Korean-Bllossom-8B") model = PeftModel.from_pretrained(base_model, "aleegis10/63737358-4804-47f9-8e79-51357ac71efb") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 1.1333621740341187, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.012984694291603772, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.492347145801887e-05, | |
| "grad_norm": 0.9931908845901489, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3955, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.492347145801887e-05, | |
| "eval_loss": 1.7274296283721924, | |
| "eval_runtime": 1977.018, | |
| "eval_samples_per_second": 13.122, | |
| "eval_steps_per_second": 3.281, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012984694291603773, | |
| "grad_norm": 1.0798954963684082, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3863, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00019477041437405659, | |
| "grad_norm": 1.0102638006210327, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025969388583207547, | |
| "grad_norm": 0.9370899200439453, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3396, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003246173572900943, | |
| "grad_norm": 0.9130417704582214, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3537, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00038954082874811317, | |
| "grad_norm": 0.779731273651123, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3177, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000454464300206132, | |
| "grad_norm": 0.8486445546150208, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2826, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005193877716641509, | |
| "grad_norm": 0.7455570101737976, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2758, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005843112431221698, | |
| "grad_norm": 0.7085099220275879, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3594, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006492347145801886, | |
| "grad_norm": 0.7316816449165344, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007141581860382074, | |
| "grad_norm": 0.6275414824485779, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.1666, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007790816574962263, | |
| "grad_norm": 0.6202852725982666, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.1277, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008440051289542452, | |
| "grad_norm": 0.7840100526809692, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.3031, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000908928600412264, | |
| "grad_norm": 0.7042649388313293, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.2561, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0009738520718702829, | |
| "grad_norm": 0.7233424186706543, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.1765, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010387755433283019, | |
| "grad_norm": 0.8116744756698608, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.3183, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011036990147863207, | |
| "grad_norm": 0.7582995891571045, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.1255, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0011686224862443395, | |
| "grad_norm": 0.9140874743461609, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.2337, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012335459577023583, | |
| "grad_norm": 0.8358305096626282, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.2083, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0012984694291603772, | |
| "grad_norm": 0.7706372737884521, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.2085, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001363392900618396, | |
| "grad_norm": 0.8367209434509277, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.1951, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014283163720764148, | |
| "grad_norm": 0.8315708637237549, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.3058, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0014932398435344339, | |
| "grad_norm": 0.9688097238540649, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.3118, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0015581633149924527, | |
| "grad_norm": 0.9234626293182373, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.2319, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016230867864504715, | |
| "grad_norm": 0.9571717381477356, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.4181, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0016880102579084903, | |
| "grad_norm": 0.9896688461303711, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.2098, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0017529337293665092, | |
| "grad_norm": 1.1687928438186646, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.2726, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001817857200824528, | |
| "grad_norm": 1.0942400693893433, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.2064, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001882780672282547, | |
| "grad_norm": 1.1253615617752075, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.9644, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0019477041437405659, | |
| "grad_norm": 1.1539970636367798, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1615, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020126276151985847, | |
| "grad_norm": 1.3887709379196167, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.1989, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0020775510866566037, | |
| "grad_norm": 1.5097383260726929, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.2143, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0021424745581146223, | |
| "grad_norm": 1.6619794368743896, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.2105, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0022073980295726414, | |
| "grad_norm": 1.5333211421966553, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.2919, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00227232150103066, | |
| "grad_norm": 1.4457088708877563, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.2386, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.002337244972488679, | |
| "grad_norm": 1.7561287879943848, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.3722, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0024021684439466976, | |
| "grad_norm": 2.0252134799957275, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.2896, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0024670919154047167, | |
| "grad_norm": 1.8449949026107788, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.0604, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0025320153868627357, | |
| "grad_norm": 2.2796454429626465, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.1968, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0025969388583207543, | |
| "grad_norm": 2.556976795196533, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.3272, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0026618623297787734, | |
| "grad_norm": 2.114734172821045, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.9987, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002726785801236792, | |
| "grad_norm": 2.5981175899505615, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.1206, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002791709272694811, | |
| "grad_norm": 3.1078953742980957, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.1143, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0028566327441528296, | |
| "grad_norm": 2.515855550765991, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.125, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0029215562156108487, | |
| "grad_norm": 2.6677591800689697, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.3043, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0029864796870688677, | |
| "grad_norm": 2.6532673835754395, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.0881, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0030514031585268863, | |
| "grad_norm": 3.1073367595672607, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.2669, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0031163266299849054, | |
| "grad_norm": 4.078120708465576, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.1428, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.003181250101442924, | |
| "grad_norm": 3.010019302368164, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.9161, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.003246173572900943, | |
| "grad_norm": 6.848526954650879, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.5014, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003246173572900943, | |
| "eval_loss": 1.299052357673645, | |
| "eval_runtime": 1987.8913, | |
| "eval_samples_per_second": 13.05, | |
| "eval_steps_per_second": 3.263, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003311097044358962, | |
| "grad_norm": 1.2080974578857422, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 1.3732, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0033760205158169807, | |
| "grad_norm": 1.0366750955581665, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.3542, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0034409439872749997, | |
| "grad_norm": 0.8017165660858154, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.2771, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0035058674587330183, | |
| "grad_norm": 0.6454352140426636, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.2082, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0035707909301910374, | |
| "grad_norm": 0.5630488991737366, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.2867, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.003635714401649056, | |
| "grad_norm": 0.5941081047058105, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.3867, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.003700637873107075, | |
| "grad_norm": 0.5265991687774658, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 1.1819, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.003765561344565094, | |
| "grad_norm": 0.6069496273994446, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.329, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0038304848160231127, | |
| "grad_norm": 0.5526225566864014, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 1.3544, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0038954082874811317, | |
| "grad_norm": 0.5585722923278809, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.1676, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00396033175893915, | |
| "grad_norm": 0.607186496257782, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 1.2331, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.004025255230397169, | |
| "grad_norm": 0.6697636246681213, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 1.2704, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.004090178701855188, | |
| "grad_norm": 0.637630820274353, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 1.302, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0041551021733132075, | |
| "grad_norm": 0.5607894062995911, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 1.2677, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.004220025644771226, | |
| "grad_norm": 0.6919241547584534, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 1.2737, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004284949116229245, | |
| "grad_norm": 0.6876102685928345, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 1.3166, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.004349872587687264, | |
| "grad_norm": 0.689167857170105, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.2214, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.004414796059145283, | |
| "grad_norm": 0.6596851944923401, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.1761, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.004479719530603301, | |
| "grad_norm": 0.7586140036582947, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 1.1865, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.00454464300206132, | |
| "grad_norm": 0.7845248579978943, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.3945, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.004609566473519339, | |
| "grad_norm": 0.7617992162704468, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 1.2725, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.004674489944977358, | |
| "grad_norm": 0.7202935814857483, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 1.1927, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.004739413416435377, | |
| "grad_norm": 0.7859868407249451, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 1.141, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.004804336887893395, | |
| "grad_norm": 0.8661206960678101, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 1.258, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.004869260359351414, | |
| "grad_norm": 0.7583446502685547, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 1.1712, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.004934183830809433, | |
| "grad_norm": 0.8483708500862122, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 1.2513, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.004999107302267452, | |
| "grad_norm": 1.0224113464355469, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 1.2345, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0050640307737254715, | |
| "grad_norm": 1.1613913774490356, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.238, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.00512895424518349, | |
| "grad_norm": 1.1426547765731812, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 1.1792, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.005193877716641509, | |
| "grad_norm": 0.8753805160522461, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 1.0544, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005258801188099528, | |
| "grad_norm": 1.1446024179458618, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 1.142, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005323724659557547, | |
| "grad_norm": 1.1448880434036255, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 1.0176, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.005388648131015566, | |
| "grad_norm": 1.6133174896240234, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 1.203, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.005453571602473584, | |
| "grad_norm": 1.3233124017715454, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 1.1138, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.005518495073931603, | |
| "grad_norm": 1.4611351490020752, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 1.1687, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.005583418545389622, | |
| "grad_norm": 1.374987006187439, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.0252, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.005648342016847641, | |
| "grad_norm": 1.7475776672363281, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 1.2686, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.005713265488305659, | |
| "grad_norm": 1.59104323387146, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 1.2136, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.005778188959763678, | |
| "grad_norm": 1.4034353494644165, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 1.1042, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.005843112431221697, | |
| "grad_norm": 2.776643991470337, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 1.2741, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.005908035902679716, | |
| "grad_norm": 1.8914669752120972, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 1.0276, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0059729593741377355, | |
| "grad_norm": 2.04311466217041, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 1.1038, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.006037882845595754, | |
| "grad_norm": 2.6776349544525146, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 1.1857, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.006102806317053773, | |
| "grad_norm": 2.771602153778076, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 1.2257, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.006167729788511792, | |
| "grad_norm": 2.431309938430786, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.8131, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.006232653259969811, | |
| "grad_norm": 2.611177682876587, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 1.4079, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.00629757673142783, | |
| "grad_norm": 2.3767051696777344, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.8592, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.006362500202885848, | |
| "grad_norm": 3.8793766498565674, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 1.1688, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.006427423674343867, | |
| "grad_norm": 2.860419750213623, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.9343, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.006492347145801886, | |
| "grad_norm": 3.3667044639587402, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 1.2536, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006492347145801886, | |
| "eval_loss": 1.2086118459701538, | |
| "eval_runtime": 1986.2248, | |
| "eval_samples_per_second": 13.061, | |
| "eval_steps_per_second": 3.265, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006557270617259905, | |
| "grad_norm": 0.7666314244270325, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 1.1916, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.006622194088717924, | |
| "grad_norm": 0.7668541073799133, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 1.2555, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.006687117560175942, | |
| "grad_norm": 0.6754006147384644, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 1.439, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.006752041031633961, | |
| "grad_norm": 0.6046998500823975, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 1.3285, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.00681696450309198, | |
| "grad_norm": 0.5599321722984314, | |
| "learning_rate": 5e-05, | |
| "loss": 1.095, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.0068818879745499995, | |
| "grad_norm": 0.5471016764640808, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 1.2777, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.006946811446008018, | |
| "grad_norm": 0.49177172780036926, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 1.1703, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.007011734917466037, | |
| "grad_norm": 0.5032525658607483, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 1.1511, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.007076658388924056, | |
| "grad_norm": 0.5286602973937988, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 1.115, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.007141581860382075, | |
| "grad_norm": 0.5137684941291809, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 1.147, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.007206505331840094, | |
| "grad_norm": 0.5753626823425293, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 1.2481, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.007271428803298112, | |
| "grad_norm": 0.5408186316490173, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 1.2194, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.007336352274756131, | |
| "grad_norm": 0.5109596252441406, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 1.1028, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.00740127574621415, | |
| "grad_norm": 0.5321526527404785, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 1.1843, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.007466199217672169, | |
| "grad_norm": 0.6054028868675232, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 1.3398, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.007531122689130188, | |
| "grad_norm": 0.5974127650260925, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 1.1662, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.007596046160588206, | |
| "grad_norm": 0.6349529027938843, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 1.1256, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.007660969632046225, | |
| "grad_norm": 0.6932494640350342, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 1.1376, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.007725893103504244, | |
| "grad_norm": 0.6950923800468445, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 1.3131, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0077908165749622635, | |
| "grad_norm": 0.6611078381538391, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 1.1848, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.007855740046420282, | |
| "grad_norm": 0.6949260830879211, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 1.1571, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.0079206635178783, | |
| "grad_norm": 0.7227311134338379, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 1.235, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.00798558698933632, | |
| "grad_norm": 0.7589835524559021, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 1.2022, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.008050510460794339, | |
| "grad_norm": 0.9023049473762512, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.1878, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.008115433932252357, | |
| "grad_norm": 0.779160737991333, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 1.136, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.008180357403710377, | |
| "grad_norm": 0.8739699125289917, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 1.1297, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.008245280875168395, | |
| "grad_norm": 1.034454107284546, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 1.3353, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.008310204346626415, | |
| "grad_norm": 0.9376235604286194, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 1.1614, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.008375127818084433, | |
| "grad_norm": 0.8876826763153076, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 1.1918, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.008440051289542451, | |
| "grad_norm": 1.2257558107376099, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 1.029, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.008504974761000471, | |
| "grad_norm": 0.9673946499824524, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 1.0787, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.00856989823245849, | |
| "grad_norm": 1.084344506263733, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 1.2127, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.00863482170391651, | |
| "grad_norm": 1.0751358270645142, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 1.0577, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.008699745175374527, | |
| "grad_norm": 1.241531252861023, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 1.0526, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.008764668646832546, | |
| "grad_norm": 1.5708144903182983, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 1.1888, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.008829592118290566, | |
| "grad_norm": 1.5015288591384888, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 1.1294, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.008894515589748584, | |
| "grad_norm": 1.4662539958953857, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 1.0714, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.008959439061206602, | |
| "grad_norm": 1.8017679452896118, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 1.2173, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.009024362532664622, | |
| "grad_norm": 1.651761770248413, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.9604, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.00908928600412264, | |
| "grad_norm": 2.246441125869751, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 1.0027, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.00915420947558066, | |
| "grad_norm": 2.0347628593444824, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.9599, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.009219132947038678, | |
| "grad_norm": 2.0897066593170166, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 1.0067, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.009284056418496696, | |
| "grad_norm": 4.240103244781494, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.0535, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.009348979889954716, | |
| "grad_norm": 2.844397783279419, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 1.0563, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.009413903361412734, | |
| "grad_norm": 2.234746217727661, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.9805, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.009478826832870754, | |
| "grad_norm": 2.4138054847717285, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.9855, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.009543750304328772, | |
| "grad_norm": 2.2872800827026367, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.9283, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.00960867377578679, | |
| "grad_norm": 2.9530155658721924, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 1.4646, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.00967359724724481, | |
| "grad_norm": 3.5457417964935303, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 1.1648, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.009738520718702829, | |
| "grad_norm": 4.596130847930908, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 1.5164, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.009738520718702829, | |
| "eval_loss": 1.1435943841934204, | |
| "eval_runtime": 1987.4184, | |
| "eval_samples_per_second": 13.053, | |
| "eval_steps_per_second": 3.264, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.009803444190160849, | |
| "grad_norm": 0.4648900628089905, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 1.1738, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.009868367661618867, | |
| "grad_norm": 0.47376006841659546, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 1.1942, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.009933291133076885, | |
| "grad_norm": 0.506817638874054, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 1.1309, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.009998214604534905, | |
| "grad_norm": 0.5413241982460022, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 1.1963, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.010063138075992923, | |
| "grad_norm": 0.5183156132698059, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 1.2809, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.010128061547450943, | |
| "grad_norm": 0.5198935270309448, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 1.1352, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.010192985018908961, | |
| "grad_norm": 0.49471908807754517, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 1.1093, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.01025790849036698, | |
| "grad_norm": 0.5173000693321228, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 1.117, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.010322831961825, | |
| "grad_norm": 0.5447592735290527, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 1.0858, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.010387755433283017, | |
| "grad_norm": 0.5424394607543945, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 1.2066, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.010452678904741037, | |
| "grad_norm": 0.5785081386566162, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 1.2159, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.010517602376199055, | |
| "grad_norm": 0.5406847596168518, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.0608, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.010582525847657074, | |
| "grad_norm": 0.5609476566314697, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 1.1001, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.010647449319115094, | |
| "grad_norm": 0.5584609508514404, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 1.1751, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.010712372790573112, | |
| "grad_norm": 0.5613505840301514, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 1.2026, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.010777296262031132, | |
| "grad_norm": 0.5688934326171875, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 1.1394, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.01084221973348915, | |
| "grad_norm": 0.6710279583930969, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 1.2487, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.010907143204947168, | |
| "grad_norm": 0.631956160068512, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 1.1739, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.010972066676405188, | |
| "grad_norm": 0.7510198354721069, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 1.2052, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.011036990147863206, | |
| "grad_norm": 0.715456485748291, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 1.2109, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.011101913619321226, | |
| "grad_norm": 0.8131726384162903, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 1.4097, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.011166837090779244, | |
| "grad_norm": 0.6952980160713196, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 1.1616, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.011231760562237262, | |
| "grad_norm": 0.7602817416191101, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 1.2224, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.011296684033695282, | |
| "grad_norm": 0.7706920504570007, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 1.1654, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.0113616075051533, | |
| "grad_norm": 0.900113046169281, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 1.1503, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.011426530976611319, | |
| "grad_norm": 0.9739847779273987, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 1.2107, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.011491454448069338, | |
| "grad_norm": 0.9037585258483887, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 1.0987, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.011556377919527357, | |
| "grad_norm": 0.872492790222168, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 1.0692, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.011621301390985377, | |
| "grad_norm": 1.093956708908081, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 1.254, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.011686224862443395, | |
| "grad_norm": 1.2187851667404175, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 1.2702, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.011751148333901413, | |
| "grad_norm": 0.9881110191345215, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.003, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.011816071805359433, | |
| "grad_norm": 1.1868014335632324, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 1.2017, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.011880995276817451, | |
| "grad_norm": 1.2892512083053589, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 1.0537, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.011945918748275471, | |
| "grad_norm": 1.180896282196045, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 1.1474, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.012010842219733489, | |
| "grad_norm": 1.4036606550216675, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 1.1058, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.012075765691191507, | |
| "grad_norm": 1.5504472255706787, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 1.1239, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.012140689162649527, | |
| "grad_norm": 1.4706414937973022, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 1.0088, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.012205612634107545, | |
| "grad_norm": 1.609456181526184, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.8632, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.012270536105565565, | |
| "grad_norm": 1.7156457901000977, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 1.0837, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.012335459577023583, | |
| "grad_norm": 1.482324242591858, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.8694, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.012400383048481602, | |
| "grad_norm": 1.701109528541565, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.8236, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.012465306519939622, | |
| "grad_norm": 2.056856870651245, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.9344, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.01253022999139764, | |
| "grad_norm": 2.379714250564575, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 1.0607, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.01259515346285566, | |
| "grad_norm": 1.9792193174362183, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 1.1894, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.012660076934313678, | |
| "grad_norm": 2.1936213970184326, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 1.084, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.012725000405771696, | |
| "grad_norm": 2.0612998008728027, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.9894, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.012789923877229716, | |
| "grad_norm": 2.886000394821167, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.9119, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.012854847348687734, | |
| "grad_norm": 2.9128880500793457, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 1.3275, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.012919770820145754, | |
| "grad_norm": 3.7713398933410645, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.9659, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.012984694291603772, | |
| "grad_norm": 3.659714937210083, | |
| "learning_rate": 0.0, | |
| "loss": 1.0505, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.012984694291603772, | |
| "eval_loss": 1.1333621740341187, | |
| "eval_runtime": 1986.1663, | |
| "eval_samples_per_second": 13.061, | |
| "eval_steps_per_second": 3.266, | |
| "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": 3.0321122932791706e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |