| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03443921478590288, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004591895304787051, | |
| "grad_norm": 1.1419830322265625, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004591895304787051, | |
| "eval_loss": 1.300444483757019, | |
| "eval_runtime": 461.8779, | |
| "eval_samples_per_second": 3.971, | |
| "eval_steps_per_second": 1.985, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009183790609574102, | |
| "grad_norm": 1.1880234479904175, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.036, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013775685914361152, | |
| "grad_norm": 1.1058253049850464, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0533, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018367581219148204, | |
| "grad_norm": 0.8739814758300781, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 1.0222, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0022959476523935255, | |
| "grad_norm": 1.1297332048416138, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 1.0771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0027551371828722303, | |
| "grad_norm": 1.0218960046768188, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9766, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032143267133509356, | |
| "grad_norm": 0.9368105530738831, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.9208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003673516243829641, | |
| "grad_norm": 0.7900261878967285, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.9225, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004132705774308346, | |
| "grad_norm": 0.7937513589859009, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8457, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004591895304787051, | |
| "grad_norm": 0.7547521591186523, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.834, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005051084835265756, | |
| "grad_norm": 0.7325078845024109, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.8298, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005510274365744461, | |
| "grad_norm": 0.6860811114311218, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8015, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005969463896223166, | |
| "grad_norm": 0.6838340759277344, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.7436, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006428653426701871, | |
| "grad_norm": 0.7004528045654297, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.7086, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006887842957180576, | |
| "grad_norm": 0.6048188209533691, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7169, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007347032487659282, | |
| "grad_norm": 0.5844050049781799, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.707, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007806222018137987, | |
| "grad_norm": 0.5827935934066772, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.6838, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008265411548616692, | |
| "grad_norm": 0.6372345089912415, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6679, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008724601079095397, | |
| "grad_norm": 0.6254321336746216, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.6719, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009183790609574102, | |
| "grad_norm": 0.6155533790588379, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.7132, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009642980140052807, | |
| "grad_norm": 0.5951682329177856, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6667, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010102169670531512, | |
| "grad_norm": 0.5539524555206299, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.6211, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010561359201010216, | |
| "grad_norm": 0.5512757897377014, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.6512, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011020548731488921, | |
| "grad_norm": 0.5660426616668701, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6527, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011479738261967628, | |
| "grad_norm": 0.5754444003105164, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.6099, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011479738261967628, | |
| "eval_loss": 0.6897526979446411, | |
| "eval_runtime": 464.8934, | |
| "eval_samples_per_second": 3.945, | |
| "eval_steps_per_second": 1.972, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011938927792446333, | |
| "grad_norm": 0.5573870539665222, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.5653, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012398117322925038, | |
| "grad_norm": 0.5551594495773315, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6139, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012857306853403742, | |
| "grad_norm": 0.593977153301239, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.6182, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013316496383882447, | |
| "grad_norm": 0.5621492266654968, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.5892, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.013775685914361152, | |
| "grad_norm": 0.5908278822898865, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5825, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014234875444839857, | |
| "grad_norm": 0.6430060863494873, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.6062, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.014694064975318563, | |
| "grad_norm": 0.545280933380127, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.5722, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.015153254505797268, | |
| "grad_norm": 0.652656614780426, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6536, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015612444036275973, | |
| "grad_norm": 0.6264194250106812, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.5823, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.016071633566754676, | |
| "grad_norm": 0.62241530418396, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.5793, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016530823097233385, | |
| "grad_norm": 0.6142162084579468, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5762, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01699001262771209, | |
| "grad_norm": 0.5530565977096558, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.6092, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.017449202158190794, | |
| "grad_norm": 0.6179258823394775, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.5751, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0179083916886695, | |
| "grad_norm": 0.6282462477684021, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5948, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018367581219148204, | |
| "grad_norm": 0.6314778923988342, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.5389, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01882677074962691, | |
| "grad_norm": 0.7459428310394287, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.6414, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019285960280105614, | |
| "grad_norm": 0.725232720375061, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6711, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01974514981058432, | |
| "grad_norm": 0.6939031481742859, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.5777, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020204339341063023, | |
| "grad_norm": 0.7400466799736023, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.641, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020663528871541728, | |
| "grad_norm": 0.7789513468742371, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7023, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021122718402020433, | |
| "grad_norm": 0.7750358581542969, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.7727, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.021581907932499138, | |
| "grad_norm": 0.8089461922645569, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.749, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.022041097462977843, | |
| "grad_norm": 0.8801223635673523, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.739, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022500286993456547, | |
| "grad_norm": 0.9937826991081238, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.7846, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.022959476523935256, | |
| "grad_norm": 1.058200716972351, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.7814, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022959476523935256, | |
| "eval_loss": 0.6795315742492676, | |
| "eval_runtime": 464.6954, | |
| "eval_samples_per_second": 3.947, | |
| "eval_steps_per_second": 1.973, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02341866605441396, | |
| "grad_norm": 1.049940824508667, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8132, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.023877855584892665, | |
| "grad_norm": 1.0071134567260742, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.7913, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02433704511537137, | |
| "grad_norm": 0.8402441740036011, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.7837, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.024796234645850075, | |
| "grad_norm": 0.7800126075744629, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7519, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.02525542417632878, | |
| "grad_norm": 0.6317635774612427, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.7225, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.025714613706807485, | |
| "grad_norm": 0.5558218359947205, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.7201, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02617380323728619, | |
| "grad_norm": 0.564495325088501, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7005, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.026632992767764894, | |
| "grad_norm": 0.4901668131351471, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.7271, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0270921822982436, | |
| "grad_norm": 0.47251802682876587, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.6856, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.027551371828722304, | |
| "grad_norm": 0.48661911487579346, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6638, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02801056135920101, | |
| "grad_norm": 0.5135563611984253, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.621, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.028469750889679714, | |
| "grad_norm": 0.4911552965641022, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.6375, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.02892894042015842, | |
| "grad_norm": 0.522821843624115, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6292, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.029388129950637127, | |
| "grad_norm": 0.48059335350990295, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.6706, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.029847319481115832, | |
| "grad_norm": 0.5201355814933777, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.681, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.030306509011594537, | |
| "grad_norm": 0.5210537910461426, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6545, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03076569854207324, | |
| "grad_norm": 0.5189217329025269, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.6052, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.031224888072551946, | |
| "grad_norm": 0.559215784072876, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.6467, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03168407760303065, | |
| "grad_norm": 0.5408816337585449, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6004, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.03214326713350935, | |
| "grad_norm": 0.5203858017921448, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.6152, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03260245666398806, | |
| "grad_norm": 0.5649285316467285, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.5943, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.03306164619446677, | |
| "grad_norm": 0.5590580105781555, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6372, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.03352083572494547, | |
| "grad_norm": 0.5505293011665344, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.5813, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.03398002525542418, | |
| "grad_norm": 0.5618359446525574, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.6209, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.03443921478590288, | |
| "grad_norm": 0.5541989207267761, | |
| "learning_rate": 0.0, | |
| "loss": 0.6078, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03443921478590288, | |
| "eval_loss": 0.6394286155700684, | |
| "eval_runtime": 464.4129, | |
| "eval_samples_per_second": 3.949, | |
| "eval_steps_per_second": 1.975, | |
| "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": 1.119015678246912e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |