| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09918175055789735, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004959087527894868, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.333333333333333e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004959087527894868, | |
| "eval_loss": NaN, | |
| "eval_runtime": 338.9156, | |
| "eval_samples_per_second": 10.023, | |
| "eval_steps_per_second": 2.508, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009918175055789735, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.666666666666666e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014877262583684603, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001983635011157947, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.333333333333333e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002479543763947434, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1666666666666665e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029754525167369206, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034713612695264073, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.633333333333333e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003967270022315894, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8666666666666665e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004463178775105381, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004959087527894868, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.333333333333333e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005454996280684354, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5666666666666663e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005950905033473841, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006446813786263328, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0333333333333333e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006942722539052815, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.266666666666666e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007438631291842301, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007934540044631788, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.733333333333333e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008430448797421275, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9666666666666664e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008926357550210762, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009422266303000248, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4333333333333324e-05, | |
| "loss": 4.6481, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009918175055789735, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.666666666666666e-05, | |
| "loss": 21.5072, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010414083808579222, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.899999999999999e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010909992561368709, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1333333333333325e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011405901314158196, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3666666666666666e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011901810066947682, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012397718819737169, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.833333333333333e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012893627572526656, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0666666666666666e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013389536325316143, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.3e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01388544507810563, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.533333333333333e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014381353830895116, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.766666666666667e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014877262583684603, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01537317133647409, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.999402376603183e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015869080089263576, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.99760971050058e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016364988842053063, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.994622613886018e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01686089759484255, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.990442106850258e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017356806347632037, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.98506961703262e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017852715100421523, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.978506979133457e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01834862385321101, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.9707564342876e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018844532606000497, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.96182062929901e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019340441358789984, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.951702615736908e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01983635011157947, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.940405848893656e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020332258864368957, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.92793418660478e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020828167617158444, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.914291887931528e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02132407636994793, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.899483611706398e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021819985122737418, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.883514414942155e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.022315893875526904, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.866389751104867e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02281180262831639, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.848115468251542e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023307711381105878, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.828697807033038e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023803620133895365, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.808143398562868e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02429952888668485, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.786459262152698e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024795437639474338, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.763652802915244e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024795437639474338, | |
| "eval_loss": NaN, | |
| "eval_runtime": 337.9793, | |
| "eval_samples_per_second": 10.051, | |
| "eval_steps_per_second": 2.515, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025291346392263825, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.739731809235446e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.02578725514505331, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.71470445011073e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0262831638978428, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.688579272361309e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.026779072650632285, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.66136519771145e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.027274981403421772, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.633071519742718e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02777089015621126, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.603707900720217e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.028266798909000745, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.573284368292943e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.028762707661790232, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.541811312069348e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.02925861641457972, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.509299480069303e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.029754525167369206, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.47575997505365e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.030250433920158692, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.441204250732624e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03074634267294818, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.405644107854427e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.031242251425737666, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.369091690175273e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03173816017852715, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.331559480312315e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.03223406893131664, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.293060295480838e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.032729977684106126, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.25360728311719e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03322588643689561, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.213213916388954e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0337217951896851, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.171893989593859e-05, | |
| "loss": 0.8073, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03421770394247459, | |
| "grad_norm": 26.310998916625977, | |
| "learning_rate": 6.129661613449057e-05, | |
| "loss": 6.619, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.03471361269526407, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.086531210272306e-05, | |
| "loss": 81.0255, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03520952144805356, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.042517509056784e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.03570543020084305, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.997635540441133e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.036201338953632534, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9519006315765176e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.03669724770642202, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9053284008924185e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.03719315645921151, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.85793475276295e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.037689065212000994, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.809735872075529e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.03818497396479048, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.760748218703755e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.03868088271757997, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.710988521886378e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.039176791470369454, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.660473774514275e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.03967270022315894, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6092212273273975e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04016860897594843, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.557248383023655e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.040664517728737914, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5045729902817676e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0411604264815274, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4512130377000987e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.04165633523431689, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.397186747653573e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.042152243987106375, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.342512570070745e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04264815273989586, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.287209176133174e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.04314406149268535, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.231295451899226e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.043639970245474835, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174790491854502e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.04413587899826432, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.117713592391096e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.04463178775105381, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060084245217884e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.045127696503843295, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0019221307041306e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.04562360525663278, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.943247111158662e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.04611951400942227, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.884079224046898e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.046615422762211756, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.824438675148086e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.04711133151500124, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.764345831655036e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04760724026779073, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.703821215218748e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.048103149020580216, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.642885494940291e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0485990577733697, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.581559480312316e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.04909496652615919, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.519864114112636e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.049590875278948676, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.45782046525229e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.049590875278948676, | |
| "eval_loss": NaN, | |
| "eval_runtime": 338.0774, | |
| "eval_samples_per_second": 10.048, | |
| "eval_steps_per_second": 2.514, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05008678403173816, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3954497215805244e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.05058269278452765, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.332773182649165e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.051078601537317136, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2698122524388405e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.05157451029010662, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.206588432049535e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.05207041904289611, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.143123312357996e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.0525663277956856, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.079438566644454e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.053062236548475084, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.015555943191231e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.05355814530126457, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9514972578557114e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8872843866202525e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.054549962806843544, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8229392581215565e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05504587155963303, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7584838461620587e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.05554178031242252, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.693940162205895e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.056037689065212004, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.629330247862007e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.05653359781800149, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.564676167356954e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.05702950657079098, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.057525415323580464, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.435323832643046e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.05802132407636995, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.370669752137993e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.05851723282915944, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.306059837794105e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.059013141581948925, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.241516153837941e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.05950905033473841, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.177060741878443e-05, | |
| "loss": 2.3783, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0600049590875279, | |
| "grad_norm": 10.533272743225098, | |
| "learning_rate": 3.1127156133797475e-05, | |
| "loss": 5.9216, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.060500867840317385, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.048502742144289e-05, | |
| "loss": 80.022, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.06099677659310687, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.984444056808768e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.06149268534589636, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9205614333555444e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.061988594098685845, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.856876687642003e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06248450285147533, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7934115679504645e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.06298041160426482, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7301877475611606e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.0634763203570543, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.667226817350835e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.06397222910984379, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.604550278419475e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.06446813786263328, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.54217953474771e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06496404661542277, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4801358858873636e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.06545995536821225, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4184405196876842e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.06595586412100174, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3571145050597088e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.06645177287379123, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.296178784781251e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.06694768162658071, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2356541683449646e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0674435903793702, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.175561324851914e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.06793949913215969, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1159207759531013e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.06843540788494917, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0567528888413382e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.06893131663773866, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9980778692958684e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.06942722539052815, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9399157547821162e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06992313414331763, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.882286407608904e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.07041904289610712, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.825209508145497e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.07091495164889661, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7687045481007746e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.0714108604016861, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.712790823866826e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.07190676915447558, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.657487429929254e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07240267790726507, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602813252346427e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.07289858666005455, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5487869622999004e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.07339449541284404, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4954270097182317e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.07389040416563353, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4427516169763444e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.07438631291842301, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3907787726726029e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07438631291842301, | |
| "eval_loss": NaN, | |
| "eval_runtime": 339.1066, | |
| "eval_samples_per_second": 10.017, | |
| "eval_steps_per_second": 2.507, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0748822216712125, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339526225485725e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.07537813042400199, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2890114781136224e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.07587403917679147, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.239251781296245e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.07636994792958096, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1902641279244715e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.07686585668237045, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1420652472370497e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.07736176543515993, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0946715991075805e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.07785767418794942, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0480993684234815e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.07835358294073891, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0023644595588671e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.0788494916935284, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.57482490943216e-06, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.07934540044631788, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.134687897276934e-06, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07984130919910737, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.703383865509432e-06, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.08033721795189686, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.281060104061394e-06, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.08083312670468634, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.867860836110453e-06, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.08132903545747583, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.463927168828087e-06, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.08182494421026532, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.069397045191617e-06, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.0823208529630548, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.684405196876842e-06, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.08281676171584429, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.309083098247264e-06, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.08331267046863378, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.943558921455733e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.08380857922142326, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.587957492673759e-06, | |
| "loss": 3.2668, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.08430448797421275, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2424002494635095e-06, | |
| "loss": 50.263, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.08480039672700224, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9070051993069636e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.08529630547979172, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.581886879306507e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.08579221423258121, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2671563170705725e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.0862881229853707, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.962920992797834e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.08678403173816018, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6692848025728216e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.08727994049094967, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.38634802288549e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.08777584924373916, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1142072763869042e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.08827175799652864, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.852955498892694e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.08876766674931813, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6026819076455325e-06, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.08926357550210762, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.36347197084755e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0897594842548971, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1354073784730253e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.09025539300768659, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9185660143713184e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.09075130176047608, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7130219296696263e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.09124721051326556, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5188453174845743e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.09174311926605505, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3361024889513333e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.09223902801884454, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.16485585057844e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.09273493677163402, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0051638829360127e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.09323084552442351, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.570811206847189e-07, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.093726754277213, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.206581339521939e-07, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.09422266303000248, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.959415110634375e-07, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09471857178279197, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.829738426309099e-07, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.09521448053558146, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.817937070098914e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.09571038928837095, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9243565712400384e-07, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.09620629804116043, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1493020866542365e-07, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.09670220679394992, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4930382967379363e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.0971981155467394, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.557893149741924e-08, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.09769402429952889, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.377386113981197e-08, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.09818993305231838, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3902894994198286e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.09868584180510787, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.976233968155164e-09, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.09918175055789735, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09918175055789735, | |
| "eval_loss": NaN, | |
| "eval_runtime": 338.2367, | |
| "eval_samples_per_second": 10.043, | |
| "eval_steps_per_second": 2.513, | |
| "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": 4, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.875744616724562e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |