| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13917884481558804, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013917884481558804, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013917884481558804, | |
| "eval_loss": NaN, | |
| "eval_runtime": 39.9661, | |
| "eval_samples_per_second": 7.581, | |
| "eval_steps_per_second": 1.902, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027835768963117608, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041753653444676405, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0055671537926235215, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006958942240779402, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008350730688935281, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009742519137091163, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011134307585247043, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012526096033402923, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013917884481558803, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015309672929714684, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016701461377870562, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018093249826026444, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019485038274182326, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020876826722338204, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022268615170494086, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023660403618649965, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.025052192066805846, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026443980514961725, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027835768963117607, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029227557411273485, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030619345859429367, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.032011134307585246, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.033402922755741124, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03479471120389701, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03618649965205289, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.037578288100208766, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03897007654836465, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04036186499652053, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04175365344467641, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04314544189283229, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9984895998119723e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04453723034098817, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.993961440992859e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04592901878914405, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9864246426519023e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04732080723729993, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9758943828979444e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04871259568545581, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9623918682727355e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05010438413361169, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9459442910437798e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05149617258176757, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9265847744427305e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05288796102992345, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.904352305959606e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.054279749478079335, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8792916588271762e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.055671537926235214, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8514533018536286e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05706332637439109, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.820893297785107e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05845511482254697, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7876731904027994e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.059846903270702856, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7518598805819542e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.061238691718858734, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06263048016701461, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.672747223702045e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06402226861517049, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6296071990054167e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06541405706332637, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5841922957410875e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06680584551148225, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5365939734802973e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06819763395963814, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4869080889095693e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06958942240779402, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4352347027881003e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06958942240779402, | |
| "eval_loss": NaN, | |
| "eval_runtime": 39.5128, | |
| "eval_samples_per_second": 7.668, | |
| "eval_steps_per_second": 1.923, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0709812108559499, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3816778784387097e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.07237299930410578, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3263454721781537e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.07376478775226165, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2693489161088592e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.07515657620041753, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.210802993709498e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.07654836464857341, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1508256086763372e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0779401530967293, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0895375474808857e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07933194154488518, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0270622361220143e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.08072372999304106, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.963525491562421e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.08211551844119694, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8990552683500128e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.08350730688935282, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8337814009344716e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0848990953375087, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.767835342197955e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.08629088378566457, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7013498987264832e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.08768267223382047, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6344589633551502e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08907446068197634, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5672972455257726e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.09046624913013222, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0918580375782881, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4327027544742281e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.09324982602644398, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.36554103664485e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.09464161447459986, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2986501012735174e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.09603340292275574, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2321646578020452e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.09742519137091162, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1662185990655285e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09881697981906751, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1009447316499875e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.10020876826722339, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.036474508437579e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.10160055671537926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.729377638779859e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.10299234516353514, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.104624525191147e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.10438413361169102, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.491743913236629e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1057759220598469, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.89197006290502e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.10716771050800278, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.30651083891141e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.10855949895615867, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.736545278218464e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.10995128740431455, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.1832212156129045e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.11134307585247043, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.647652972118998e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1127348643006263, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.130919110904311e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.11412665274878218, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6340602651970304e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.11551844119693806, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.158077042589129e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.11691022964509394, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7039280099458373e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.11830201809324982, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272527762979553e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.11969380654140571, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.86474508437579e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.12108559498956159, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4814011941804603e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.12247738343771747, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1232680959720085e-06, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.12386917188587335, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.79106702214893e-06, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.12526096033402923, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4854669814637145e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1266527487821851, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2070834117282414e-06, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.12804453723034098, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.56476940403942e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.12943632567849686, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.341522555726971e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.13082811412665274, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.405570895622014e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.13221990257480862, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.760813172726457e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1336116910229645, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.41056171020555e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.1350034794711204, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.357535734809795e-07, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.13639526791927628, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.038559007141397e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.13778705636743216, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.510400188028116e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.13917884481558804, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13917884481558804, | |
| "eval_loss": NaN, | |
| "eval_runtime": 39.2007, | |
| "eval_samples_per_second": 7.729, | |
| "eval_steps_per_second": 1.939, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.938645079320166e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |