| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.27347310847766637, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036463081130355514, | |
| "grad_norm": 0.8260515332221985, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.4916, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036463081130355514, | |
| "eval_loss": 1.4711146354675293, | |
| "eval_runtime": 35.8851, | |
| "eval_samples_per_second": 6.437, | |
| "eval_steps_per_second": 3.233, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007292616226071103, | |
| "grad_norm": 0.9562111496925354, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.1876, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010938924339106655, | |
| "grad_norm": 1.0414786338806152, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2457, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014585232452142206, | |
| "grad_norm": 1.100989818572998, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 9.8543, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018231540565177756, | |
| "grad_norm": 1.2875176668167114, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.6001, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02187784867821331, | |
| "grad_norm": 1.292757272720337, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.8068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02552415679124886, | |
| "grad_norm": 1.4418549537658691, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 9.0652, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02917046490428441, | |
| "grad_norm": 1.5038715600967407, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 10.2297, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032816773017319965, | |
| "grad_norm": 1.5690864324569702, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.9497, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03646308113035551, | |
| "grad_norm": 1.6616734266281128, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 9.5513, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.040109389243391066, | |
| "grad_norm": 1.8219513893127441, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 9.5726, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04375569735642662, | |
| "grad_norm": 1.9465745687484741, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.7049, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04740200546946217, | |
| "grad_norm": 1.967482328414917, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 9.4006, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05104831358249772, | |
| "grad_norm": 1.7798552513122559, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 9.8486, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.054694621695533276, | |
| "grad_norm": 1.8983608484268188, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.0339, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05834092980856882, | |
| "grad_norm": 1.9173567295074463, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 9.1742, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06198723792160438, | |
| "grad_norm": 2.7075579166412354, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 9.7573, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06563354603463993, | |
| "grad_norm": 1.8774495124816895, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 9.7642, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06927985414767548, | |
| "grad_norm": 1.7866919040679932, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 9.0481, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07292616226071102, | |
| "grad_norm": 2.1817097663879395, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.5923, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07657247037374658, | |
| "grad_norm": 1.7108845710754395, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.1387, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08021877848678213, | |
| "grad_norm": 2.11926007270813, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.3624, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08386508659981769, | |
| "grad_norm": 2.068971872329712, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 8.0856, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08751139471285324, | |
| "grad_norm": 2.0737385749816895, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 8.4977, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09115770282588878, | |
| "grad_norm": 2.146387815475464, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 9.9969, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09115770282588878, | |
| "eval_loss": 1.2849068641662598, | |
| "eval_runtime": 35.9194, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.229, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09480401093892434, | |
| "grad_norm": 1.8341199159622192, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 9.8156, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09845031905195989, | |
| "grad_norm": 1.9661328792572021, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.0505, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10209662716499544, | |
| "grad_norm": 2.0087292194366455, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 9.4768, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.105742935278031, | |
| "grad_norm": 2.208437442779541, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 9.5623, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10938924339106655, | |
| "grad_norm": 2.0323190689086914, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.4219, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11303555150410209, | |
| "grad_norm": 1.9072842597961426, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 9.1549, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11668185961713765, | |
| "grad_norm": 2.2138895988464355, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 10.4151, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1203281677301732, | |
| "grad_norm": 2.239079236984253, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.1372, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12397447584320875, | |
| "grad_norm": 2.131258964538574, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 9.4423, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1276207839562443, | |
| "grad_norm": 2.1453845500946045, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 9.3926, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13126709206927986, | |
| "grad_norm": 3.005169153213501, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 9.9575, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1349134001823154, | |
| "grad_norm": 2.2520599365234375, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 10.8131, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13855970829535097, | |
| "grad_norm": 2.4393112659454346, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 12.2067, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1422060164083865, | |
| "grad_norm": 2.4657881259918213, | |
| "learning_rate": 5e-05, | |
| "loss": 11.86, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14585232452142205, | |
| "grad_norm": 2.2421562671661377, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 11.2129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14949863263445762, | |
| "grad_norm": 2.500739812850952, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 10.8666, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15314494074749316, | |
| "grad_norm": 2.3504726886749268, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3909, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15679124886052873, | |
| "grad_norm": 2.4648520946502686, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 12.7165, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16043755697356427, | |
| "grad_norm": 4.018390655517578, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 12.8443, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1640838650865998, | |
| "grad_norm": 2.460999011993408, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 13.6509, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16773017319963537, | |
| "grad_norm": 3.274535655975342, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 11.1371, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17137648131267091, | |
| "grad_norm": 3.133227586746216, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 11.5938, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17502278942570648, | |
| "grad_norm": 3.6370604038238525, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 13.0006, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.17866909753874202, | |
| "grad_norm": 4.2182936668396, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 12.1576, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18231540565177756, | |
| "grad_norm": 5.010047912597656, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 12.5341, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18231540565177756, | |
| "eval_loss": 1.2788481712341309, | |
| "eval_runtime": 36.0057, | |
| "eval_samples_per_second": 6.416, | |
| "eval_steps_per_second": 3.222, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18596171376481313, | |
| "grad_norm": 4.323014259338379, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.6974, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.18960802187784867, | |
| "grad_norm": 3.388489007949829, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 10.6367, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.19325432999088424, | |
| "grad_norm": 3.3765082359313965, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 9.1406, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.19690063810391978, | |
| "grad_norm": 3.401052474975586, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.7224, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.20054694621695535, | |
| "grad_norm": 3.203279495239258, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 9.5775, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2041932543299909, | |
| "grad_norm": 2.6529016494750977, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 9.0888, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.20783956244302643, | |
| "grad_norm": 2.4784176349639893, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 8.9204, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.211485870556062, | |
| "grad_norm": 2.0573184490203857, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 9.2145, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.21513217866909753, | |
| "grad_norm": 2.035629987716675, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 9.3459, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2187784867821331, | |
| "grad_norm": 1.8809788227081299, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.0335, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22242479489516864, | |
| "grad_norm": 1.7291185855865479, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 9.2373, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.22607110300820418, | |
| "grad_norm": 1.8708686828613281, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 8.5013, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.22971741112123975, | |
| "grad_norm": 1.6708974838256836, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 9.1516, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2333637192342753, | |
| "grad_norm": 1.818259358406067, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 9.0427, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.23701002734731086, | |
| "grad_norm": 1.7174487113952637, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 9.5647, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2406563354603464, | |
| "grad_norm": 1.6846184730529785, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.9359, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.24430264357338194, | |
| "grad_norm": 1.9734396934509277, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.4316, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2479489516864175, | |
| "grad_norm": 3.557767152786255, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 8.9241, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2515952597994531, | |
| "grad_norm": 1.758630394935608, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 8.3622, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2552415679124886, | |
| "grad_norm": 1.8638677597045898, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 9.3947, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.25888787602552416, | |
| "grad_norm": 2.0712227821350098, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 9.0659, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2625341841385597, | |
| "grad_norm": 1.8007419109344482, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 9.5052, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.26618049225159524, | |
| "grad_norm": 2.450610637664795, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 9.1301, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2698268003646308, | |
| "grad_norm": 1.9521738290786743, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 9.4087, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.27347310847766637, | |
| "grad_norm": 2.1234993934631348, | |
| "learning_rate": 0.0, | |
| "loss": 8.9661, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.27347310847766637, | |
| "eval_loss": 1.2587740421295166, | |
| "eval_runtime": 36.0297, | |
| "eval_samples_per_second": 6.411, | |
| "eval_steps_per_second": 3.22, | |
| "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": 1.91357779968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |