| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023937761819269897, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003191701575902653, | |
| "grad_norm": 76.5424575805664, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.8509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003191701575902653, | |
| "eval_loss": 12.318764686584473, | |
| "eval_runtime": 286.833, | |
| "eval_samples_per_second": 36.795, | |
| "eval_steps_per_second": 4.602, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006383403151805306, | |
| "grad_norm": 72.78077697753906, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.9938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009575104727707959, | |
| "grad_norm": 60.093780517578125, | |
| "learning_rate": 0.0001, | |
| "loss": 9.5676, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012766806303610612, | |
| "grad_norm": 75.02964782714844, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 3.4684, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015958507879513266, | |
| "grad_norm": 7.463681221008301, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.8647, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019150209455415918, | |
| "grad_norm": 3.288733959197998, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.1328, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002234191103131857, | |
| "grad_norm": 116.76326751708984, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.5343, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025533612607221224, | |
| "grad_norm": 14.635088920593262, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.3021, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002872531418312388, | |
| "grad_norm": 3.705400228500366, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.2108, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003191701575902653, | |
| "grad_norm": 1.0382604598999023, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0801, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035108717334929184, | |
| "grad_norm": 14.446074485778809, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.3632, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0038300418910831835, | |
| "grad_norm": 3.757319211959839, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.129, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004149212048673449, | |
| "grad_norm": 1.9307399988174438, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.1287, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004468382206263714, | |
| "grad_norm": 0.20209403336048126, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0047, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "grad_norm": 3.280022621154785, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.221, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005106722521444245, | |
| "grad_norm": 1.8760838508605957, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0975, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00542589267903451, | |
| "grad_norm": 0.9887204766273499, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0311, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005745062836624776, | |
| "grad_norm": 1.185797929763794, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0325, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006064232994215041, | |
| "grad_norm": 1.277153491973877, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.075, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006383403151805306, | |
| "grad_norm": 1.5196043252944946, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0356, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0067025733093955715, | |
| "grad_norm": 0.40731021761894226, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0102, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007021743466985837, | |
| "grad_norm": 0.7067326903343201, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0365, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007340913624576102, | |
| "grad_norm": 1.3174384832382202, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0985, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007660083782166367, | |
| "grad_norm": 2.2587265968322754, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0756, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "grad_norm": 1.116852879524231, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0537, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "eval_loss": 0.03236299753189087, | |
| "eval_runtime": 286.9821, | |
| "eval_samples_per_second": 36.776, | |
| "eval_steps_per_second": 4.6, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008298424097346898, | |
| "grad_norm": 1.4494647979736328, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0816, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008617594254937163, | |
| "grad_norm": 0.7066687941551208, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0262, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008936764412527429, | |
| "grad_norm": 0.8260243535041809, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0334, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009255934570117695, | |
| "grad_norm": 0.5964095592498779, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.0204, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.009575104727707959, | |
| "grad_norm": 0.4692519009113312, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009894274885298225, | |
| "grad_norm": 1.4883151054382324, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.06, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01021344504288849, | |
| "grad_norm": 0.21536561846733093, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.005, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010532615200478756, | |
| "grad_norm": 1.1327840089797974, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0278, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01085178535806902, | |
| "grad_norm": 0.9777172207832336, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0202, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011170955515659286, | |
| "grad_norm": 1.0507439374923706, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0252, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011490125673249552, | |
| "grad_norm": 0.8614091277122498, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0152, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011809295830839816, | |
| "grad_norm": 0.41616290807724, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.005, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012128465988430082, | |
| "grad_norm": 1.297167420387268, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0125, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.012447636146020347, | |
| "grad_norm": 1.1140822172164917, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0137, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012766806303610613, | |
| "grad_norm": 1.8954771757125854, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0162, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013085976461200877, | |
| "grad_norm": 1.8588792085647583, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0407, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.013405146618791143, | |
| "grad_norm": 1.1832501888275146, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0177, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013724316776381409, | |
| "grad_norm": 0.1914079785346985, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.002, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.014043486933971673, | |
| "grad_norm": 0.8026562333106995, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.006, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01436265709156194, | |
| "grad_norm": 0.1954847127199173, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0016, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014681827249152204, | |
| "grad_norm": 0.0970122441649437, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0009, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01500099740674247, | |
| "grad_norm": 2.05657696723938, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0471, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.015320167564332734, | |
| "grad_norm": 0.10873958468437195, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0012, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.015639337721923, | |
| "grad_norm": 2.274010419845581, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0141, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "grad_norm": 0.029483182355761528, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "eval_loss": 0.030417734757065773, | |
| "eval_runtime": 286.7279, | |
| "eval_samples_per_second": 36.808, | |
| "eval_steps_per_second": 4.604, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.016277678037103532, | |
| "grad_norm": 0.7061015367507935, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0273, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.016596848194693797, | |
| "grad_norm": 1.4263066053390503, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.0627, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.01691601835228406, | |
| "grad_norm": 3.364551544189453, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0422, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.017235188509874325, | |
| "grad_norm": 0.22881293296813965, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0025, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.017554358667464593, | |
| "grad_norm": 3.359604597091675, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0986, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.017873528825054857, | |
| "grad_norm": 1.4804641008377075, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.014, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.01819269898264512, | |
| "grad_norm": 0.19417449831962585, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0026, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.01851186914023539, | |
| "grad_norm": 0.15018554031848907, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.002, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.018831039297825654, | |
| "grad_norm": 1.6474734544754028, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0157, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.019150209455415918, | |
| "grad_norm": 1.0258785486221313, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0088, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.019469379613006182, | |
| "grad_norm": 1.42870032787323, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.083, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01978854977059645, | |
| "grad_norm": 2.3368937969207764, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.0441, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.020107719928186715, | |
| "grad_norm": 2.7078840732574463, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1096, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02042689008577698, | |
| "grad_norm": 0.5454818606376648, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0041, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.020746060243367247, | |
| "grad_norm": 2.5583629608154297, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.0481, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02106523040095751, | |
| "grad_norm": 1.2198500633239746, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0182, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.021384400558547775, | |
| "grad_norm": 3.154790163040161, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0193, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.02170357071613804, | |
| "grad_norm": 0.5123023390769958, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0056, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.022022740873728307, | |
| "grad_norm": 1.2270593643188477, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0547, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.022341911031318572, | |
| "grad_norm": 1.1699939966201782, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.112, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.022661081188908836, | |
| "grad_norm": 2.3367903232574463, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0669, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.022980251346499104, | |
| "grad_norm": 0.013470455072820187, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0003, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.023299421504089368, | |
| "grad_norm": 3.0410115718841553, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0349, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.023618591661679633, | |
| "grad_norm": 1.0063241720199585, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.0092, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.023937761819269897, | |
| "grad_norm": 1.7765662670135498, | |
| "learning_rate": 0.0, | |
| "loss": 0.0721, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.023937761819269897, | |
| "eval_loss": 0.026059947907924652, | |
| "eval_runtime": 286.7265, | |
| "eval_samples_per_second": 36.809, | |
| "eval_steps_per_second": 4.604, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.476062712987648e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |