| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 89, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011235955056179775, | |
| "grad_norm": 10.042351722717285, | |
| "learning_rate": 4e-05, | |
| "loss": 9.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02247191011235955, | |
| "grad_norm": 10.187106132507324, | |
| "learning_rate": 8e-05, | |
| "loss": 9.1846, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.033707865168539325, | |
| "grad_norm": 8.38694953918457, | |
| "learning_rate": 0.00012, | |
| "loss": 7.9832, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 5.938446521759033, | |
| "learning_rate": 0.00016, | |
| "loss": 5.6493, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056179775280898875, | |
| "grad_norm": 4.586862087249756, | |
| "learning_rate": 0.0002, | |
| "loss": 4.0131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06741573033707865, | |
| "grad_norm": 4.84490442276001, | |
| "learning_rate": 0.00019954545454545455, | |
| "loss": 2.9931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07865168539325842, | |
| "grad_norm": 4.460867881774902, | |
| "learning_rate": 0.0001990909090909091, | |
| "loss": 2.261, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 3.067777395248413, | |
| "learning_rate": 0.00019863636363636364, | |
| "loss": 1.8861, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10112359550561797, | |
| "grad_norm": 1.5425913333892822, | |
| "learning_rate": 0.00019818181818181821, | |
| "loss": 1.4675, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11235955056179775, | |
| "grad_norm": 1.346417784690857, | |
| "learning_rate": 0.00019772727272727273, | |
| "loss": 1.3642, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12359550561797752, | |
| "grad_norm": 1.1825133562088013, | |
| "learning_rate": 0.00019727272727272728, | |
| "loss": 1.0109, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "grad_norm": 0.9976914525032043, | |
| "learning_rate": 0.00019681818181818185, | |
| "loss": 0.9873, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14606741573033707, | |
| "grad_norm": 0.6481193900108337, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 0.6746, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15730337078651685, | |
| "grad_norm": 0.5585954189300537, | |
| "learning_rate": 0.0001959090909090909, | |
| "loss": 0.5289, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16853932584269662, | |
| "grad_norm": 0.9624674916267395, | |
| "learning_rate": 0.00019545454545454548, | |
| "loss": 0.5552, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 0.7732966542243958, | |
| "learning_rate": 0.000195, | |
| "loss": 0.5047, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19101123595505617, | |
| "grad_norm": 0.7540618777275085, | |
| "learning_rate": 0.00019454545454545457, | |
| "loss": 0.5803, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20224719101123595, | |
| "grad_norm": 0.9345465302467346, | |
| "learning_rate": 0.0001940909090909091, | |
| "loss": 0.611, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21348314606741572, | |
| "grad_norm": 0.5613678693771362, | |
| "learning_rate": 0.00019363636363636363, | |
| "loss": 0.4007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2247191011235955, | |
| "grad_norm": 0.8053308725357056, | |
| "learning_rate": 0.0001931818181818182, | |
| "loss": 0.5202, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23595505617977527, | |
| "grad_norm": 0.6621015667915344, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 0.4851, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24719101123595505, | |
| "grad_norm": 0.797894299030304, | |
| "learning_rate": 0.00019227272727272726, | |
| "loss": 0.5401, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25842696629213485, | |
| "grad_norm": 0.5635455250740051, | |
| "learning_rate": 0.00019181818181818183, | |
| "loss": 0.4295, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": 0.5012619495391846, | |
| "learning_rate": 0.00019136363636363638, | |
| "loss": 0.3133, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2808988764044944, | |
| "grad_norm": 0.5143508911132812, | |
| "learning_rate": 0.00019090909090909092, | |
| "loss": 0.3207, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29213483146067415, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090909090909092, | |
| "loss": 0.622, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.30337078651685395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090909090909092, | |
| "loss": 0.5544, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3146067415730337, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090909090909092, | |
| "loss": 0.4251, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3258426966292135, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090909090909092, | |
| "loss": 0.626, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33707865168539325, | |
| "grad_norm": 551.2264404296875, | |
| "learning_rate": 0.00019045454545454547, | |
| "loss": 0.5757, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34831460674157305, | |
| "grad_norm": 0.5639562010765076, | |
| "learning_rate": 0.00019, | |
| "loss": 0.3197, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "grad_norm": 0.5104588270187378, | |
| "learning_rate": 0.00018954545454545455, | |
| "loss": 0.2792, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3707865168539326, | |
| "grad_norm": 0.6046687960624695, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 0.4017, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38202247191011235, | |
| "grad_norm": 0.5290363430976868, | |
| "learning_rate": 0.00018863636363636364, | |
| "loss": 0.2522, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39325842696629215, | |
| "grad_norm": 0.4888989329338074, | |
| "learning_rate": 0.0001881818181818182, | |
| "loss": 0.2513, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4044943820224719, | |
| "grad_norm": 0.4538341164588928, | |
| "learning_rate": 0.00018772727272727273, | |
| "loss": 0.2394, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4157303370786517, | |
| "grad_norm": 0.5249782800674438, | |
| "learning_rate": 0.00018727272727272728, | |
| "loss": 0.3383, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.42696629213483145, | |
| "grad_norm": 0.544735312461853, | |
| "learning_rate": 0.00018681818181818182, | |
| "loss": 0.3345, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.43820224719101125, | |
| "grad_norm": 0.3868374228477478, | |
| "learning_rate": 0.00018636363636363636, | |
| "loss": 0.2425, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 0.41138726472854614, | |
| "learning_rate": 0.0001859090909090909, | |
| "loss": 0.2625, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4606741573033708, | |
| "grad_norm": 0.684403657913208, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 0.3363, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47191011235955055, | |
| "grad_norm": 0.4800611138343811, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 0.2339, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48314606741573035, | |
| "grad_norm": 0.47672778367996216, | |
| "learning_rate": 0.00018454545454545454, | |
| "loss": 0.2908, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4943820224719101, | |
| "grad_norm": 0.44971343874931335, | |
| "learning_rate": 0.00018409090909090909, | |
| "loss": 0.2553, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5056179775280899, | |
| "grad_norm": 0.45129504799842834, | |
| "learning_rate": 0.00018363636363636366, | |
| "loss": 0.325, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5168539325842697, | |
| "grad_norm": 0.48597297072410583, | |
| "learning_rate": 0.00018318181818181817, | |
| "loss": 0.2843, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5280898876404494, | |
| "grad_norm": 0.3514116704463959, | |
| "learning_rate": 0.00018272727272727275, | |
| "loss": 0.2128, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 0.46826595067977905, | |
| "learning_rate": 0.0001822727272727273, | |
| "loss": 0.2601, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.550561797752809, | |
| "grad_norm": 0.3118669390678406, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.2192, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5617977528089888, | |
| "grad_norm": 0.37151020765304565, | |
| "learning_rate": 0.00018136363636363638, | |
| "loss": 0.2255, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5730337078651685, | |
| "grad_norm": 0.4220457971096039, | |
| "learning_rate": 0.00018090909090909092, | |
| "loss": 0.2463, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5842696629213483, | |
| "grad_norm": 0.298927366733551, | |
| "learning_rate": 0.00018045454545454547, | |
| "loss": 0.1939, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5955056179775281, | |
| "grad_norm": 0.3494245707988739, | |
| "learning_rate": 0.00018, | |
| "loss": 0.2276, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6067415730337079, | |
| "grad_norm": 0.7135240435600281, | |
| "learning_rate": 0.00017954545454545456, | |
| "loss": 0.316, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6179775280898876, | |
| "grad_norm": 0.47558313608169556, | |
| "learning_rate": 0.0001790909090909091, | |
| "loss": 0.1915, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6292134831460674, | |
| "grad_norm": 0.47424033284187317, | |
| "learning_rate": 0.00017863636363636364, | |
| "loss": 0.268, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6404494382022472, | |
| "grad_norm": 0.3898255228996277, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 0.2346, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.651685393258427, | |
| "grad_norm": 0.3044908940792084, | |
| "learning_rate": 0.00017772727272727273, | |
| "loss": 0.2244, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6629213483146067, | |
| "grad_norm": 0.4012211561203003, | |
| "learning_rate": 0.00017727272727272728, | |
| "loss": 0.2548, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6741573033707865, | |
| "grad_norm": 0.36978745460510254, | |
| "learning_rate": 0.00017681818181818182, | |
| "loss": 0.1945, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6853932584269663, | |
| "grad_norm": 0.3404884338378906, | |
| "learning_rate": 0.00017636363636363637, | |
| "loss": 0.2486, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6966292134831461, | |
| "grad_norm": 0.3647669851779938, | |
| "learning_rate": 0.0001759090909090909, | |
| "loss": 0.2267, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.7078651685393258, | |
| "grad_norm": 0.2504497170448303, | |
| "learning_rate": 0.00017545454545454548, | |
| "loss": 0.1854, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7191011235955056, | |
| "grad_norm": 0.3424750566482544, | |
| "learning_rate": 0.000175, | |
| "loss": 0.2586, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7303370786516854, | |
| "grad_norm": 0.3164011836051941, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 0.217, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7415730337078652, | |
| "grad_norm": 0.32831573486328125, | |
| "learning_rate": 0.00017409090909090911, | |
| "loss": 0.2326, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7528089887640449, | |
| "grad_norm": 0.3514035940170288, | |
| "learning_rate": 0.00017363636363636363, | |
| "loss": 0.2591, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7640449438202247, | |
| "grad_norm": 0.30864688754081726, | |
| "learning_rate": 0.0001731818181818182, | |
| "loss": 0.2073, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7752808988764045, | |
| "grad_norm": 0.32905542850494385, | |
| "learning_rate": 0.00017272727272727275, | |
| "loss": 0.2224, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7865168539325843, | |
| "grad_norm": 0.27842977643013, | |
| "learning_rate": 0.00017227272727272726, | |
| "loss": 0.1893, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.797752808988764, | |
| "grad_norm": 0.3048170804977417, | |
| "learning_rate": 0.00017181818181818184, | |
| "loss": 0.2206, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8089887640449438, | |
| "grad_norm": 0.25344306230545044, | |
| "learning_rate": 0.00017136363636363638, | |
| "loss": 0.1876, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8202247191011236, | |
| "grad_norm": 0.3092687427997589, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 0.1791, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8314606741573034, | |
| "grad_norm": 0.30857375264167786, | |
| "learning_rate": 0.00017045454545454547, | |
| "loss": 0.2099, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.8426966292134831, | |
| "grad_norm": 0.20455722510814667, | |
| "learning_rate": 0.00017, | |
| "loss": 0.1705, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8539325842696629, | |
| "grad_norm": 0.273429274559021, | |
| "learning_rate": 0.00016954545454545456, | |
| "loss": 0.162, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8651685393258427, | |
| "grad_norm": 0.25422728061676025, | |
| "learning_rate": 0.0001690909090909091, | |
| "loss": 0.1804, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8764044943820225, | |
| "grad_norm": 0.2745291292667389, | |
| "learning_rate": 0.00016863636363636364, | |
| "loss": 0.2184, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8876404494382022, | |
| "grad_norm": 0.30162861943244934, | |
| "learning_rate": 0.0001681818181818182, | |
| "loss": 0.2371, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 0.29733604192733765, | |
| "learning_rate": 0.00016772727272727273, | |
| "loss": 0.2018, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9101123595505618, | |
| "grad_norm": 0.22824084758758545, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 0.1819, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.9213483146067416, | |
| "grad_norm": 0.2034444659948349, | |
| "learning_rate": 0.00016681818181818182, | |
| "loss": 0.1715, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9325842696629213, | |
| "grad_norm": 0.2859365940093994, | |
| "learning_rate": 0.00016636363636363637, | |
| "loss": 0.2157, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9438202247191011, | |
| "grad_norm": 0.2006848305463791, | |
| "learning_rate": 0.00016590909090909094, | |
| "loss": 0.1595, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9550561797752809, | |
| "grad_norm": 0.3615463972091675, | |
| "learning_rate": 0.00016545454545454545, | |
| "loss": 0.2056, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9662921348314607, | |
| "grad_norm": 0.24181589484214783, | |
| "learning_rate": 0.000165, | |
| "loss": 0.2051, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9775280898876404, | |
| "grad_norm": 0.1747487634420395, | |
| "learning_rate": 0.00016454545454545457, | |
| "loss": 0.155, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9887640449438202, | |
| "grad_norm": 0.240757554769516, | |
| "learning_rate": 0.0001640909090909091, | |
| "loss": 0.1786, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.27025192975997925, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.1894, | |
| "step": 89 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 445, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.466718076264448e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |