| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1662510390689942, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016625103906899418, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016625103906899418, | |
| "eval_loss": NaN, | |
| "eval_runtime": 97.6098, | |
| "eval_samples_per_second": 5.194, | |
| "eval_steps_per_second": 0.656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033250207813798837, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004987531172069825, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006650041562759767, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00831255195344971, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00997506234413965, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011637572734829594, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013300083125519535, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014962593516209476, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014962593516209476, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6004, | |
| "eval_samples_per_second": 5.248, | |
| "eval_steps_per_second": 0.663, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01662510390689942, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01828761429758936, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.999390827019096e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0199501246882793, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021612635078969242, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023275145469659187, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02493765586034913, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02660016625103907, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02826267664172901, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.029925187032418952, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.029925187032418952, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6099, | |
| "eval_samples_per_second": 5.248, | |
| "eval_steps_per_second": 0.662, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03158769742310889, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03325020781379884, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.034912718204488775, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9271838545667876e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03657522859517872, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.038237738985868665, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8987940462991673e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0399002493765586, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04156275976724855, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043225270157938485, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.848048096156426e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04488778054862843, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8290375725550417e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04488778054862843, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6279, | |
| "eval_samples_per_second": 5.247, | |
| "eval_steps_per_second": 0.662, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.046550290939318374, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04821280133000831, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.788010753606722e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04987531172069826, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.051537822111388194, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05320033250207814, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05486284289276808, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6946583704589973e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05652535328345802, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.058187863674147966, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.059850374064837904, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6156614753256583e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.059850374064837904, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6597, | |
| "eval_samples_per_second": 5.245, | |
| "eval_steps_per_second": 0.662, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06151288445552785, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06317539484621779, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5591929034707468e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06483790523690773, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.529919264233205e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06650041562759768, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06816292601828762, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.469471562785891e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06982543640897755, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4383711467890776e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0714879467996675, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07315045719035744, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3746065934159123e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07481296758104738, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07481296758104738, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.5875, | |
| "eval_samples_per_second": 5.249, | |
| "eval_steps_per_second": 0.663, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07647547797173733, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07813798836242726, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2756373558169992e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0798004987531172, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2419218955996677e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08146300914380715, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0831255195344971, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08478802992518704, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1391731009600655e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08645054031587697, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08811305070656691, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0697564737441254e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.08977556109725686, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0348994967025012e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.08977556109725686, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6415, | |
| "eval_samples_per_second": 5.246, | |
| "eval_steps_per_second": 0.662, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0914380714879468, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09310058187863675, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.651005032974994e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.09476309226932668, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.302435262558748e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09642560266001662, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.09808811305070657, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.60826899039935e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.09975062344139651, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10141313383208644, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.92088309182241e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.10307564422277639, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.580781044003324e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10473815461346633, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.243626441830009e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10473815461346633, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6267, | |
| "eval_samples_per_second": 5.247, | |
| "eval_steps_per_second": 0.662, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10640066500415628, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.10806317539484622, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10972568578553615, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.25393406584088e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1113881961762261, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.11305070656691604, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.616288532109225e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.11471321695760599, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.305284372141095e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.11637572734829593, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11803823773898586, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.700807357667953e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.11970074812967581, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.408070965292534e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.11970074812967581, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6383, | |
| "eval_samples_per_second": 5.246, | |
| "eval_steps_per_second": 0.662, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.12136325852036575, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1230257689110557, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8433852467434175e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.12468827930174564, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346067e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.12635078969243557, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.12801330008312553, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0534162954100264e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.12967581047381546, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8066019966134907e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1313383208645054, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5685517452260566e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.13300083125519535, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13466334164588528, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.119892463932781e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13466334164588528, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6256, | |
| "eval_samples_per_second": 5.247, | |
| "eval_steps_per_second": 0.662, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13632585203657524, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.13798836242726517, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.709624274449584e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1396508728179551, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5195190384357405e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.14131338320864506, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.142975893599335, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1705240714107301e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.14463840399002495, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.012059537008332e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.14630091438071488, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.1479634247714048, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.281614543321269e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.14962593516209477, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14962593516209477, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6211, | |
| "eval_samples_per_second": 5.247, | |
| "eval_steps_per_second": 0.662, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1512884455527847, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.894348370484648e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.15295095594347466, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8738304061681107e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.1546134663341646, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.970427372400353e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.15627597672485452, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.15793848711554448, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.519224698779198e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1596009975062344, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.731931258429638e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.16126350789692437, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4781046317267103e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1629260182876143, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4359497401758026e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.16458852867830423, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.091729809042379e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.16458852867830423, | |
| "eval_loss": NaN, | |
| "eval_runtime": 96.6138, | |
| "eval_samples_per_second": 5.248, | |
| "eval_steps_per_second": 0.662, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1662510390689942, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3869079534239744e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |