| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.992, | |
| "eval_steps": 16, | |
| "global_step": 62, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 1.4910566806793213, | |
| "learning_rate": 1e-05, | |
| "loss": 88.7097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "eval_loss": 11.088533401489258, | |
| "eval_runtime": 1.124, | |
| "eval_samples_per_second": 94.304, | |
| "eval_steps_per_second": 24.021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 1.4108612537384033, | |
| "learning_rate": 2e-05, | |
| "loss": 88.7293, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 1.486616849899292, | |
| "learning_rate": 3e-05, | |
| "loss": 88.7434, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 1.7622555494308472, | |
| "learning_rate": 4e-05, | |
| "loss": 88.7179, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.5639805793762207, | |
| "learning_rate": 5e-05, | |
| "loss": 88.6803, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 1.7514230012893677, | |
| "learning_rate": 6e-05, | |
| "loss": 88.7313, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 1.9987614154815674, | |
| "learning_rate": 7e-05, | |
| "loss": 88.7164, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 1.940069317817688, | |
| "learning_rate": 8e-05, | |
| "loss": 88.7398, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 1.8506841659545898, | |
| "learning_rate": 9e-05, | |
| "loss": 88.6965, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.9289461374282837, | |
| "learning_rate": 0.0001, | |
| "loss": 88.8021, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 1.9998689889907837, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 88.6776, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 2.1637938022613525, | |
| "learning_rate": 0.00012, | |
| "loss": 88.7963, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 2.258723497390747, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 88.7175, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 2.3891043663024902, | |
| "learning_rate": 0.00014, | |
| "loss": 88.6413, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 2.612598180770874, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 88.7464, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 2.633556365966797, | |
| "learning_rate": 0.00016, | |
| "loss": 88.7045, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "eval_loss": 11.084848403930664, | |
| "eval_runtime": 0.8206, | |
| "eval_samples_per_second": 129.18, | |
| "eval_steps_per_second": 32.904, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "grad_norm": 1.444272756576538, | |
| "learning_rate": 0.00017, | |
| "loss": 88.719, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 1.4536869525909424, | |
| "learning_rate": 0.00018, | |
| "loss": 88.7756, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "grad_norm": 1.6990916728973389, | |
| "learning_rate": 0.00019, | |
| "loss": 88.719, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.6907556056976318, | |
| "learning_rate": 0.0002, | |
| "loss": 88.6939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 1.7854983806610107, | |
| "learning_rate": 0.00019972037971811802, | |
| "loss": 88.6928, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 1.7495782375335693, | |
| "learning_rate": 0.00019888308262251285, | |
| "loss": 88.7139, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "grad_norm": 1.8135170936584473, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 88.6808, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 1.9571936130523682, | |
| "learning_rate": 0.0001955572805786141, | |
| "loss": 88.7278, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.9375219345092773, | |
| "learning_rate": 0.00019308737486442045, | |
| "loss": 88.661, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 2.0492427349090576, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 88.6735, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 2.057321786880493, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 88.5661, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 2.227236747741699, | |
| "learning_rate": 0.0001826238774315995, | |
| "loss": 88.6781, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.464, | |
| "grad_norm": 2.3857967853546143, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 88.6794, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.7329936027526855, | |
| "learning_rate": 0.00017330518718298264, | |
| "loss": 88.6323, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.496, | |
| "grad_norm": 3.2216603755950928, | |
| "learning_rate": 0.00016801727377709194, | |
| "loss": 88.5737, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 1.5606772899627686, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 88.6774, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "eval_loss": 11.075674057006836, | |
| "eval_runtime": 0.8047, | |
| "eval_samples_per_second": 131.72, | |
| "eval_steps_per_second": 33.551, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 1.6445367336273193, | |
| "learning_rate": 0.0001563320058063622, | |
| "loss": 88.6368, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 1.6764920949935913, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 88.6352, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 1.6223012208938599, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 88.6562, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 1.6213066577911377, | |
| "learning_rate": 0.00013653410243663952, | |
| "loss": 88.6551, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.592, | |
| "grad_norm": 1.6623308658599854, | |
| "learning_rate": 0.00012947551744109043, | |
| "loss": 88.6895, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 1.8002474308013916, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 88.674, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 1.8450833559036255, | |
| "learning_rate": 0.00011490422661761744, | |
| "loss": 88.5731, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.9053994417190552, | |
| "learning_rate": 0.00010747300935864243, | |
| "loss": 88.6383, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.656, | |
| "grad_norm": 1.9040968418121338, | |
| "learning_rate": 0.0001, | |
| "loss": 88.6602, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 2.163938522338867, | |
| "learning_rate": 9.252699064135758e-05, | |
| "loss": 88.5704, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.688, | |
| "grad_norm": 2.156372547149658, | |
| "learning_rate": 8.509577338238255e-05, | |
| "loss": 88.4837, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 2.1990439891815186, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 88.6662, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 2.474072217941284, | |
| "learning_rate": 7.052448255890957e-05, | |
| "loss": 88.5809, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 2.7647547721862793, | |
| "learning_rate": 6.34658975633605e-05, | |
| "loss": 88.6076, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.752, | |
| "grad_norm": 2.5142226219177246, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 88.7863, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 1.5332900285720825, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 88.6006, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "eval_loss": 11.07020378112793, | |
| "eval_runtime": 0.612, | |
| "eval_samples_per_second": 173.197, | |
| "eval_steps_per_second": 44.116, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.784, | |
| "grad_norm": 1.6119565963745117, | |
| "learning_rate": 4.3667994193637796e-05, | |
| "loss": 88.609, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.591171145439148, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 88.6227, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 1.7413899898529053, | |
| "learning_rate": 3.198272622290804e-05, | |
| "loss": 88.6242, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 1.8746490478515625, | |
| "learning_rate": 2.669481281701739e-05, | |
| "loss": 88.5348, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.848, | |
| "grad_norm": 1.946791172027588, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 88.5242, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 1.9902241230010986, | |
| "learning_rate": 1.7376122568400532e-05, | |
| "loss": 88.6423, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 1.9461379051208496, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 88.6454, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 2.044666290283203, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 88.5542, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 1.9682707786560059, | |
| "learning_rate": 6.9126251355795864e-06, | |
| "loss": 88.6255, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 2.2248926162719727, | |
| "learning_rate": 4.442719421385922e-06, | |
| "loss": 88.5276, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.944, | |
| "grad_norm": 2.1064934730529785, | |
| "learning_rate": 2.5072087818176382e-06, | |
| "loss": 88.6175, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 2.4718239307403564, | |
| "learning_rate": 1.1169173774871478e-06, | |
| "loss": 88.5009, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.976, | |
| "grad_norm": 2.4647696018218994, | |
| "learning_rate": 2.7962028188198706e-07, | |
| "loss": 88.6283, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 3.2278006076812744, | |
| "learning_rate": 0.0, | |
| "loss": 88.4972, | |
| "step": 62 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 62, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 16, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1856734494720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |