| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.001648750247312537, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.648750247312537e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.648750247312537e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4953.4443, | |
| "eval_samples_per_second": 5.156, | |
| "eval_steps_per_second": 2.578, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.297500494625074e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.946250741937611e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.595000989250148e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.243751236562685e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.892501483875222e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011541251731187759, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00013190001978500296, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00014838752225812833, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001648750247312537, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00018136252720437907, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00019785002967750444, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00021433753215062981, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00023082503462375518, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00024731253709688055, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002638000395700059, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002802875420431313, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00029677504451625667, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00031326254698938204, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0003297500494625074, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003462375519356328, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00036272505440875815, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0003792125568818835, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0003957000593550089, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00041218756182813426, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00042867506430125963, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.000445162566774385, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00046165006924751037, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00047813757172063574, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0004946250741937611, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005111125766668865, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0005276000791400118, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0005440875816131373, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0005605750840862626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.000577062586559388, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0005935500890325133, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0006100375915056388, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0006265250939787641, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0006430125964518895, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0006595000989250148, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006759876013981402, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0006924751038712656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.000708962606344391, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0007254501088175163, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0007419376112906417, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000758425113763767, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0007749126162368925, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0007914001187100178, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0008078876211831432, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0008243751236562685, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008243751236562685, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4953.0287, | |
| "eval_samples_per_second": 5.156, | |
| "eval_steps_per_second": 2.578, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008408626261293939, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0008573501286025193, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0008738376310756447, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.00089032513354877, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0009068126360218954, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0009233001384950207, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0009397876409681462, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0009562751434412715, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0009727626459143969, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0009892501483875222, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0010057376508606475, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.001022225153333773, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0010387126558068984, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0010552001582800237, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.001071687660753149, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0010881751632262745, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0011046626656993999, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0011211501681725252, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0011376376706456505, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.001154125173118776, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0011706126755919013, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0011871001780650267, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.001203587680538152, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0012200751830112775, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0012365626854844028, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0012530501879575281, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9876321572751144e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0012695376904306535, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7557479520891104e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.001286025192903779, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5317852301584643e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0013025126953769043, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.315988891431412e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0013190001978500296, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0013354877003231552, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0013519752027962805, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7199116885197995e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0013684627052694058, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5390474757906446e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.001384950207742531, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3674351904242611e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0014014377102156566, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.001417925212688782, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0527067017923654e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0014344127151619073, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.09934649508375e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0014509002176350326, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.771024502261526e-06, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.0014673877201081581, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.543553540053926e-06, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.0014838752225812834, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0015003627250544087, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3964218465642355e-06, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.001516850227527534, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4791089722651436e-06, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.0015333377300006596, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.667340275199426e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.001549825232473785, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9620034125190644e-06, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0015663127349469102, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0015828002374200355, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.735930673024806e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.001599287739893161, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.917097454988584e-07, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0016157752423662864, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1863727812254653e-07, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0016322627448394117, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.467426590739511e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.001648750247312537, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.001648750247312537, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4954.0916, | |
| "eval_samples_per_second": 5.155, | |
| "eval_steps_per_second": 2.577, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.51427898343424e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |