| { | |
| "best_global_step": null, | |
| "best_metric": 0.8121369481086731, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.915813424345847, | |
| "eval_steps": 200, | |
| "global_step": 10400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02844141069397042, | |
| "grad_norm": 8.889737129211426, | |
| "learning_rate": 9.099526066350711e-07, | |
| "loss": 4.4241, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05688282138794084, | |
| "grad_norm": 7.543558120727539, | |
| "learning_rate": 1.8578199052132703e-06, | |
| "loss": 3.4415, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08532423208191127, | |
| "grad_norm": 7.774235725402832, | |
| "learning_rate": 2.8056872037914696e-06, | |
| "loss": 2.6725, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11376564277588168, | |
| "grad_norm": 7.825632572174072, | |
| "learning_rate": 3.7535545023696683e-06, | |
| "loss": 2.4137, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11376564277588168, | |
| "eval_loss": 2.2685751914978027, | |
| "eval_runtime": 29.7449, | |
| "eval_samples_per_second": 840.481, | |
| "eval_steps_per_second": 6.589, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1422070534698521, | |
| "grad_norm": 8.4616060256958, | |
| "learning_rate": 4.701421800947868e-06, | |
| "loss": 2.2701, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17064846416382254, | |
| "grad_norm": 7.439651966094971, | |
| "learning_rate": 5.6492890995260666e-06, | |
| "loss": 2.1523, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19908987485779295, | |
| "grad_norm": 8.319734573364258, | |
| "learning_rate": 6.597156398104266e-06, | |
| "loss": 2.0805, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "grad_norm": 7.824019432067871, | |
| "learning_rate": 7.545023696682466e-06, | |
| "loss": 2.0513, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "eval_loss": 1.9506336450576782, | |
| "eval_runtime": 28.6984, | |
| "eval_samples_per_second": 871.127, | |
| "eval_steps_per_second": 6.83, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25597269624573377, | |
| "grad_norm": 8.402134895324707, | |
| "learning_rate": 8.492890995260664e-06, | |
| "loss": 2.0048, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2844141069397042, | |
| "grad_norm": 7.345431327819824, | |
| "learning_rate": 9.440758293838863e-06, | |
| "loss": 1.9552, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31285551763367464, | |
| "grad_norm": 8.147149085998535, | |
| "learning_rate": 1.0388625592417063e-05, | |
| "loss": 1.8778, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3412969283276451, | |
| "grad_norm": 7.802554130554199, | |
| "learning_rate": 1.133649289099526e-05, | |
| "loss": 1.8549, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3412969283276451, | |
| "eval_loss": 1.7629565000534058, | |
| "eval_runtime": 33.6232, | |
| "eval_samples_per_second": 743.534, | |
| "eval_steps_per_second": 5.829, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.36973833902161546, | |
| "grad_norm": 7.983552932739258, | |
| "learning_rate": 1.228436018957346e-05, | |
| "loss": 1.822, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3981797497155859, | |
| "grad_norm": 8.035250663757324, | |
| "learning_rate": 1.323222748815166e-05, | |
| "loss": 1.8128, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.42662116040955633, | |
| "grad_norm": 8.409351348876953, | |
| "learning_rate": 1.4180094786729858e-05, | |
| "loss": 1.7742, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.4550625711035267, | |
| "grad_norm": 7.7319183349609375, | |
| "learning_rate": 1.5127962085308059e-05, | |
| "loss": 1.7076, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4550625711035267, | |
| "eval_loss": 1.6330854892730713, | |
| "eval_runtime": 33.0226, | |
| "eval_samples_per_second": 757.058, | |
| "eval_steps_per_second": 5.935, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.48350398179749715, | |
| "grad_norm": 7.466287136077881, | |
| "learning_rate": 1.6075829383886257e-05, | |
| "loss": 1.6919, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5119453924914675, | |
| "grad_norm": 7.655446529388428, | |
| "learning_rate": 1.7023696682464458e-05, | |
| "loss": 1.64, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.540386803185438, | |
| "grad_norm": 8.173416137695312, | |
| "learning_rate": 1.7971563981042655e-05, | |
| "loss": 1.6291, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.5688282138794084, | |
| "grad_norm": 7.376980781555176, | |
| "learning_rate": 1.8919431279620855e-05, | |
| "loss": 1.5881, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5688282138794084, | |
| "eval_loss": 1.5367897748947144, | |
| "eval_runtime": 32.9799, | |
| "eval_samples_per_second": 758.038, | |
| "eval_steps_per_second": 5.943, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5972696245733788, | |
| "grad_norm": 7.863293170928955, | |
| "learning_rate": 1.9867298578199055e-05, | |
| "loss": 1.6018, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6257110352673493, | |
| "grad_norm": 7.6200385093688965, | |
| "learning_rate": 1.9909406931423158e-05, | |
| "loss": 1.5664, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6541524459613197, | |
| "grad_norm": 8.286286354064941, | |
| "learning_rate": 1.9804066154008218e-05, | |
| "loss": 1.5545, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.6825938566552902, | |
| "grad_norm": 7.845026969909668, | |
| "learning_rate": 1.969872537659328e-05, | |
| "loss": 1.5292, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6825938566552902, | |
| "eval_loss": 1.4531670808792114, | |
| "eval_runtime": 29.4807, | |
| "eval_samples_per_second": 848.011, | |
| "eval_steps_per_second": 6.648, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7110352673492605, | |
| "grad_norm": 7.120193004608154, | |
| "learning_rate": 1.9593384599178345e-05, | |
| "loss": 1.5166, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7394766780432309, | |
| "grad_norm": 7.721842288970947, | |
| "learning_rate": 1.9488043821763408e-05, | |
| "loss": 1.517, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.7679180887372014, | |
| "grad_norm": 7.104468822479248, | |
| "learning_rate": 1.938270304434847e-05, | |
| "loss": 1.4639, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.7963594994311718, | |
| "grad_norm": 7.570240020751953, | |
| "learning_rate": 1.927736226693353e-05, | |
| "loss": 1.4729, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7963594994311718, | |
| "eval_loss": 1.368685245513916, | |
| "eval_runtime": 28.6992, | |
| "eval_samples_per_second": 871.103, | |
| "eval_steps_per_second": 6.829, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8248009101251422, | |
| "grad_norm": 7.745856761932373, | |
| "learning_rate": 1.9172021489518595e-05, | |
| "loss": 1.4501, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.8532423208191127, | |
| "grad_norm": 7.175948619842529, | |
| "learning_rate": 1.906668071210366e-05, | |
| "loss": 1.3932, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8816837315130831, | |
| "grad_norm": 8.291092872619629, | |
| "learning_rate": 1.8961339934688722e-05, | |
| "loss": 1.4063, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.9101251422070534, | |
| "grad_norm": 7.994405269622803, | |
| "learning_rate": 1.8855999157273782e-05, | |
| "loss": 1.3825, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.9101251422070534, | |
| "eval_loss": 1.300325632095337, | |
| "eval_runtime": 28.6638, | |
| "eval_samples_per_second": 872.179, | |
| "eval_steps_per_second": 6.838, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.9385665529010239, | |
| "grad_norm": 8.009012222290039, | |
| "learning_rate": 1.8750658379858845e-05, | |
| "loss": 1.3647, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.9670079635949943, | |
| "grad_norm": 8.436450004577637, | |
| "learning_rate": 1.864531760244391e-05, | |
| "loss": 1.3431, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9954493742889647, | |
| "grad_norm": 7.547204971313477, | |
| "learning_rate": 1.8539976825028972e-05, | |
| "loss": 1.3417, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.023890784982935, | |
| "grad_norm": 6.637471675872803, | |
| "learning_rate": 1.8434636047614032e-05, | |
| "loss": 1.0839, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.023890784982935, | |
| "eval_loss": 1.2430765628814697, | |
| "eval_runtime": 28.6828, | |
| "eval_samples_per_second": 871.603, | |
| "eval_steps_per_second": 6.833, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.0523321956769056, | |
| "grad_norm": 7.198896408081055, | |
| "learning_rate": 1.8329295270199096e-05, | |
| "loss": 1.0801, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.080773606370876, | |
| "grad_norm": 7.391284942626953, | |
| "learning_rate": 1.8223954492784156e-05, | |
| "loss": 1.0577, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.1092150170648465, | |
| "grad_norm": 6.571183681488037, | |
| "learning_rate": 1.811861371536922e-05, | |
| "loss": 1.0159, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.1376564277588168, | |
| "grad_norm": 7.20968770980835, | |
| "learning_rate": 1.8013272937954283e-05, | |
| "loss": 1.0239, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.1376564277588168, | |
| "eval_loss": 1.213191270828247, | |
| "eval_runtime": 28.5325, | |
| "eval_samples_per_second": 876.195, | |
| "eval_steps_per_second": 6.869, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.1660978384527874, | |
| "grad_norm": 6.97741174697876, | |
| "learning_rate": 1.7907932160539346e-05, | |
| "loss": 1.0335, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.1945392491467577, | |
| "grad_norm": 7.157691478729248, | |
| "learning_rate": 1.7802591383124406e-05, | |
| "loss": 1.0117, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.222980659840728, | |
| "grad_norm": 7.168184280395508, | |
| "learning_rate": 1.769725060570947e-05, | |
| "loss": 1.0343, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.2514220705346986, | |
| "grad_norm": 7.099086284637451, | |
| "learning_rate": 1.7591909828294533e-05, | |
| "loss": 1.0193, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.2514220705346986, | |
| "eval_loss": 1.1807738542556763, | |
| "eval_runtime": 28.5908, | |
| "eval_samples_per_second": 874.407, | |
| "eval_steps_per_second": 6.855, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.2798634812286689, | |
| "grad_norm": 7.232935905456543, | |
| "learning_rate": 1.7486569050879597e-05, | |
| "loss": 1.0235, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.3083048919226394, | |
| "grad_norm": 6.775105953216553, | |
| "learning_rate": 1.738122827346466e-05, | |
| "loss": 0.9949, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.3367463026166098, | |
| "grad_norm": 6.916153430938721, | |
| "learning_rate": 1.727588749604972e-05, | |
| "loss": 1.0058, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.36518771331058, | |
| "grad_norm": 6.561580181121826, | |
| "learning_rate": 1.7170546718634784e-05, | |
| "loss": 1.0039, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.36518771331058, | |
| "eval_loss": 1.1427565813064575, | |
| "eval_runtime": 28.6907, | |
| "eval_samples_per_second": 871.363, | |
| "eval_steps_per_second": 6.831, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.3936291240045506, | |
| "grad_norm": 6.508544921875, | |
| "learning_rate": 1.7065205941219847e-05, | |
| "loss": 1.0164, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.4220705346985212, | |
| "grad_norm": 7.889155387878418, | |
| "learning_rate": 1.695986516380491e-05, | |
| "loss": 0.9934, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4505119453924915, | |
| "grad_norm": 7.1703782081604, | |
| "learning_rate": 1.685452438638997e-05, | |
| "loss": 0.9777, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.4789533560864618, | |
| "grad_norm": 7.198650360107422, | |
| "learning_rate": 1.6749183608975034e-05, | |
| "loss": 0.9753, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.4789533560864618, | |
| "eval_loss": 1.1101032495498657, | |
| "eval_runtime": 28.9361, | |
| "eval_samples_per_second": 863.971, | |
| "eval_steps_per_second": 6.774, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.5073947667804322, | |
| "grad_norm": 7.485228061676025, | |
| "learning_rate": 1.6643842831560098e-05, | |
| "loss": 0.9621, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.5358361774744027, | |
| "grad_norm": 6.426005840301514, | |
| "learning_rate": 1.653850205414516e-05, | |
| "loss": 0.9756, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.5642775881683733, | |
| "grad_norm": 6.803189277648926, | |
| "learning_rate": 1.643316127673022e-05, | |
| "loss": 0.9725, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.5927189988623436, | |
| "grad_norm": 7.307713508605957, | |
| "learning_rate": 1.6327820499315285e-05, | |
| "loss": 0.9649, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.5927189988623436, | |
| "eval_loss": 1.0812790393829346, | |
| "eval_runtime": 28.8811, | |
| "eval_samples_per_second": 865.619, | |
| "eval_steps_per_second": 6.786, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.621160409556314, | |
| "grad_norm": 6.56484317779541, | |
| "learning_rate": 1.6222479721900348e-05, | |
| "loss": 0.9652, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.6496018202502845, | |
| "grad_norm": 6.714264392852783, | |
| "learning_rate": 1.6117138944485412e-05, | |
| "loss": 0.9861, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.6780432309442548, | |
| "grad_norm": 6.9539642333984375, | |
| "learning_rate": 1.6011798167070475e-05, | |
| "loss": 0.916, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.7064846416382253, | |
| "grad_norm": 6.552751541137695, | |
| "learning_rate": 1.5906457389655535e-05, | |
| "loss": 0.9417, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.7064846416382253, | |
| "eval_loss": 1.0522855520248413, | |
| "eval_runtime": 28.864, | |
| "eval_samples_per_second": 866.132, | |
| "eval_steps_per_second": 6.79, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.7349260523321957, | |
| "grad_norm": 6.961670875549316, | |
| "learning_rate": 1.58011166122406e-05, | |
| "loss": 0.9599, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.763367463026166, | |
| "grad_norm": 7.874273300170898, | |
| "learning_rate": 1.5695775834825662e-05, | |
| "loss": 0.9275, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.7918088737201365, | |
| "grad_norm": 5.82428503036499, | |
| "learning_rate": 1.5590435057410726e-05, | |
| "loss": 0.9247, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.820250284414107, | |
| "grad_norm": 6.425380706787109, | |
| "learning_rate": 1.5485094279995786e-05, | |
| "loss": 0.9417, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.820250284414107, | |
| "eval_loss": 1.0305691957473755, | |
| "eval_runtime": 28.6406, | |
| "eval_samples_per_second": 872.888, | |
| "eval_steps_per_second": 6.843, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.8486916951080774, | |
| "grad_norm": 6.136819362640381, | |
| "learning_rate": 1.537975350258085e-05, | |
| "loss": 0.9275, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.8771331058020477, | |
| "grad_norm": 6.463824272155762, | |
| "learning_rate": 1.5274412725165913e-05, | |
| "loss": 0.9431, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.905574516496018, | |
| "grad_norm": 6.83174467086792, | |
| "learning_rate": 1.5169071947750974e-05, | |
| "loss": 0.9147, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.9340159271899886, | |
| "grad_norm": 7.504420280456543, | |
| "learning_rate": 1.5063731170336038e-05, | |
| "loss": 0.8957, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.9340159271899886, | |
| "eval_loss": 1.0050827264785767, | |
| "eval_runtime": 28.9461, | |
| "eval_samples_per_second": 863.675, | |
| "eval_steps_per_second": 6.771, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.9624573378839592, | |
| "grad_norm": 7.271299839019775, | |
| "learning_rate": 1.49583903929211e-05, | |
| "loss": 0.9169, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.9908987485779295, | |
| "grad_norm": 6.796669960021973, | |
| "learning_rate": 1.4853049615506163e-05, | |
| "loss": 0.9079, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0193401592719, | |
| "grad_norm": 5.5628180503845215, | |
| "learning_rate": 1.4747708838091227e-05, | |
| "loss": 0.7057, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.04778156996587, | |
| "grad_norm": 5.777904987335205, | |
| "learning_rate": 1.4642368060676288e-05, | |
| "loss": 0.6037, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.04778156996587, | |
| "eval_loss": 0.9944195747375488, | |
| "eval_runtime": 28.8677, | |
| "eval_samples_per_second": 866.019, | |
| "eval_steps_per_second": 6.79, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.076222980659841, | |
| "grad_norm": 5.112311363220215, | |
| "learning_rate": 1.4537027283261352e-05, | |
| "loss": 0.5888, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.1046643913538112, | |
| "grad_norm": 6.392485618591309, | |
| "learning_rate": 1.4431686505846414e-05, | |
| "loss": 0.6134, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.1331058020477816, | |
| "grad_norm": 6.09423303604126, | |
| "learning_rate": 1.4326345728431477e-05, | |
| "loss": 0.6209, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.161547212741752, | |
| "grad_norm": 6.144412040710449, | |
| "learning_rate": 1.4221004951016539e-05, | |
| "loss": 0.6163, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.161547212741752, | |
| "eval_loss": 0.9836474061012268, | |
| "eval_runtime": 28.9354, | |
| "eval_samples_per_second": 863.993, | |
| "eval_steps_per_second": 6.774, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.189988623435722, | |
| "grad_norm": 5.410032272338867, | |
| "learning_rate": 1.4115664173601602e-05, | |
| "loss": 0.6271, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.218430034129693, | |
| "grad_norm": 5.688889980316162, | |
| "learning_rate": 1.4010323396186664e-05, | |
| "loss": 0.629, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.2468714448236633, | |
| "grad_norm": 5.400741100311279, | |
| "learning_rate": 1.3904982618771728e-05, | |
| "loss": 0.6041, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.2753128555176336, | |
| "grad_norm": 6.409387111663818, | |
| "learning_rate": 1.379964184135679e-05, | |
| "loss": 0.622, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.2753128555176336, | |
| "eval_loss": 0.9791940450668335, | |
| "eval_runtime": 29.3397, | |
| "eval_samples_per_second": 852.088, | |
| "eval_steps_per_second": 6.68, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.303754266211604, | |
| "grad_norm": 5.827444076538086, | |
| "learning_rate": 1.3694301063941853e-05, | |
| "loss": 0.6175, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.3321956769055747, | |
| "grad_norm": 6.436943054199219, | |
| "learning_rate": 1.3588960286526916e-05, | |
| "loss": 0.627, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.360637087599545, | |
| "grad_norm": 5.842226028442383, | |
| "learning_rate": 1.3483619509111978e-05, | |
| "loss": 0.6339, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.3890784982935154, | |
| "grad_norm": 6.457271575927734, | |
| "learning_rate": 1.3378278731697042e-05, | |
| "loss": 0.6325, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.3890784982935154, | |
| "eval_loss": 0.9643296003341675, | |
| "eval_runtime": 28.9755, | |
| "eval_samples_per_second": 862.799, | |
| "eval_steps_per_second": 6.764, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.4175199089874857, | |
| "grad_norm": 6.070743560791016, | |
| "learning_rate": 1.3272937954282103e-05, | |
| "loss": 0.6044, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.445961319681456, | |
| "grad_norm": 6.5427565574646, | |
| "learning_rate": 1.3167597176867167e-05, | |
| "loss": 0.6124, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.474402730375427, | |
| "grad_norm": 5.342416286468506, | |
| "learning_rate": 1.3062256399452229e-05, | |
| "loss": 0.6326, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.502844141069397, | |
| "grad_norm": 5.6298041343688965, | |
| "learning_rate": 1.2956915622037292e-05, | |
| "loss": 0.6349, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.502844141069397, | |
| "eval_loss": 0.9462358355522156, | |
| "eval_runtime": 29.0573, | |
| "eval_samples_per_second": 860.369, | |
| "eval_steps_per_second": 6.745, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.5312855517633674, | |
| "grad_norm": 5.618624210357666, | |
| "learning_rate": 1.2851574844622354e-05, | |
| "loss": 0.6286, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.5597269624573378, | |
| "grad_norm": 5.629756927490234, | |
| "learning_rate": 1.2746234067207417e-05, | |
| "loss": 0.6325, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.5881683731513085, | |
| "grad_norm": 5.6407318115234375, | |
| "learning_rate": 1.2640893289792479e-05, | |
| "loss": 0.6399, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.616609783845279, | |
| "grad_norm": 6.080498695373535, | |
| "learning_rate": 1.2535552512377542e-05, | |
| "loss": 0.6184, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.616609783845279, | |
| "eval_loss": 0.9317007064819336, | |
| "eval_runtime": 29.0538, | |
| "eval_samples_per_second": 860.472, | |
| "eval_steps_per_second": 6.746, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.645051194539249, | |
| "grad_norm": 6.4962239265441895, | |
| "learning_rate": 1.2430211734962604e-05, | |
| "loss": 0.6292, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.6734926052332195, | |
| "grad_norm": 6.621969223022461, | |
| "learning_rate": 1.2324870957547668e-05, | |
| "loss": 0.6017, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.70193401592719, | |
| "grad_norm": 5.2126054763793945, | |
| "learning_rate": 1.2219530180132731e-05, | |
| "loss": 0.6305, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.73037542662116, | |
| "grad_norm": 6.410334587097168, | |
| "learning_rate": 1.2114189402717793e-05, | |
| "loss": 0.6152, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.73037542662116, | |
| "eval_loss": 0.9212636947631836, | |
| "eval_runtime": 29.0224, | |
| "eval_samples_per_second": 861.404, | |
| "eval_steps_per_second": 6.753, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.758816837315131, | |
| "grad_norm": 6.005552291870117, | |
| "learning_rate": 1.2008848625302856e-05, | |
| "loss": 0.5972, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 2.7872582480091013, | |
| "grad_norm": 6.479732990264893, | |
| "learning_rate": 1.1903507847887918e-05, | |
| "loss": 0.6048, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.8156996587030716, | |
| "grad_norm": 6.2526397705078125, | |
| "learning_rate": 1.1798167070472982e-05, | |
| "loss": 0.6096, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 2.8441410693970424, | |
| "grad_norm": 6.823054313659668, | |
| "learning_rate": 1.1692826293058043e-05, | |
| "loss": 0.6156, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.8441410693970424, | |
| "eval_loss": 0.9072502851486206, | |
| "eval_runtime": 29.0918, | |
| "eval_samples_per_second": 859.348, | |
| "eval_steps_per_second": 6.737, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.8725824800910127, | |
| "grad_norm": 5.63970422744751, | |
| "learning_rate": 1.1587485515643107e-05, | |
| "loss": 0.5942, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 2.901023890784983, | |
| "grad_norm": 5.7269182205200195, | |
| "learning_rate": 1.1482144738228169e-05, | |
| "loss": 0.592, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.9294653014789533, | |
| "grad_norm": 6.235472202301025, | |
| "learning_rate": 1.1376803960813232e-05, | |
| "loss": 0.6088, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 2.9579067121729237, | |
| "grad_norm": 6.49041748046875, | |
| "learning_rate": 1.1271463183398294e-05, | |
| "loss": 0.5941, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.9579067121729237, | |
| "eval_loss": 0.8950417041778564, | |
| "eval_runtime": 29.0632, | |
| "eval_samples_per_second": 860.195, | |
| "eval_steps_per_second": 6.744, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.986348122866894, | |
| "grad_norm": 6.089723587036133, | |
| "learning_rate": 1.1166122405983357e-05, | |
| "loss": 0.6161, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.0147895335608648, | |
| "grad_norm": 4.977637767791748, | |
| "learning_rate": 1.1060781628568419e-05, | |
| "loss": 0.5021, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.043230944254835, | |
| "grad_norm": 5.729337215423584, | |
| "learning_rate": 1.0955440851153483e-05, | |
| "loss": 0.4116, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 3.0716723549488054, | |
| "grad_norm": 4.303124904632568, | |
| "learning_rate": 1.0850100073738546e-05, | |
| "loss": 0.3936, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.0716723549488054, | |
| "eval_loss": 0.9009103775024414, | |
| "eval_runtime": 28.839, | |
| "eval_samples_per_second": 866.881, | |
| "eval_steps_per_second": 6.796, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.1001137656427757, | |
| "grad_norm": 5.400048732757568, | |
| "learning_rate": 1.0744759296323608e-05, | |
| "loss": 0.4193, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 3.1285551763367465, | |
| "grad_norm": 6.018354415893555, | |
| "learning_rate": 1.0639418518908671e-05, | |
| "loss": 0.422, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.156996587030717, | |
| "grad_norm": 5.685466766357422, | |
| "learning_rate": 1.0534077741493733e-05, | |
| "loss": 0.432, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 3.185437997724687, | |
| "grad_norm": 5.172823905944824, | |
| "learning_rate": 1.0428736964078797e-05, | |
| "loss": 0.4281, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.185437997724687, | |
| "eval_loss": 0.8985010981559753, | |
| "eval_runtime": 28.8596, | |
| "eval_samples_per_second": 866.262, | |
| "eval_steps_per_second": 6.791, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.2138794084186575, | |
| "grad_norm": 4.836643218994141, | |
| "learning_rate": 1.0323396186663858e-05, | |
| "loss": 0.4091, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 3.242320819112628, | |
| "grad_norm": 5.528740406036377, | |
| "learning_rate": 1.0218055409248922e-05, | |
| "loss": 0.4305, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.2707622298065986, | |
| "grad_norm": 4.45158576965332, | |
| "learning_rate": 1.0112714631833984e-05, | |
| "loss": 0.4203, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 3.299203640500569, | |
| "grad_norm": 6.183067798614502, | |
| "learning_rate": 1.0007373854419047e-05, | |
| "loss": 0.4193, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.299203640500569, | |
| "eval_loss": 0.8869061470031738, | |
| "eval_runtime": 28.6962, | |
| "eval_samples_per_second": 871.197, | |
| "eval_steps_per_second": 6.83, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.3276450511945392, | |
| "grad_norm": 5.19403600692749, | |
| "learning_rate": 9.902033077004109e-06, | |
| "loss": 0.4238, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 3.3560864618885096, | |
| "grad_norm": 5.304056644439697, | |
| "learning_rate": 9.796692299589172e-06, | |
| "loss": 0.4274, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.3845278725824803, | |
| "grad_norm": 4.698873519897461, | |
| "learning_rate": 9.691351522174236e-06, | |
| "loss": 0.4124, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 3.4129692832764507, | |
| "grad_norm": 5.627292156219482, | |
| "learning_rate": 9.586010744759297e-06, | |
| "loss": 0.4241, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.4129692832764507, | |
| "eval_loss": 0.8842443823814392, | |
| "eval_runtime": 28.6817, | |
| "eval_samples_per_second": 871.636, | |
| "eval_steps_per_second": 6.834, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.441410693970421, | |
| "grad_norm": 6.473363876342773, | |
| "learning_rate": 9.480669967344361e-06, | |
| "loss": 0.427, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 3.4698521046643913, | |
| "grad_norm": 4.9653801918029785, | |
| "learning_rate": 9.375329189929423e-06, | |
| "loss": 0.4275, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.4982935153583616, | |
| "grad_norm": 4.9852294921875, | |
| "learning_rate": 9.269988412514486e-06, | |
| "loss": 0.4152, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 3.526734926052332, | |
| "grad_norm": 5.868428707122803, | |
| "learning_rate": 9.164647635099548e-06, | |
| "loss": 0.4247, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.526734926052332, | |
| "eval_loss": 0.8732792139053345, | |
| "eval_runtime": 28.8814, | |
| "eval_samples_per_second": 865.608, | |
| "eval_steps_per_second": 6.786, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.5551763367463027, | |
| "grad_norm": 5.333588600158691, | |
| "learning_rate": 9.05930685768461e-06, | |
| "loss": 0.4111, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 3.583617747440273, | |
| "grad_norm": 5.569532871246338, | |
| "learning_rate": 8.953966080269673e-06, | |
| "loss": 0.4396, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 3.6120591581342434, | |
| "grad_norm": 5.38419771194458, | |
| "learning_rate": 8.848625302854735e-06, | |
| "loss": 0.4122, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 3.640500568828214, | |
| "grad_norm": 5.328497409820557, | |
| "learning_rate": 8.743284525439798e-06, | |
| "loss": 0.4252, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.640500568828214, | |
| "eval_loss": 0.8656958937644958, | |
| "eval_runtime": 28.751, | |
| "eval_samples_per_second": 869.534, | |
| "eval_steps_per_second": 6.817, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.6689419795221845, | |
| "grad_norm": 5.675217151641846, | |
| "learning_rate": 8.63794374802486e-06, | |
| "loss": 0.4167, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 3.697383390216155, | |
| "grad_norm": 5.26973295211792, | |
| "learning_rate": 8.532602970609924e-06, | |
| "loss": 0.4282, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.725824800910125, | |
| "grad_norm": 5.991490840911865, | |
| "learning_rate": 8.427262193194985e-06, | |
| "loss": 0.411, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 3.7542662116040955, | |
| "grad_norm": 5.413957118988037, | |
| "learning_rate": 8.321921415780049e-06, | |
| "loss": 0.4273, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.7542662116040955, | |
| "eval_loss": 0.8539847135543823, | |
| "eval_runtime": 28.8669, | |
| "eval_samples_per_second": 866.045, | |
| "eval_steps_per_second": 6.79, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.782707622298066, | |
| "grad_norm": 5.672956466674805, | |
| "learning_rate": 8.21658063836511e-06, | |
| "loss": 0.4327, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 3.8111490329920366, | |
| "grad_norm": 6.0553059577941895, | |
| "learning_rate": 8.111239860950174e-06, | |
| "loss": 0.431, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 3.839590443686007, | |
| "grad_norm": 6.111351013183594, | |
| "learning_rate": 8.005899083535238e-06, | |
| "loss": 0.4347, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 3.868031854379977, | |
| "grad_norm": 6.185035705566406, | |
| "learning_rate": 7.9005583061203e-06, | |
| "loss": 0.4264, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.868031854379977, | |
| "eval_loss": 0.8523036241531372, | |
| "eval_runtime": 28.7415, | |
| "eval_samples_per_second": 869.823, | |
| "eval_steps_per_second": 6.819, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.8964732650739475, | |
| "grad_norm": 4.952618598937988, | |
| "learning_rate": 7.795217528705363e-06, | |
| "loss": 0.4213, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 3.9249146757679183, | |
| "grad_norm": 5.168086528778076, | |
| "learning_rate": 7.689876751290425e-06, | |
| "loss": 0.4285, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 3.9533560864618886, | |
| "grad_norm": 5.6217732429504395, | |
| "learning_rate": 7.584535973875487e-06, | |
| "loss": 0.4138, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 3.981797497155859, | |
| "grad_norm": 4.983550548553467, | |
| "learning_rate": 7.47919519646055e-06, | |
| "loss": 0.4051, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.981797497155859, | |
| "eval_loss": 0.8406953811645508, | |
| "eval_runtime": 28.8132, | |
| "eval_samples_per_second": 867.659, | |
| "eval_steps_per_second": 6.802, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.010238907849829, | |
| "grad_norm": 3.829274892807007, | |
| "learning_rate": 7.373854419045613e-06, | |
| "loss": 0.3779, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 4.0386803185438, | |
| "grad_norm": 4.154295921325684, | |
| "learning_rate": 7.268513641630676e-06, | |
| "loss": 0.2957, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 4.06712172923777, | |
| "grad_norm": 5.0097222328186035, | |
| "learning_rate": 7.1631728642157386e-06, | |
| "loss": 0.2939, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 4.09556313993174, | |
| "grad_norm": 5.015048027038574, | |
| "learning_rate": 7.057832086800801e-06, | |
| "loss": 0.3065, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.09556313993174, | |
| "eval_loss": 0.8590184450149536, | |
| "eval_runtime": 28.7607, | |
| "eval_samples_per_second": 869.241, | |
| "eval_steps_per_second": 6.815, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.1240045506257115, | |
| "grad_norm": 4.9901018142700195, | |
| "learning_rate": 6.952491309385864e-06, | |
| "loss": 0.3081, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 4.152445961319682, | |
| "grad_norm": 4.8424391746521, | |
| "learning_rate": 6.847150531970926e-06, | |
| "loss": 0.3043, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 4.180887372013652, | |
| "grad_norm": 5.147951602935791, | |
| "learning_rate": 6.741809754555989e-06, | |
| "loss": 0.3176, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 4.2093287827076225, | |
| "grad_norm": 4.292293548583984, | |
| "learning_rate": 6.636468977141052e-06, | |
| "loss": 0.3067, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.2093287827076225, | |
| "eval_loss": 0.848746657371521, | |
| "eval_runtime": 29.0524, | |
| "eval_samples_per_second": 860.514, | |
| "eval_steps_per_second": 6.746, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.237770193401593, | |
| "grad_norm": 4.796692848205566, | |
| "learning_rate": 6.531128199726114e-06, | |
| "loss": 0.299, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 4.266211604095563, | |
| "grad_norm": 5.196813583374023, | |
| "learning_rate": 6.425787422311177e-06, | |
| "loss": 0.3106, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.294653014789533, | |
| "grad_norm": 4.551479816436768, | |
| "learning_rate": 6.3204466448962395e-06, | |
| "loss": 0.3062, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 4.323094425483504, | |
| "grad_norm": 4.6921257972717285, | |
| "learning_rate": 6.215105867481302e-06, | |
| "loss": 0.3153, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.323094425483504, | |
| "eval_loss": 0.8497870564460754, | |
| "eval_runtime": 29.0027, | |
| "eval_samples_per_second": 861.988, | |
| "eval_steps_per_second": 6.758, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.351535836177474, | |
| "grad_norm": 4.535303592681885, | |
| "learning_rate": 6.109765090066366e-06, | |
| "loss": 0.3206, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 4.379977246871444, | |
| "grad_norm": 5.174567222595215, | |
| "learning_rate": 6.004424312651428e-06, | |
| "loss": 0.3202, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 4.408418657565416, | |
| "grad_norm": 4.402812480926514, | |
| "learning_rate": 5.899083535236491e-06, | |
| "loss": 0.3167, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 4.436860068259386, | |
| "grad_norm": 4.917297840118408, | |
| "learning_rate": 5.7937427578215534e-06, | |
| "loss": 0.3044, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 4.436860068259386, | |
| "eval_loss": 0.8426228165626526, | |
| "eval_runtime": 29.2233, | |
| "eval_samples_per_second": 855.482, | |
| "eval_steps_per_second": 6.707, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 4.465301478953356, | |
| "grad_norm": 5.476150989532471, | |
| "learning_rate": 5.688401980406616e-06, | |
| "loss": 0.3015, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 4.493742889647327, | |
| "grad_norm": 5.594091415405273, | |
| "learning_rate": 5.583061202991679e-06, | |
| "loss": 0.3157, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 4.522184300341297, | |
| "grad_norm": 4.798509120941162, | |
| "learning_rate": 5.477720425576741e-06, | |
| "loss": 0.3109, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 4.550625711035267, | |
| "grad_norm": 4.705766201019287, | |
| "learning_rate": 5.372379648161804e-06, | |
| "loss": 0.3164, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.550625711035267, | |
| "eval_loss": 0.8384647369384766, | |
| "eval_runtime": 29.0223, | |
| "eval_samples_per_second": 861.406, | |
| "eval_steps_per_second": 6.753, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.579067121729238, | |
| "grad_norm": 5.214234352111816, | |
| "learning_rate": 5.269145686295165e-06, | |
| "loss": 0.2996, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 4.607508532423208, | |
| "grad_norm": 3.9629294872283936, | |
| "learning_rate": 5.163804908880228e-06, | |
| "loss": 0.3247, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 4.635949943117178, | |
| "grad_norm": 5.35923957824707, | |
| "learning_rate": 5.058464131465291e-06, | |
| "loss": 0.3093, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 4.664391353811149, | |
| "grad_norm": 4.924727916717529, | |
| "learning_rate": 4.9531233540503534e-06, | |
| "loss": 0.3017, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 4.664391353811149, | |
| "eval_loss": 0.8293972611427307, | |
| "eval_runtime": 29.0332, | |
| "eval_samples_per_second": 861.084, | |
| "eval_steps_per_second": 6.751, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 4.69283276450512, | |
| "grad_norm": 4.929891586303711, | |
| "learning_rate": 4.847782576635416e-06, | |
| "loss": 0.3075, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 4.72127417519909, | |
| "grad_norm": 4.345849514007568, | |
| "learning_rate": 4.742441799220479e-06, | |
| "loss": 0.3006, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 4.74971558589306, | |
| "grad_norm": 4.58878231048584, | |
| "learning_rate": 4.637101021805541e-06, | |
| "loss": 0.3134, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 4.778156996587031, | |
| "grad_norm": 5.448882579803467, | |
| "learning_rate": 4.531760244390604e-06, | |
| "loss": 0.3111, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 4.778156996587031, | |
| "eval_loss": 0.8249350786209106, | |
| "eval_runtime": 29.1624, | |
| "eval_samples_per_second": 857.269, | |
| "eval_steps_per_second": 6.721, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 4.806598407281001, | |
| "grad_norm": 4.381404399871826, | |
| "learning_rate": 4.4264194669756665e-06, | |
| "loss": 0.3165, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 4.835039817974971, | |
| "grad_norm": 4.86619234085083, | |
| "learning_rate": 4.321078689560729e-06, | |
| "loss": 0.3071, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.863481228668942, | |
| "grad_norm": 5.313292503356934, | |
| "learning_rate": 4.215737912145792e-06, | |
| "loss": 0.3017, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 4.891922639362912, | |
| "grad_norm": 4.802574157714844, | |
| "learning_rate": 4.110397134730854e-06, | |
| "loss": 0.3092, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 4.891922639362912, | |
| "eval_loss": 0.8224520087242126, | |
| "eval_runtime": 29.0511, | |
| "eval_samples_per_second": 860.551, | |
| "eval_steps_per_second": 6.747, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 4.920364050056882, | |
| "grad_norm": 5.428598880767822, | |
| "learning_rate": 4.005056357315917e-06, | |
| "loss": 0.3, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 4.948805460750854, | |
| "grad_norm": 5.6783528327941895, | |
| "learning_rate": 3.8997155799009805e-06, | |
| "loss": 0.2999, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 4.977246871444824, | |
| "grad_norm": 5.2957940101623535, | |
| "learning_rate": 3.7943748024860427e-06, | |
| "loss": 0.3116, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 5.005688282138794, | |
| "grad_norm": 4.1276631355285645, | |
| "learning_rate": 3.6890340250711053e-06, | |
| "loss": 0.3046, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 5.005688282138794, | |
| "eval_loss": 0.8173409700393677, | |
| "eval_runtime": 28.9634, | |
| "eval_samples_per_second": 863.157, | |
| "eval_steps_per_second": 6.767, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 5.034129692832765, | |
| "grad_norm": 4.093660354614258, | |
| "learning_rate": 3.5836932476561683e-06, | |
| "loss": 0.2501, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 5.062571103526735, | |
| "grad_norm": 5.549435615539551, | |
| "learning_rate": 3.478352470241231e-06, | |
| "loss": 0.2443, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 5.091012514220705, | |
| "grad_norm": 4.558211803436279, | |
| "learning_rate": 3.3730116928262936e-06, | |
| "loss": 0.2338, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 5.1194539249146755, | |
| "grad_norm": 3.450760841369629, | |
| "learning_rate": 3.267670915411356e-06, | |
| "loss": 0.2382, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.1194539249146755, | |
| "eval_loss": 0.8248207569122314, | |
| "eval_runtime": 29.0514, | |
| "eval_samples_per_second": 860.545, | |
| "eval_steps_per_second": 6.747, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.147895335608646, | |
| "grad_norm": 4.0541205406188965, | |
| "learning_rate": 3.162330137996419e-06, | |
| "loss": 0.2524, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 5.176336746302616, | |
| "grad_norm": 4.376137733459473, | |
| "learning_rate": 3.0569893605814814e-06, | |
| "loss": 0.2427, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 5.204778156996587, | |
| "grad_norm": 4.169808864593506, | |
| "learning_rate": 2.951648583166544e-06, | |
| "loss": 0.2512, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 5.233219567690558, | |
| "grad_norm": 4.089740753173828, | |
| "learning_rate": 2.846307805751607e-06, | |
| "loss": 0.2377, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 5.233219567690558, | |
| "eval_loss": 0.8218184113502502, | |
| "eval_runtime": 28.9027, | |
| "eval_samples_per_second": 864.97, | |
| "eval_steps_per_second": 6.781, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 5.261660978384528, | |
| "grad_norm": 4.028066635131836, | |
| "learning_rate": 2.7409670283366697e-06, | |
| "loss": 0.2458, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 5.290102389078498, | |
| "grad_norm": 5.62259578704834, | |
| "learning_rate": 2.635626250921732e-06, | |
| "loss": 0.2515, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 5.318543799772469, | |
| "grad_norm": 4.931870937347412, | |
| "learning_rate": 2.5302854735067945e-06, | |
| "loss": 0.2453, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 5.346985210466439, | |
| "grad_norm": 4.307934284210205, | |
| "learning_rate": 2.4249446960918575e-06, | |
| "loss": 0.244, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 5.346985210466439, | |
| "eval_loss": 0.8225930333137512, | |
| "eval_runtime": 28.8011, | |
| "eval_samples_per_second": 868.022, | |
| "eval_steps_per_second": 6.805, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 5.375426621160409, | |
| "grad_norm": 3.650233030319214, | |
| "learning_rate": 2.31960391867692e-06, | |
| "loss": 0.2389, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 5.40386803185438, | |
| "grad_norm": 4.171177864074707, | |
| "learning_rate": 2.2142631412619828e-06, | |
| "loss": 0.253, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.43230944254835, | |
| "grad_norm": 5.055683135986328, | |
| "learning_rate": 2.1089223638470454e-06, | |
| "loss": 0.2509, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 5.460750853242321, | |
| "grad_norm": 4.621593952178955, | |
| "learning_rate": 2.003581586432108e-06, | |
| "loss": 0.2492, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 5.460750853242321, | |
| "eval_loss": 0.8198309540748596, | |
| "eval_runtime": 28.7042, | |
| "eval_samples_per_second": 870.954, | |
| "eval_steps_per_second": 6.828, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 5.489192263936292, | |
| "grad_norm": 5.461741924285889, | |
| "learning_rate": 1.8982408090171708e-06, | |
| "loss": 0.2379, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 5.517633674630262, | |
| "grad_norm": 4.083144664764404, | |
| "learning_rate": 1.7929000316022333e-06, | |
| "loss": 0.247, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 5.546075085324232, | |
| "grad_norm": 4.508319854736328, | |
| "learning_rate": 1.6875592541872959e-06, | |
| "loss": 0.2419, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 5.5745164960182025, | |
| "grad_norm": 4.420298099517822, | |
| "learning_rate": 1.5822184767723587e-06, | |
| "loss": 0.244, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 5.5745164960182025, | |
| "eval_loss": 0.8149560689926147, | |
| "eval_runtime": 28.7025, | |
| "eval_samples_per_second": 871.004, | |
| "eval_steps_per_second": 6.829, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 5.602957906712173, | |
| "grad_norm": 4.702558517456055, | |
| "learning_rate": 1.4768776993574213e-06, | |
| "loss": 0.2498, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 5.631399317406143, | |
| "grad_norm": 3.864471912384033, | |
| "learning_rate": 1.371536921942484e-06, | |
| "loss": 0.2381, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 5.6598407281001135, | |
| "grad_norm": 4.41420316696167, | |
| "learning_rate": 1.2661961445275468e-06, | |
| "loss": 0.2425, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 5.688282138794084, | |
| "grad_norm": 4.402945041656494, | |
| "learning_rate": 1.1608553671126094e-06, | |
| "loss": 0.2451, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.688282138794084, | |
| "eval_loss": 0.8147642016410828, | |
| "eval_runtime": 28.751, | |
| "eval_samples_per_second": 869.534, | |
| "eval_steps_per_second": 6.817, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.716723549488055, | |
| "grad_norm": 4.66687536239624, | |
| "learning_rate": 1.055514589697672e-06, | |
| "loss": 0.2468, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 5.745164960182025, | |
| "grad_norm": 4.6121649742126465, | |
| "learning_rate": 9.501738122827347e-07, | |
| "loss": 0.2404, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 5.773606370875996, | |
| "grad_norm": 4.210214614868164, | |
| "learning_rate": 8.469398504160961e-07, | |
| "loss": 0.2397, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 5.802047781569966, | |
| "grad_norm": 4.265695095062256, | |
| "learning_rate": 7.415990730011588e-07, | |
| "loss": 0.2417, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 5.802047781569966, | |
| "eval_loss": 0.8124446868896484, | |
| "eval_runtime": 28.7474, | |
| "eval_samples_per_second": 869.643, | |
| "eval_steps_per_second": 6.818, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 5.830489192263936, | |
| "grad_norm": 4.166738033294678, | |
| "learning_rate": 6.362582955862215e-07, | |
| "loss": 0.2446, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 5.858930602957907, | |
| "grad_norm": 4.40815544128418, | |
| "learning_rate": 5.309175181712841e-07, | |
| "loss": 0.2443, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 5.887372013651877, | |
| "grad_norm": 3.757612466812134, | |
| "learning_rate": 4.255767407563468e-07, | |
| "loss": 0.2465, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 5.915813424345847, | |
| "grad_norm": 5.059196472167969, | |
| "learning_rate": 3.202359633414095e-07, | |
| "loss": 0.2472, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 5.915813424345847, | |
| "eval_loss": 0.8121369481086731, | |
| "eval_runtime": 28.8178, | |
| "eval_samples_per_second": 867.521, | |
| "eval_steps_per_second": 6.801, | |
| "step": 10400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 10548, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |