| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 13.285714285714286, | |
| "eval_steps": 500, | |
| "global_step": 70, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 11.114676475524902, | |
| "learning_rate": 2e-05, | |
| "loss": 4.9155, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 10.886661529541016, | |
| "learning_rate": 4e-05, | |
| "loss": 5.2012, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 10.0223388671875, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4341, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 8.667222023010254, | |
| "learning_rate": 8e-05, | |
| "loss": 4.6939, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 6.8060832023620605, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9619, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 10.650321006774902, | |
| "learning_rate": 0.00012, | |
| "loss": 6.2246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 5.177021026611328, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1182, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 4.4564313888549805, | |
| "learning_rate": 0.00016, | |
| "loss": 3.4089, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 3.8821651935577393, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8449, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 4.001584529876709, | |
| "learning_rate": 0.0002, | |
| "loss": 2.541, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0476190476190474, | |
| "grad_norm": 5.516446590423584, | |
| "learning_rate": 0.0001998629534754574, | |
| "loss": 3.0792, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.238095238095238, | |
| "grad_norm": 3.4709484577178955, | |
| "learning_rate": 0.00019945218953682734, | |
| "loss": 2.7096, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 2.045745372772217, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 1.6279, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.619047619047619, | |
| "grad_norm": 2.5490376949310303, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.9507, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.8095238095238093, | |
| "grad_norm": 2.9036448001861572, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.9104, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 4.653842449188232, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.1175, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.1904761904761907, | |
| "grad_norm": 2.397826671600342, | |
| "learning_rate": 0.00019335804264972018, | |
| "loss": 1.7851, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.380952380952381, | |
| "grad_norm": 2.003856897354126, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.3112, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.571428571428571, | |
| "grad_norm": 1.5474413633346558, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 1.4914, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.761904761904762, | |
| "grad_norm": 1.5208486318588257, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.2772, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.9523809523809526, | |
| "grad_norm": 1.8079063892364502, | |
| "learning_rate": 0.00018386705679454242, | |
| "loss": 1.3938, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 4.142857142857143, | |
| "grad_norm": 3.1666009426116943, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5114, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.333333333333333, | |
| "grad_norm": 1.6823382377624512, | |
| "learning_rate": 0.0001777145961456971, | |
| "loss": 1.4207, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 4.523809523809524, | |
| "grad_norm": 1.3504416942596436, | |
| "learning_rate": 0.00017431448254773944, | |
| "loss": 0.9105, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.714285714285714, | |
| "grad_norm": 1.3855412006378174, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.0832, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.904761904761905, | |
| "grad_norm": 1.378572940826416, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.1635, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 5.095238095238095, | |
| "grad_norm": 2.8164830207824707, | |
| "learning_rate": 0.00016293203910498376, | |
| "loss": 1.4419, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 5.285714285714286, | |
| "grad_norm": 1.147581696510315, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.6387, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 5.476190476190476, | |
| "grad_norm": 1.5747478008270264, | |
| "learning_rate": 0.00015446390350150273, | |
| "loss": 1.0435, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 5.666666666666667, | |
| "grad_norm": 1.3611525297164917, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.9718, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.857142857142857, | |
| "grad_norm": 1.1871294975280762, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.7409, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 6.0476190476190474, | |
| "grad_norm": 4.008199214935303, | |
| "learning_rate": 0.00014067366430758004, | |
| "loss": 1.6548, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.238095238095238, | |
| "grad_norm": 1.111243486404419, | |
| "learning_rate": 0.00013583679495453, | |
| "loss": 0.5545, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 6.428571428571429, | |
| "grad_norm": 1.1197227239608765, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.5296, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 6.619047619047619, | |
| "grad_norm": 1.1618750095367432, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.5923, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 6.809523809523809, | |
| "grad_norm": 1.0321106910705566, | |
| "learning_rate": 0.00012079116908177593, | |
| "loss": 0.6033, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 3.302760601043701, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 1.269, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 7.190476190476191, | |
| "grad_norm": 1.3132500648498535, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.5142, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 7.380952380952381, | |
| "grad_norm": 0.8678253293037415, | |
| "learning_rate": 0.0001052335956242944, | |
| "loss": 0.4287, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 7.571428571428571, | |
| "grad_norm": 1.0537868738174438, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5592, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.761904761904762, | |
| "grad_norm": 0.9256157279014587, | |
| "learning_rate": 9.476640437570562e-05, | |
| "loss": 0.3902, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 7.9523809523809526, | |
| "grad_norm": 0.938805341720581, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.442, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 8.142857142857142, | |
| "grad_norm": 1.98072350025177, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.6278, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 0.8120888471603394, | |
| "learning_rate": 7.920883091822408e-05, | |
| "loss": 0.2643, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 8.523809523809524, | |
| "grad_norm": 0.8413763642311096, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.3042, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 8.714285714285714, | |
| "grad_norm": 0.7817604541778564, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.3137, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 8.904761904761905, | |
| "grad_norm": 0.7885234355926514, | |
| "learning_rate": 6.416320504546997e-05, | |
| "loss": 0.2808, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 9.095238095238095, | |
| "grad_norm": 1.5161521434783936, | |
| "learning_rate": 5.9326335692419995e-05, | |
| "loss": 0.5427, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 9.285714285714286, | |
| "grad_norm": 0.5991838574409485, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.2195, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 9.476190476190476, | |
| "grad_norm": 0.7848747968673706, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.2632, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 9.666666666666666, | |
| "grad_norm": 0.6151169538497925, | |
| "learning_rate": 4.5536096498497295e-05, | |
| "loss": 0.2032, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 9.857142857142858, | |
| "grad_norm": 1.1136269569396973, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.2819, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 10.095238095238095, | |
| "grad_norm": 0.659062922000885, | |
| "learning_rate": 3.7067960895016275e-05, | |
| "loss": 0.1995, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 10.285714285714286, | |
| "grad_norm": 0.6866421699523926, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.18, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 10.476190476190476, | |
| "grad_norm": 0.6459683775901794, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.2022, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 10.666666666666666, | |
| "grad_norm": 0.6483227014541626, | |
| "learning_rate": 2.5685517452260567e-05, | |
| "loss": 0.1876, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "grad_norm": 0.5956599116325378, | |
| "learning_rate": 2.2285403854302912e-05, | |
| "loss": 0.1969, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 11.047619047619047, | |
| "grad_norm": 2.297029733657837, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.3517, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 11.238095238095237, | |
| "grad_norm": 0.5542204976081848, | |
| "learning_rate": 1.6132943205457606e-05, | |
| "loss": 0.1701, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 0.5855220556259155, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.1588, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 11.619047619047619, | |
| "grad_norm": 0.6266547441482544, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.1762, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 11.80952380952381, | |
| "grad_norm": 0.5979227423667908, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.1604, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.2808066606521606, | |
| "learning_rate": 6.6419573502798374e-06, | |
| "loss": 0.2592, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 12.19047619047619, | |
| "grad_norm": 0.5678392052650452, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 0.1635, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 12.380952380952381, | |
| "grad_norm": 0.746486246585846, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.1914, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "grad_norm": 0.6837660074234009, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.1632, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 12.761904761904763, | |
| "grad_norm": 0.6320339441299438, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.1514, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 12.952380952380953, | |
| "grad_norm": 0.6253515481948853, | |
| "learning_rate": 5.478104631726711e-07, | |
| "loss": 0.1538, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 13.095238095238095, | |
| "grad_norm": 0.8237464427947998, | |
| "learning_rate": 1.3704652454261668e-07, | |
| "loss": 0.1993, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 13.285714285714286, | |
| "grad_norm": 0.6406182646751404, | |
| "learning_rate": 0.0, | |
| "loss": 0.1828, | |
| "step": 70 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 70, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 14, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 62994788646912.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |