| { | |
| "best_metric": 0.4470236301422119, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.009298721425804, | |
| "eval_steps": 25, | |
| "global_step": 81, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02479659046881054, | |
| "grad_norm": 9.463377952575684, | |
| "learning_rate": 0.00015, | |
| "loss": 8.2539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02479659046881054, | |
| "eval_loss": 8.061068534851074, | |
| "eval_runtime": 1.5646, | |
| "eval_samples_per_second": 31.957, | |
| "eval_steps_per_second": 8.309, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04959318093762108, | |
| "grad_norm": 10.420730590820312, | |
| "learning_rate": 0.0003, | |
| "loss": 8.1104, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07438977140643162, | |
| "grad_norm": 9.304948806762695, | |
| "learning_rate": 0.0002998932686256857, | |
| "loss": 5.7079, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09918636187524216, | |
| "grad_norm": 7.6371588706970215, | |
| "learning_rate": 0.0002995732432669839, | |
| "loss": 4.4867, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1239829523440527, | |
| "grad_norm": 5.276372909545898, | |
| "learning_rate": 0.00029904042994976636, | |
| "loss": 4.1186, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14877954281286324, | |
| "grad_norm": 7.107175827026367, | |
| "learning_rate": 0.000298295671161405, | |
| "loss": 3.336, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17357613328167376, | |
| "grad_norm": 7.58524751663208, | |
| "learning_rate": 0.00029734014451862585, | |
| "loss": 2.9452, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19837272375048431, | |
| "grad_norm": 4.276736259460449, | |
| "learning_rate": 0.0002961753609054553, | |
| "loss": 2.3813, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22316931421929484, | |
| "grad_norm": 3.3326385021209717, | |
| "learning_rate": 0.00029480316208420175, | |
| "loss": 1.6502, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2479659046881054, | |
| "grad_norm": 2.8657619953155518, | |
| "learning_rate": 0.0002932257177832507, | |
| "loss": 1.3725, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2727624951569159, | |
| "grad_norm": 6.442175388336182, | |
| "learning_rate": 0.0002914455222662782, | |
| "loss": 2.0797, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.29755908562572647, | |
| "grad_norm": 4.634378910064697, | |
| "learning_rate": 0.00028946539038830787, | |
| "loss": 1.4848, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.322355676094537, | |
| "grad_norm": 3.6060268878936768, | |
| "learning_rate": 0.0002872884531448456, | |
| "loss": 1.1722, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3471522665633475, | |
| "grad_norm": 3.540088176727295, | |
| "learning_rate": 0.0002849181527211328, | |
| "loss": 0.9732, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3719488570321581, | |
| "grad_norm": 2.787266492843628, | |
| "learning_rate": 0.0002823582370493436, | |
| "loss": 0.8253, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.39674544750096863, | |
| "grad_norm": 2.26003360748291, | |
| "learning_rate": 0.00027961275388233416, | |
| "loss": 0.7514, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4215420379697792, | |
| "grad_norm": 1.5791990756988525, | |
| "learning_rate": 0.0002766860443933127, | |
| "loss": 0.7033, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4463386284385897, | |
| "grad_norm": 2.00994610786438, | |
| "learning_rate": 0.00027358273631155326, | |
| "loss": 0.8012, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47113521890740023, | |
| "grad_norm": 1.9376633167266846, | |
| "learning_rate": 0.0002703077366050036, | |
| "loss": 0.7117, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4959318093762108, | |
| "grad_norm": 0.8688062429428101, | |
| "learning_rate": 0.00026686622372136103, | |
| "loss": 0.6083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5207283998450213, | |
| "grad_norm": 2.4382097721099854, | |
| "learning_rate": 0.0002632636393998817, | |
| "loss": 0.7095, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5455249903138318, | |
| "grad_norm": 1.1420600414276123, | |
| "learning_rate": 0.0002595056800668724, | |
| "loss": 0.5918, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5703215807826424, | |
| "grad_norm": 1.245035171508789, | |
| "learning_rate": 0.00025559828782846994, | |
| "loss": 0.6538, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5951181712514529, | |
| "grad_norm": 0.8991405367851257, | |
| "learning_rate": 0.0002515476410749497, | |
| "loss": 0.6102, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6199147617202635, | |
| "grad_norm": 1.0999940633773804, | |
| "learning_rate": 0.00024736014471142076, | |
| "loss": 0.5558, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6199147617202635, | |
| "eval_loss": 0.5675167441368103, | |
| "eval_runtime": 1.566, | |
| "eval_samples_per_second": 31.929, | |
| "eval_steps_per_second": 8.302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.644711352189074, | |
| "grad_norm": 0.8524123430252075, | |
| "learning_rate": 0.0002430424200303545, | |
| "loss": 0.5466, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6695079426578845, | |
| "grad_norm": 0.7143929600715637, | |
| "learning_rate": 0.00023860129424196008, | |
| "loss": 0.5559, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.694304533126695, | |
| "grad_norm": 0.33965978026390076, | |
| "learning_rate": 0.000234043789678962, | |
| "loss": 0.5331, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7191011235955056, | |
| "grad_norm": 0.8655706644058228, | |
| "learning_rate": 0.00022937711269284834, | |
| "loss": 0.6151, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7438977140643162, | |
| "grad_norm": 0.618858277797699, | |
| "learning_rate": 0.00022460864225914807, | |
| "loss": 0.5515, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7686943045331267, | |
| "grad_norm": 1.0988430976867676, | |
| "learning_rate": 0.00021974591830975417, | |
| "loss": 0.5621, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7934908950019373, | |
| "grad_norm": 0.6801258325576782, | |
| "learning_rate": 0.00021479662981074103, | |
| "loss": 0.5204, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8182874854707478, | |
| "grad_norm": 0.7187148928642273, | |
| "learning_rate": 0.00020976860260452914, | |
| "loss": 0.5153, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8430840759395584, | |
| "grad_norm": 0.48717305064201355, | |
| "learning_rate": 0.00020466978703561934, | |
| "loss": 0.4948, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8678806664083688, | |
| "grad_norm": 0.4217776656150818, | |
| "learning_rate": 0.00019950824537946405, | |
| "loss": 0.4804, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8926772568771794, | |
| "grad_norm": 0.37866833806037903, | |
| "learning_rate": 0.00019429213909435291, | |
| "loss": 0.4657, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9174738473459899, | |
| "grad_norm": 0.3701322674751282, | |
| "learning_rate": 0.00018902971591646932, | |
| "loss": 0.4642, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9422704378148005, | |
| "grad_norm": 0.4386747181415558, | |
| "learning_rate": 0.00018372929681852423, | |
| "loss": 0.4875, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.967067028283611, | |
| "grad_norm": 0.5399623513221741, | |
| "learning_rate": 0.0001783992628525883, | |
| "loss": 0.5031, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9918636187524216, | |
| "grad_norm": 0.3022868037223816, | |
| "learning_rate": 0.00017304804189792567, | |
| "loss": 0.4871, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0170476559473072, | |
| "grad_norm": 1.213976502418518, | |
| "learning_rate": 0.00016768409533478448, | |
| "loss": 0.8302, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0418442464161177, | |
| "grad_norm": 0.42101261019706726, | |
| "learning_rate": 0.0001623159046652155, | |
| "loss": 0.4438, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0666408368849283, | |
| "grad_norm": 0.4285363554954529, | |
| "learning_rate": 0.0001569519581020743, | |
| "loss": 0.4617, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0914374273537388, | |
| "grad_norm": 0.37666165828704834, | |
| "learning_rate": 0.00015160073714741169, | |
| "loss": 0.4486, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1162340178225494, | |
| "grad_norm": 0.28406891226768494, | |
| "learning_rate": 0.00014627070318147577, | |
| "loss": 0.4323, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.14103060829136, | |
| "grad_norm": 0.28831884264945984, | |
| "learning_rate": 0.0001409702840835307, | |
| "loss": 0.4359, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1658271987601705, | |
| "grad_norm": 0.35207369923591614, | |
| "learning_rate": 0.00013570786090564706, | |
| "loss": 0.4276, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.190623789228981, | |
| "grad_norm": 0.44619789719581604, | |
| "learning_rate": 0.0001304917546205359, | |
| "loss": 0.4528, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2154203796977916, | |
| "grad_norm": 0.42749229073524475, | |
| "learning_rate": 0.00012533021296438072, | |
| "loss": 0.4688, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.2402169701666022, | |
| "grad_norm": 0.536782443523407, | |
| "learning_rate": 0.00012023139739547084, | |
| "loss": 0.4451, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2402169701666022, | |
| "eval_loss": 0.4470236301422119, | |
| "eval_runtime": 1.5686, | |
| "eval_samples_per_second": 31.875, | |
| "eval_steps_per_second": 8.287, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2650135606354127, | |
| "grad_norm": 1.0695531368255615, | |
| "learning_rate": 0.00011520337018925895, | |
| "loss": 0.4534, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.289810151104223, | |
| "grad_norm": 0.326072633266449, | |
| "learning_rate": 0.00011025408169024583, | |
| "loss": 0.4319, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.3146067415730336, | |
| "grad_norm": 0.3365119993686676, | |
| "learning_rate": 0.00010539135774085195, | |
| "loss": 0.4362, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.3394033320418441, | |
| "grad_norm": 0.4222407042980194, | |
| "learning_rate": 0.0001006228873071517, | |
| "loss": 0.43, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.3641999225106547, | |
| "grad_norm": 0.35905617475509644, | |
| "learning_rate": 9.595621032103801e-05, | |
| "loss": 0.427, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.3889965129794652, | |
| "grad_norm": 0.26657891273498535, | |
| "learning_rate": 9.139870575803991e-05, | |
| "loss": 0.4208, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.4137931034482758, | |
| "grad_norm": 0.2459261119365692, | |
| "learning_rate": 8.695757996964544e-05, | |
| "loss": 0.4123, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.4385896939170864, | |
| "grad_norm": 0.3061677813529968, | |
| "learning_rate": 8.263985528857921e-05, | |
| "loss": 0.429, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.463386284385897, | |
| "grad_norm": 0.4884737432003021, | |
| "learning_rate": 7.845235892505033e-05, | |
| "loss": 0.4428, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.4881828748547075, | |
| "grad_norm": 0.3974491059780121, | |
| "learning_rate": 7.440171217153001e-05, | |
| "loss": 0.4357, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.512979465323518, | |
| "grad_norm": 0.31677502393722534, | |
| "learning_rate": 7.049431993312759e-05, | |
| "loss": 0.4063, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.5377760557923286, | |
| "grad_norm": 0.5034978985786438, | |
| "learning_rate": 6.67363606001183e-05, | |
| "loss": 0.416, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.5625726462611391, | |
| "grad_norm": 0.3409871757030487, | |
| "learning_rate": 6.313377627863891e-05, | |
| "loss": 0.406, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.5873692367299497, | |
| "grad_norm": 0.2753334939479828, | |
| "learning_rate": 5.9692263394996376e-05, | |
| "loss": 0.3993, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.6121658271987602, | |
| "grad_norm": 0.4815467596054077, | |
| "learning_rate": 5.641726368844675e-05, | |
| "loss": 0.4139, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.6369624176675708, | |
| "grad_norm": 0.42127665877342224, | |
| "learning_rate": 5.3313955606687296e-05, | |
| "loss": 0.4155, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.6617590081363813, | |
| "grad_norm": 0.29522252082824707, | |
| "learning_rate": 5.038724611766585e-05, | |
| "loss": 0.4038, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.6865555986051919, | |
| "grad_norm": 0.3209092319011688, | |
| "learning_rate": 4.764176295065636e-05, | |
| "loss": 0.4012, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.7113521890740024, | |
| "grad_norm": 0.4263613820075989, | |
| "learning_rate": 4.508184727886723e-05, | |
| "loss": 0.4195, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.736148779542813, | |
| "grad_norm": 0.42666929960250854, | |
| "learning_rate": 4.271154685515435e-05, | |
| "loss": 0.4198, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.7609453700116235, | |
| "grad_norm": 0.29947665333747864, | |
| "learning_rate": 4.0534609611692115e-05, | |
| "loss": 0.3954, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.785741960480434, | |
| "grad_norm": 0.3265860676765442, | |
| "learning_rate": 3.855447773372175e-05, | |
| "loss": 0.402, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.8105385509492444, | |
| "grad_norm": 0.4390391707420349, | |
| "learning_rate": 3.6774282216749336e-05, | |
| "loss": 0.3979, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.835335141418055, | |
| "grad_norm": 0.28207874298095703, | |
| "learning_rate": 3.519683791579824e-05, | |
| "loss": 0.3837, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.8601317318868655, | |
| "grad_norm": 0.3026869297027588, | |
| "learning_rate": 3.382463909454464e-05, | |
| "loss": 0.3973, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.8601317318868655, | |
| "eval_loss": 0.39713945984840393, | |
| "eval_runtime": 1.5675, | |
| "eval_samples_per_second": 31.898, | |
| "eval_steps_per_second": 8.294, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.884928322355676, | |
| "grad_norm": 0.25843551754951477, | |
| "learning_rate": 3.265985548137413e-05, | |
| "loss": 0.3886, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.9097249128244866, | |
| "grad_norm": 0.23140764236450195, | |
| "learning_rate": 3.1704328838595e-05, | |
| "loss": 0.3856, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.9345215032932972, | |
| "grad_norm": 0.34332171082496643, | |
| "learning_rate": 3.0959570050233586e-05, | |
| "loss": 0.3945, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.9593180937621077, | |
| "grad_norm": 0.3156374990940094, | |
| "learning_rate": 3.0426756733016063e-05, | |
| "loss": 0.3956, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.9841146842309183, | |
| "grad_norm": 0.34009358286857605, | |
| "learning_rate": 3.010673137431425e-05, | |
| "loss": 0.4036, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.009298721425804, | |
| "grad_norm": 0.43867069482803345, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.6494, | |
| "step": 81 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 81, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9339388490004562e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |