| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9953917050691244, | |
| "eval_steps": 500, | |
| "global_step": 72, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013824884792626729, | |
| "grad_norm": 34.963134765625, | |
| "learning_rate": 5.0000000000000004e-08, | |
| "loss": 2.5476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027649769585253458, | |
| "grad_norm": 35.32600021362305, | |
| "learning_rate": 1.0000000000000001e-07, | |
| "loss": 2.6058, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041474654377880185, | |
| "grad_norm": 34.955448150634766, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 2.5871, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.055299539170506916, | |
| "grad_norm": 35.09806442260742, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 2.5912, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06912442396313365, | |
| "grad_norm": 34.88739776611328, | |
| "learning_rate": 2.5000000000000004e-07, | |
| "loss": 2.592, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08294930875576037, | |
| "grad_norm": 34.84288024902344, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 2.5609, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0967741935483871, | |
| "grad_norm": 35.0090217590332, | |
| "learning_rate": 3.5000000000000004e-07, | |
| "loss": 2.5651, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11059907834101383, | |
| "grad_norm": 35.03983688354492, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 2.5437, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12442396313364056, | |
| "grad_norm": 34.802833557128906, | |
| "learning_rate": 4.5000000000000003e-07, | |
| "loss": 2.5448, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1382488479262673, | |
| "grad_norm": 34.5220947265625, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 2.504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15207373271889402, | |
| "grad_norm": 34.401580810546875, | |
| "learning_rate": 5.5e-07, | |
| "loss": 2.4814, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16589861751152074, | |
| "grad_norm": 33.76997375488281, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 2.4282, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17972350230414746, | |
| "grad_norm": 33.53415298461914, | |
| "learning_rate": 6.5e-07, | |
| "loss": 2.4216, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1935483870967742, | |
| "grad_norm": 32.401580810546875, | |
| "learning_rate": 7.000000000000001e-07, | |
| "loss": 2.3362, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2073732718894009, | |
| "grad_norm": 33.636661529541016, | |
| "learning_rate": 7.5e-07, | |
| "loss": 2.2978, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22119815668202766, | |
| "grad_norm": 31.3782901763916, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 2.1358, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2350230414746544, | |
| "grad_norm": 30.72391700744629, | |
| "learning_rate": 8.500000000000001e-07, | |
| "loss": 2.0652, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2488479262672811, | |
| "grad_norm": 30.817584991455078, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 2.0115, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2626728110599078, | |
| "grad_norm": 29.683996200561523, | |
| "learning_rate": 9.500000000000001e-07, | |
| "loss": 1.8668, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2764976958525346, | |
| "grad_norm": 29.506683349609375, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.7796, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2903225806451613, | |
| "grad_norm": 27.55340003967285, | |
| "learning_rate": 1.0500000000000001e-06, | |
| "loss": 1.5656, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.30414746543778803, | |
| "grad_norm": 27.78036880493164, | |
| "learning_rate": 1.1e-06, | |
| "loss": 1.5112, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31797235023041476, | |
| "grad_norm": 26.36115264892578, | |
| "learning_rate": 1.1500000000000002e-06, | |
| "loss": 1.3283, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3317972350230415, | |
| "grad_norm": 25.388761520385742, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 1.137, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3456221198156682, | |
| "grad_norm": 25.21432876586914, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.9867, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35944700460829493, | |
| "grad_norm": 24.924489974975586, | |
| "learning_rate": 1.3e-06, | |
| "loss": 0.7122, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.37327188940092165, | |
| "grad_norm": 21.881420135498047, | |
| "learning_rate": 1.3500000000000002e-06, | |
| "loss": 0.4952, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 17.67154884338379, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 0.3602, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4009216589861751, | |
| "grad_norm": 11.489490509033203, | |
| "learning_rate": 1.45e-06, | |
| "loss": 0.2432, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4147465437788018, | |
| "grad_norm": 7.622438907623291, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.189, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 4.340638637542725, | |
| "learning_rate": 1.5500000000000002e-06, | |
| "loss": 0.1302, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4423963133640553, | |
| "grad_norm": 3.079514980316162, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.1075, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.45622119815668205, | |
| "grad_norm": 2.355943441390991, | |
| "learning_rate": 1.6500000000000003e-06, | |
| "loss": 0.0998, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4700460829493088, | |
| "grad_norm": 1.9480725526809692, | |
| "learning_rate": 1.7000000000000002e-06, | |
| "loss": 0.0926, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "grad_norm": 1.8598166704177856, | |
| "learning_rate": 1.75e-06, | |
| "loss": 0.0733, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4976958525345622, | |
| "grad_norm": 0.9892730712890625, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 0.0664, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.511520737327189, | |
| "grad_norm": 0.8992418050765991, | |
| "learning_rate": 1.85e-06, | |
| "loss": 0.0709, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5253456221198156, | |
| "grad_norm": 0.7340101599693298, | |
| "learning_rate": 1.9000000000000002e-06, | |
| "loss": 0.0535, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5391705069124424, | |
| "grad_norm": 0.7032178044319153, | |
| "learning_rate": 1.9500000000000004e-06, | |
| "loss": 0.0573, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5529953917050692, | |
| "grad_norm": 0.6449429392814636, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0576, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5668202764976958, | |
| "grad_norm": 0.6358592510223389, | |
| "learning_rate": 2.05e-06, | |
| "loss": 0.0502, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5806451612903226, | |
| "grad_norm": 0.572036623954773, | |
| "learning_rate": 2.1000000000000002e-06, | |
| "loss": 0.0556, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5944700460829493, | |
| "grad_norm": 0.6538863778114319, | |
| "learning_rate": 2.15e-06, | |
| "loss": 0.0556, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6082949308755761, | |
| "grad_norm": 0.3532159626483917, | |
| "learning_rate": 2.2e-06, | |
| "loss": 0.0452, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6221198156682027, | |
| "grad_norm": 0.4853012263774872, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.0471, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6359447004608295, | |
| "grad_norm": 0.4761648178100586, | |
| "learning_rate": 2.3000000000000004e-06, | |
| "loss": 0.0469, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6497695852534562, | |
| "grad_norm": 0.6094638109207153, | |
| "learning_rate": 2.35e-06, | |
| "loss": 0.047, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.663594470046083, | |
| "grad_norm": 0.5211306214332581, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0402, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6774193548387096, | |
| "grad_norm": 0.2997778356075287, | |
| "learning_rate": 2.4500000000000003e-06, | |
| "loss": 0.0425, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6912442396313364, | |
| "grad_norm": 0.37834689021110535, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0446, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7050691244239631, | |
| "grad_norm": 0.31011995673179626, | |
| "learning_rate": 2.55e-06, | |
| "loss": 0.0406, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7188940092165899, | |
| "grad_norm": 0.3113131523132324, | |
| "learning_rate": 2.6e-06, | |
| "loss": 0.0368, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7327188940092166, | |
| "grad_norm": 0.5685846209526062, | |
| "learning_rate": 2.6500000000000005e-06, | |
| "loss": 0.0389, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7465437788018433, | |
| "grad_norm": 0.29334983229637146, | |
| "learning_rate": 2.7000000000000004e-06, | |
| "loss": 0.0423, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7603686635944701, | |
| "grad_norm": 0.5776861906051636, | |
| "learning_rate": 2.7500000000000004e-06, | |
| "loss": 0.0399, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.35423165559768677, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 0.0357, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7880184331797235, | |
| "grad_norm": 0.37902742624282837, | |
| "learning_rate": 2.85e-06, | |
| "loss": 0.0407, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8018433179723502, | |
| "grad_norm": 0.26948878169059753, | |
| "learning_rate": 2.9e-06, | |
| "loss": 0.0351, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.815668202764977, | |
| "grad_norm": 0.35688117146492004, | |
| "learning_rate": 2.95e-06, | |
| "loss": 0.0377, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8294930875576036, | |
| "grad_norm": 0.5287911891937256, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0377, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8433179723502304, | |
| "grad_norm": 0.2950785756111145, | |
| "learning_rate": 3.05e-06, | |
| "loss": 0.0361, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.2789723575115204, | |
| "learning_rate": 3.1000000000000004e-06, | |
| "loss": 0.032, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8709677419354839, | |
| "grad_norm": 0.2802198529243469, | |
| "learning_rate": 3.1500000000000003e-06, | |
| "loss": 0.0394, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8847926267281107, | |
| "grad_norm": 0.286981463432312, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.033, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8986175115207373, | |
| "grad_norm": 0.37392762303352356, | |
| "learning_rate": 3.2500000000000002e-06, | |
| "loss": 0.0335, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9124423963133641, | |
| "grad_norm": 0.25025588274002075, | |
| "learning_rate": 3.3000000000000006e-06, | |
| "loss": 0.0311, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.9262672811059908, | |
| "grad_norm": 0.4292861521244049, | |
| "learning_rate": 3.3500000000000005e-06, | |
| "loss": 0.0362, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9400921658986175, | |
| "grad_norm": 0.4717651307582855, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 0.0303, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.9539170506912442, | |
| "grad_norm": 0.49291253089904785, | |
| "learning_rate": 3.45e-06, | |
| "loss": 0.0352, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 0.3729935586452484, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0297, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9815668202764977, | |
| "grad_norm": 0.27150583267211914, | |
| "learning_rate": 3.5500000000000003e-06, | |
| "loss": 0.0326, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9953917050691244, | |
| "grad_norm": 0.34516096115112305, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.0336, | |
| "step": 72 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 432, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 72, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.631891949769458e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |