| { | |
| "best_metric": 0.33531588315963745, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.32948929159802304, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016474464579901153, | |
| "grad_norm": 0.09833762794733047, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2895, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016474464579901153, | |
| "eval_loss": 0.5550563931465149, | |
| "eval_runtime": 138.4887, | |
| "eval_samples_per_second": 7.387, | |
| "eval_steps_per_second": 1.849, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032948929159802307, | |
| "grad_norm": 0.10695746541023254, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2826, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004942339373970346, | |
| "grad_norm": 0.12669576704502106, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3467, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006589785831960461, | |
| "grad_norm": 0.14476247131824493, | |
| "learning_rate": 4e-05, | |
| "loss": 0.384, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008237232289950576, | |
| "grad_norm": 0.14292767643928528, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3769, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009884678747940691, | |
| "grad_norm": 0.15339472889900208, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3934, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011532125205930808, | |
| "grad_norm": 0.1499355286359787, | |
| "learning_rate": 7e-05, | |
| "loss": 0.4003, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013179571663920923, | |
| "grad_norm": 0.1409144550561905, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4029, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014827018121911038, | |
| "grad_norm": 0.13928787410259247, | |
| "learning_rate": 9e-05, | |
| "loss": 0.3292, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016474464579901153, | |
| "grad_norm": 0.16985270380973816, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3174, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018121911037891267, | |
| "grad_norm": 0.16463865339756012, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.3517, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019769357495881382, | |
| "grad_norm": 0.1663835495710373, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.3552, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0214168039538715, | |
| "grad_norm": 0.1397836059331894, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.403, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023064250411861616, | |
| "grad_norm": 0.11862882226705551, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.3518, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02471169686985173, | |
| "grad_norm": 0.13293981552124023, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.4206, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026359143327841845, | |
| "grad_norm": 0.14594757556915283, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.396, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02800658978583196, | |
| "grad_norm": 0.1293398141860962, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.3894, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.029654036243822075, | |
| "grad_norm": 0.15542484819889069, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.37, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03130148270181219, | |
| "grad_norm": 0.14950259029865265, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.4163, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.032948929159802305, | |
| "grad_norm": 0.1420469731092453, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.4277, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03459637561779242, | |
| "grad_norm": 0.15825937688350677, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.3524, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036243822075782535, | |
| "grad_norm": 0.15298204123973846, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.3996, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03789126853377265, | |
| "grad_norm": 0.1467004120349884, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.397, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.039538714991762765, | |
| "grad_norm": 0.14487476646900177, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.3243, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04118616144975288, | |
| "grad_norm": 0.14483661949634552, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.3732, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042833607907743, | |
| "grad_norm": 0.1448603719472885, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.3738, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.044481054365733116, | |
| "grad_norm": 0.15915794670581818, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.3807, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04612850082372323, | |
| "grad_norm": 0.1394796520471573, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.3366, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.047775947281713346, | |
| "grad_norm": 0.14767640829086304, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.3658, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04942339373970346, | |
| "grad_norm": 0.15104010701179504, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.3588, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.051070840197693576, | |
| "grad_norm": 0.15823905169963837, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.3647, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05271828665568369, | |
| "grad_norm": 0.14908240735530853, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.3488, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.054365733113673806, | |
| "grad_norm": 0.15767070651054382, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.3278, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05601317957166392, | |
| "grad_norm": 0.1770012229681015, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.3656, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.057660626029654036, | |
| "grad_norm": 0.17861847579479218, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.3983, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05930807248764415, | |
| "grad_norm": 0.1964598000049591, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.4297, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.060955518945634266, | |
| "grad_norm": 0.14996610581874847, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.302, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06260296540362438, | |
| "grad_norm": 0.17590104043483734, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.3915, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0642504118616145, | |
| "grad_norm": 0.1804283857345581, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.3936, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06589785831960461, | |
| "grad_norm": 0.17284002900123596, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.3756, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06754530477759473, | |
| "grad_norm": 0.19819098711013794, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.3969, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06919275123558484, | |
| "grad_norm": 0.18832913041114807, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.3831, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07084019769357495, | |
| "grad_norm": 0.18674547970294952, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.3987, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07248764415156507, | |
| "grad_norm": 0.17630259692668915, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.3522, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07413509060955518, | |
| "grad_norm": 0.17837630212306976, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.3549, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0757825370675453, | |
| "grad_norm": 0.2065899670124054, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.3039, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07742998352553541, | |
| "grad_norm": 0.21110694110393524, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.3749, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07907742998352553, | |
| "grad_norm": 0.25675275921821594, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3435, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08072487644151564, | |
| "grad_norm": 0.2816130220890045, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.4668, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08237232289950576, | |
| "grad_norm": 0.641676664352417, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.4362, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08237232289950576, | |
| "eval_loss": 0.41651421785354614, | |
| "eval_runtime": 139.3183, | |
| "eval_samples_per_second": 7.343, | |
| "eval_steps_per_second": 1.838, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08401976935749589, | |
| "grad_norm": 0.1991819441318512, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.2877, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.085667215815486, | |
| "grad_norm": 0.18471182882785797, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.3119, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08731466227347612, | |
| "grad_norm": 0.13579897582530975, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.3079, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.08896210873146623, | |
| "grad_norm": 0.11216560751199722, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.3491, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09060955518945635, | |
| "grad_norm": 0.1041259914636612, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.3704, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09225700164744646, | |
| "grad_norm": 0.09888610988855362, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.3568, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.09390444810543658, | |
| "grad_norm": 0.10044589638710022, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.3429, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09555189456342669, | |
| "grad_norm": 0.11643680185079575, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.3572, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.09719934102141681, | |
| "grad_norm": 0.12925311923027039, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.3764, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.09884678747940692, | |
| "grad_norm": 0.1256956309080124, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.3895, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10049423393739704, | |
| "grad_norm": 0.11921319365501404, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.3231, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.10214168039538715, | |
| "grad_norm": 0.11790497601032257, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.329, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10378912685337727, | |
| "grad_norm": 0.12554842233657837, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.3728, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10543657331136738, | |
| "grad_norm": 0.11191652715206146, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.3281, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1070840197693575, | |
| "grad_norm": 0.13239502906799316, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.4435, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.10873146622734761, | |
| "grad_norm": 0.12777960300445557, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.363, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.11037891268533773, | |
| "grad_norm": 0.1333911120891571, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.4103, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.11202635914332784, | |
| "grad_norm": 0.13242995738983154, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.3661, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.11367380560131796, | |
| "grad_norm": 0.13358387351036072, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.406, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.11532125205930807, | |
| "grad_norm": 0.12072084844112396, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.3505, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11696869851729819, | |
| "grad_norm": 0.12484239786863327, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.3827, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1186161449752883, | |
| "grad_norm": 0.12913241982460022, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.3885, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.12026359143327842, | |
| "grad_norm": 0.13131500780582428, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.3543, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.12191103789126853, | |
| "grad_norm": 0.1276056319475174, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.3615, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.12355848434925865, | |
| "grad_norm": 0.1369161158800125, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.3277, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.12520593080724876, | |
| "grad_norm": 0.13961659371852875, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.389, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.12685337726523888, | |
| "grad_norm": 0.1416119933128357, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.3906, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.128500823723229, | |
| "grad_norm": 0.1403471976518631, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.3469, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1301482701812191, | |
| "grad_norm": 0.1442699134349823, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.3739, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.13179571663920922, | |
| "grad_norm": 0.1491308957338333, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.3646, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13344316309719934, | |
| "grad_norm": 0.1451076865196228, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.3519, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13509060955518945, | |
| "grad_norm": 0.15581031143665314, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.3385, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.13673805601317957, | |
| "grad_norm": 0.15515553951263428, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.4059, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.13838550247116968, | |
| "grad_norm": 0.14925862848758698, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.3488, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1400329489291598, | |
| "grad_norm": 0.16472037136554718, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.3326, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1416803953871499, | |
| "grad_norm": 0.1497831493616104, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.3223, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.14332784184514002, | |
| "grad_norm": 0.15523536503314972, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.3498, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.14497528830313014, | |
| "grad_norm": 0.13872024416923523, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.2939, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.14662273476112025, | |
| "grad_norm": 0.16493260860443115, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.3576, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.14827018121911037, | |
| "grad_norm": 0.15549318492412567, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.2858, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14991762767710048, | |
| "grad_norm": 0.18647244572639465, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.3891, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.1515650741350906, | |
| "grad_norm": 0.1645464450120926, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.3501, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.15321252059308071, | |
| "grad_norm": 0.17893564701080322, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.3496, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.15485996705107083, | |
| "grad_norm": 0.17226094007492065, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.3069, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.15650741350906094, | |
| "grad_norm": 0.1970873326063156, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.358, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.15815485996705106, | |
| "grad_norm": 0.17530538141727448, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.3133, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.15980230642504117, | |
| "grad_norm": 0.20767785608768463, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.3492, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1614497528830313, | |
| "grad_norm": 0.19300808012485504, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.3381, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1630971993410214, | |
| "grad_norm": 0.22722351551055908, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.3332, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.16474464579901152, | |
| "grad_norm": 0.3118744492530823, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.407, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16474464579901152, | |
| "eval_loss": 0.37044182419776917, | |
| "eval_runtime": 139.7653, | |
| "eval_samples_per_second": 7.319, | |
| "eval_steps_per_second": 1.832, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16639209225700163, | |
| "grad_norm": 0.14618542790412903, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.2786, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.16803953871499178, | |
| "grad_norm": 0.16265349090099335, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.2977, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.1696869851729819, | |
| "grad_norm": 0.15795961022377014, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.3318, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.171334431630972, | |
| "grad_norm": 0.13996830582618713, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.349, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.17298187808896212, | |
| "grad_norm": 0.10808467864990234, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3073, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.17462932454695224, | |
| "grad_norm": 0.10059759020805359, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.3077, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.17627677100494235, | |
| "grad_norm": 0.1200738400220871, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.3996, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.17792421746293247, | |
| "grad_norm": 0.1048455610871315, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.3478, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.17957166392092258, | |
| "grad_norm": 0.11230103671550751, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.3721, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.1812191103789127, | |
| "grad_norm": 0.11038646847009659, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.3595, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1828665568369028, | |
| "grad_norm": 0.1388077735900879, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.3116, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.18451400329489293, | |
| "grad_norm": 0.11409083753824234, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.3251, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.18616144975288304, | |
| "grad_norm": 0.11755376309156418, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.3294, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.18780889621087316, | |
| "grad_norm": 0.1129239946603775, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.3067, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.18945634266886327, | |
| "grad_norm": 0.12179818749427795, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.382, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.19110378912685339, | |
| "grad_norm": 0.12584486603736877, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.3473, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.1927512355848435, | |
| "grad_norm": 0.12674686312675476, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.387, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.19439868204283361, | |
| "grad_norm": 0.12840886414051056, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.3422, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.19604612850082373, | |
| "grad_norm": 0.13262827694416046, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.3826, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.19769357495881384, | |
| "grad_norm": 0.13012638688087463, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.3328, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.19934102141680396, | |
| "grad_norm": 0.12670789659023285, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.3535, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.20098846787479407, | |
| "grad_norm": 0.1337648630142212, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.3532, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.2026359143327842, | |
| "grad_norm": 0.13287080824375153, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.37, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.2042833607907743, | |
| "grad_norm": 0.14960862696170807, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.3602, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.20593080724876442, | |
| "grad_norm": 0.13266746699810028, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.3877, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.20757825370675453, | |
| "grad_norm": 0.13430094718933105, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.3265, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.20922570016474465, | |
| "grad_norm": 0.13731937110424042, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.3692, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.21087314662273476, | |
| "grad_norm": 0.1341460943222046, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.319, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.21252059308072488, | |
| "grad_norm": 0.14977669715881348, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.3752, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.214168039538715, | |
| "grad_norm": 0.14493146538734436, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.3874, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2158154859967051, | |
| "grad_norm": 0.13880854845046997, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.3478, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.21746293245469522, | |
| "grad_norm": 0.14300213754177094, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.3601, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.21911037891268534, | |
| "grad_norm": 0.1512204110622406, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.365, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.22075782537067545, | |
| "grad_norm": 0.15568716824054718, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.3509, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.22240527182866557, | |
| "grad_norm": 0.1601901650428772, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.3693, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.22405271828665568, | |
| "grad_norm": 0.1470739096403122, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.3248, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.2257001647446458, | |
| "grad_norm": 0.14510512351989746, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.3098, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.2273476112026359, | |
| "grad_norm": 0.15918153524398804, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.357, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.22899505766062603, | |
| "grad_norm": 0.15598979592323303, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.3369, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.23064250411861614, | |
| "grad_norm": 0.15520276129245758, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.3265, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23228995057660626, | |
| "grad_norm": 0.18635183572769165, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.4275, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.23393739703459637, | |
| "grad_norm": 0.1621357649564743, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.3324, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.2355848434925865, | |
| "grad_norm": 0.18017056584358215, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.3689, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.2372322899505766, | |
| "grad_norm": 0.1664380431175232, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.2921, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.23887973640856672, | |
| "grad_norm": 0.18880164623260498, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.3332, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.24052718286655683, | |
| "grad_norm": 0.2054162472486496, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.3558, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.24217462932454695, | |
| "grad_norm": 0.18269827961921692, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.3395, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.24382207578253706, | |
| "grad_norm": 0.21836520731449127, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.3889, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.24546952224052718, | |
| "grad_norm": 0.21840327978134155, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.3704, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.2471169686985173, | |
| "grad_norm": 0.25706344842910767, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.3902, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2471169686985173, | |
| "eval_loss": 0.342384397983551, | |
| "eval_runtime": 139.6314, | |
| "eval_samples_per_second": 7.326, | |
| "eval_steps_per_second": 1.833, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2487644151565074, | |
| "grad_norm": 0.07788684964179993, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.2601, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.2504118616144975, | |
| "grad_norm": 0.0902789756655693, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.2353, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.25205930807248766, | |
| "grad_norm": 0.10044808685779572, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.3136, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.25370675453047775, | |
| "grad_norm": 0.10885512083768845, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.2856, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.2553542009884679, | |
| "grad_norm": 0.10997948050498962, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.2809, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.257001647446458, | |
| "grad_norm": 0.11492530256509781, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.3235, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.2586490939044481, | |
| "grad_norm": 0.11498770862817764, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.2902, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.2602965403624382, | |
| "grad_norm": 0.14230814576148987, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.3713, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.26194398682042835, | |
| "grad_norm": 0.11751173436641693, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.3479, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.26359143327841844, | |
| "grad_norm": 0.12746025621891022, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.3624, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2652388797364086, | |
| "grad_norm": 0.14811520278453827, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.3327, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.26688632619439867, | |
| "grad_norm": 0.12954500317573547, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.3845, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.2685337726523888, | |
| "grad_norm": 0.12051427364349365, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.3401, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.2701812191103789, | |
| "grad_norm": 0.12770628929138184, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.3307, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.27182866556836904, | |
| "grad_norm": 0.1280841827392578, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.3254, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.27347611202635913, | |
| "grad_norm": 0.12260039150714874, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.3464, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.2751235584843493, | |
| "grad_norm": 0.12239458411931992, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.3534, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.27677100494233936, | |
| "grad_norm": 0.11654067784547806, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.2965, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2784184514003295, | |
| "grad_norm": 0.12907373905181885, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.366, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2800658978583196, | |
| "grad_norm": 0.14050835371017456, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.3985, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.28171334431630973, | |
| "grad_norm": 0.1293203979730606, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.3744, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.2833607907742998, | |
| "grad_norm": 0.12564347684383392, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.3781, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.28500823723228996, | |
| "grad_norm": 0.14210841059684753, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.3634, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.28665568369028005, | |
| "grad_norm": 0.13845568895339966, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.4007, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.2883031301482702, | |
| "grad_norm": 0.14582672715187073, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.3902, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2899505766062603, | |
| "grad_norm": 0.14082463085651398, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.3755, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.2915980230642504, | |
| "grad_norm": 0.12261424958705902, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.2937, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.2932454695222405, | |
| "grad_norm": 0.14349566400051117, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.389, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.29489291598023065, | |
| "grad_norm": 0.14432135224342346, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.354, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.29654036243822074, | |
| "grad_norm": 0.15195347368717194, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.3739, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2981878088962109, | |
| "grad_norm": 0.13570450246334076, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.293, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.29983525535420097, | |
| "grad_norm": 0.1377730518579483, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.3382, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.3014827018121911, | |
| "grad_norm": 0.15515458583831787, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.3815, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.3031301482701812, | |
| "grad_norm": 0.151368647813797, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.3247, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.30477759472817134, | |
| "grad_norm": 0.16193626821041107, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.385, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.30642504118616143, | |
| "grad_norm": 0.1491345316171646, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.3322, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.30807248764415157, | |
| "grad_norm": 0.1667986661195755, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.3815, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.30971993410214166, | |
| "grad_norm": 0.15640690922737122, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.3736, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.3113673805601318, | |
| "grad_norm": 0.1465839147567749, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.2871, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.3130148270181219, | |
| "grad_norm": 0.16388766467571259, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.3298, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.31466227347611203, | |
| "grad_norm": 0.1944657862186432, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.388, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.3163097199341021, | |
| "grad_norm": 0.1617269665002823, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.3196, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.31795716639209226, | |
| "grad_norm": 0.17897528409957886, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.3178, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.31960461285008235, | |
| "grad_norm": 0.18072108924388885, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.3041, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.3212520593080725, | |
| "grad_norm": 0.18485189974308014, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.3396, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.3228995057660626, | |
| "grad_norm": 0.2076258510351181, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.347, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.3245469522240527, | |
| "grad_norm": 0.2142169028520584, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.3138, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.3261943986820428, | |
| "grad_norm": 0.21588295698165894, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.3358, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.32784184514003295, | |
| "grad_norm": 0.25630298256874084, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.3862, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.32948929159802304, | |
| "grad_norm": 0.35187631845474243, | |
| "learning_rate": 0.0, | |
| "loss": 0.4441, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32948929159802304, | |
| "eval_loss": 0.33531588315963745, | |
| "eval_runtime": 139.696, | |
| "eval_samples_per_second": 7.323, | |
| "eval_steps_per_second": 1.833, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 5.715087116677939e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |