| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004013270547945206, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.351027397260274e-05, | |
| "grad_norm": 3.4412171840667725, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 9.5299, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.351027397260274e-05, | |
| "eval_loss": 1.1119320392608643, | |
| "eval_runtime": 2160.453, | |
| "eval_samples_per_second": 7.285, | |
| "eval_steps_per_second": 3.642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010702054794520547, | |
| "grad_norm": 3.5267574787139893, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 8.5445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001605308219178082, | |
| "grad_norm": 4.200962543487549, | |
| "learning_rate": 0.0001, | |
| "loss": 9.5069, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021404109589041095, | |
| "grad_norm": 2.991516351699829, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 7.5923, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002675513698630137, | |
| "grad_norm": 4.5141520500183105, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 9.3669, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003210616438356164, | |
| "grad_norm": 3.5825226306915283, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.0533, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00037457191780821916, | |
| "grad_norm": 3.585103750228882, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 9.2888, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004280821917808219, | |
| "grad_norm": 3.0140938758850098, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 7.9157, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00048159246575342463, | |
| "grad_norm": 2.723397970199585, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 7.173, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005351027397260274, | |
| "grad_norm": 3.36850643157959, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 8.088, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005886130136986301, | |
| "grad_norm": 4.041073799133301, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 8.5535, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0006421232876712328, | |
| "grad_norm": 4.422593116760254, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9489, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006956335616438356, | |
| "grad_norm": 4.800517559051514, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 7.9887, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007491438356164383, | |
| "grad_norm": 3.9624767303466797, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 7.9977, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.000802654109589041, | |
| "grad_norm": 3.386883497238159, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 7.6339, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008561643835616438, | |
| "grad_norm": 4.2820539474487305, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 7.1733, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0009096746575342465, | |
| "grad_norm": 3.999424934387207, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 7.1131, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0009631849315068493, | |
| "grad_norm": 3.930689573287964, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 7.4491, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001016695205479452, | |
| "grad_norm": 3.9529831409454346, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 7.2537, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0010702054794520547, | |
| "grad_norm": 4.9496307373046875, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 7.0658, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011237157534246575, | |
| "grad_norm": 3.3722610473632812, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.6348, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011772260273972602, | |
| "grad_norm": 3.6756198406219482, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 8.3285, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001230736301369863, | |
| "grad_norm": 3.552631378173828, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 8.7068, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0012842465753424657, | |
| "grad_norm": 3.2053675651550293, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 7.7342, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013377568493150684, | |
| "grad_norm": 3.083847999572754, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 7.9201, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013377568493150684, | |
| "eval_loss": 0.9074388742446899, | |
| "eval_runtime": 2160.8303, | |
| "eval_samples_per_second": 7.283, | |
| "eval_steps_per_second": 3.642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013912671232876712, | |
| "grad_norm": 3.115147590637207, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 5.6922, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001444777397260274, | |
| "grad_norm": 3.4430694580078125, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.9599, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0014982876712328766, | |
| "grad_norm": 3.203700542449951, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 6.4039, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0015517979452054794, | |
| "grad_norm": 3.7065799236297607, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 7.1779, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.001605308219178082, | |
| "grad_norm": 3.401582717895508, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.5066, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016588184931506848, | |
| "grad_norm": 3.41133975982666, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 7.854, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0017123287671232876, | |
| "grad_norm": 3.8782904148101807, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 8.3734, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0017658390410958903, | |
| "grad_norm": 3.4962656497955322, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.9779, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.001819349315068493, | |
| "grad_norm": 3.0437915325164795, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 6.3532, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0018728595890410958, | |
| "grad_norm": 3.930208921432495, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 6.8118, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0019263698630136985, | |
| "grad_norm": 3.7718610763549805, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 7.3981, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0019798801369863015, | |
| "grad_norm": 3.5606725215911865, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 6.9738, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002033390410958904, | |
| "grad_norm": 3.5234267711639404, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 7.7004, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.002086900684931507, | |
| "grad_norm": 3.824514389038086, | |
| "learning_rate": 5e-05, | |
| "loss": 7.7513, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0021404109589041095, | |
| "grad_norm": 4.543697357177734, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 8.0452, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021939212328767124, | |
| "grad_norm": 4.090927600860596, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 6.377, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002247431506849315, | |
| "grad_norm": 3.5463740825653076, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 7.5359, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002300941780821918, | |
| "grad_norm": 3.0797812938690186, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 6.253, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0023544520547945204, | |
| "grad_norm": 3.326676368713379, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 6.6982, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0024079623287671234, | |
| "grad_norm": 2.822622299194336, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 6.012, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002461472602739726, | |
| "grad_norm": 2.613372802734375, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 5.9406, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.002514982876712329, | |
| "grad_norm": 3.6091737747192383, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 7.7066, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0025684931506849314, | |
| "grad_norm": 4.005115032196045, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 8.5424, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0026220034246575343, | |
| "grad_norm": 3.131537675857544, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 6.281, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.002675513698630137, | |
| "grad_norm": 3.379215717315674, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 6.5812, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002675513698630137, | |
| "eval_loss": 0.8749306201934814, | |
| "eval_runtime": 2159.0999, | |
| "eval_samples_per_second": 7.289, | |
| "eval_steps_per_second": 3.645, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00272902397260274, | |
| "grad_norm": 3.2952077388763428, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 7.3355, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0027825342465753423, | |
| "grad_norm": 3.3396549224853516, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 6.6649, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0028360445205479453, | |
| "grad_norm": 4.649153232574463, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 8.7628, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.002889554794520548, | |
| "grad_norm": 3.6606626510620117, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 6.8996, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0029430650684931507, | |
| "grad_norm": 3.4278030395507812, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 7.3124, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0029965753424657533, | |
| "grad_norm": 3.267777681350708, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 6.8136, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.003050085616438356, | |
| "grad_norm": 3.700079917907715, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.78, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0031035958904109587, | |
| "grad_norm": 3.482595682144165, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 7.8277, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0031571061643835617, | |
| "grad_norm": 3.9059576988220215, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 6.7461, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.003210616438356164, | |
| "grad_norm": 3.3149898052215576, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 7.1818, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.003264126712328767, | |
| "grad_norm": 2.8718600273132324, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 6.8146, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0033176369863013697, | |
| "grad_norm": 3.4928603172302246, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 5.8661, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0033711472602739726, | |
| "grad_norm": 3.289541482925415, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 6.6667, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003424657534246575, | |
| "grad_norm": 3.2029364109039307, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 7.2747, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.003478167808219178, | |
| "grad_norm": 3.1482632160186768, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 7.4577, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0035316780821917806, | |
| "grad_norm": 3.4329683780670166, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.6697, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0035851883561643836, | |
| "grad_norm": 3.0778117179870605, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 7.5335, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.003638698630136986, | |
| "grad_norm": 3.8979506492614746, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 8.1609, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.003692208904109589, | |
| "grad_norm": 3.739900588989258, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 7.5071, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0037457191780821916, | |
| "grad_norm": 3.5693302154541016, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 6.7223, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0037992294520547945, | |
| "grad_norm": 4.022164821624756, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 7.1291, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.003852739726027397, | |
| "grad_norm": 3.5596697330474854, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 6.016, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.00390625, | |
| "grad_norm": 4.030635356903076, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 7.129, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.003959760273972603, | |
| "grad_norm": 2.96244740486145, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 6.2029, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.004013270547945206, | |
| "grad_norm": 3.192884683609009, | |
| "learning_rate": 0.0, | |
| "loss": 6.3423, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.004013270547945206, | |
| "eval_loss": 0.8689998984336853, | |
| "eval_runtime": 2162.9086, | |
| "eval_samples_per_second": 7.276, | |
| "eval_steps_per_second": 3.638, | |
| "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": 1.442508980701102e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |