| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009448818897637795, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012598425196850394, | |
| "grad_norm": 4.49857759475708, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.1742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012598425196850394, | |
| "eval_loss": 1.215790033340454, | |
| "eval_runtime": 1680.5898, | |
| "eval_samples_per_second": 3.978, | |
| "eval_steps_per_second": 1.989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002519685039370079, | |
| "grad_norm": 4.2249956130981445, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.118, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003779527559055118, | |
| "grad_norm": 3.5851938724517822, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0507, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005039370078740158, | |
| "grad_norm": 3.1795814037323, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.7279, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006299212598425197, | |
| "grad_norm": 4.160511493682861, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.6767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007559055118110237, | |
| "grad_norm": 2.9607021808624268, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.5793, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008818897637795275, | |
| "grad_norm": 1.9980815649032593, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.4986, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010078740157480315, | |
| "grad_norm": 1.6180553436279297, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.4405, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011338582677165355, | |
| "grad_norm": 1.7591142654418945, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5017, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012598425196850393, | |
| "grad_norm": 2.138441562652588, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.4375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013858267716535433, | |
| "grad_norm": 1.852003574371338, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.4284, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0015118110236220473, | |
| "grad_norm": 1.5829808712005615, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5171, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001637795275590551, | |
| "grad_norm": 1.6981840133666992, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.492, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001763779527559055, | |
| "grad_norm": 1.1615180969238281, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.4131, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001889763779527559, | |
| "grad_norm": 1.3211286067962646, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4482, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002015748031496063, | |
| "grad_norm": 1.4025088548660278, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.4023, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002141732283464567, | |
| "grad_norm": 1.4087685346603394, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.4651, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002267716535433071, | |
| "grad_norm": 1.3379063606262207, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4122, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002393700787401575, | |
| "grad_norm": 1.4114474058151245, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.4775, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0025196850393700786, | |
| "grad_norm": 1.4185856580734253, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.4664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002645669291338583, | |
| "grad_norm": 1.5691876411437988, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5104, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0027716535433070866, | |
| "grad_norm": 1.127351999282837, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.43, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0028976377952755904, | |
| "grad_norm": 1.2459053993225098, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.4195, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0030236220472440946, | |
| "grad_norm": 1.2657814025878906, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0031496062992125984, | |
| "grad_norm": 1.5992778539657593, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.4185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0031496062992125984, | |
| "eval_loss": 0.48135948181152344, | |
| "eval_runtime": 1691.0237, | |
| "eval_samples_per_second": 3.953, | |
| "eval_steps_per_second": 1.977, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003275590551181102, | |
| "grad_norm": 1.4434717893600464, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.4383, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0034015748031496064, | |
| "grad_norm": 1.187625765800476, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4064, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00352755905511811, | |
| "grad_norm": 1.288070797920227, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.3957, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0036535433070866144, | |
| "grad_norm": 1.3888908624649048, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.4349, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.003779527559055118, | |
| "grad_norm": 1.2192840576171875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3789, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003905511811023622, | |
| "grad_norm": 1.7539172172546387, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.4327, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004031496062992126, | |
| "grad_norm": 1.2005337476730347, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.416, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00415748031496063, | |
| "grad_norm": 1.3382314443588257, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4181, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004283464566929134, | |
| "grad_norm": 1.445595622062683, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.4458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004409448818897638, | |
| "grad_norm": 1.3078209161758423, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.3524, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004535433070866142, | |
| "grad_norm": 1.3248423337936401, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4059, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0046614173228346455, | |
| "grad_norm": 1.2014515399932861, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.3862, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00478740157480315, | |
| "grad_norm": 1.251442313194275, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.4217, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004913385826771654, | |
| "grad_norm": 1.549546480178833, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3972, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005039370078740157, | |
| "grad_norm": 1.5308916568756104, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.4102, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0051653543307086614, | |
| "grad_norm": 1.7657283544540405, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.4259, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005291338582677166, | |
| "grad_norm": 1.9394474029541016, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.384, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005417322834645669, | |
| "grad_norm": 1.7663687467575073, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.3748, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005543307086614173, | |
| "grad_norm": 1.4035406112670898, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.3698, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005669291338582677, | |
| "grad_norm": 1.6968581676483154, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4055, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005795275590551181, | |
| "grad_norm": 1.6501572132110596, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.376, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005921259842519685, | |
| "grad_norm": 1.4387761354446411, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.3797, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006047244094488189, | |
| "grad_norm": 2.231095552444458, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.409, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0061732283464566926, | |
| "grad_norm": 2.0894861221313477, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.4164, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.006299212598425197, | |
| "grad_norm": 2.8405890464782715, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.4957, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006299212598425197, | |
| "eval_loss": 0.46602168679237366, | |
| "eval_runtime": 1691.0057, | |
| "eval_samples_per_second": 3.953, | |
| "eval_steps_per_second": 1.977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006425196850393701, | |
| "grad_norm": 3.830735683441162, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5254, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006551181102362204, | |
| "grad_norm": 4.045533657073975, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.5314, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0066771653543307085, | |
| "grad_norm": 2.6203715801239014, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.4299, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.006803149606299213, | |
| "grad_norm": 2.2109479904174805, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4133, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006929133858267717, | |
| "grad_norm": 1.6112823486328125, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.3646, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.00705511811023622, | |
| "grad_norm": 1.4806196689605713, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.3811, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0071811023622047245, | |
| "grad_norm": 1.619550108909607, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3262, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.007307086614173229, | |
| "grad_norm": 1.5869569778442383, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.4286, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.007433070866141732, | |
| "grad_norm": 1.411007046699524, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.3441, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007559055118110236, | |
| "grad_norm": 1.3262393474578857, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3322, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0076850393700787405, | |
| "grad_norm": 1.3001681566238403, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.3168, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.007811023622047244, | |
| "grad_norm": 1.0694575309753418, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.352, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.007937007874015748, | |
| "grad_norm": 1.2116413116455078, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3719, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.008062992125984252, | |
| "grad_norm": 1.154064655303955, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.3342, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.008188976377952756, | |
| "grad_norm": 0.9787663817405701, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.3416, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.00831496062992126, | |
| "grad_norm": 1.04434335231781, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3214, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.008440944881889763, | |
| "grad_norm": 1.0488498210906982, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.32, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.008566929133858267, | |
| "grad_norm": 1.2639235258102417, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.3507, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.008692913385826772, | |
| "grad_norm": 1.2547246217727661, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3217, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.008818897637795276, | |
| "grad_norm": 1.1020681858062744, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.328, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.00894488188976378, | |
| "grad_norm": 1.242504596710205, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.3537, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.009070866141732284, | |
| "grad_norm": 1.1716359853744507, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3599, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.009196850393700787, | |
| "grad_norm": 0.999187171459198, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.3442, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.009322834645669291, | |
| "grad_norm": 1.0128037929534912, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.3309, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.009448818897637795, | |
| "grad_norm": 1.1647950410842896, | |
| "learning_rate": 0.0, | |
| "loss": 0.347, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.009448818897637795, | |
| "eval_loss": 0.3494592607021332, | |
| "eval_runtime": 1690.2407, | |
| "eval_samples_per_second": 3.955, | |
| "eval_steps_per_second": 1.978, | |
| "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 | |
| } | |