| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.3255813953488373, | |
| "eval_steps": 10, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011627906976744186, | |
| "grad_norm": 1.630926489830017, | |
| "learning_rate": 0.0, | |
| "loss": 2.6815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023255813953488372, | |
| "grad_norm": 1.7017581462860107, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 2.8172, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03488372093023256, | |
| "grad_norm": 1.7061189413070679, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 2.7979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.046511627906976744, | |
| "grad_norm": 1.735384225845337, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 2.7698, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05813953488372093, | |
| "grad_norm": 1.8297396898269653, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 2.6846, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06976744186046512, | |
| "grad_norm": 1.9019414186477661, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 2.4865, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08139534883720931, | |
| "grad_norm": 2.0125694274902344, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 2.3993, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09302325581395349, | |
| "grad_norm": 2.0356626510620117, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 2.0547, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10465116279069768, | |
| "grad_norm": 2.1409757137298584, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 1.7189, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 2.369163751602173, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 1.4047, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "eval_loss": 1.1081944704055786, | |
| "eval_runtime": 69.1299, | |
| "eval_samples_per_second": 70.707, | |
| "eval_steps_per_second": 1.114, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12790697674418605, | |
| "grad_norm": 2.303812265396118, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.0561, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13953488372093023, | |
| "grad_norm": 1.9584007263183594, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.7269, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1511627906976744, | |
| "grad_norm": 1.8204364776611328, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.4613, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16279069767441862, | |
| "grad_norm": 1.328773021697998, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2739, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1744186046511628, | |
| "grad_norm": 1.0226366519927979, | |
| "learning_rate": 0.0001076923076923077, | |
| "loss": 0.1802, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 0.5955405831336975, | |
| "learning_rate": 0.00011538461538461538, | |
| "loss": 0.1093, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19767441860465115, | |
| "grad_norm": 0.2616266906261444, | |
| "learning_rate": 0.0001230769230769231, | |
| "loss": 0.0676, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20930232558139536, | |
| "grad_norm": 0.12042512744665146, | |
| "learning_rate": 0.00013076923076923077, | |
| "loss": 0.045, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.22093023255813954, | |
| "grad_norm": 0.12201035767793655, | |
| "learning_rate": 0.00013846153846153847, | |
| "loss": 0.0505, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 0.09313634783029556, | |
| "learning_rate": 0.00014615384615384615, | |
| "loss": 0.0377, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "eval_loss": 0.04212512448430061, | |
| "eval_runtime": 68.7789, | |
| "eval_samples_per_second": 71.068, | |
| "eval_steps_per_second": 1.12, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2441860465116279, | |
| "grad_norm": 0.11886867135763168, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.0409, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2558139534883721, | |
| "grad_norm": 0.09348498284816742, | |
| "learning_rate": 0.00016153846153846155, | |
| "loss": 0.0322, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26744186046511625, | |
| "grad_norm": 0.11308024078607559, | |
| "learning_rate": 0.00016923076923076923, | |
| "loss": 0.0389, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.27906976744186046, | |
| "grad_norm": 0.10123038291931152, | |
| "learning_rate": 0.00017692307692307693, | |
| "loss": 0.0355, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.29069767441860467, | |
| "grad_norm": 0.20477375388145447, | |
| "learning_rate": 0.00018461538461538463, | |
| "loss": 0.0392, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3023255813953488, | |
| "grad_norm": 0.09108395129442215, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 0.0311, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.313953488372093, | |
| "grad_norm": 0.10242355614900589, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0311, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.32558139534883723, | |
| "grad_norm": 0.10945220291614532, | |
| "learning_rate": 0.00019999083173529673, | |
| "loss": 0.0304, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3372093023255814, | |
| "grad_norm": 0.07543787360191345, | |
| "learning_rate": 0.0001999633286223284, | |
| "loss": 0.0295, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "grad_norm": 0.07906319946050644, | |
| "learning_rate": 0.00019991749570421146, | |
| "loss": 0.0309, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "eval_loss": 0.03273880109190941, | |
| "eval_runtime": 69.34, | |
| "eval_samples_per_second": 70.493, | |
| "eval_steps_per_second": 1.11, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36046511627906974, | |
| "grad_norm": 0.07591050863265991, | |
| "learning_rate": 0.00019985334138511237, | |
| "loss": 0.0298, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 0.07976777851581573, | |
| "learning_rate": 0.0001997708774287068, | |
| "loss": 0.0346, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.38372093023255816, | |
| "grad_norm": 0.06528059393167496, | |
| "learning_rate": 0.0001996701189560223, | |
| "loss": 0.0301, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3953488372093023, | |
| "grad_norm": 0.04785207286477089, | |
| "learning_rate": 0.00019955108444266585, | |
| "loss": 0.0291, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4069767441860465, | |
| "grad_norm": 0.06423522531986237, | |
| "learning_rate": 0.00019941379571543596, | |
| "loss": 0.0302, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4186046511627907, | |
| "grad_norm": 0.043477609753608704, | |
| "learning_rate": 0.00019925827794832056, | |
| "loss": 0.0281, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.43023255813953487, | |
| "grad_norm": 0.0563591867685318, | |
| "learning_rate": 0.00019908455965788067, | |
| "loss": 0.0321, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4418604651162791, | |
| "grad_norm": 0.07481367886066437, | |
| "learning_rate": 0.00019889267269802176, | |
| "loss": 0.0285, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.45348837209302323, | |
| "grad_norm": 0.05782244727015495, | |
| "learning_rate": 0.00019868265225415265, | |
| "loss": 0.0283, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 0.05342981219291687, | |
| "learning_rate": 0.00019845453683673368, | |
| "loss": 0.0276, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "eval_loss": 0.02999330498278141, | |
| "eval_runtime": 68.8117, | |
| "eval_samples_per_second": 71.034, | |
| "eval_steps_per_second": 1.119, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47674418604651164, | |
| "grad_norm": 0.07017785310745239, | |
| "learning_rate": 0.0001982083682742156, | |
| "loss": 0.0298, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4883720930232558, | |
| "grad_norm": 0.04703626409173012, | |
| "learning_rate": 0.00019794419170536916, | |
| "loss": 0.0264, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.04164445772767067, | |
| "learning_rate": 0.00019766205557100868, | |
| "loss": 0.0286, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5116279069767442, | |
| "grad_norm": 0.04445081949234009, | |
| "learning_rate": 0.00019736201160510931, | |
| "loss": 0.0282, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5232558139534884, | |
| "grad_norm": 0.03947937488555908, | |
| "learning_rate": 0.00019704411482532116, | |
| "loss": 0.0253, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5348837209302325, | |
| "grad_norm": 0.04509953781962395, | |
| "learning_rate": 0.0001967084235228807, | |
| "loss": 0.0218, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5465116279069767, | |
| "grad_norm": 0.0683850422501564, | |
| "learning_rate": 0.0001963549992519223, | |
| "loss": 0.028, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "grad_norm": 0.045640990138053894, | |
| "learning_rate": 0.0001959839068181914, | |
| "loss": 0.0302, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5697674418604651, | |
| "grad_norm": 0.1620291918516159, | |
| "learning_rate": 0.00019559521426716118, | |
| "loss": 0.0242, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "grad_norm": 0.04173683002591133, | |
| "learning_rate": 0.00019518899287155556, | |
| "loss": 0.0307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "eval_loss": 0.02883034199476242, | |
| "eval_runtime": 69.0904, | |
| "eval_samples_per_second": 70.748, | |
| "eval_steps_per_second": 1.114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5930232558139535, | |
| "grad_norm": 0.03936028108000755, | |
| "learning_rate": 0.00019476531711828027, | |
| "loss": 0.0251, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6046511627906976, | |
| "grad_norm": 0.04982665926218033, | |
| "learning_rate": 0.0001943242646947643, | |
| "loss": 0.0252, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6162790697674418, | |
| "grad_norm": 0.042471516877412796, | |
| "learning_rate": 0.00019386591647471506, | |
| "loss": 0.0287, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.627906976744186, | |
| "grad_norm": 0.03394132852554321, | |
| "learning_rate": 0.00019339035650328869, | |
| "loss": 0.0278, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6395348837209303, | |
| "grad_norm": 0.03576912358403206, | |
| "learning_rate": 0.00019289767198167916, | |
| "loss": 0.0259, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6511627906976745, | |
| "grad_norm": 0.035896990448236465, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0252, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6627906976744186, | |
| "grad_norm": 0.03331352025270462, | |
| "learning_rate": 0.0001918612937763622, | |
| "loss": 0.0274, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6744186046511628, | |
| "grad_norm": 0.04263336956501007, | |
| "learning_rate": 0.00019131779012844912, | |
| "loss": 0.0231, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.686046511627907, | |
| "grad_norm": 0.04020223766565323, | |
| "learning_rate": 0.00019075754196709572, | |
| "loss": 0.0224, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 0.043280404061079025, | |
| "learning_rate": 0.00019018065202237083, | |
| "loss": 0.0266, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "eval_loss": 0.028244854882359505, | |
| "eval_runtime": 68.7936, | |
| "eval_samples_per_second": 71.053, | |
| "eval_steps_per_second": 1.119, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7093023255813954, | |
| "grad_norm": 0.03325851261615753, | |
| "learning_rate": 0.0001895872260758688, | |
| "loss": 0.024, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.7209302325581395, | |
| "grad_norm": 0.02916116639971733, | |
| "learning_rate": 0.00018897737294131284, | |
| "loss": 0.0237, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.7325581395348837, | |
| "grad_norm": 0.033790189772844315, | |
| "learning_rate": 0.0001883512044446023, | |
| "loss": 0.0261, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 0.03239690884947777, | |
| "learning_rate": 0.0001877088354033077, | |
| "loss": 0.0272, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7558139534883721, | |
| "grad_norm": 0.03925548493862152, | |
| "learning_rate": 0.0001870503836056172, | |
| "loss": 0.0246, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7674418604651163, | |
| "grad_norm": 0.03802689164876938, | |
| "learning_rate": 0.00018637596978873835, | |
| "loss": 0.0294, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7790697674418605, | |
| "grad_norm": 0.03799804300069809, | |
| "learning_rate": 0.00018568571761675893, | |
| "loss": 0.025, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7906976744186046, | |
| "grad_norm": 0.034483980387449265, | |
| "learning_rate": 0.0001849797536579715, | |
| "loss": 0.0261, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8023255813953488, | |
| "grad_norm": 0.049156103283166885, | |
| "learning_rate": 0.0001842582073616649, | |
| "loss": 0.024, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "grad_norm": 0.03340472653508186, | |
| "learning_rate": 0.000183521211034388, | |
| "loss": 0.0293, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "eval_loss": 0.02760264091193676, | |
| "eval_runtime": 68.781, | |
| "eval_samples_per_second": 71.066, | |
| "eval_steps_per_second": 1.119, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8255813953488372, | |
| "grad_norm": 0.030273284763097763, | |
| "learning_rate": 0.00018276889981568906, | |
| "loss": 0.026, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8372093023255814, | |
| "grad_norm": 0.02898152358829975, | |
| "learning_rate": 0.0001820014116533359, | |
| "loss": 0.0247, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8488372093023255, | |
| "grad_norm": 0.03946846351027489, | |
| "learning_rate": 0.00018121888727802113, | |
| "loss": 0.0259, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8604651162790697, | |
| "grad_norm": 0.035859089344739914, | |
| "learning_rate": 0.0001804214701775569, | |
| "loss": 0.0276, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.872093023255814, | |
| "grad_norm": 0.03241611272096634, | |
| "learning_rate": 0.00017960930657056438, | |
| "loss": 0.0229, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8837209302325582, | |
| "grad_norm": 0.025535929948091507, | |
| "learning_rate": 0.00017878254537966216, | |
| "loss": 0.0202, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8953488372093024, | |
| "grad_norm": 0.03790373355150223, | |
| "learning_rate": 0.00017794133820415916, | |
| "loss": 0.026, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.9069767441860465, | |
| "grad_norm": 0.0408620722591877, | |
| "learning_rate": 0.0001770858392922565, | |
| "loss": 0.0253, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.9186046511627907, | |
| "grad_norm": 0.033651720732450485, | |
| "learning_rate": 0.00017621620551276366, | |
| "loss": 0.0227, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 0.03782816231250763, | |
| "learning_rate": 0.00017533259632633442, | |
| "loss": 0.0254, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "eval_loss": 0.026909608393907547, | |
| "eval_runtime": 68.7973, | |
| "eval_samples_per_second": 71.049, | |
| "eval_steps_per_second": 1.119, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9418604651162791, | |
| "grad_norm": 0.03370513767004013, | |
| "learning_rate": 0.00017443517375622704, | |
| "loss": 0.0261, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.9534883720930233, | |
| "grad_norm": 0.03856685757637024, | |
| "learning_rate": 0.00017352410235859503, | |
| "loss": 0.0256, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9651162790697675, | |
| "grad_norm": 0.04497801512479782, | |
| "learning_rate": 0.0001725995491923131, | |
| "loss": 0.0262, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9767441860465116, | |
| "grad_norm": 0.031994592398405075, | |
| "learning_rate": 0.00017166168378834448, | |
| "loss": 0.0251, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9883720930232558, | |
| "grad_norm": 0.035724181681871414, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0254, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.029222311452031136, | |
| "learning_rate": 0.00016974670656467824, | |
| "loss": 0.0238, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.0116279069767442, | |
| "grad_norm": 0.039559703320264816, | |
| "learning_rate": 0.00016876994588534234, | |
| "loss": 0.0296, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.0232558139534884, | |
| "grad_norm": 0.031729090958833694, | |
| "learning_rate": 0.0001677805751846563, | |
| "loss": 0.018, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.0348837209302326, | |
| "grad_norm": 0.029029319062829018, | |
| "learning_rate": 0.00016677877587886956, | |
| "loss": 0.0244, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.0465116279069768, | |
| "grad_norm": 0.025509672239422798, | |
| "learning_rate": 0.00016576473166320644, | |
| "loss": 0.0215, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0465116279069768, | |
| "eval_loss": 0.026453962549567223, | |
| "eval_runtime": 68.7872, | |
| "eval_samples_per_second": 71.06, | |
| "eval_steps_per_second": 1.119, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.058139534883721, | |
| "grad_norm": 0.027732428163290024, | |
| "learning_rate": 0.00016473862847818277, | |
| "loss": 0.0251, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.069767441860465, | |
| "grad_norm": 0.023567862808704376, | |
| "learning_rate": 0.00016370065447551078, | |
| "loss": 0.0224, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.0813953488372092, | |
| "grad_norm": 0.030995313078165054, | |
| "learning_rate": 0.00016265099998359866, | |
| "loss": 0.0236, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.0930232558139534, | |
| "grad_norm": 0.03294675052165985, | |
| "learning_rate": 0.00016158985747265108, | |
| "loss": 0.0253, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.1046511627906976, | |
| "grad_norm": 0.030441010370850563, | |
| "learning_rate": 0.00016051742151937655, | |
| "loss": 0.0228, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.1162790697674418, | |
| "grad_norm": 0.029724519699811935, | |
| "learning_rate": 0.000159433888771309, | |
| "loss": 0.0193, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.127906976744186, | |
| "grad_norm": 0.04900391027331352, | |
| "learning_rate": 0.00015833945791074943, | |
| "loss": 0.0206, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.1395348837209303, | |
| "grad_norm": 0.0280914343893528, | |
| "learning_rate": 0.0001572343296183344, | |
| "loss": 0.0189, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.1511627906976745, | |
| "grad_norm": 0.031953178346157074, | |
| "learning_rate": 0.00015611870653623825, | |
| "loss": 0.0226, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "grad_norm": 0.02610064297914505, | |
| "learning_rate": 0.0001549927932310155, | |
| "loss": 0.0176, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "eval_loss": 0.026211915537714958, | |
| "eval_runtime": 68.7868, | |
| "eval_samples_per_second": 71.06, | |
| "eval_steps_per_second": 1.119, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1744186046511629, | |
| "grad_norm": 0.04419023171067238, | |
| "learning_rate": 0.00015385679615609042, | |
| "loss": 0.0269, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.1860465116279069, | |
| "grad_norm": 0.09231790900230408, | |
| "learning_rate": 0.00015271092361390077, | |
| "loss": 0.0258, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.197674418604651, | |
| "grad_norm": 0.034355148673057556, | |
| "learning_rate": 0.00015155538571770218, | |
| "loss": 0.0244, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.2093023255813953, | |
| "grad_norm": 0.03240971267223358, | |
| "learning_rate": 0.00015039039435304078, | |
| "loss": 0.0235, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.2209302325581395, | |
| "grad_norm": 0.02766534686088562, | |
| "learning_rate": 0.00014921616313890072, | |
| "loss": 0.021, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.2325581395348837, | |
| "grad_norm": 0.030099626630544662, | |
| "learning_rate": 0.00014803290738853395, | |
| "loss": 0.0218, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.244186046511628, | |
| "grad_norm": 0.030833614990115166, | |
| "learning_rate": 0.00014684084406997903, | |
| "loss": 0.0197, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.255813953488372, | |
| "grad_norm": 0.02916071005165577, | |
| "learning_rate": 0.0001456401917662769, | |
| "loss": 0.022, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.2674418604651163, | |
| "grad_norm": 0.024599241092801094, | |
| "learning_rate": 0.00014443117063539038, | |
| "loss": 0.0249, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.2790697674418605, | |
| "grad_norm": 0.04152291268110275, | |
| "learning_rate": 0.00014321400236983457, | |
| "loss": 0.0227, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2790697674418605, | |
| "eval_loss": 0.025697337463498116, | |
| "eval_runtime": 68.7913, | |
| "eval_samples_per_second": 71.055, | |
| "eval_steps_per_second": 1.119, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2906976744186047, | |
| "grad_norm": 0.026202471926808357, | |
| "learning_rate": 0.00014198891015602646, | |
| "loss": 0.0225, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.302325581395349, | |
| "grad_norm": 0.026729293167591095, | |
| "learning_rate": 0.0001407561186333601, | |
| "loss": 0.0231, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.3139534883720931, | |
| "grad_norm": 0.03199277073144913, | |
| "learning_rate": 0.00013951585385301555, | |
| "loss": 0.0187, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.3255813953488373, | |
| "grad_norm": 0.030409252271056175, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0251, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.3372093023255813, | |
| "grad_norm": 0.029044533148407936, | |
| "learning_rate": 0.00013701381553399145, | |
| "loss": 0.0206, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.3488372093023255, | |
| "grad_norm": 0.0352545827627182, | |
| "learning_rate": 0.000135752500782304, | |
| "loss": 0.0195, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.3604651162790697, | |
| "grad_norm": 0.03767949342727661, | |
| "learning_rate": 0.00013448463026279704, | |
| "loss": 0.0253, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.372093023255814, | |
| "grad_norm": 0.02688649669289589, | |
| "learning_rate": 0.0001332104364589212, | |
| "loss": 0.0196, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.3837209302325582, | |
| "grad_norm": 0.03161188215017319, | |
| "learning_rate": 0.000131930153013598, | |
| "loss": 0.0219, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.3953488372093024, | |
| "grad_norm": 0.03074447624385357, | |
| "learning_rate": 0.00013064401468637792, | |
| "loss": 0.0198, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3953488372093024, | |
| "eval_loss": 0.025383805856108665, | |
| "eval_runtime": 68.781, | |
| "eval_samples_per_second": 71.066, | |
| "eval_steps_per_second": 1.119, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.4069767441860466, | |
| "grad_norm": 0.03676707297563553, | |
| "learning_rate": 0.00012935225731039348, | |
| "loss": 0.0268, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.4186046511627908, | |
| "grad_norm": 0.04459831491112709, | |
| "learning_rate": 0.00012805511774911584, | |
| "loss": 0.0233, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.4302325581395348, | |
| "grad_norm": 0.03590243309736252, | |
| "learning_rate": 0.00012675283385292212, | |
| "loss": 0.0222, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.441860465116279, | |
| "grad_norm": 0.036192964762449265, | |
| "learning_rate": 0.00012544564441548182, | |
| "loss": 0.0251, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.4534883720930232, | |
| "grad_norm": 0.03172110393643379, | |
| "learning_rate": 0.00012413378912997058, | |
| "loss": 0.0202, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4651162790697674, | |
| "grad_norm": 0.032995227724313736, | |
| "learning_rate": 0.0001228175085451186, | |
| "loss": 0.0219, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.4767441860465116, | |
| "grad_norm": 0.02672835998237133, | |
| "learning_rate": 0.00012149704402110243, | |
| "loss": 0.0185, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.4883720930232558, | |
| "grad_norm": 0.03171510249376297, | |
| "learning_rate": 0.00012017263768528775, | |
| "loss": 0.0196, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.03766058757901192, | |
| "learning_rate": 0.00011884453238783185, | |
| "loss": 0.0223, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.5116279069767442, | |
| "grad_norm": 0.038156960159540176, | |
| "learning_rate": 0.00011751297165715309, | |
| "loss": 0.0245, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.5116279069767442, | |
| "eval_loss": 0.025349650532007217, | |
| "eval_runtime": 68.7837, | |
| "eval_samples_per_second": 71.063, | |
| "eval_steps_per_second": 1.119, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.5232558139534884, | |
| "grad_norm": 0.03054482489824295, | |
| "learning_rate": 0.0001161781996552765, | |
| "loss": 0.0217, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.5348837209302326, | |
| "grad_norm": 0.026866618543863297, | |
| "learning_rate": 0.00011484046113306262, | |
| "loss": 0.0196, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.5465116279069768, | |
| "grad_norm": 0.035294584929943085, | |
| "learning_rate": 0.00011350000138532902, | |
| "loss": 0.0237, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.558139534883721, | |
| "grad_norm": 0.02969173528254032, | |
| "learning_rate": 0.00011215706620587149, | |
| "loss": 0.0203, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.5697674418604652, | |
| "grad_norm": 0.031717926263809204, | |
| "learning_rate": 0.00011081190184239419, | |
| "loss": 0.0192, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.5813953488372094, | |
| "grad_norm": 0.03667771443724632, | |
| "learning_rate": 0.0001094647549513561, | |
| "loss": 0.0268, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.5930232558139537, | |
| "grad_norm": 0.0326247438788414, | |
| "learning_rate": 0.00010811587255274313, | |
| "loss": 0.0213, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.6046511627906976, | |
| "grad_norm": 0.03693091496825218, | |
| "learning_rate": 0.00010676550198477293, | |
| "loss": 0.0203, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.6162790697674418, | |
| "grad_norm": 0.037649210542440414, | |
| "learning_rate": 0.00010541389085854176, | |
| "loss": 0.0255, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.627906976744186, | |
| "grad_norm": 0.03507932275533676, | |
| "learning_rate": 0.00010406128701262128, | |
| "loss": 0.0217, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.627906976744186, | |
| "eval_loss": 0.025237275287508965, | |
| "eval_runtime": 69.013, | |
| "eval_samples_per_second": 70.827, | |
| "eval_steps_per_second": 1.116, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.6395348837209303, | |
| "grad_norm": 0.02867533639073372, | |
| "learning_rate": 0.00010270793846761347, | |
| "loss": 0.022, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.6511627906976745, | |
| "grad_norm": 0.02936953864991665, | |
| "learning_rate": 0.00010135409338067219, | |
| "loss": 0.0208, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.6627906976744184, | |
| "grad_norm": 0.02879083901643753, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0226, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.6744186046511627, | |
| "grad_norm": 0.029482927173376083, | |
| "learning_rate": 9.864590661932783e-05, | |
| "loss": 0.0216, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.6860465116279069, | |
| "grad_norm": 0.033599238842725754, | |
| "learning_rate": 9.729206153238657e-05, | |
| "loss": 0.0255, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.697674418604651, | |
| "grad_norm": 0.03904499486088753, | |
| "learning_rate": 9.59387129873787e-05, | |
| "loss": 0.0273, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.7093023255813953, | |
| "grad_norm": 0.028350962325930595, | |
| "learning_rate": 9.458610914145826e-05, | |
| "loss": 0.0206, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.7209302325581395, | |
| "grad_norm": 0.030183596536517143, | |
| "learning_rate": 9.323449801522709e-05, | |
| "loss": 0.0194, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.7325581395348837, | |
| "grad_norm": 0.030208786949515343, | |
| "learning_rate": 9.18841274472569e-05, | |
| "loss": 0.0184, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.744186046511628, | |
| "grad_norm": 0.033600978553295135, | |
| "learning_rate": 9.05352450486439e-05, | |
| "loss": 0.0209, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.744186046511628, | |
| "eval_loss": 0.024917516857385635, | |
| "eval_runtime": 68.8307, | |
| "eval_samples_per_second": 71.015, | |
| "eval_steps_per_second": 1.119, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.755813953488372, | |
| "grad_norm": 0.030587706714868546, | |
| "learning_rate": 8.918809815760585e-05, | |
| "loss": 0.0193, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.7674418604651163, | |
| "grad_norm": 0.03076143190264702, | |
| "learning_rate": 8.78429337941285e-05, | |
| "loss": 0.0234, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.7790697674418605, | |
| "grad_norm": 0.031419869512319565, | |
| "learning_rate": 8.649999861467099e-05, | |
| "loss": 0.0213, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.7906976744186047, | |
| "grad_norm": 0.03213745728135109, | |
| "learning_rate": 8.515953886693739e-05, | |
| "loss": 0.02, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.802325581395349, | |
| "grad_norm": 0.035864025354385376, | |
| "learning_rate": 8.382180034472353e-05, | |
| "loss": 0.0199, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.8139534883720931, | |
| "grad_norm": 0.029758954420685768, | |
| "learning_rate": 8.248702834284693e-05, | |
| "loss": 0.0227, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.8255813953488373, | |
| "grad_norm": 0.02980395406484604, | |
| "learning_rate": 8.115546761216822e-05, | |
| "loss": 0.0168, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.8372093023255816, | |
| "grad_norm": 0.04690724238753319, | |
| "learning_rate": 7.982736231471224e-05, | |
| "loss": 0.022, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.8488372093023255, | |
| "grad_norm": 0.035520877689123154, | |
| "learning_rate": 7.85029559788976e-05, | |
| "loss": 0.0221, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 0.032926399260759354, | |
| "learning_rate": 7.718249145488142e-05, | |
| "loss": 0.0227, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "eval_loss": 0.024740872904658318, | |
| "eval_runtime": 69.0656, | |
| "eval_samples_per_second": 70.773, | |
| "eval_steps_per_second": 1.115, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.872093023255814, | |
| "grad_norm": 0.030970241874456406, | |
| "learning_rate": 7.586621087002945e-05, | |
| "loss": 0.0192, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.8837209302325582, | |
| "grad_norm": 0.03738875314593315, | |
| "learning_rate": 7.455435558451823e-05, | |
| "loss": 0.0213, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.8953488372093024, | |
| "grad_norm": 0.043416742235422134, | |
| "learning_rate": 7.324716614707793e-05, | |
| "loss": 0.0212, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.9069767441860463, | |
| "grad_norm": 0.029200483113527298, | |
| "learning_rate": 7.194488225088417e-05, | |
| "loss": 0.0172, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.9186046511627906, | |
| "grad_norm": 0.03626865893602371, | |
| "learning_rate": 7.064774268960653e-05, | |
| "loss": 0.0218, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.9302325581395348, | |
| "grad_norm": 0.03200054168701172, | |
| "learning_rate": 6.93559853136221e-05, | |
| "loss": 0.02, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.941860465116279, | |
| "grad_norm": 0.04698159173130989, | |
| "learning_rate": 6.806984698640202e-05, | |
| "loss": 0.0245, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.9534883720930232, | |
| "grad_norm": 0.03742319345474243, | |
| "learning_rate": 6.678956354107882e-05, | |
| "loss": 0.025, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.9651162790697674, | |
| "grad_norm": 0.033966902643442154, | |
| "learning_rate": 6.551536973720298e-05, | |
| "loss": 0.0174, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.9767441860465116, | |
| "grad_norm": 0.03295022249221802, | |
| "learning_rate": 6.4247499217696e-05, | |
| "loss": 0.0195, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.9767441860465116, | |
| "eval_loss": 0.02444678172469139, | |
| "eval_runtime": 69.9558, | |
| "eval_samples_per_second": 69.873, | |
| "eval_steps_per_second": 1.101, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.9883720930232558, | |
| "grad_norm": 0.031102096661925316, | |
| "learning_rate": 6.298618446600856e-05, | |
| "loss": 0.02, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.03594454750418663, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0211, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.011627906976744, | |
| "grad_norm": 0.02976617030799389, | |
| "learning_rate": 6.048414614698448e-05, | |
| "loss": 0.0205, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.0232558139534884, | |
| "grad_norm": 0.03257077932357788, | |
| "learning_rate": 5.924388136663992e-05, | |
| "loss": 0.0187, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.0348837209302326, | |
| "grad_norm": 0.027616139501333237, | |
| "learning_rate": 5.801108984397354e-05, | |
| "loss": 0.0153, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.046511627906977, | |
| "grad_norm": 0.029210377484560013, | |
| "learning_rate": 5.6785997630165435e-05, | |
| "loss": 0.0192, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.058139534883721, | |
| "grad_norm": 0.029252031818032265, | |
| "learning_rate": 5.5568829364609664e-05, | |
| "loss": 0.0171, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.0697674418604652, | |
| "grad_norm": 0.029388127848505974, | |
| "learning_rate": 5.435980823372311e-05, | |
| "loss": 0.0184, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.0813953488372094, | |
| "grad_norm": 0.028690453618764877, | |
| "learning_rate": 5.3159155930021e-05, | |
| "loss": 0.0191, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "grad_norm": 0.027052663266658783, | |
| "learning_rate": 5.196709261146606e-05, | |
| "loss": 0.0174, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "eval_loss": 0.024556750431656837, | |
| "eval_runtime": 68.786, | |
| "eval_samples_per_second": 71.061, | |
| "eval_steps_per_second": 1.119, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.104651162790698, | |
| "grad_norm": 0.027682358399033546, | |
| "learning_rate": 5.078383686109926e-05, | |
| "loss": 0.0192, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.116279069767442, | |
| "grad_norm": 0.030152970924973488, | |
| "learning_rate": 4.9609605646959226e-05, | |
| "loss": 0.0182, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.1279069767441863, | |
| "grad_norm": 0.030966833233833313, | |
| "learning_rate": 4.844461428229782e-05, | |
| "loss": 0.0168, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.13953488372093, | |
| "grad_norm": 0.02938106097280979, | |
| "learning_rate": 4.728907638609925e-05, | |
| "loss": 0.0209, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.1511627906976742, | |
| "grad_norm": 0.03003690205514431, | |
| "learning_rate": 4.614320384390959e-05, | |
| "loss": 0.0171, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.1627906976744184, | |
| "grad_norm": 0.03510993719100952, | |
| "learning_rate": 4.500720676898452e-05, | |
| "loss": 0.0196, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.1744186046511627, | |
| "grad_norm": 0.028933702036738396, | |
| "learning_rate": 4.388129346376178e-05, | |
| "loss": 0.0154, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.186046511627907, | |
| "grad_norm": 0.040435321629047394, | |
| "learning_rate": 4.276567038166563e-05, | |
| "loss": 0.0214, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.197674418604651, | |
| "grad_norm": 0.03420122340321541, | |
| "learning_rate": 4.16605420892506e-05, | |
| "loss": 0.0162, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.2093023255813953, | |
| "grad_norm": 0.033222515136003494, | |
| "learning_rate": 4.0566111228691064e-05, | |
| "loss": 0.018, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.2093023255813953, | |
| "eval_loss": 0.02473200112581253, | |
| "eval_runtime": 68.7641, | |
| "eval_samples_per_second": 71.084, | |
| "eval_steps_per_second": 1.12, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.2209302325581395, | |
| "grad_norm": 0.03317669406533241, | |
| "learning_rate": 3.948257848062351e-05, | |
| "loss": 0.0169, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 2.2325581395348837, | |
| "grad_norm": 0.03263445943593979, | |
| "learning_rate": 3.841014252734896e-05, | |
| "loss": 0.0179, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.244186046511628, | |
| "grad_norm": 0.030220864340662956, | |
| "learning_rate": 3.734900001640135e-05, | |
| "loss": 0.0185, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 2.255813953488372, | |
| "grad_norm": 0.033804602921009064, | |
| "learning_rate": 3.629934552448925e-05, | |
| "loss": 0.0192, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.2674418604651163, | |
| "grad_norm": 0.03279354050755501, | |
| "learning_rate": 3.5261371521817244e-05, | |
| "loss": 0.0211, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.2790697674418605, | |
| "grad_norm": 0.03980812057852745, | |
| "learning_rate": 3.423526833679355e-05, | |
| "loss": 0.0187, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.2906976744186047, | |
| "grad_norm": 0.03647474944591522, | |
| "learning_rate": 3.322122412113047e-05, | |
| "loss": 0.0187, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.302325581395349, | |
| "grad_norm": 0.0309713426977396, | |
| "learning_rate": 3.2219424815343735e-05, | |
| "loss": 0.0175, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.313953488372093, | |
| "grad_norm": 0.030178574845194817, | |
| "learning_rate": 3.123005411465766e-05, | |
| "loss": 0.0174, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "grad_norm": 0.03233598917722702, | |
| "learning_rate": 3.0253293435321793e-05, | |
| "loss": 0.0176, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "eval_loss": 0.024754056707024574, | |
| "eval_runtime": 68.7907, | |
| "eval_samples_per_second": 71.056, | |
| "eval_steps_per_second": 1.119, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 258, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.5918719337187246e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |