| { | |
| "best_metric": 0.23508746922016144, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.007125552230297848, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.125552230297848e-05, | |
| "grad_norm": 1.042211651802063, | |
| "learning_rate": 1e-06, | |
| "loss": 0.3057, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.125552230297848e-05, | |
| "eval_loss": 0.7187018990516663, | |
| "eval_runtime": 728.4647, | |
| "eval_samples_per_second": 8.112, | |
| "eval_steps_per_second": 2.029, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014251104460595695, | |
| "grad_norm": 1.606184959411621, | |
| "learning_rate": 2e-06, | |
| "loss": 0.4561, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021376656690893543, | |
| "grad_norm": 1.5126073360443115, | |
| "learning_rate": 3e-06, | |
| "loss": 0.4418, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002850220892119139, | |
| "grad_norm": 1.9431225061416626, | |
| "learning_rate": 4e-06, | |
| "loss": 0.5693, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003562776115148924, | |
| "grad_norm": 1.9813414812088013, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 0.5906, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042753313381787086, | |
| "grad_norm": 1.8735884428024292, | |
| "learning_rate": 6e-06, | |
| "loss": 0.4769, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004987886561208494, | |
| "grad_norm": 1.8006073236465454, | |
| "learning_rate": 7e-06, | |
| "loss": 0.5359, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005700441784238278, | |
| "grad_norm": 1.539935827255249, | |
| "learning_rate": 8e-06, | |
| "loss": 0.4696, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006412997007268063, | |
| "grad_norm": 2.0199615955352783, | |
| "learning_rate": 9e-06, | |
| "loss": 0.5917, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007125552230297848, | |
| "grad_norm": 1.9582463502883911, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.4258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007838107453327633, | |
| "grad_norm": 1.63983952999115, | |
| "learning_rate": 1.1e-05, | |
| "loss": 0.3967, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008550662676357417, | |
| "grad_norm": 1.615180253982544, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.4462, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009263217899387203, | |
| "grad_norm": 1.6889790296554565, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.3865, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009975773122416988, | |
| "grad_norm": 1.7628371715545654, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.5235, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010688328345446773, | |
| "grad_norm": 1.7251651287078857, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.2985, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011400883568476556, | |
| "grad_norm": 1.7641141414642334, | |
| "learning_rate": 1.6e-05, | |
| "loss": 0.4062, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012113438791506342, | |
| "grad_norm": 1.7730730772018433, | |
| "learning_rate": 1.7e-05, | |
| "loss": 0.2535, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012825994014536127, | |
| "grad_norm": 1.6763519048690796, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.2611, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013538549237565912, | |
| "grad_norm": 1.8056228160858154, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.3504, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014251104460595695, | |
| "grad_norm": 1.7897692918777466, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.2584, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001496365968362548, | |
| "grad_norm": 1.8470932245254517, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.2949, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015676214906655266, | |
| "grad_norm": 1.2270846366882324, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.2835, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016388770129685051, | |
| "grad_norm": 1.2478747367858887, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.2585, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0017101325352714834, | |
| "grad_norm": 1.7448375225067139, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.3246, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001781388057574462, | |
| "grad_norm": 1.377163290977478, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1817, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018526435798774405, | |
| "grad_norm": 1.6893903017044067, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.2882, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001923899102180419, | |
| "grad_norm": 1.412766456604004, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.293, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0019951546244833976, | |
| "grad_norm": 1.3407995700836182, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.1812, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002066410146786376, | |
| "grad_norm": 1.8757520914077759, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.2906, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0021376656690893546, | |
| "grad_norm": 1.1567577123641968, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2146, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002208921191392333, | |
| "grad_norm": 1.3666956424713135, | |
| "learning_rate": 2.9984895998119723e-05, | |
| "loss": 0.1976, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0022801767136953113, | |
| "grad_norm": 1.3091264963150024, | |
| "learning_rate": 2.993961440992859e-05, | |
| "loss": 0.1436, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00235143223599829, | |
| "grad_norm": 1.0269235372543335, | |
| "learning_rate": 2.9864246426519023e-05, | |
| "loss": 0.1848, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0024226877583012683, | |
| "grad_norm": 1.5328474044799805, | |
| "learning_rate": 2.9758943828979444e-05, | |
| "loss": 0.2269, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0024939432806042466, | |
| "grad_norm": 1.4854594469070435, | |
| "learning_rate": 2.9623918682727355e-05, | |
| "loss": 0.1739, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0025651988029072254, | |
| "grad_norm": 1.223655104637146, | |
| "learning_rate": 2.9459442910437798e-05, | |
| "loss": 0.1476, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0026364543252102037, | |
| "grad_norm": 1.455477237701416, | |
| "learning_rate": 2.9265847744427305e-05, | |
| "loss": 0.1762, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0027077098475131824, | |
| "grad_norm": 1.223581075668335, | |
| "learning_rate": 2.904352305959606e-05, | |
| "loss": 0.1392, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0027789653698161608, | |
| "grad_norm": 1.1783467531204224, | |
| "learning_rate": 2.8792916588271762e-05, | |
| "loss": 0.1729, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002850220892119139, | |
| "grad_norm": 1.8590701818466187, | |
| "learning_rate": 2.8514533018536286e-05, | |
| "loss": 0.3492, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002921476414422118, | |
| "grad_norm": 1.1538301706314087, | |
| "learning_rate": 2.820893297785107e-05, | |
| "loss": 0.1841, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002992731936725096, | |
| "grad_norm": 1.5694233179092407, | |
| "learning_rate": 2.7876731904027994e-05, | |
| "loss": 0.2156, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003063987459028075, | |
| "grad_norm": 1.357988953590393, | |
| "learning_rate": 2.7518598805819542e-05, | |
| "loss": 0.2037, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.003135242981331053, | |
| "grad_norm": 1.150630235671997, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 0.1607, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0032064985036340315, | |
| "grad_norm": 1.2249001264572144, | |
| "learning_rate": 2.672747223702045e-05, | |
| "loss": 0.2267, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0032777540259370103, | |
| "grad_norm": 1.1600937843322754, | |
| "learning_rate": 2.6296071990054167e-05, | |
| "loss": 0.1363, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0033490095482399886, | |
| "grad_norm": 1.2449615001678467, | |
| "learning_rate": 2.5841922957410875e-05, | |
| "loss": 0.2024, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.003420265070542967, | |
| "grad_norm": 1.292077660560608, | |
| "learning_rate": 2.5365939734802973e-05, | |
| "loss": 0.1311, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0034915205928459456, | |
| "grad_norm": 1.2999500036239624, | |
| "learning_rate": 2.4869080889095693e-05, | |
| "loss": 0.1977, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.003562776115148924, | |
| "grad_norm": 1.0472160577774048, | |
| "learning_rate": 2.4352347027881003e-05, | |
| "loss": 0.1228, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003562776115148924, | |
| "eval_loss": 0.2451000064611435, | |
| "eval_runtime": 732.9403, | |
| "eval_samples_per_second": 8.062, | |
| "eval_steps_per_second": 2.017, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0036340316374519027, | |
| "grad_norm": 0.9585462808609009, | |
| "learning_rate": 2.3816778784387097e-05, | |
| "loss": 0.4262, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.003705287159754881, | |
| "grad_norm": 1.3350521326065063, | |
| "learning_rate": 2.3263454721781537e-05, | |
| "loss": 0.3508, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0037765426820578593, | |
| "grad_norm": 0.9149147868156433, | |
| "learning_rate": 2.2693489161088592e-05, | |
| "loss": 0.2918, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.003847798204360838, | |
| "grad_norm": 0.9929086565971375, | |
| "learning_rate": 2.210802993709498e-05, | |
| "loss": 0.2762, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.003919053726663816, | |
| "grad_norm": 1.152302861213684, | |
| "learning_rate": 2.1508256086763372e-05, | |
| "loss": 0.4493, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.003990309248966795, | |
| "grad_norm": 0.7821376919746399, | |
| "learning_rate": 2.0895375474808857e-05, | |
| "loss": 0.3416, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.004061564771269773, | |
| "grad_norm": 0.9475064277648926, | |
| "learning_rate": 2.0270622361220143e-05, | |
| "loss": 0.2441, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004132820293572752, | |
| "grad_norm": 1.1275452375411987, | |
| "learning_rate": 1.963525491562421e-05, | |
| "loss": 0.2919, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0042040758158757305, | |
| "grad_norm": 1.3180280923843384, | |
| "learning_rate": 1.8990552683500128e-05, | |
| "loss": 0.3509, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.004275331338178709, | |
| "grad_norm": 0.9340567588806152, | |
| "learning_rate": 1.8337814009344716e-05, | |
| "loss": 0.3231, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004346586860481687, | |
| "grad_norm": 0.8491362929344177, | |
| "learning_rate": 1.767835342197955e-05, | |
| "loss": 0.241, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.004417842382784666, | |
| "grad_norm": 1.1892591714859009, | |
| "learning_rate": 1.7013498987264832e-05, | |
| "loss": 0.2353, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.004489097905087645, | |
| "grad_norm": 0.8448580503463745, | |
| "learning_rate": 1.6344589633551502e-05, | |
| "loss": 0.317, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0045603534273906225, | |
| "grad_norm": 1.1618448495864868, | |
| "learning_rate": 1.5672972455257726e-05, | |
| "loss": 0.3225, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.004631608949693601, | |
| "grad_norm": 1.12700355052948, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.3619, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.00470286447199658, | |
| "grad_norm": 1.1308168172836304, | |
| "learning_rate": 1.4327027544742281e-05, | |
| "loss": 0.3482, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.004774119994299558, | |
| "grad_norm": 0.7516178488731384, | |
| "learning_rate": 1.36554103664485e-05, | |
| "loss": 0.1622, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.004845375516602537, | |
| "grad_norm": 1.1769253015518188, | |
| "learning_rate": 1.2986501012735174e-05, | |
| "loss": 0.2047, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.004916631038905515, | |
| "grad_norm": 0.9646146297454834, | |
| "learning_rate": 1.2321646578020452e-05, | |
| "loss": 0.2437, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.004987886561208493, | |
| "grad_norm": 1.2298526763916016, | |
| "learning_rate": 1.1662185990655285e-05, | |
| "loss": 0.4731, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005059142083511472, | |
| "grad_norm": 0.7508978247642517, | |
| "learning_rate": 1.1009447316499875e-05, | |
| "loss": 0.1173, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.005130397605814451, | |
| "grad_norm": 1.2414405345916748, | |
| "learning_rate": 1.036474508437579e-05, | |
| "loss": 0.293, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0052016531281174295, | |
| "grad_norm": 0.951433539390564, | |
| "learning_rate": 9.729377638779859e-06, | |
| "loss": 0.1768, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.005272908650420407, | |
| "grad_norm": 1.0032628774642944, | |
| "learning_rate": 9.104624525191147e-06, | |
| "loss": 0.2115, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.005344164172723386, | |
| "grad_norm": 1.182035207748413, | |
| "learning_rate": 8.491743913236629e-06, | |
| "loss": 0.2316, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.005415419695026365, | |
| "grad_norm": 1.3811928033828735, | |
| "learning_rate": 7.89197006290502e-06, | |
| "loss": 0.2767, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.005486675217329343, | |
| "grad_norm": 1.2715567350387573, | |
| "learning_rate": 7.30651083891141e-06, | |
| "loss": 0.1368, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0055579307396323215, | |
| "grad_norm": 1.1821553707122803, | |
| "learning_rate": 6.736545278218464e-06, | |
| "loss": 0.164, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0056291862619353, | |
| "grad_norm": 1.0368329286575317, | |
| "learning_rate": 6.1832212156129045e-06, | |
| "loss": 0.2001, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.005700441784238278, | |
| "grad_norm": 0.8645971417427063, | |
| "learning_rate": 5.647652972118998e-06, | |
| "loss": 0.1707, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005771697306541257, | |
| "grad_norm": 0.9727141857147217, | |
| "learning_rate": 5.130919110904311e-06, | |
| "loss": 0.2369, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005842952828844236, | |
| "grad_norm": 0.7467105388641357, | |
| "learning_rate": 4.6340602651970304e-06, | |
| "loss": 0.1482, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0059142083511472135, | |
| "grad_norm": 1.139006495475769, | |
| "learning_rate": 4.158077042589129e-06, | |
| "loss": 0.1787, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.005985463873450192, | |
| "grad_norm": 1.2143248319625854, | |
| "learning_rate": 3.7039280099458373e-06, | |
| "loss": 0.2871, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.006056719395753171, | |
| "grad_norm": 2.230907678604126, | |
| "learning_rate": 3.272527762979553e-06, | |
| "loss": 0.2485, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.00612797491805615, | |
| "grad_norm": 1.4834065437316895, | |
| "learning_rate": 2.86474508437579e-06, | |
| "loss": 0.2082, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.006199230440359128, | |
| "grad_norm": 1.2078521251678467, | |
| "learning_rate": 2.4814011941804603e-06, | |
| "loss": 0.205, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.006270485962662106, | |
| "grad_norm": 1.078839659690857, | |
| "learning_rate": 2.1232680959720085e-06, | |
| "loss": 0.1255, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.006341741484965085, | |
| "grad_norm": 1.7553359270095825, | |
| "learning_rate": 1.79106702214893e-06, | |
| "loss": 0.271, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.006412997007268063, | |
| "grad_norm": 1.4102157354354858, | |
| "learning_rate": 1.4854669814637145e-06, | |
| "loss": 0.192, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006484252529571042, | |
| "grad_norm": 0.9362900853157043, | |
| "learning_rate": 1.2070834117282414e-06, | |
| "loss": 0.1759, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0065555080518740205, | |
| "grad_norm": 1.3166675567626953, | |
| "learning_rate": 9.56476940403942e-07, | |
| "loss": 0.2363, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.006626763574176998, | |
| "grad_norm": 1.0089662075042725, | |
| "learning_rate": 7.341522555726971e-07, | |
| "loss": 0.2477, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.006698019096479977, | |
| "grad_norm": 1.362122654914856, | |
| "learning_rate": 5.405570895622014e-07, | |
| "loss": 0.2324, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.006769274618782956, | |
| "grad_norm": 0.8471099734306335, | |
| "learning_rate": 3.760813172726457e-07, | |
| "loss": 0.1179, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.006840530141085934, | |
| "grad_norm": 1.2971007823944092, | |
| "learning_rate": 2.41056171020555e-07, | |
| "loss": 0.1556, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0069117856633889125, | |
| "grad_norm": 1.1084494590759277, | |
| "learning_rate": 1.357535734809795e-07, | |
| "loss": 0.2148, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.006983041185691891, | |
| "grad_norm": 1.6969143152236938, | |
| "learning_rate": 6.038559007141397e-08, | |
| "loss": 0.2654, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.00705429670799487, | |
| "grad_norm": 1.321176290512085, | |
| "learning_rate": 1.510400188028116e-08, | |
| "loss": 0.2057, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.007125552230297848, | |
| "grad_norm": 1.1489577293395996, | |
| "learning_rate": 0.0, | |
| "loss": 0.1503, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007125552230297848, | |
| "eval_loss": 0.23508746922016144, | |
| "eval_runtime": 733.1631, | |
| "eval_samples_per_second": 8.06, | |
| "eval_steps_per_second": 2.016, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.808996786333286e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |