{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0041376746591671315, "eval_steps": 500, "global_step": 64, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.465116654948643e-05, "grad_norm": 44.632102966308594, "learning_rate": 6.451612903225807e-08, "loss": 1.8854, "step": 1 }, { "epoch": 0.00012930233309897286, "grad_norm": 46.18963623046875, "learning_rate": 1.2903225806451614e-07, "loss": 1.7711, "step": 2 }, { "epoch": 0.0001939534996484593, "grad_norm": 45.15989685058594, "learning_rate": 1.935483870967742e-07, "loss": 1.9258, "step": 3 }, { "epoch": 0.0002586046661979457, "grad_norm": 48.17970275878906, "learning_rate": 2.580645161290323e-07, "loss": 1.9478, "step": 4 }, { "epoch": 0.00032325583274743215, "grad_norm": 46.92567443847656, "learning_rate": 3.2258064516129035e-07, "loss": 1.8888, "step": 5 }, { "epoch": 0.0003879069992969186, "grad_norm": 32.95823287963867, "learning_rate": 3.870967741935484e-07, "loss": 1.877, "step": 6 }, { "epoch": 0.000452558165846405, "grad_norm": 25.36848258972168, "learning_rate": 4.5161290322580644e-07, "loss": 1.7888, "step": 7 }, { "epoch": 0.0005172093323958914, "grad_norm": 31.360990524291992, "learning_rate": 5.161290322580646e-07, "loss": 1.8526, "step": 8 }, { "epoch": 0.0005818604989453779, "grad_norm": 23.622682571411133, "learning_rate": 5.806451612903227e-07, "loss": 1.8157, "step": 9 }, { "epoch": 0.0006465116654948643, "grad_norm": 22.565826416015625, "learning_rate": 6.451612903225807e-07, "loss": 1.7774, "step": 10 }, { "epoch": 0.0007111628320443507, "grad_norm": 22.03154945373535, "learning_rate": 7.096774193548388e-07, "loss": 1.7796, "step": 11 }, { "epoch": 0.0007758139985938372, "grad_norm": 22.295787811279297, "learning_rate": 7.741935483870968e-07, "loss": 1.7066, "step": 12 }, { "epoch": 0.0008404651651433236, "grad_norm": 18.35325050354004, "learning_rate": 8.38709677419355e-07, "loss": 1.7261, "step": 13 }, { "epoch": 0.00090511633169281, "grad_norm": 20.82447052001953, "learning_rate": 9.032258064516129e-07, "loss": 1.8172, "step": 14 }, { "epoch": 0.0009697674982422964, "grad_norm": 10.829120635986328, "learning_rate": 9.67741935483871e-07, "loss": 1.7402, "step": 15 }, { "epoch": 0.0010344186647917829, "grad_norm": 31.75849723815918, "learning_rate": 1.0322580645161291e-06, "loss": 1.618, "step": 16 }, { "epoch": 0.0010990698313412693, "grad_norm": 27.484895706176758, "learning_rate": 1.0967741935483872e-06, "loss": 1.5973, "step": 17 }, { "epoch": 0.0011637209978907557, "grad_norm": 20.07984161376953, "learning_rate": 1.1612903225806454e-06, "loss": 1.6907, "step": 18 }, { "epoch": 0.0012283721644402422, "grad_norm": 14.788183212280273, "learning_rate": 1.2258064516129033e-06, "loss": 1.6986, "step": 19 }, { "epoch": 0.0012930233309897286, "grad_norm": 9.38936996459961, "learning_rate": 1.2903225806451614e-06, "loss": 1.6164, "step": 20 }, { "epoch": 0.001357674497539215, "grad_norm": 8.975388526916504, "learning_rate": 1.3548387096774195e-06, "loss": 1.5637, "step": 21 }, { "epoch": 0.0014223256640887015, "grad_norm": 14.67812442779541, "learning_rate": 1.4193548387096776e-06, "loss": 1.6869, "step": 22 }, { "epoch": 0.0014869768306381879, "grad_norm": 8.56955337524414, "learning_rate": 1.4838709677419356e-06, "loss": 1.5948, "step": 23 }, { "epoch": 0.0015516279971876743, "grad_norm": 5.918207168579102, "learning_rate": 1.5483870967741937e-06, "loss": 1.61, "step": 24 }, { "epoch": 0.0016162791637371607, "grad_norm": 8.165249824523926, "learning_rate": 1.6129032258064516e-06, "loss": 1.712, "step": 25 }, { "epoch": 0.0016809303302866472, "grad_norm": 9.301441192626953, "learning_rate": 1.67741935483871e-06, "loss": 1.6957, "step": 26 }, { "epoch": 0.0017455814968361336, "grad_norm": 7.351085662841797, "learning_rate": 1.7419354838709678e-06, "loss": 1.5153, "step": 27 }, { "epoch": 0.00181023266338562, "grad_norm": 7.347102642059326, "learning_rate": 1.8064516129032258e-06, "loss": 1.6625, "step": 28 }, { "epoch": 0.0018748838299351065, "grad_norm": 7.22580623626709, "learning_rate": 1.870967741935484e-06, "loss": 1.5632, "step": 29 }, { "epoch": 0.001939534996484593, "grad_norm": 5.857529163360596, "learning_rate": 1.935483870967742e-06, "loss": 1.5339, "step": 30 }, { "epoch": 0.002004186163034079, "grad_norm": 7.3882222175598145, "learning_rate": 2.0000000000000003e-06, "loss": 1.5775, "step": 31 }, { "epoch": 0.0020688373295835658, "grad_norm": 6.075866222381592, "learning_rate": 2.0645161290322582e-06, "loss": 1.55, "step": 32 }, { "epoch": 0.002133488496133052, "grad_norm": 4.930643081665039, "learning_rate": 2.129032258064516e-06, "loss": 1.5525, "step": 33 }, { "epoch": 0.0021981396626825386, "grad_norm": 6.426210880279541, "learning_rate": 2.1935483870967745e-06, "loss": 1.5845, "step": 34 }, { "epoch": 0.002262790829232025, "grad_norm": 7.546030521392822, "learning_rate": 2.2580645161290324e-06, "loss": 1.6313, "step": 35 }, { "epoch": 0.0023274419957815115, "grad_norm": 4.881446361541748, "learning_rate": 2.3225806451612907e-06, "loss": 1.5387, "step": 36 }, { "epoch": 0.0023920931623309977, "grad_norm": 5.156312942504883, "learning_rate": 2.3870967741935486e-06, "loss": 1.4912, "step": 37 }, { "epoch": 0.0024567443288804843, "grad_norm": 6.470444202423096, "learning_rate": 2.4516129032258066e-06, "loss": 1.4706, "step": 38 }, { "epoch": 0.0025213954954299705, "grad_norm": 15.289785385131836, "learning_rate": 2.5161290322580645e-06, "loss": 1.4612, "step": 39 }, { "epoch": 0.002586046661979457, "grad_norm": 6.442019939422607, "learning_rate": 2.580645161290323e-06, "loss": 1.5178, "step": 40 }, { "epoch": 0.0026506978285289434, "grad_norm": 5.88471794128418, "learning_rate": 2.645161290322581e-06, "loss": 1.5095, "step": 41 }, { "epoch": 0.00271534899507843, "grad_norm": 7.326111316680908, "learning_rate": 2.709677419354839e-06, "loss": 1.5718, "step": 42 }, { "epoch": 0.0027800001616279163, "grad_norm": 4.946439266204834, "learning_rate": 2.774193548387097e-06, "loss": 1.5057, "step": 43 }, { "epoch": 0.002844651328177403, "grad_norm": 5.956087589263916, "learning_rate": 2.8387096774193553e-06, "loss": 1.4635, "step": 44 }, { "epoch": 0.002909302494726889, "grad_norm": 7.258240222930908, "learning_rate": 2.903225806451613e-06, "loss": 1.5494, "step": 45 }, { "epoch": 0.0029739536612763758, "grad_norm": 5.20070743560791, "learning_rate": 2.967741935483871e-06, "loss": 1.5329, "step": 46 }, { "epoch": 0.003038604827825862, "grad_norm": 6.215978145599365, "learning_rate": 3.0322580645161295e-06, "loss": 1.4822, "step": 47 }, { "epoch": 0.0031032559943753486, "grad_norm": 4.830237865447998, "learning_rate": 3.0967741935483874e-06, "loss": 1.457, "step": 48 }, { "epoch": 0.003167907160924835, "grad_norm": 6.3563971519470215, "learning_rate": 3.1612903225806453e-06, "loss": 1.4619, "step": 49 }, { "epoch": 0.0032325583274743215, "grad_norm": 5.210926532745361, "learning_rate": 3.225806451612903e-06, "loss": 1.446, "step": 50 }, { "epoch": 0.0032972094940238077, "grad_norm": 5.412484169006348, "learning_rate": 3.2903225806451615e-06, "loss": 1.4154, "step": 51 }, { "epoch": 0.0033618606605732944, "grad_norm": 5.500335693359375, "learning_rate": 3.35483870967742e-06, "loss": 1.4902, "step": 52 }, { "epoch": 0.0034265118271227806, "grad_norm": 5.576430320739746, "learning_rate": 3.4193548387096773e-06, "loss": 1.4931, "step": 53 }, { "epoch": 0.003491162993672267, "grad_norm": 4.996302604675293, "learning_rate": 3.4838709677419357e-06, "loss": 1.374, "step": 54 }, { "epoch": 0.0035558141602217534, "grad_norm": 4.846431255340576, "learning_rate": 3.548387096774194e-06, "loss": 1.5605, "step": 55 }, { "epoch": 0.00362046532677124, "grad_norm": 5.039584636688232, "learning_rate": 3.6129032258064515e-06, "loss": 1.4703, "step": 56 }, { "epoch": 0.0036851164933207263, "grad_norm": 4.541802406311035, "learning_rate": 3.67741935483871e-06, "loss": 1.4888, "step": 57 }, { "epoch": 0.003749767659870213, "grad_norm": 4.2027997970581055, "learning_rate": 3.741935483870968e-06, "loss": 1.5091, "step": 58 }, { "epoch": 0.003814418826419699, "grad_norm": 5.916923522949219, "learning_rate": 3.8064516129032257e-06, "loss": 1.4113, "step": 59 }, { "epoch": 0.003879069992969186, "grad_norm": 4.324679374694824, "learning_rate": 3.870967741935484e-06, "loss": 1.5304, "step": 60 }, { "epoch": 0.0039437211595186724, "grad_norm": 4.319639205932617, "learning_rate": 3.935483870967742e-06, "loss": 1.4203, "step": 61 }, { "epoch": 0.004008372326068158, "grad_norm": 5.848201274871826, "learning_rate": 4.000000000000001e-06, "loss": 1.4394, "step": 62 }, { "epoch": 0.004073023492617645, "grad_norm": 5.865200042724609, "learning_rate": 4.064516129032259e-06, "loss": 1.4537, "step": 63 }, { "epoch": 0.0041376746591671315, "grad_norm": 4.825560569763184, "learning_rate": 4.1290322580645165e-06, "loss": 1.4732, "step": 64 } ], "logging_steps": 1, "max_steps": 15467, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 16, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 6.80601377625047e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }