{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 124, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008064516129032258, "grad_norm": 20.875, "learning_rate": 1.25e-06, "loss": 8.243, "step": 1 }, { "epoch": 0.016129032258064516, "grad_norm": 20.375, "learning_rate": 2.5e-06, "loss": 8.1865, "step": 2 }, { "epoch": 0.024193548387096774, "grad_norm": 20.0, "learning_rate": 3.7500000000000005e-06, "loss": 8.0673, "step": 3 }, { "epoch": 0.03225806451612903, "grad_norm": 20.625, "learning_rate": 5e-06, "loss": 8.0871, "step": 4 }, { "epoch": 0.04032258064516129, "grad_norm": 20.75, "learning_rate": 4.999143312438893e-06, "loss": 8.0484, "step": 5 }, { "epoch": 0.04838709677419355, "grad_norm": 20.5, "learning_rate": 4.9965738368864345e-06, "loss": 7.7429, "step": 6 }, { "epoch": 0.056451612903225805, "grad_norm": 18.0, "learning_rate": 4.992293334332821e-06, "loss": 8.0224, "step": 7 }, { "epoch": 0.06451612903225806, "grad_norm": 18.0, "learning_rate": 4.986304738420684e-06, "loss": 7.6741, "step": 8 }, { "epoch": 0.07258064516129033, "grad_norm": 18.625, "learning_rate": 4.978612153434527e-06, "loss": 7.7528, "step": 9 }, { "epoch": 0.08064516129032258, "grad_norm": 17.875, "learning_rate": 4.9692208514878445e-06, "loss": 7.5786, "step": 10 }, { "epoch": 0.08870967741935484, "grad_norm": 17.625, "learning_rate": 4.958137268909887e-06, "loss": 7.5182, "step": 11 }, { "epoch": 0.0967741935483871, "grad_norm": 16.0, "learning_rate": 4.9453690018345144e-06, "loss": 7.5339, "step": 12 }, { "epoch": 0.10483870967741936, "grad_norm": 16.5, "learning_rate": 4.930924800994192e-06, "loss": 7.5517, "step": 13 }, { "epoch": 0.11290322580645161, "grad_norm": 16.375, "learning_rate": 4.914814565722671e-06, "loss": 7.3944, "step": 14 }, { "epoch": 0.12096774193548387, "grad_norm": 15.6875, "learning_rate": 4.897049337170483e-06, "loss": 7.1319, "step": 15 }, { "epoch": 0.12903225806451613, "grad_norm": 15.125, "learning_rate": 4.8776412907378845e-06, "loss": 7.0313, "step": 16 }, { "epoch": 0.13709677419354838, "grad_norm": 15.3125, "learning_rate": 4.856603727730446e-06, "loss": 6.9869, "step": 17 }, { "epoch": 0.14516129032258066, "grad_norm": 14.125, "learning_rate": 4.833951066243004e-06, "loss": 7.131, "step": 18 }, { "epoch": 0.1532258064516129, "grad_norm": 13.0625, "learning_rate": 4.809698831278217e-06, "loss": 6.9202, "step": 19 }, { "epoch": 0.16129032258064516, "grad_norm": 13.625, "learning_rate": 4.783863644106502e-06, "loss": 6.9279, "step": 20 }, { "epoch": 0.1693548387096774, "grad_norm": 13.0, "learning_rate": 4.7564632108746524e-06, "loss": 6.6326, "step": 21 }, { "epoch": 0.1774193548387097, "grad_norm": 12.875, "learning_rate": 4.72751631047092e-06, "loss": 6.7503, "step": 22 }, { "epoch": 0.18548387096774194, "grad_norm": 12.25, "learning_rate": 4.697042781654913e-06, "loss": 6.6069, "step": 23 }, { "epoch": 0.1935483870967742, "grad_norm": 10.0, "learning_rate": 4.665063509461098e-06, "loss": 6.4378, "step": 24 }, { "epoch": 0.20161290322580644, "grad_norm": 10.125, "learning_rate": 4.631600410885231e-06, "loss": 6.6957, "step": 25 }, { "epoch": 0.20967741935483872, "grad_norm": 9.75, "learning_rate": 4.596676419863561e-06, "loss": 6.4625, "step": 26 }, { "epoch": 0.21774193548387097, "grad_norm": 10.125, "learning_rate": 4.560315471555039e-06, "loss": 6.5304, "step": 27 }, { "epoch": 0.22580645161290322, "grad_norm": 9.9375, "learning_rate": 4.522542485937369e-06, "loss": 6.3632, "step": 28 }, { "epoch": 0.23387096774193547, "grad_norm": 8.75, "learning_rate": 4.4833833507280884e-06, "loss": 6.3071, "step": 29 }, { "epoch": 0.24193548387096775, "grad_norm": 8.5, "learning_rate": 4.442864903642428e-06, "loss": 6.428, "step": 30 }, { "epoch": 0.25, "grad_norm": 9.125, "learning_rate": 4.401014914000078e-06, "loss": 6.3937, "step": 31 }, { "epoch": 0.25806451612903225, "grad_norm": 8.375, "learning_rate": 4.357862063693486e-06, "loss": 6.4951, "step": 32 }, { "epoch": 0.2661290322580645, "grad_norm": 7.625, "learning_rate": 4.313435927530719e-06, "loss": 6.1423, "step": 33 }, { "epoch": 0.27419354838709675, "grad_norm": 8.125, "learning_rate": 4.267766952966369e-06, "loss": 6.0947, "step": 34 }, { "epoch": 0.28225806451612906, "grad_norm": 7.75, "learning_rate": 4.220886439234385e-06, "loss": 6.1428, "step": 35 }, { "epoch": 0.2903225806451613, "grad_norm": 7.375, "learning_rate": 4.172826515897146e-06, "loss": 6.1118, "step": 36 }, { "epoch": 0.29838709677419356, "grad_norm": 7.4375, "learning_rate": 4.123620120825459e-06, "loss": 5.9917, "step": 37 }, { "epoch": 0.3064516129032258, "grad_norm": 7.53125, "learning_rate": 4.073300977624594e-06, "loss": 5.7956, "step": 38 }, { "epoch": 0.31451612903225806, "grad_norm": 6.96875, "learning_rate": 4.021903572521802e-06, "loss": 5.8347, "step": 39 }, { "epoch": 0.3225806451612903, "grad_norm": 7.71875, "learning_rate": 3.969463130731183e-06, "loss": 6.1252, "step": 40 }, { "epoch": 0.33064516129032256, "grad_norm": 6.8125, "learning_rate": 3.916015592312083e-06, "loss": 6.0318, "step": 41 }, { "epoch": 0.3387096774193548, "grad_norm": 6.46875, "learning_rate": 3.861597587537568e-06, "loss": 5.902, "step": 42 }, { "epoch": 0.3467741935483871, "grad_norm": 6.5, "learning_rate": 3.806246411789872e-06, "loss": 5.9344, "step": 43 }, { "epoch": 0.3548387096774194, "grad_norm": 6.25, "learning_rate": 3.7500000000000005e-06, "loss": 5.7523, "step": 44 }, { "epoch": 0.3629032258064516, "grad_norm": 6.46875, "learning_rate": 3.6928969006490212e-06, "loss": 5.9654, "step": 45 }, { "epoch": 0.3709677419354839, "grad_norm": 6.3125, "learning_rate": 3.634976249348867e-06, "loss": 5.8617, "step": 46 }, { "epoch": 0.3790322580645161, "grad_norm": 6.09375, "learning_rate": 3.5762777420207382e-06, "loss": 5.7341, "step": 47 }, { "epoch": 0.3870967741935484, "grad_norm": 5.71875, "learning_rate": 3.516841607689501e-06, "loss": 5.896, "step": 48 }, { "epoch": 0.3951612903225806, "grad_norm": 5.625, "learning_rate": 3.4567085809127247e-06, "loss": 5.8032, "step": 49 }, { "epoch": 0.4032258064516129, "grad_norm": 5.9375, "learning_rate": 3.39591987386325e-06, "loss": 5.8156, "step": 50 }, { "epoch": 0.4112903225806452, "grad_norm": 6.1875, "learning_rate": 3.3345171480844275e-06, "loss": 5.7496, "step": 51 }, { "epoch": 0.41935483870967744, "grad_norm": 5.90625, "learning_rate": 3.272542485937369e-06, "loss": 5.7032, "step": 52 }, { "epoch": 0.4274193548387097, "grad_norm": 5.6875, "learning_rate": 3.2100383617598075e-06, "loss": 5.688, "step": 53 }, { "epoch": 0.43548387096774194, "grad_norm": 7.0625, "learning_rate": 3.147047612756302e-06, "loss": 5.9719, "step": 54 }, { "epoch": 0.4435483870967742, "grad_norm": 5.09375, "learning_rate": 3.0836134096397642e-06, "loss": 5.8026, "step": 55 }, { "epoch": 0.45161290322580644, "grad_norm": 5.21875, "learning_rate": 3.019779227044398e-06, "loss": 5.5754, "step": 56 }, { "epoch": 0.4596774193548387, "grad_norm": 5.5625, "learning_rate": 2.9555888137303695e-06, "loss": 5.8139, "step": 57 }, { "epoch": 0.46774193548387094, "grad_norm": 5.46875, "learning_rate": 2.8910861626005774e-06, "loss": 5.6032, "step": 58 }, { "epoch": 0.47580645161290325, "grad_norm": 5.59375, "learning_rate": 2.82631548055013e-06, "loss": 5.6906, "step": 59 }, { "epoch": 0.4838709677419355, "grad_norm": 5.40625, "learning_rate": 2.761321158169134e-06, "loss": 5.7467, "step": 60 }, { "epoch": 0.49193548387096775, "grad_norm": 5.875, "learning_rate": 2.696147739319613e-06, "loss": 5.9122, "step": 61 }, { "epoch": 0.5, "grad_norm": 5.5, "learning_rate": 2.6308398906073603e-06, "loss": 5.6152, "step": 62 }, { "epoch": 0.5080645161290323, "grad_norm": 5.03125, "learning_rate": 2.5654423707696834e-06, "loss": 5.8207, "step": 63 }, { "epoch": 0.5161290322580645, "grad_norm": 6.1875, "learning_rate": 2.5e-06, "loss": 5.8129, "step": 64 }, { "epoch": 0.5241935483870968, "grad_norm": 5.3125, "learning_rate": 2.434557629230318e-06, "loss": 5.7729, "step": 65 }, { "epoch": 0.532258064516129, "grad_norm": 5.1875, "learning_rate": 2.3691601093926406e-06, "loss": 5.5761, "step": 66 }, { "epoch": 0.5403225806451613, "grad_norm": 5.4375, "learning_rate": 2.3038522606803882e-06, "loss": 5.6013, "step": 67 }, { "epoch": 0.5483870967741935, "grad_norm": 4.96875, "learning_rate": 2.238678841830867e-06, "loss": 5.5553, "step": 68 }, { "epoch": 0.5564516129032258, "grad_norm": 5.0625, "learning_rate": 2.173684519449872e-06, "loss": 5.5334, "step": 69 }, { "epoch": 0.5645161290322581, "grad_norm": 4.78125, "learning_rate": 2.1089138373994226e-06, "loss": 5.5125, "step": 70 }, { "epoch": 0.5725806451612904, "grad_norm": 5.34375, "learning_rate": 2.0444111862696313e-06, "loss": 5.704, "step": 71 }, { "epoch": 0.5806451612903226, "grad_norm": 5.03125, "learning_rate": 1.9802207729556023e-06, "loss": 5.6541, "step": 72 }, { "epoch": 0.5887096774193549, "grad_norm": 4.84375, "learning_rate": 1.9163865903602374e-06, "loss": 5.5812, "step": 73 }, { "epoch": 0.5967741935483871, "grad_norm": 5.21875, "learning_rate": 1.852952387243698e-06, "loss": 5.597, "step": 74 }, { "epoch": 0.6048387096774194, "grad_norm": 5.0625, "learning_rate": 1.7899616382401935e-06, "loss": 5.692, "step": 75 }, { "epoch": 0.6129032258064516, "grad_norm": 4.75, "learning_rate": 1.7274575140626318e-06, "loss": 5.6938, "step": 76 }, { "epoch": 0.6209677419354839, "grad_norm": 4.96875, "learning_rate": 1.665482851915573e-06, "loss": 5.5474, "step": 77 }, { "epoch": 0.6290322580645161, "grad_norm": 4.84375, "learning_rate": 1.6040801261367494e-06, "loss": 5.681, "step": 78 }, { "epoch": 0.6370967741935484, "grad_norm": 4.875, "learning_rate": 1.5432914190872757e-06, "loss": 5.6655, "step": 79 }, { "epoch": 0.6451612903225806, "grad_norm": 4.8125, "learning_rate": 1.4831583923105e-06, "loss": 5.3145, "step": 80 }, { "epoch": 0.6532258064516129, "grad_norm": 4.59375, "learning_rate": 1.4237222579792618e-06, "loss": 5.5851, "step": 81 }, { "epoch": 0.6612903225806451, "grad_norm": 5.5625, "learning_rate": 1.3650237506511333e-06, "loss": 5.6114, "step": 82 }, { "epoch": 0.6693548387096774, "grad_norm": 5.78125, "learning_rate": 1.307103099350979e-06, "loss": 5.7918, "step": 83 }, { "epoch": 0.6774193548387096, "grad_norm": 6.46875, "learning_rate": 1.2500000000000007e-06, "loss": 5.6083, "step": 84 }, { "epoch": 0.6854838709677419, "grad_norm": 5.78125, "learning_rate": 1.193753588210128e-06, "loss": 5.6588, "step": 85 }, { "epoch": 0.6935483870967742, "grad_norm": 4.6875, "learning_rate": 1.1384024124624324e-06, "loss": 5.552, "step": 86 }, { "epoch": 0.7016129032258065, "grad_norm": 4.9375, "learning_rate": 1.0839844076879186e-06, "loss": 5.4991, "step": 87 }, { "epoch": 0.7096774193548387, "grad_norm": 4.4375, "learning_rate": 1.0305368692688175e-06, "loss": 5.6138, "step": 88 }, { "epoch": 0.717741935483871, "grad_norm": 4.90625, "learning_rate": 9.780964274781984e-07, "loss": 5.5677, "step": 89 }, { "epoch": 0.7258064516129032, "grad_norm": 5.125, "learning_rate": 9.266990223754069e-07, "loss": 5.5496, "step": 90 }, { "epoch": 0.7338709677419355, "grad_norm": 4.9375, "learning_rate": 8.763798791745413e-07, "loss": 5.6754, "step": 91 }, { "epoch": 0.7419354838709677, "grad_norm": 4.90625, "learning_rate": 8.271734841028553e-07, "loss": 5.3941, "step": 92 }, { "epoch": 0.75, "grad_norm": 4.65625, "learning_rate": 7.791135607656147e-07, "loss": 5.5303, "step": 93 }, { "epoch": 0.7580645161290323, "grad_norm": 4.625, "learning_rate": 7.322330470336314e-07, "loss": 5.5491, "step": 94 }, { "epoch": 0.7661290322580645, "grad_norm": 5.9375, "learning_rate": 6.865640724692815e-07, "loss": 5.7337, "step": 95 }, { "epoch": 0.7741935483870968, "grad_norm": 4.9375, "learning_rate": 6.421379363065142e-07, "loss": 5.4986, "step": 96 }, { "epoch": 0.782258064516129, "grad_norm": 4.84375, "learning_rate": 5.989850859999227e-07, "loss": 5.5802, "step": 97 }, { "epoch": 0.7903225806451613, "grad_norm": 5.09375, "learning_rate": 5.571350963575728e-07, "loss": 5.6567, "step": 98 }, { "epoch": 0.7983870967741935, "grad_norm": 5.6875, "learning_rate": 5.166166492719124e-07, "loss": 5.6235, "step": 99 }, { "epoch": 0.8064516129032258, "grad_norm": 4.75, "learning_rate": 4.774575140626317e-07, "loss": 5.6329, "step": 100 }, { "epoch": 0.8145161290322581, "grad_norm": 4.96875, "learning_rate": 4.396845284449608e-07, "loss": 5.5273, "step": 101 }, { "epoch": 0.8225806451612904, "grad_norm": 4.625, "learning_rate": 4.033235801364402e-07, "loss": 5.4076, "step": 102 }, { "epoch": 0.8306451612903226, "grad_norm": 4.5, "learning_rate": 3.683995891147696e-07, "loss": 5.5664, "step": 103 }, { "epoch": 0.8387096774193549, "grad_norm": 5.71875, "learning_rate": 3.3493649053890325e-07, "loss": 5.6994, "step": 104 }, { "epoch": 0.8467741935483871, "grad_norm": 5.46875, "learning_rate": 3.0295721834508686e-07, "loss": 5.6093, "step": 105 }, { "epoch": 0.8548387096774194, "grad_norm": 4.65625, "learning_rate": 2.7248368952908055e-07, "loss": 5.4977, "step": 106 }, { "epoch": 0.8629032258064516, "grad_norm": 5.0, "learning_rate": 2.43536789125349e-07, "loss": 5.5823, "step": 107 }, { "epoch": 0.8709677419354839, "grad_norm": 7.625, "learning_rate": 2.1613635589349756e-07, "loss": 5.5065, "step": 108 }, { "epoch": 0.8790322580645161, "grad_norm": 5.0625, "learning_rate": 1.9030116872178317e-07, "loss": 5.5458, "step": 109 }, { "epoch": 0.8870967741935484, "grad_norm": 5.375, "learning_rate": 1.6604893375699594e-07, "loss": 5.5587, "step": 110 }, { "epoch": 0.8951612903225806, "grad_norm": 5.25, "learning_rate": 1.4339627226955394e-07, "loss": 5.6694, "step": 111 }, { "epoch": 0.9032258064516129, "grad_norm": 5.28125, "learning_rate": 1.223587092621162e-07, "loss": 5.5847, "step": 112 }, { "epoch": 0.9112903225806451, "grad_norm": 4.6875, "learning_rate": 1.0295066282951738e-07, "loss": 5.5174, "step": 113 }, { "epoch": 0.9193548387096774, "grad_norm": 4.75, "learning_rate": 8.518543427732951e-08, "loss": 5.6295, "step": 114 }, { "epoch": 0.9274193548387096, "grad_norm": 5.375, "learning_rate": 6.907519900580862e-08, "loss": 5.5846, "step": 115 }, { "epoch": 0.9354838709677419, "grad_norm": 4.875, "learning_rate": 5.463099816548578e-08, "loss": 5.5643, "step": 116 }, { "epoch": 0.9435483870967742, "grad_norm": 4.59375, "learning_rate": 4.186273109011374e-08, "loss": 5.5587, "step": 117 }, { "epoch": 0.9516129032258065, "grad_norm": 4.9375, "learning_rate": 3.077914851215585e-08, "loss": 5.7314, "step": 118 }, { "epoch": 0.9596774193548387, "grad_norm": 5.0, "learning_rate": 2.1387846565474047e-08, "loss": 5.5992, "step": 119 }, { "epoch": 0.967741935483871, "grad_norm": 5.0, "learning_rate": 1.3695261579316776e-08, "loss": 5.7444, "step": 120 }, { "epoch": 0.9758064516129032, "grad_norm": 4.6875, "learning_rate": 7.70666566718009e-09, "loss": 5.4073, "step": 121 }, { "epoch": 0.9838709677419355, "grad_norm": 4.78125, "learning_rate": 3.4261631135654174e-09, "loss": 5.6541, "step": 122 }, { "epoch": 0.9919354838709677, "grad_norm": 4.96875, "learning_rate": 8.566875611068503e-10, "loss": 5.6101, "step": 123 }, { "epoch": 1.0, "grad_norm": 5.40625, "learning_rate": 0.0, "loss": 5.6066, "step": 124 } ], "logging_steps": 1, "max_steps": 124, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7570556190720000.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }