| { | |
| "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": 12.549942016601562, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 17.412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001136848088674151, | |
| "eval_loss": 2.1443395614624023, | |
| "eval_runtime": 66.3426, | |
| "eval_samples_per_second": 11.169, | |
| "eval_steps_per_second": 5.592, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002273696177348302, | |
| "grad_norm": 19.546024322509766, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 20.1466, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003410544266022453, | |
| "grad_norm": 13.155139923095703, | |
| "learning_rate": 0.0001, | |
| "loss": 18.9999, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004547392354696604, | |
| "grad_norm": 10.267646789550781, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 17.0896, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "grad_norm": 8.46841812133789, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 18.8043, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006821088532044906, | |
| "grad_norm": 9.922762870788574, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 13.901, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007957936620719057, | |
| "grad_norm": 8.48350715637207, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 15.7619, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009094784709393207, | |
| "grad_norm": 9.610814094543457, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 15.5471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010231632798067358, | |
| "grad_norm": 8.592899322509766, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 12.7241, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "grad_norm": 6.759888648986816, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 18.8752, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01250532897541566, | |
| "grad_norm": 7.15319299697876, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 15.7519, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013642177064089812, | |
| "grad_norm": 8.924838066101074, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.8917, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014779025152763962, | |
| "grad_norm": 6.7501749992370605, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 12.3339, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015915873241438113, | |
| "grad_norm": 6.784092426300049, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 13.9071, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "grad_norm": 7.0436320304870605, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 15.3224, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018189569418786414, | |
| "grad_norm": 6.630817890167236, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 14.9763, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019326417507460565, | |
| "grad_norm": 8.37083911895752, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 12.5683, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020463265596134716, | |
| "grad_norm": 22.17447853088379, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 14.6574, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021600113684808867, | |
| "grad_norm": 8.09908390045166, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 13.1111, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "grad_norm": 10.496138572692871, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 16.7398, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023873809862157168, | |
| "grad_norm": 43.967933654785156, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 14.1475, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02501065795083132, | |
| "grad_norm": 7.2808451652526855, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 13.2917, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026147506039505473, | |
| "grad_norm": 7.135393142700195, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 16.542, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027284354128179623, | |
| "grad_norm": 8.165382385253906, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 15.5284, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "grad_norm": 8.087389945983887, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 15.624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "eval_loss": 1.7818211317062378, | |
| "eval_runtime": 66.6436, | |
| "eval_samples_per_second": 11.119, | |
| "eval_steps_per_second": 5.567, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029558050305527925, | |
| "grad_norm": 7.320021629333496, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 13.1999, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.030694898394202075, | |
| "grad_norm": 7.271773815155029, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 15.5507, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.031831746482876226, | |
| "grad_norm": 7.728046894073486, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 17.3175, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03296859457155037, | |
| "grad_norm": 5.821549892425537, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 10.6975, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03410544266022453, | |
| "grad_norm": 6.840242385864258, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 15.8851, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03524229074889868, | |
| "grad_norm": 12.806135177612305, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 13.5899, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03637913883757283, | |
| "grad_norm": 6.994766712188721, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 15.6565, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03751598692624698, | |
| "grad_norm": 7.654018402099609, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 15.5655, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03865283501492113, | |
| "grad_norm": 8.867931365966797, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 16.6892, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.039789683103595284, | |
| "grad_norm": 7.223085403442383, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 12.9233, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04092653119226943, | |
| "grad_norm": 6.747748851776123, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 13.6085, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.042063379280943586, | |
| "grad_norm": 6.9611616134643555, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 13.9404, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04320022736961773, | |
| "grad_norm": 8.217069625854492, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 13.8488, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04433707545829189, | |
| "grad_norm": 6.399670124053955, | |
| "learning_rate": 5e-05, | |
| "loss": 13.4894, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.045473923546966034, | |
| "grad_norm": 6.03984260559082, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 15.3474, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04661077163564019, | |
| "grad_norm": 7.631984710693359, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 12.2432, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.047747619724314336, | |
| "grad_norm": 6.203024864196777, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 13.4534, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04888446781298849, | |
| "grad_norm": 6.871401309967041, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 14.3178, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05002131590166264, | |
| "grad_norm": 7.451761722564697, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 14.6442, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05115816399033679, | |
| "grad_norm": 7.06754732131958, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 12.303, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.052295012079010945, | |
| "grad_norm": 6.363272190093994, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 18.1736, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05343186016768509, | |
| "grad_norm": 7.741644382476807, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 13.9887, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05456870825635925, | |
| "grad_norm": 7.256255149841309, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 18.5768, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.055705556345033394, | |
| "grad_norm": 8.02944564819336, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 13.2399, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05684240443370755, | |
| "grad_norm": 6.896628379821777, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 10.77, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05684240443370755, | |
| "eval_loss": 1.744654893875122, | |
| "eval_runtime": 66.449, | |
| "eval_samples_per_second": 11.151, | |
| "eval_steps_per_second": 5.583, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.057979252522381695, | |
| "grad_norm": 5.924437046051025, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 12.278, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05911610061105585, | |
| "grad_norm": 6.9019951820373535, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 12.2277, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06025294869973, | |
| "grad_norm": 8.663328170776367, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 16.2151, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06138979678840415, | |
| "grad_norm": 7.101144790649414, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 12.9355, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0625266448770783, | |
| "grad_norm": 6.247992992401123, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 15.3862, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06366349296575245, | |
| "grad_norm": 6.452046871185303, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 15.4312, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0648003410544266, | |
| "grad_norm": 8.117711067199707, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 15.8753, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.06593718914310075, | |
| "grad_norm": 7.468315124511719, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 17.0208, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06707403723177491, | |
| "grad_norm": 6.299598217010498, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 14.5744, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06821088532044906, | |
| "grad_norm": 8.590055465698242, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 12.2129, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0693477334091232, | |
| "grad_norm": 20.570341110229492, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 16.3481, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.07048458149779736, | |
| "grad_norm": 6.487506866455078, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 13.0091, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07162142958647151, | |
| "grad_norm": 7.227597236633301, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 19.0134, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07275827767514566, | |
| "grad_norm": 9.197311401367188, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 16.6898, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0738951257638198, | |
| "grad_norm": 8.438094139099121, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 8.918, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07503197385249397, | |
| "grad_norm": 8.239605903625488, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 15.4048, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07616882194116811, | |
| "grad_norm": 6.532566547393799, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.6503, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.07730567002984226, | |
| "grad_norm": 7.610565185546875, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 13.7247, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07844251811851641, | |
| "grad_norm": 7.103012561798096, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 13.4282, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07957936620719057, | |
| "grad_norm": 7.29534912109375, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 14.6105, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08071621429586472, | |
| "grad_norm": 7.118172645568848, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 15.4684, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.08185306238453886, | |
| "grad_norm": 8.032720565795898, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 12.0972, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.08298991047321301, | |
| "grad_norm": 5.702446937561035, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 14.8636, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.08412675856188717, | |
| "grad_norm": 6.32309627532959, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 14.2163, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.08526360665056132, | |
| "grad_norm": 6.813048362731934, | |
| "learning_rate": 0.0, | |
| "loss": 11.5691, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08526360665056132, | |
| "eval_loss": 1.739717721939087, | |
| "eval_runtime": 66.4587, | |
| "eval_samples_per_second": 11.15, | |
| "eval_steps_per_second": 5.582, | |
| "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": 4573317650448384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |