| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.47808764940239046, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006374501992031873, | |
| "grad_norm": 0.5776119828224182, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006374501992031873, | |
| "eval_loss": 1.051254153251648, | |
| "eval_runtime": 29.2997, | |
| "eval_samples_per_second": 9.044, | |
| "eval_steps_per_second": 4.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012749003984063745, | |
| "grad_norm": 0.6642381548881531, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.4101, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019123505976095617, | |
| "grad_norm": 0.6346176862716675, | |
| "learning_rate": 0.0001, | |
| "loss": 0.404, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02549800796812749, | |
| "grad_norm": 0.5157294273376465, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.3433, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03187250996015936, | |
| "grad_norm": 0.4020949900150299, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.2673, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03824701195219123, | |
| "grad_norm": 0.4330461621284485, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.2404, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04462151394422311, | |
| "grad_norm": 0.3167223036289215, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.1883, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05099601593625498, | |
| "grad_norm": 0.7258068919181824, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.1843, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05737051792828685, | |
| "grad_norm": 0.3239709734916687, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1234, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06374501992031872, | |
| "grad_norm": 0.3959621787071228, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.1336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0701195219123506, | |
| "grad_norm": 0.5370655655860901, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1147, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07649402390438247, | |
| "grad_norm": 0.7307567596435547, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1131, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08286852589641434, | |
| "grad_norm": 0.46945270895957947, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.0875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08924302788844622, | |
| "grad_norm": 0.2729243040084839, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0752, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09561752988047809, | |
| "grad_norm": 0.2799117863178253, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0803, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10199203187250996, | |
| "grad_norm": 0.3926849663257599, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0718, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10836653386454183, | |
| "grad_norm": 0.3918418288230896, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0657, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1147410358565737, | |
| "grad_norm": 0.3637863099575043, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.05, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12111553784860558, | |
| "grad_norm": 0.3199478089809418, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12749003984063745, | |
| "grad_norm": 0.3835548758506775, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0716, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13386454183266933, | |
| "grad_norm": 0.5802797675132751, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0534, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1402390438247012, | |
| "grad_norm": 0.3737954795360565, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0325, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14661354581673305, | |
| "grad_norm": 0.3237304091453552, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.054, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15298804780876493, | |
| "grad_norm": 0.2729124128818512, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0204, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1593625498007968, | |
| "grad_norm": 0.36050495505332947, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0357, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1593625498007968, | |
| "eval_loss": 0.07187294214963913, | |
| "eval_runtime": 28.4766, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.671, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1657370517928287, | |
| "grad_norm": 0.44654762744903564, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0428, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17211155378486057, | |
| "grad_norm": 0.4134571850299835, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0506, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17848605577689244, | |
| "grad_norm": 0.24441246688365936, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0159, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1848605577689243, | |
| "grad_norm": 0.44964155554771423, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.054, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.19123505976095617, | |
| "grad_norm": 0.22025738656520844, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0233, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19760956175298805, | |
| "grad_norm": 0.5241214632987976, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0493, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20398406374501993, | |
| "grad_norm": 0.7061783671379089, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.0439, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2103585657370518, | |
| "grad_norm": 1.2703156471252441, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0372, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21673306772908366, | |
| "grad_norm": 0.614372193813324, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0617, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22310756972111553, | |
| "grad_norm": 0.6067790389060974, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0296, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2294820717131474, | |
| "grad_norm": 0.2267586588859558, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.022, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2358565737051793, | |
| "grad_norm": 0.16750691831111908, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.017, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24223107569721117, | |
| "grad_norm": 0.482281357049942, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0178, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24860557768924302, | |
| "grad_norm": 1.8239290714263916, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2721, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2549800796812749, | |
| "grad_norm": 0.316111296415329, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0421, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2613545816733068, | |
| "grad_norm": 0.2607780992984772, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0442, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.26772908366533865, | |
| "grad_norm": 0.34263813495635986, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0468, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.27410358565737053, | |
| "grad_norm": 0.23391367495059967, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0463, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2804780876494024, | |
| "grad_norm": 0.1930956095457077, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.039, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2868525896414343, | |
| "grad_norm": 0.19257277250289917, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0351, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2932270916334661, | |
| "grad_norm": 0.2096574753522873, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0425, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.299601593625498, | |
| "grad_norm": 0.18197529017925262, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0397, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.30597609561752986, | |
| "grad_norm": 0.18108899891376495, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0401, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31235059760956174, | |
| "grad_norm": 0.21128466725349426, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0355, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3187250996015936, | |
| "grad_norm": 0.20305347442626953, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0345, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3187250996015936, | |
| "eval_loss": 0.04450911656022072, | |
| "eval_runtime": 28.4605, | |
| "eval_samples_per_second": 9.311, | |
| "eval_steps_per_second": 4.673, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3250996015936255, | |
| "grad_norm": 0.20304904878139496, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.025, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3314741035856574, | |
| "grad_norm": 0.18800340592861176, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.0323, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.33784860557768925, | |
| "grad_norm": 0.17694565653800964, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0348, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.34422310756972113, | |
| "grad_norm": 0.2166670709848404, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0458, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.350597609561753, | |
| "grad_norm": 0.16114047169685364, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0334, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3569721115537849, | |
| "grad_norm": 0.25571057200431824, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.04, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3633466135458167, | |
| "grad_norm": 0.28820469975471497, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0357, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3697211155378486, | |
| "grad_norm": 0.22852648794651031, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.0419, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.37609561752988047, | |
| "grad_norm": 0.22057059407234192, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0259, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.38247011952191234, | |
| "grad_norm": 0.251699835062027, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0323, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3888446215139442, | |
| "grad_norm": 0.4483722150325775, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.0478, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3952191235059761, | |
| "grad_norm": 0.20875990390777588, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.0316, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.401593625498008, | |
| "grad_norm": 0.27821633219718933, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0452, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.40796812749003986, | |
| "grad_norm": 0.2893379032611847, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0434, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.41434262948207173, | |
| "grad_norm": 0.2663540244102478, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.0256, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4207171314741036, | |
| "grad_norm": 0.16980110108852386, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0288, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.42709163346613543, | |
| "grad_norm": 0.36909863352775574, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0238, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4334661354581673, | |
| "grad_norm": 0.7255321741104126, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0393, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4398406374501992, | |
| "grad_norm": 0.5421790480613708, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0505, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.44621513944223107, | |
| "grad_norm": 0.4364238381385803, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.0218, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.45258964143426295, | |
| "grad_norm": 0.37261253595352173, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0376, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4589641434262948, | |
| "grad_norm": 0.3598557114601135, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0248, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4653386454183267, | |
| "grad_norm": 0.32301172614097595, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0396, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4717131474103586, | |
| "grad_norm": 0.21462203562259674, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.0217, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.47808764940239046, | |
| "grad_norm": 0.8589568138122559, | |
| "learning_rate": 0.0, | |
| "loss": 0.0735, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47808764940239046, | |
| "eval_loss": 0.040345437824726105, | |
| "eval_runtime": 28.5358, | |
| "eval_samples_per_second": 9.287, | |
| "eval_steps_per_second": 4.661, | |
| "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": 1.99507203588096e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |