| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17740981667652278, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.4166666666666664e-05, | |
| "loss": 2.8488, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00010833333333333333, | |
| "loss": 2.7815, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001625, | |
| "loss": 2.8002, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00021666666666666666, | |
| "loss": 2.7473, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002708333333333333, | |
| "loss": 2.4233, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000325, | |
| "loss": 1.9676, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00037916666666666665, | |
| "loss": 1.7562, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0004333333333333333, | |
| "loss": 1.3949, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0004875, | |
| "loss": 1.2908, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005416666666666666, | |
| "loss": 1.2542, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005958333333333333, | |
| "loss": 1.2959, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00065, | |
| "loss": 1.1706, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0006499947173877214, | |
| "loss": 1.0829, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0006499788697226147, | |
| "loss": 1.128, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006499524575198621, | |
| "loss": 1.0847, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006499154816380815, | |
| "loss": 1.1143, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006498679432792988, | |
| "loss": 1.0751, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006498098439889095, | |
| "loss": 1.179, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006497411856556275, | |
| "loss": 1.0327, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006496619705114241, | |
| "loss": 1.0672, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006495722011314557, | |
| "loss": 1.1625, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006494718804339797, | |
| "loss": 1.0751, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006493610116802598, | |
| "loss": 0.996, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006492395984744599, | |
| "loss": 1.0478, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006491076447635269, | |
| "loss": 1.064, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006489651548370628, | |
| "loss": 0.9393, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006488121333271846, | |
| "loss": 0.9282, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006486485852083744, | |
| "loss": 1.0558, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006484745157973169, | |
| "loss": 1.0015, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006482899307527272, | |
| "loss": 1.0261, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006480948360751669, | |
| "loss": 1.0507, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006478892381068483, | |
| "loss": 1.0225, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006476731435314292, | |
| "loss": 0.9411, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006474465593737948, | |
| "loss": 0.9884, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006472094929998295, | |
| "loss": 0.9892, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006469619521161782, | |
| "loss": 1.0527, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006467039447699945, | |
| "loss": 0.969, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006464354793486803, | |
| "loss": 1.0009, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006461565645796124, | |
| "loss": 1.0068, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006458672095298589, | |
| "loss": 0.9626, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006455674236058847, | |
| "loss": 0.934, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006452572165532456, | |
| "loss": 1.0217, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006449365984562712, | |
| "loss": 1.0036, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006446055797377376, | |
| "loss": 0.9234, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000644264171158528, | |
| "loss": 0.9771, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006439123838172836, | |
| "loss": 1.013, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006435502291500418, | |
| "loss": 0.9154, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006431777189298656, | |
| "loss": 0.9098, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006427948652664599, | |
| "loss": 0.9243, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006424016806057781, | |
| "loss": 0.9162, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006419981777296182, | |
| "loss": 0.9538, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006415843697552062, | |
| "loss": 0.9454, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006411602701347703, | |
| "loss": 0.9296, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006407258926551036, | |
| "loss": 0.929, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006402812514371154, | |
| "loss": 0.9172, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006398263609353731, | |
| "loss": 0.9871, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006393612359376315, | |
| "loss": 0.9279, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006388858915643519, | |
| "loss": 0.9191, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006384003432682119, | |
| "loss": 0.9828, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006379046068336013, | |
| "loss": 0.8912, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00063739869837611, | |
| "loss": 0.9023, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006368826343420043, | |
| "loss": 0.9978, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006363564315076915, | |
| "loss": 0.9097, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006358201069791749, | |
| "loss": 0.8475, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000635273678191498, | |
| "loss": 0.9763, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000634717162908177, | |
| "loss": 0.8673, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006341505792206243, | |
| "loss": 0.9188, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006335739455475594, | |
| "loss": 0.865, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006329872806344108, | |
| "loss": 0.9187, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006323906035527062, | |
| "loss": 0.887, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006317839336994531, | |
| "loss": 0.908, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006311672907965074, | |
| "loss": 0.918, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006305406948899329, | |
| "loss": 0.9399, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006299041663493497, | |
| "loss": 0.9741, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006292577258672713, | |
| "loss": 0.8738, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006286013944584328, | |
| "loss": 0.9192, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006279351934591071, | |
| "loss": 0.8589, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006272591445264116, | |
| "loss": 0.955, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006265732696376042, | |
| "loss": 0.928, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006258775910893685, | |
| "loss": 0.8454, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006251721314970894, | |
| "loss": 0.8709, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006244569137941179, | |
| "loss": 0.8732, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006237319612310249, | |
| "loss": 0.9345, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006229972973748463, | |
| "loss": 0.9342, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006222529461083165, | |
| "loss": 0.8803, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006214989316290914, | |
| "loss": 0.8676, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006207352784489629, | |
| "loss": 0.9195, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.000619962011393061, | |
| "loss": 0.9505, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006191791555990477, | |
| "loss": 0.8778, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006183867365162994, | |
| "loss": 0.9663, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006175847799050789, | |
| "loss": 0.9304, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006167733118356993, | |
| "loss": 0.9233, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006159523586876756, | |
| "loss": 0.9167, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006151219471488673, | |
| "loss": 0.882, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006142821042146112, | |
| "loss": 0.8295, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006134328571868428, | |
| "loss": 0.7799, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006125742336732103, | |
| "loss": 0.9368, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000611706261586176, | |
| "loss": 0.8542, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006108289691421089, | |
| "loss": 0.9263, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006099423848603682, | |
| "loss": 0.8572, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 563, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 1.5159455254020096e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |