| { | |
| "best_metric": 6.867819786071777, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.023317678741502184, | |
| "eval_steps": 25, | |
| "global_step": 142, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016420900522184638, | |
| "grad_norm": 0.18168503046035767, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016420900522184638, | |
| "eval_loss": 6.944418907165527, | |
| "eval_runtime": 0.6891, | |
| "eval_samples_per_second": 72.556, | |
| "eval_steps_per_second": 13.06, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032841801044369276, | |
| "grad_norm": 0.1871073693037033, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9417, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004926270156655391, | |
| "grad_norm": 0.18547073006629944, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9422, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006568360208873855, | |
| "grad_norm": 0.19758914411067963, | |
| "learning_rate": 8e-05, | |
| "loss": 6.9364, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008210450261092318, | |
| "grad_norm": 0.1958891600370407, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9404, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009852540313310782, | |
| "grad_norm": 0.20084300637245178, | |
| "learning_rate": 9.99881689824633e-05, | |
| "loss": 6.9411, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011494630365529246, | |
| "grad_norm": 0.19459381699562073, | |
| "learning_rate": 9.995268215087426e-05, | |
| "loss": 6.9339, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001313672041774771, | |
| "grad_norm": 0.20113036036491394, | |
| "learning_rate": 9.989355816502525e-05, | |
| "loss": 6.9377, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014778810469966172, | |
| "grad_norm": 0.207706481218338, | |
| "learning_rate": 9.981082811366797e-05, | |
| "loss": 6.9359, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016420900522184636, | |
| "grad_norm": 0.17941485345363617, | |
| "learning_rate": 9.970453549816632e-05, | |
| "loss": 6.9367, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00180629905744031, | |
| "grad_norm": 0.20235049724578857, | |
| "learning_rate": 9.957473620962246e-05, | |
| "loss": 6.9335, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0019705080626621564, | |
| "grad_norm": 0.2030957043170929, | |
| "learning_rate": 9.94214984994879e-05, | |
| "loss": 6.9291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021347170678840026, | |
| "grad_norm": 0.21488922834396362, | |
| "learning_rate": 9.924490294367533e-05, | |
| "loss": 6.9362, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022989260731058492, | |
| "grad_norm": 0.2119452953338623, | |
| "learning_rate": 9.904504240019e-05, | |
| "loss": 6.9315, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0024631350783276954, | |
| "grad_norm": 0.2180822491645813, | |
| "learning_rate": 9.88220219603028e-05, | |
| "loss": 6.9296, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002627344083549542, | |
| "grad_norm": 0.19745118916034698, | |
| "learning_rate": 9.85759588932908e-05, | |
| "loss": 6.9261, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027915530887713882, | |
| "grad_norm": 0.20321951806545258, | |
| "learning_rate": 9.830698258477458e-05, | |
| "loss": 6.9285, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0029557620939932344, | |
| "grad_norm": 0.2177504599094391, | |
| "learning_rate": 9.801523446868399e-05, | |
| "loss": 6.9288, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003119971099215081, | |
| "grad_norm": 0.21581852436065674, | |
| "learning_rate": 9.770086795288913e-05, | |
| "loss": 6.9266, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032841801044369272, | |
| "grad_norm": 0.22525547444820404, | |
| "learning_rate": 9.736404833853502e-05, | |
| "loss": 6.9243, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003448389109658774, | |
| "grad_norm": 0.24186238646507263, | |
| "learning_rate": 9.700495273312223e-05, | |
| "loss": 6.92, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00361259811488062, | |
| "grad_norm": 0.21517185866832733, | |
| "learning_rate": 9.662376995737989e-05, | |
| "loss": 6.9185, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037768071201024662, | |
| "grad_norm": 0.20967762172222137, | |
| "learning_rate": 9.622070044597935e-05, | |
| "loss": 6.9212, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003941016125324313, | |
| "grad_norm": 0.23955151438713074, | |
| "learning_rate": 9.579595614214087e-05, | |
| "loss": 6.9187, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0041052251305461595, | |
| "grad_norm": 0.228123739361763, | |
| "learning_rate": 9.534976038618931e-05, | |
| "loss": 6.9194, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0041052251305461595, | |
| "eval_loss": 6.920280933380127, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 309.601, | |
| "eval_steps_per_second": 55.728, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004269434135768005, | |
| "grad_norm": 0.24925658106803894, | |
| "learning_rate": 9.488234779811635e-05, | |
| "loss": 6.9146, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004433643140989852, | |
| "grad_norm": 0.24287429451942444, | |
| "learning_rate": 9.439396415421204e-05, | |
| "loss": 6.9166, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0045978521462116985, | |
| "grad_norm": 0.2547374963760376, | |
| "learning_rate": 9.388486625782995e-05, | |
| "loss": 6.9139, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004762061151433544, | |
| "grad_norm": 0.2530066668987274, | |
| "learning_rate": 9.335532180435412e-05, | |
| "loss": 6.9132, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004926270156655391, | |
| "grad_norm": 0.2472325563430786, | |
| "learning_rate": 9.280560924043858e-05, | |
| "loss": 6.9146, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0050904791618772375, | |
| "grad_norm": 0.25216802954673767, | |
| "learning_rate": 9.223601761759367e-05, | |
| "loss": 6.915, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005254688167099084, | |
| "grad_norm": 0.2528752386569977, | |
| "learning_rate": 9.164684644019624e-05, | |
| "loss": 6.9113, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00541889717232093, | |
| "grad_norm": 0.24980315566062927, | |
| "learning_rate": 9.103840550800329e-05, | |
| "loss": 6.9052, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0055831061775427765, | |
| "grad_norm": 0.26271212100982666, | |
| "learning_rate": 9.041101475325209e-05, | |
| "loss": 6.9033, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005747315182764623, | |
| "grad_norm": 0.2919352948665619, | |
| "learning_rate": 8.976500407243247e-05, | |
| "loss": 6.9013, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005911524187986469, | |
| "grad_norm": 0.27319350838661194, | |
| "learning_rate": 8.910071315281975e-05, | |
| "loss": 6.9097, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0060757331932083155, | |
| "grad_norm": 0.29328155517578125, | |
| "learning_rate": 8.841849129385921e-05, | |
| "loss": 6.904, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006239942198430162, | |
| "grad_norm": 0.2633126676082611, | |
| "learning_rate": 8.771869722349651e-05, | |
| "loss": 6.9065, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006404151203652008, | |
| "grad_norm": 0.2593594789505005, | |
| "learning_rate": 8.700169890955027e-05, | |
| "loss": 6.8937, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0065683602088738545, | |
| "grad_norm": 0.2693818211555481, | |
| "learning_rate": 8.626787336622607e-05, | |
| "loss": 6.9007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006732569214095701, | |
| "grad_norm": 0.29676708579063416, | |
| "learning_rate": 8.55176064558738e-05, | |
| "loss": 6.8984, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006896778219317548, | |
| "grad_norm": 0.3058428168296814, | |
| "learning_rate": 8.475129268609227e-05, | |
| "loss": 6.8938, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0070609872245393935, | |
| "grad_norm": 0.322170615196228, | |
| "learning_rate": 8.396933500228808e-05, | |
| "loss": 6.8846, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00722519622976124, | |
| "grad_norm": 0.34816184639930725, | |
| "learning_rate": 8.317214457579773e-05, | |
| "loss": 6.8835, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007389405234983087, | |
| "grad_norm": 0.32875800132751465, | |
| "learning_rate": 8.23601405876841e-05, | |
| "loss": 6.8953, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0075536142402049325, | |
| "grad_norm": 0.35221952199935913, | |
| "learning_rate": 8.153375000832157e-05, | |
| "loss": 6.8907, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007717823245426779, | |
| "grad_norm": 0.363881915807724, | |
| "learning_rate": 8.069340737288512e-05, | |
| "loss": 6.8798, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007882032250648626, | |
| "grad_norm": 0.44765737652778625, | |
| "learning_rate": 7.98395545528617e-05, | |
| "loss": 6.8804, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008046241255870471, | |
| "grad_norm": 0.48432090878486633, | |
| "learning_rate": 7.897264052370409e-05, | |
| "loss": 6.8855, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008210450261092319, | |
| "grad_norm": 0.6992037296295166, | |
| "learning_rate": 7.809312112874924e-05, | |
| "loss": 6.8687, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008210450261092319, | |
| "eval_loss": 6.891801834106445, | |
| "eval_runtime": 0.1484, | |
| "eval_samples_per_second": 336.864, | |
| "eval_steps_per_second": 60.635, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008374659266314165, | |
| "grad_norm": 0.23850670456886292, | |
| "learning_rate": 7.720145883952544e-05, | |
| "loss": 6.8929, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.00853886827153601, | |
| "grad_norm": 0.23872490227222443, | |
| "learning_rate": 7.629812251257401e-05, | |
| "loss": 6.8878, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.008703077276757858, | |
| "grad_norm": 0.25407809019088745, | |
| "learning_rate": 7.53835871429139e-05, | |
| "loss": 6.8843, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.008867286281979704, | |
| "grad_norm": 0.23447373509407043, | |
| "learning_rate": 7.445833361427828e-05, | |
| "loss": 6.8832, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.00903149528720155, | |
| "grad_norm": 0.2190893590450287, | |
| "learning_rate": 7.352284844625481e-05, | |
| "loss": 6.8877, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009195704292423397, | |
| "grad_norm": 0.22474221885204315, | |
| "learning_rate": 7.257762353846257e-05, | |
| "loss": 6.8882, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009359913297645243, | |
| "grad_norm": 0.21934156119823456, | |
| "learning_rate": 7.162315591189978e-05, | |
| "loss": 6.884, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.009524122302867088, | |
| "grad_norm": 0.22677500545978546, | |
| "learning_rate": 7.065994744759879e-05, | |
| "loss": 6.888, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.009688331308088936, | |
| "grad_norm": 0.21878303587436676, | |
| "learning_rate": 6.96885046227255e-05, | |
| "loss": 6.8825, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.009852540313310782, | |
| "grad_norm": 0.21341657638549805, | |
| "learning_rate": 6.8709338244262e-05, | |
| "loss": 6.8831, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010016749318532627, | |
| "grad_norm": 0.20267024636268616, | |
| "learning_rate": 6.772296318041253e-05, | |
| "loss": 6.884, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.010180958323754475, | |
| "grad_norm": 0.19920732080936432, | |
| "learning_rate": 6.672989808987385e-05, | |
| "loss": 6.8809, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.01034516732897632, | |
| "grad_norm": 0.2178788185119629, | |
| "learning_rate": 6.573066514911273e-05, | |
| "loss": 6.8755, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010509376334198168, | |
| "grad_norm": 0.210996612906456, | |
| "learning_rate": 6.472578977779339e-05, | |
| "loss": 6.8735, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.010673585339420014, | |
| "grad_norm": 0.19956302642822266, | |
| "learning_rate": 6.371580036249985e-05, | |
| "loss": 6.8776, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01083779434464186, | |
| "grad_norm": 0.20250411331653595, | |
| "learning_rate": 6.270122797889806e-05, | |
| "loss": 6.8728, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.011002003349863707, | |
| "grad_norm": 0.20616371929645538, | |
| "learning_rate": 6.168260611248417e-05, | |
| "loss": 6.8754, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.011166212355085553, | |
| "grad_norm": 0.2024230659008026, | |
| "learning_rate": 6.066047037806549e-05, | |
| "loss": 6.8729, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.011330421360307399, | |
| "grad_norm": 0.19448429346084595, | |
| "learning_rate": 5.9635358238121954e-05, | |
| "loss": 6.872, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.011494630365529246, | |
| "grad_norm": 0.18782764673233032, | |
| "learning_rate": 5.860780872019601e-05, | |
| "loss": 6.8785, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.011658839370751092, | |
| "grad_norm": 0.1987268328666687, | |
| "learning_rate": 5.7578362133459494e-05, | |
| "loss": 6.868, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.011823048375972938, | |
| "grad_norm": 0.1736784130334854, | |
| "learning_rate": 5.6547559784606675e-05, | |
| "loss": 6.8722, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.011987257381194785, | |
| "grad_norm": 0.17477966845035553, | |
| "learning_rate": 5.551594369322271e-05, | |
| "loss": 6.8697, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.012151466386416631, | |
| "grad_norm": 0.19487003982067108, | |
| "learning_rate": 5.44840563067773e-05, | |
| "loss": 6.8721, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.012315675391638477, | |
| "grad_norm": 0.20581433176994324, | |
| "learning_rate": 5.3452440215393315e-05, | |
| "loss": 6.8684, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.012315675391638477, | |
| "eval_loss": 6.876440048217773, | |
| "eval_runtime": 0.1565, | |
| "eval_samples_per_second": 319.512, | |
| "eval_steps_per_second": 57.512, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.012479884396860324, | |
| "grad_norm": 0.18974201381206512, | |
| "learning_rate": 5.242163786654051e-05, | |
| "loss": 6.8705, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.01264409340208217, | |
| "grad_norm": 0.19225001335144043, | |
| "learning_rate": 5.139219127980399e-05, | |
| "loss": 6.866, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.012808302407304016, | |
| "grad_norm": 0.18675003945827484, | |
| "learning_rate": 5.036464176187806e-05, | |
| "loss": 6.8649, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.012972511412525863, | |
| "grad_norm": 0.19270944595336914, | |
| "learning_rate": 4.933952962193452e-05, | |
| "loss": 6.8649, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.013136720417747709, | |
| "grad_norm": 0.22745263576507568, | |
| "learning_rate": 4.831739388751584e-05, | |
| "loss": 6.8694, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013300929422969556, | |
| "grad_norm": 0.2070324420928955, | |
| "learning_rate": 4.729877202110195e-05, | |
| "loss": 6.8627, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.013465138428191402, | |
| "grad_norm": 0.188340425491333, | |
| "learning_rate": 4.628419963750016e-05, | |
| "loss": 6.8661, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.013629347433413248, | |
| "grad_norm": 0.19918252527713776, | |
| "learning_rate": 4.527421022220663e-05, | |
| "loss": 6.8717, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.013793556438635095, | |
| "grad_norm": 0.20109033584594727, | |
| "learning_rate": 4.426933485088729e-05, | |
| "loss": 6.8634, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.013957765443856941, | |
| "grad_norm": 0.21436934173107147, | |
| "learning_rate": 4.327010191012617e-05, | |
| "loss": 6.8627, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.014121974449078787, | |
| "grad_norm": 0.2412048876285553, | |
| "learning_rate": 4.227703681958749e-05, | |
| "loss": 6.8715, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.014286183454300634, | |
| "grad_norm": 0.21019670367240906, | |
| "learning_rate": 4.1290661755738e-05, | |
| "loss": 6.8719, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.01445039245952248, | |
| "grad_norm": 0.23564065992832184, | |
| "learning_rate": 4.03114953772745e-05, | |
| "loss": 6.8576, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.014614601464744326, | |
| "grad_norm": 0.23380470275878906, | |
| "learning_rate": 3.934005255240122e-05, | |
| "loss": 6.8628, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.014778810469966173, | |
| "grad_norm": 0.2209361046552658, | |
| "learning_rate": 3.837684408810023e-05, | |
| "loss": 6.8548, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01494301947518802, | |
| "grad_norm": 0.23763206601142883, | |
| "learning_rate": 3.7422376461537435e-05, | |
| "loss": 6.8656, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.015107228480409865, | |
| "grad_norm": 0.2792171537876129, | |
| "learning_rate": 3.647715155374519e-05, | |
| "loss": 6.8605, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.015271437485631712, | |
| "grad_norm": 0.2585715353488922, | |
| "learning_rate": 3.554166638572175e-05, | |
| "loss": 6.8548, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.015435646490853558, | |
| "grad_norm": 0.2927703559398651, | |
| "learning_rate": 3.461641285708611e-05, | |
| "loss": 6.8593, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.015599855496075404, | |
| "grad_norm": 0.31993693113327026, | |
| "learning_rate": 3.370187748742601e-05, | |
| "loss": 6.8542, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.01576406450129725, | |
| "grad_norm": 0.3359384834766388, | |
| "learning_rate": 3.279854116047457e-05, | |
| "loss": 6.8526, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.015928273506519097, | |
| "grad_norm": 0.3367615044116974, | |
| "learning_rate": 3.190687887125077e-05, | |
| "loss": 6.8617, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.016092482511740943, | |
| "grad_norm": 0.4395657181739807, | |
| "learning_rate": 3.102735947629594e-05, | |
| "loss": 6.8552, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.01625669151696279, | |
| "grad_norm": 0.5388174653053284, | |
| "learning_rate": 3.0160445447138308e-05, | |
| "loss": 6.8528, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.016420900522184638, | |
| "grad_norm": 0.9235198497772217, | |
| "learning_rate": 2.9306592627114883e-05, | |
| "loss": 6.8479, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016420900522184638, | |
| "eval_loss": 6.867819786071777, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 309.663, | |
| "eval_steps_per_second": 55.739, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016585109527406484, | |
| "grad_norm": 0.15563268959522247, | |
| "learning_rate": 2.846624999167843e-05, | |
| "loss": 6.8711, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.01674931853262833, | |
| "grad_norm": 0.16060693562030792, | |
| "learning_rate": 2.7639859412315917e-05, | |
| "loss": 6.8678, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.016913527537850175, | |
| "grad_norm": 0.16681014001369476, | |
| "learning_rate": 2.682785542420229e-05, | |
| "loss": 6.869, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.01707773654307202, | |
| "grad_norm": 0.14798974990844727, | |
| "learning_rate": 2.603066499771192e-05, | |
| "loss": 6.8684, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.017241945548293867, | |
| "grad_norm": 0.15809090435504913, | |
| "learning_rate": 2.5248707313907747e-05, | |
| "loss": 6.8688, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.017406154553515716, | |
| "grad_norm": 0.15511666238307953, | |
| "learning_rate": 2.4482393544126215e-05, | |
| "loss": 6.8664, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.01757036355873756, | |
| "grad_norm": 0.1479611098766327, | |
| "learning_rate": 2.3732126633773928e-05, | |
| "loss": 6.8648, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.017734572563959407, | |
| "grad_norm": 0.14057576656341553, | |
| "learning_rate": 2.2998301090449738e-05, | |
| "loss": 6.8655, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.017898781569181253, | |
| "grad_norm": 0.1501767635345459, | |
| "learning_rate": 2.2281302776503497e-05, | |
| "loss": 6.8658, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.0180629905744031, | |
| "grad_norm": 0.148577019572258, | |
| "learning_rate": 2.1581508706140802e-05, | |
| "loss": 6.8669, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.018227199579624948, | |
| "grad_norm": 0.1595151275396347, | |
| "learning_rate": 2.0899286847180243e-05, | |
| "loss": 6.8665, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.018391408584846794, | |
| "grad_norm": 0.14874982833862305, | |
| "learning_rate": 2.0234995927567523e-05, | |
| "loss": 6.8682, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.01855561759006864, | |
| "grad_norm": 0.16214674711227417, | |
| "learning_rate": 1.9588985246747925e-05, | |
| "loss": 6.8665, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.018719826595290485, | |
| "grad_norm": 0.17474649846553802, | |
| "learning_rate": 1.896159449199672e-05, | |
| "loss": 6.8564, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.01888403560051233, | |
| "grad_norm": 0.17561936378479004, | |
| "learning_rate": 1.835315355980376e-05, | |
| "loss": 6.8664, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.019048244605734177, | |
| "grad_norm": 0.155584454536438, | |
| "learning_rate": 1.7763982382406352e-05, | |
| "loss": 6.8678, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.019212453610956026, | |
| "grad_norm": 0.161391481757164, | |
| "learning_rate": 1.7194390759561453e-05, | |
| "loss": 6.8642, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.019376662616177872, | |
| "grad_norm": 0.17117644846439362, | |
| "learning_rate": 1.664467819564588e-05, | |
| "loss": 6.8658, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.019540871621399718, | |
| "grad_norm": 0.15190771222114563, | |
| "learning_rate": 1.6115133742170053e-05, | |
| "loss": 6.8577, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.019705080626621563, | |
| "grad_norm": 0.15246935188770294, | |
| "learning_rate": 1.5606035845787987e-05, | |
| "loss": 6.8638, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01986928963184341, | |
| "grad_norm": 0.1524462103843689, | |
| "learning_rate": 1.511765220188367e-05, | |
| "loss": 6.8575, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.020033498637065255, | |
| "grad_norm": 0.187980517745018, | |
| "learning_rate": 1.4650239613810693e-05, | |
| "loss": 6.8698, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.020197707642287104, | |
| "grad_norm": 0.17757758498191833, | |
| "learning_rate": 1.4204043857859129e-05, | |
| "loss": 6.8604, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.02036191664750895, | |
| "grad_norm": 0.15591758489608765, | |
| "learning_rate": 1.3779299554020672e-05, | |
| "loss": 6.8676, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.020526125652730796, | |
| "grad_norm": 0.16383862495422363, | |
| "learning_rate": 1.3376230042620109e-05, | |
| "loss": 6.8664, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.020526125652730796, | |
| "eval_loss": 6.865334510803223, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 294.637, | |
| "eval_steps_per_second": 53.035, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02069033465795264, | |
| "grad_norm": 0.1573963165283203, | |
| "learning_rate": 1.2995047266877775e-05, | |
| "loss": 6.8635, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.020854543663174487, | |
| "grad_norm": 0.17853564023971558, | |
| "learning_rate": 1.2635951661464995e-05, | |
| "loss": 6.8617, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.021018752668396336, | |
| "grad_norm": 0.1534070074558258, | |
| "learning_rate": 1.2299132047110876e-05, | |
| "loss": 6.8606, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.021182961673618182, | |
| "grad_norm": 0.16048799455165863, | |
| "learning_rate": 1.1984765531316038e-05, | |
| "loss": 6.8625, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.021347170678840028, | |
| "grad_norm": 0.19437247514724731, | |
| "learning_rate": 1.1693017415225432e-05, | |
| "loss": 6.8558, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.021511379684061874, | |
| "grad_norm": 0.1909008026123047, | |
| "learning_rate": 1.1424041106709194e-05, | |
| "loss": 6.862, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.02167558868928372, | |
| "grad_norm": 0.18675506114959717, | |
| "learning_rate": 1.1177978039697217e-05, | |
| "loss": 6.8617, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.021839797694505565, | |
| "grad_norm": 0.19926699995994568, | |
| "learning_rate": 1.0954957599810003e-05, | |
| "loss": 6.8532, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.022004006699727414, | |
| "grad_norm": 0.18085141479969025, | |
| "learning_rate": 1.0755097056324672e-05, | |
| "loss": 6.8539, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.02216821570494926, | |
| "grad_norm": 0.19364075362682343, | |
| "learning_rate": 1.0578501500512109e-05, | |
| "loss": 6.8556, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.022332424710171106, | |
| "grad_norm": 0.21459238231182098, | |
| "learning_rate": 1.042526379037754e-05, | |
| "loss": 6.8641, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.02249663371539295, | |
| "grad_norm": 0.1923208385705948, | |
| "learning_rate": 1.0295464501833682e-05, | |
| "loss": 6.8561, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.022660842720614797, | |
| "grad_norm": 0.18413542211055756, | |
| "learning_rate": 1.0189171886332038e-05, | |
| "loss": 6.8555, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.022825051725836643, | |
| "grad_norm": 0.21922001242637634, | |
| "learning_rate": 1.0106441834974748e-05, | |
| "loss": 6.8461, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.022989260731058492, | |
| "grad_norm": 0.24008332192897797, | |
| "learning_rate": 1.0047317849125743e-05, | |
| "loss": 6.863, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.023153469736280338, | |
| "grad_norm": 0.23309044539928436, | |
| "learning_rate": 1.0011831017536722e-05, | |
| "loss": 6.8683, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.023317678741502184, | |
| "grad_norm": 0.2427399456501007, | |
| "learning_rate": 1e-05, | |
| "loss": 6.8653, | |
| "step": 142 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 142, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3803377213440.0, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |