| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.004016064257028, | |
| "eval_steps": 50, | |
| "global_step": 187, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0100000000000002e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.1262, | |
| "eval_samples_per_second": 3.17, | |
| "eval_steps_per_second": 0.815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0321285140562249, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0200000000000003e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0299999999999998e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0642570281124498, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0400000000000006e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08032128514056225, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.05e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0599999999999996e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11244979919678715, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.07e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1285140562248996, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.080000000000001e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.09e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1606425702811245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000101, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17670682730923695, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010099204567752381, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010096818521588718, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20883534136546184, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010092842613167647, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2248995983935743, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010087278094990467, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010080126720006563, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2570281124497992, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010071390741061192, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27309236947791166, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001006107291018579, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010049176477731007, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.30522088353413657, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001003570519134279, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.321285140562249, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010020663294781777, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3373493975903614, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010004055526586416, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3534136546184739, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.985887118580227e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.36947791164658633, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.966163794223652e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.944891766811038e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.40160642570281124, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.922077737513306e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.41767068273092367, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.89772889326693e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.871852904509895e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4497991967871486, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.844457922765326e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.46586345381526106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.815552578073581e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.785145976273591e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4979919678714859, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.75324769613431e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5140562248995983, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.719867786337189e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5301204819277109, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.685016762310616e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5461847389558233, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.648705602917312e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5622489959839357, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.610945746995745e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.571749089756634e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5943775100401606, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.531127979035687e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6104417670682731, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.489095211403759e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6265060240963856, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.445664028135631e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.642570281124498, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.40084811103872e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6586345381526104, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.354661578142996e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6746987951807228, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.307118979253472e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6907630522088354, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.2582352913667e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7068273092369478, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.208025913952674e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.156506664103642e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7389558232931727, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.103693771551366e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7550200803212851, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.049603873554393e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.994254009656934e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7871485943775101, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.937661616321026e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8032128514056225, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.879844521433655e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8032128514056225, | |
| "eval_loss": NaN, | |
| "eval_runtime": 31.6371, | |
| "eval_samples_per_second": 3.319, | |
| "eval_steps_per_second": 0.853, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8192771084337349, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.820820938690554e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8353413654618473, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.76060946185849e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8514056224899599, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.699229058917802e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.636699066087047e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8835341365461847, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.573039181731673e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8995983935742972, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.508269460158566e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9156626506024096, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.442410305298504e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9317269076305221, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.375482464278446e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9477911646586346, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.307507020885723e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.238505388926166e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9799196787148594, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.168499305478269e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9959839357429718, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.09751082404552e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0120481927710843, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.025562307609042e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0281124497991967, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.952676421582755e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0441767068273093, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.878876126673246e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0602409638554218, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.804184671646642e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0763052208835342, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.7286255860047e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.0923694779116466, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6522226725725e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.108433734939759, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.575e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.1244979919678715, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.496981895179884e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.140562248995984, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.418192935584018e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.1566265060240963, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.338657941521007e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.1726907630522088, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.25840196831722e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.1887550200803212, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.177450298423809e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.2048192771084336, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.095828433452151e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2208835341365463, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.01356208614027e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.2369477911646587, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.930677172252738e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.2530120481927711, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.847199802416624e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.2690763052208835, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.763156273896052e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.285140562248996, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.67857306230797e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3012048192771084, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.593476813281724e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.3172690763052208, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.507894334065086e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.421852585079366e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.3493975903614457, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.335378671426258e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3654618473895583, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.248499834349131e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.3815261044176708, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.161243442651405e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.3975903614457832, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0736369840747724e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.4136546184738956, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9857080566399275e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.429718875502008, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8974843599525645e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.4457831325301205, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.808993686477376e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.461847389558233, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7202639127827965e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.4779116465863453, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6313229907592483e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.4939759036144578, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5421989388136696e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.5100401606425704, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.45291983304307e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.5261044176706826, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3635137983899315e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.274008999782215e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.5582329317269075, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.184433633260763e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.5742971887550201, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.094815917096909e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.5903614457831325, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.00518408290309e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.606425702811245, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.915566366739238e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.606425702811245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 32.6131, | |
| "eval_samples_per_second": 3.22, | |
| "eval_steps_per_second": 0.828, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6224899598393574, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8259910002177846e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.6385542168674698, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.736486201610069e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6546184738955825, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.64708016695693e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.6706827309236947, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5578010611863306e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.6867469879518073, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.468677009240751e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7028112449799195, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3797360872172044e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.7188755020080322, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.291006313522626e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.7349397590361446, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.202515640047436e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.751004016064257, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1142919433600734e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.7670682730923695, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.026363015925228e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.783132530120482, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.938756557348597e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.7991967871485943, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.85150016565087e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.8152610441767068, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.764621328573742e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.8313253012048194, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.678147414920635e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.8473895582329316, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.592105665934915e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.8634538152610443, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5065231867182766e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.8795180722891565, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.42142693769203e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.895582329317269, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3368437261039466e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.9116465863453815, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.252800197583376e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.927710843373494, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.169322827747261e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9437751004016064, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086437913859731e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.9598393574297188, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0041715665478494e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.9759036144578315, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9225497015761916e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.9919678714859437, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8415980316827804e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.0080321285140563, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7613420584789948e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0240963855421685, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6818070644159833e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.040160642570281, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.603018104820117e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.0562248995983934, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.525000000000001e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.072289156626506, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.447777327427502e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.0883534136546187, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3713744139953008e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.104417670682731, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2958153283533574e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.1204819277108435, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.221123873326752e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.1365461847389557, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1473235784172456e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.1526104417670684, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0744376923909588e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.1686746987951806, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0024891759544805e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.1847389558232932, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9315006945217314e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.2008032128514055, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.861494611073834e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.216867469879518, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7924929791142774e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.2329317269076308, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7245175357215553e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.248995983935743, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6575896947014965e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.2650602409638556, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.591730539841434e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.281124497991968, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5269608182683277e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.2971887550200805, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4633009339129539e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.3132530120481927, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4007709410821999e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.3293172690763053, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3393905381415114e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.3453815261044175, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.279179061309447e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.36144578313253, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2201554785663463e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.3775100401606424, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1623383836789728e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.393574297188755, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1057459903430662e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 2.4096385542168672, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0503961264456076e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4096385542168672, | |
| "eval_loss": NaN, | |
| "eval_runtime": 27.3269, | |
| "eval_samples_per_second": 3.842, | |
| "eval_steps_per_second": 0.988, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.42570281124498, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.963062284486346e-06, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 2.4417670682730925, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.434933358963576e-06, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.4578313253012047, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.919740860473254e-06, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.4738955823293174, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.417647086332989e-06, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.4899598393574296, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.928810207465288e-06, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.5060240963855422, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.453384218570053e-06, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.522088353413655, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.991518889612788e-06, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.538152610441767, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.543359718643697e-06, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.5542168674698793, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.10904788596243e-06, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.570281124497992, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.688720209643143e-06, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.5863453815261046, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.282509102433675e-06, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.602409638554217, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.890542530042559e-06, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.6184738955823295, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.512943970826882e-06, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.6345381526104417, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.149832376893846e-06, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.6506024096385543, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8013221366281103e-06, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4675230386569094e-06, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.682730923694779, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1485402372640936e-06, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 2.6987951807228914, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8444742192641915e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.714859437751004, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5554207723467453e-06, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.7309236947791167, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2814709549010584e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.746987951807229, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.022711067330703e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.7630522088353415, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7792226248669456e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.7791164658634537, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5510823318896197e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.7951807228915664, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3383620577634734e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.8112449799196786, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.141128814197733e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.8273092369477912, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.594447341358547e-07, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.8433734939759034, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.933670521822479e-07, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.859437751004016, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.429480865721e-07, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.8755020080321287, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0823522268993e-07, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.891566265060241, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8927089814210854e-07, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.907630522088353, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.860925893880768e-07, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.923694779116466, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.987327999343721e-07, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.9397590361445785, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2721905009532497e-07, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.9558232931726907, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.157386832352181e-08, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.9718875502008033, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.181478411282512e-08, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.9879518072289155, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.954322476188714e-09, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.004016064257028, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 187 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 187, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.2268503798697165e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |