| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08526360665056132, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001136848088674151, | |
| "grad_norm": 13.681441307067871, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 19.3455, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001136848088674151, | |
| "eval_loss": 2.1432127952575684, | |
| "eval_runtime": 38.1789, | |
| "eval_samples_per_second": 19.409, | |
| "eval_steps_per_second": 9.717, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002273696177348302, | |
| "grad_norm": 8.84878158569336, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 15.1115, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003410544266022453, | |
| "grad_norm": 9.986258506774902, | |
| "learning_rate": 0.0001, | |
| "loss": 18.6546, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004547392354696604, | |
| "grad_norm": 9.296355247497559, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 15.2052, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "grad_norm": 8.245156288146973, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 14.842, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006821088532044906, | |
| "grad_norm": 8.676321029663086, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 15.0336, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007957936620719057, | |
| "grad_norm": 10.448345184326172, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 12.581, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009094784709393207, | |
| "grad_norm": 8.366747856140137, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 12.6146, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010231632798067358, | |
| "grad_norm": 6.977192401885986, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 15.2944, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "grad_norm": 8.217976570129395, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 15.2756, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01250532897541566, | |
| "grad_norm": 9.124979019165039, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 11.9569, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013642177064089812, | |
| "grad_norm": 8.218945503234863, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 13.2507, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014779025152763962, | |
| "grad_norm": 9.404376029968262, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 17.7727, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015915873241438113, | |
| "grad_norm": 8.809803009033203, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 15.4318, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "grad_norm": 14.043539047241211, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 20.6555, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018189569418786414, | |
| "grad_norm": 10.740511894226074, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 13.5507, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019326417507460565, | |
| "grad_norm": 8.008563041687012, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 15.5895, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020463265596134716, | |
| "grad_norm": 12.661676406860352, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 15.2206, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021600113684808867, | |
| "grad_norm": 7.788751125335693, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 15.9487, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "grad_norm": 8.766595840454102, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 18.9548, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023873809862157168, | |
| "grad_norm": 7.193807601928711, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 17.7629, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02501065795083132, | |
| "grad_norm": 7.72016716003418, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 17.2494, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026147506039505473, | |
| "grad_norm": 7.836511135101318, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 17.594, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027284354128179623, | |
| "grad_norm": 8.430022239685059, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 17.5101, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "grad_norm": 7.842438220977783, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 14.5361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "eval_loss": 1.724392056465149, | |
| "eval_runtime": 38.1608, | |
| "eval_samples_per_second": 19.418, | |
| "eval_steps_per_second": 9.722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029558050305527925, | |
| "grad_norm": 7.136037826538086, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 17.5904, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.030694898394202075, | |
| "grad_norm": 8.120686531066895, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 15.6992, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.031831746482876226, | |
| "grad_norm": 8.6294527053833, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 16.7682, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03296859457155037, | |
| "grad_norm": 8.904825210571289, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 18.3941, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03410544266022453, | |
| "grad_norm": 8.436539649963379, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 15.865, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03524229074889868, | |
| "grad_norm": 8.646078109741211, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 17.4423, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03637913883757283, | |
| "grad_norm": 8.919268608093262, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 14.9074, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03751598692624698, | |
| "grad_norm": 8.72852897644043, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 16.8692, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03865283501492113, | |
| "grad_norm": 8.736539840698242, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 11.9083, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.039789683103595284, | |
| "grad_norm": 9.58365535736084, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 13.4663, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04092653119226943, | |
| "grad_norm": 10.65027141571045, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 13.1416, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.042063379280943586, | |
| "grad_norm": 9.007448196411133, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 16.3553, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04320022736961773, | |
| "grad_norm": 9.968982696533203, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 13.711, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04433707545829189, | |
| "grad_norm": 11.036783218383789, | |
| "learning_rate": 5e-05, | |
| "loss": 14.8751, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.045473923546966034, | |
| "grad_norm": 9.898478507995605, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 11.9162, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04661077163564019, | |
| "grad_norm": 10.537850379943848, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 14.4648, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.047747619724314336, | |
| "grad_norm": 10.226863861083984, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.943, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04888446781298849, | |
| "grad_norm": 13.692229270935059, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 7.654, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05002131590166264, | |
| "grad_norm": 10.681045532226562, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 10.2153, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05115816399033679, | |
| "grad_norm": 12.138427734375, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 7.9938, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.052295012079010945, | |
| "grad_norm": 13.93451976776123, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 6.4668, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05343186016768509, | |
| "grad_norm": 11.52592658996582, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 7.7896, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05456870825635925, | |
| "grad_norm": 14.795572280883789, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.502, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.055705556345033394, | |
| "grad_norm": 13.952139854431152, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 6.6685, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05684240443370755, | |
| "grad_norm": 16.22222900390625, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 5.4531, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05684240443370755, | |
| "eval_loss": 1.7854145765304565, | |
| "eval_runtime": 38.1943, | |
| "eval_samples_per_second": 19.401, | |
| "eval_steps_per_second": 9.714, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.057979252522381695, | |
| "grad_norm": 31.600948333740234, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 20.401, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05911610061105585, | |
| "grad_norm": 23.095199584960938, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 16.3515, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06025294869973, | |
| "grad_norm": 19.465106964111328, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 11.0436, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06138979678840415, | |
| "grad_norm": 24.496065139770508, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 15.2372, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0625266448770783, | |
| "grad_norm": 19.609771728515625, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 12.5162, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06366349296575245, | |
| "grad_norm": 15.845856666564941, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 15.2344, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0648003410544266, | |
| "grad_norm": 19.62835693359375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 16.5892, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.06593718914310075, | |
| "grad_norm": 14.156807899475098, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 13.7909, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06707403723177491, | |
| "grad_norm": 16.480527877807617, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 11.8879, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06821088532044906, | |
| "grad_norm": 11.38010311126709, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 13.3756, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0693477334091232, | |
| "grad_norm": 10.232706069946289, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 15.2605, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.07048458149779736, | |
| "grad_norm": 11.701848983764648, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 19.6999, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07162142958647151, | |
| "grad_norm": 11.662482261657715, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 18.2158, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07275827767514566, | |
| "grad_norm": 11.12790584564209, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 17.7721, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0738951257638198, | |
| "grad_norm": 8.93850040435791, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 16.637, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07503197385249397, | |
| "grad_norm": 9.515388488769531, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 15.8094, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07616882194116811, | |
| "grad_norm": 10.64154052734375, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 15.4739, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.07730567002984226, | |
| "grad_norm": 11.352025032043457, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 18.6491, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07844251811851641, | |
| "grad_norm": 10.24422550201416, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 17.2373, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07957936620719057, | |
| "grad_norm": 9.423773765563965, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 15.38, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08071621429586472, | |
| "grad_norm": 9.517950057983398, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 12.7865, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.08185306238453886, | |
| "grad_norm": 9.021355628967285, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 17.7134, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.08298991047321301, | |
| "grad_norm": 9.259770393371582, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 17.2819, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.08412675856188717, | |
| "grad_norm": 11.53695011138916, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 15.3022, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.08526360665056132, | |
| "grad_norm": 8.795744895935059, | |
| "learning_rate": 0.0, | |
| "loss": 17.66, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08526360665056132, | |
| "eval_loss": 1.7146401405334473, | |
| "eval_runtime": 38.162, | |
| "eval_samples_per_second": 19.417, | |
| "eval_steps_per_second": 9.722, | |
| "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": 4666552800509952.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |