| { | |
| "best_metric": 3.843121703539509e-06, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.47468354430379744, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031645569620253164, | |
| "grad_norm": 39.122718811035156, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 4.7862, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031645569620253164, | |
| "eval_loss": 5.090167999267578, | |
| "eval_runtime": 4.6691, | |
| "eval_samples_per_second": 10.709, | |
| "eval_steps_per_second": 1.499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006329113924050633, | |
| "grad_norm": 38.526920318603516, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.8726, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00949367088607595, | |
| "grad_norm": 35.14896011352539, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.2408, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "grad_norm": 18.20745086669922, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.5564, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015822784810126583, | |
| "grad_norm": 14.840872764587402, | |
| "learning_rate": 0.00015, | |
| "loss": 1.0869, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0189873417721519, | |
| "grad_norm": 6.644170761108398, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.283, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022151898734177215, | |
| "grad_norm": 42.69538497924805, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.5808, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02531645569620253, | |
| "grad_norm": 16.369243621826172, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.5497, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028481012658227847, | |
| "grad_norm": 19.000972747802734, | |
| "learning_rate": 0.00027, | |
| "loss": 0.5608, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03164556962025317, | |
| "grad_norm": 11.529747009277344, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3618, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03481012658227848, | |
| "grad_norm": 15.791008949279785, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.5098, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0379746835443038, | |
| "grad_norm": 3.0417582988739014, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0882, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04113924050632911, | |
| "grad_norm": 3.213977336883545, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0588, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04430379746835443, | |
| "grad_norm": 0.42049989104270935, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0048, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04746835443037975, | |
| "grad_norm": 0.010697176679968834, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0002, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05063291139240506, | |
| "grad_norm": 0.08972659707069397, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0003, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05379746835443038, | |
| "grad_norm": 90.54857635498047, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.2488, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.056962025316455694, | |
| "grad_norm": 0.0011396000627428293, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.060126582278481014, | |
| "grad_norm": 32.987918853759766, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.3497, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06329113924050633, | |
| "grad_norm": 0.0006623624940402806, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06645569620253164, | |
| "grad_norm": 0.002704908140003681, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06962025316455696, | |
| "grad_norm": 0.074082151055336, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0003, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07278481012658228, | |
| "grad_norm": 0.051233161240816116, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0002, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0759493670886076, | |
| "grad_norm": 0.002620099810883403, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07911392405063292, | |
| "grad_norm": 0.002381028374657035, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07911392405063292, | |
| "eval_loss": 1.5358215023297817e-05, | |
| "eval_runtime": 4.2105, | |
| "eval_samples_per_second": 11.875, | |
| "eval_steps_per_second": 1.663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08227848101265822, | |
| "grad_norm": 0.0008074412471614778, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08544303797468354, | |
| "grad_norm": 80.40802001953125, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.216, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08860759493670886, | |
| "grad_norm": 0.0007025494705885649, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09177215189873418, | |
| "grad_norm": 0.16022445261478424, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0004, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0949367088607595, | |
| "grad_norm": 0.00044286646880209446, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0981012658227848, | |
| "grad_norm": 0.0007045658421702683, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 4.665228366851807, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.2712, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10443037974683544, | |
| "grad_norm": 35.976463317871094, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 2.2757, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10759493670886076, | |
| "grad_norm": 3.145080089569092, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0429, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11075949367088607, | |
| "grad_norm": 0.7390124201774597, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0082, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11392405063291139, | |
| "grad_norm": 56.273048400878906, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.5411, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11708860759493671, | |
| "grad_norm": 0.016222132369875908, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0002, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12025316455696203, | |
| "grad_norm": 0.00250585051253438, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12341772151898735, | |
| "grad_norm": 0.0014803847298026085, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12658227848101267, | |
| "grad_norm": 0.0008740597986616194, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12974683544303797, | |
| "grad_norm": 0.0006211165455169976, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13291139240506328, | |
| "grad_norm": 0.000527973985299468, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1360759493670886, | |
| "grad_norm": 0.0007822936167940497, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13924050632911392, | |
| "grad_norm": 14.17163372039795, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0377, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14240506329113925, | |
| "grad_norm": 37.15114974975586, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 1.6189, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14556962025316456, | |
| "grad_norm": 0.1055205836892128, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0009, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14873417721518986, | |
| "grad_norm": 15.12343978881836, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.1632, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1518987341772152, | |
| "grad_norm": 0.004173843655735254, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1550632911392405, | |
| "grad_norm": 0.010756113566458225, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0001, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15822784810126583, | |
| "grad_norm": 0.014636156149208546, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15822784810126583, | |
| "eval_loss": 0.0001311919477302581, | |
| "eval_runtime": 4.2069, | |
| "eval_samples_per_second": 11.885, | |
| "eval_steps_per_second": 1.664, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16139240506329114, | |
| "grad_norm": 0.005091713275760412, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.0001, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.16455696202531644, | |
| "grad_norm": 0.009237410500645638, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.0001, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.16772151898734178, | |
| "grad_norm": 0.015599989332258701, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.0002, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.17088607594936708, | |
| "grad_norm": 0.018040731549263, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.0002, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.17405063291139242, | |
| "grad_norm": 0.006186929531395435, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.0001, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17721518987341772, | |
| "grad_norm": 0.006048174574971199, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.0001, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.18037974683544303, | |
| "grad_norm": 0.006537523120641708, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.0001, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.18354430379746836, | |
| "grad_norm": 0.0067470865324139595, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.0001, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18670886075949367, | |
| "grad_norm": 0.007332624401897192, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.0001, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.189873417721519, | |
| "grad_norm": 10.264739036560059, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.051, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1930379746835443, | |
| "grad_norm": 0.002097963122650981, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1962025316455696, | |
| "grad_norm": 0.002509267069399357, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.19936708860759494, | |
| "grad_norm": 0.0069679687730968, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.0001, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 6.7228193283081055, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.0133, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.20569620253164558, | |
| "grad_norm": 0.012821373529732227, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.0001, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2088607594936709, | |
| "grad_norm": 0.005173238459974527, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.0001, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2120253164556962, | |
| "grad_norm": 0.0032975596841424704, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.21518987341772153, | |
| "grad_norm": 0.000420216383645311, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.21835443037974683, | |
| "grad_norm": 0.0010184341808781028, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.22151898734177214, | |
| "grad_norm": 0.0004159672826062888, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22468354430379747, | |
| "grad_norm": 0.00039001807454042137, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.22784810126582278, | |
| "grad_norm": 0.00029691364034079015, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2310126582278481, | |
| "grad_norm": 0.01934441365301609, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23417721518987342, | |
| "grad_norm": 0.0179350096732378, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.23734177215189872, | |
| "grad_norm": 0.005893515422940254, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.23734177215189872, | |
| "eval_loss": 0.0001237610267708078, | |
| "eval_runtime": 4.2074, | |
| "eval_samples_per_second": 11.884, | |
| "eval_steps_per_second": 1.664, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24050632911392406, | |
| "grad_norm": 0.011769886128604412, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.24367088607594936, | |
| "grad_norm": 7.769101142883301, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.0063, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.2468354430379747, | |
| "grad_norm": 0.0002909549803007394, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.00034072331618517637, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.25316455696202533, | |
| "grad_norm": 0.000480585265904665, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2563291139240506, | |
| "grad_norm": 0.000765742443036288, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.25949367088607594, | |
| "grad_norm": 0.0006269936566241086, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2626582278481013, | |
| "grad_norm": 0.0013830035459250212, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.26582278481012656, | |
| "grad_norm": 0.0014289645478129387, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2689873417721519, | |
| "grad_norm": 0.0011403183452785015, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2721518987341772, | |
| "grad_norm": 0.002971477573737502, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.27531645569620256, | |
| "grad_norm": 0.002385311061516404, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.27848101265822783, | |
| "grad_norm": 0.002337276004254818, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.28164556962025317, | |
| "grad_norm": 0.0024681647773832083, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2848101265822785, | |
| "grad_norm": 0.00227755936793983, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2879746835443038, | |
| "grad_norm": 0.002350766211748123, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2911392405063291, | |
| "grad_norm": 0.0026261964812874794, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.29430379746835444, | |
| "grad_norm": 0.0026209403295069933, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.2974683544303797, | |
| "grad_norm": 0.002259510103613138, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.30063291139240506, | |
| "grad_norm": 0.0035024185199290514, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 0.0025430647656321526, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3069620253164557, | |
| "grad_norm": 0.004395894706249237, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.310126582278481, | |
| "grad_norm": 0.0013291619252413511, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.31329113924050633, | |
| "grad_norm": 0.0007702799630351365, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.31645569620253167, | |
| "grad_norm": 0.00030097755370661616, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31645569620253167, | |
| "eval_loss": 1.022299602482235e-05, | |
| "eval_runtime": 4.2028, | |
| "eval_samples_per_second": 11.897, | |
| "eval_steps_per_second": 1.666, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31962025316455694, | |
| "grad_norm": 0.0004665693559218198, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3227848101265823, | |
| "grad_norm": 0.00041321059688925743, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.3259493670886076, | |
| "grad_norm": 0.00036460647243075073, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.3291139240506329, | |
| "grad_norm": 0.00037778099067509174, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.3322784810126582, | |
| "grad_norm": 0.00030751843587495387, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.33544303797468356, | |
| "grad_norm": 0.0002456666261423379, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.33860759493670883, | |
| "grad_norm": 0.0002447838196530938, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.34177215189873417, | |
| "grad_norm": 0.0002842728281393647, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.3449367088607595, | |
| "grad_norm": 0.00024505757028236985, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.34810126582278483, | |
| "grad_norm": 0.00028874975396320224, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3512658227848101, | |
| "grad_norm": 0.00020624457101803273, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.35443037974683544, | |
| "grad_norm": 0.00018322498362977058, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3575949367088608, | |
| "grad_norm": 0.0001932728773681447, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.36075949367088606, | |
| "grad_norm": 0.00017445687262807041, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.3639240506329114, | |
| "grad_norm": 0.00018252633162774146, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3670886075949367, | |
| "grad_norm": 0.00015503902977798134, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.370253164556962, | |
| "grad_norm": 0.00015010620700195432, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.37341772151898733, | |
| "grad_norm": 0.00015455068205483258, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.37658227848101267, | |
| "grad_norm": 0.00016562936070840806, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.379746835443038, | |
| "grad_norm": 0.00018217816250398755, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3829113924050633, | |
| "grad_norm": 0.00015457313566002995, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3860759493670886, | |
| "grad_norm": 0.00016017950838431716, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.38924050632911394, | |
| "grad_norm": 0.0001542173558846116, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.3924050632911392, | |
| "grad_norm": 0.00012690690346062183, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.39556962025316456, | |
| "grad_norm": 0.00013292804942466319, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.39556962025316456, | |
| "eval_loss": 4.310821168473922e-06, | |
| "eval_runtime": 4.2161, | |
| "eval_samples_per_second": 11.859, | |
| "eval_steps_per_second": 1.66, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3987341772151899, | |
| "grad_norm": 0.00013347961066756397, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.40189873417721517, | |
| "grad_norm": 0.00014006522542331368, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 0.00015326595166698098, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.40822784810126583, | |
| "grad_norm": 0.00013687805039808154, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.41139240506329117, | |
| "grad_norm": 0.0001343508338322863, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.41455696202531644, | |
| "grad_norm": 0.00014204278704710305, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4177215189873418, | |
| "grad_norm": 0.00013165705604478717, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4208860759493671, | |
| "grad_norm": 0.00014004629338160157, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.4240506329113924, | |
| "grad_norm": 0.00012275339395273477, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.4272151898734177, | |
| "grad_norm": 0.00013257791579235345, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.43037974683544306, | |
| "grad_norm": 0.00012513244291767478, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.43354430379746833, | |
| "grad_norm": 0.00012306036660447717, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.43670886075949367, | |
| "grad_norm": 0.00014830312284175307, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.439873417721519, | |
| "grad_norm": 0.00013106982805766165, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.4430379746835443, | |
| "grad_norm": 0.00012754443741869181, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4462025316455696, | |
| "grad_norm": 0.00011957551032537594, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.44936708860759494, | |
| "grad_norm": 0.0001281919830944389, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.4525316455696203, | |
| "grad_norm": 0.00011107423779321834, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.45569620253164556, | |
| "grad_norm": 0.0001152564727817662, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.4588607594936709, | |
| "grad_norm": 0.0001198223399114795, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.4620253164556962, | |
| "grad_norm": 0.00011749119585147128, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.4651898734177215, | |
| "grad_norm": 0.00012622641224879771, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.46835443037974683, | |
| "grad_norm": 9.978269372368231e-05, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.47151898734177217, | |
| "grad_norm": 0.00010149357694899663, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.47468354430379744, | |
| "grad_norm": 0.00010994034528266639, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47468354430379744, | |
| "eval_loss": 3.843121703539509e-06, | |
| "eval_runtime": 4.2162, | |
| "eval_samples_per_second": 11.859, | |
| "eval_steps_per_second": 1.66, | |
| "step": 150 | |
| } | |
| ], | |
| "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": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.364765716348928e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |