| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.322234156820623, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 17.51933479309082, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 12.3387, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "eval_loss": 14.726823806762695, | |
| "eval_runtime": 31.9634, | |
| "eval_samples_per_second": 6.132, | |
| "eval_steps_per_second": 3.066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 18.739076614379883, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 13.1398, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 13.577031135559082, | |
| "learning_rate": 0.0001, | |
| "loss": 12.1759, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 18.537343978881836, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 10.922, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 17.2657470703125, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 8.0517, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 23.952505111694336, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.6968, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 15.488723754882812, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 5.8581, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 14.229116439819336, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 5.3963, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": 13.335371017456055, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.8322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 10.152738571166992, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 3.6478, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047261009667024706, | |
| "grad_norm": 7.60871696472168, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.1707, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05155746509129968, | |
| "grad_norm": 12.572739601135254, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.8969, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.055853920515574654, | |
| "grad_norm": 6.163885116577148, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 2.7814, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 9.737069129943848, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 2.9291, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0644468313641246, | |
| "grad_norm": 15.192973136901855, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.7453, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06874328678839957, | |
| "grad_norm": 6.198273658752441, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 2.5762, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07303974221267455, | |
| "grad_norm": 9.232662200927734, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 2.4606, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07733619763694952, | |
| "grad_norm": 10.766953468322754, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.9624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 20.73750877380371, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 3.0332, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08592910848549946, | |
| "grad_norm": 8.655370712280273, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 2.4121, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": 1.5770183801651, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5083, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09452201933404941, | |
| "grad_norm": 9.22127914428711, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 2.5667, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09881847475832438, | |
| "grad_norm": 1.7212750911712646, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.3424, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10311493018259936, | |
| "grad_norm": 3.1742970943450928, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.6105, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10741138560687433, | |
| "grad_norm": 15.835758209228516, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 2.5565, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10741138560687433, | |
| "eval_loss": 2.6903557777404785, | |
| "eval_runtime": 32.5076, | |
| "eval_samples_per_second": 6.029, | |
| "eval_steps_per_second": 3.015, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11170784103114931, | |
| "grad_norm": 20.040693283081055, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 2.8217, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11600429645542427, | |
| "grad_norm": 8.479001998901367, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4105, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 4.354423522949219, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 2.4466, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12459720730397422, | |
| "grad_norm": 3.0479633808135986, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 2.496, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1288936627282492, | |
| "grad_norm": 5.260918617248535, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.7696, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13319011815252416, | |
| "grad_norm": 2.6381261348724365, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.4536, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13748657357679914, | |
| "grad_norm": 2.3083853721618652, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 2.4325, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14178302900107412, | |
| "grad_norm": 4.7310791015625, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.4458, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1460794844253491, | |
| "grad_norm": 3.6756527423858643, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 2.5719, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": 2.2964797019958496, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.5365, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15467239527389903, | |
| "grad_norm": 4.085907459259033, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.684, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.158968850698174, | |
| "grad_norm": 5.398529052734375, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 2.5946, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 4.9892754554748535, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 2.7752, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16756176154672395, | |
| "grad_norm": 4.568504810333252, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5394, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17185821697099893, | |
| "grad_norm": 5.603278636932373, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 2.3277, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1761546723952739, | |
| "grad_norm": 5.817256927490234, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 2.7044, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": 5.201894283294678, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.8322, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18474758324382384, | |
| "grad_norm": 2.171565055847168, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.495, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18904403866809882, | |
| "grad_norm": 4.212491035461426, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 2.7337, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1933404940923738, | |
| "grad_norm": 4.5573954582214355, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.6864, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19763694951664876, | |
| "grad_norm": 7.083897113800049, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 2.9271, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20193340494092374, | |
| "grad_norm": 5.476693153381348, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 2.7912, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20622986036519872, | |
| "grad_norm": 2.044529676437378, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4948, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 4.62539529800415, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 2.4246, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21482277121374865, | |
| "grad_norm": 8.88616943359375, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 3.1202, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21482277121374865, | |
| "eval_loss": 2.50577712059021, | |
| "eval_runtime": 32.5083, | |
| "eval_samples_per_second": 6.029, | |
| "eval_steps_per_second": 3.015, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21911922663802363, | |
| "grad_norm": 18.871131896972656, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.5053, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.22341568206229862, | |
| "grad_norm": 14.663223266601562, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 2.3519, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.22771213748657357, | |
| "grad_norm": 14.215468406677246, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 2.1756, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.23200859291084855, | |
| "grad_norm": 13.670672416687012, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8397, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.23630504833512353, | |
| "grad_norm": 8.020715713500977, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.8855, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 10.989826202392578, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 1.764, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 5.959054946899414, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7138, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.24919441460794844, | |
| "grad_norm": 7.55777645111084, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 2.2298, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2534908700322234, | |
| "grad_norm": 2.828930377960205, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.6894, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2577873254564984, | |
| "grad_norm": 5.5222883224487305, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.7706, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2620837808807734, | |
| "grad_norm": 3.887505054473877, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 1.8653, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2663802363050483, | |
| "grad_norm": 3.8996193408966064, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 1.5454, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2706766917293233, | |
| "grad_norm": 2.5269007682800293, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.0161, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2749731471535983, | |
| "grad_norm": 6.614835739135742, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 2.288, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.27926960257787325, | |
| "grad_norm": 3.5039703845977783, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.7184, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.28356605800214824, | |
| "grad_norm": 3.9075820446014404, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.2969, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2878625134264232, | |
| "grad_norm": 3.1495635509490967, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.1496, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2921589688506982, | |
| "grad_norm": 2.422870397567749, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 2.0091, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2964554242749731, | |
| "grad_norm": 1.5962601900100708, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.7433, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 3.402613878250122, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 2.3376, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3050483351235231, | |
| "grad_norm": 5.880324363708496, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 2.4027, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.30934479054779807, | |
| "grad_norm": 4.647853374481201, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.0494, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.31364124597207305, | |
| "grad_norm": 3.6768651008605957, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 2.2827, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.317937701396348, | |
| "grad_norm": 2.7547430992126465, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 2.1691, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.322234156820623, | |
| "grad_norm": 2.9051625728607178, | |
| "learning_rate": 0.0, | |
| "loss": 2.2072, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.322234156820623, | |
| "eval_loss": 2.352761745452881, | |
| "eval_runtime": 32.5272, | |
| "eval_samples_per_second": 6.026, | |
| "eval_steps_per_second": 3.013, | |
| "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": 1.119015678246912e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |