| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.16675931072818231, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022234574763757642, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022234574763757642, | |
| "eval_loss": NaN, | |
| "eval_runtime": 65.1763, | |
| "eval_samples_per_second": 5.815, | |
| "eval_steps_per_second": 2.915, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0044469149527515284, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006670372429127293, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008893829905503057, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011117287381878822, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013340744858254585, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01556420233463035, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017787659811006114, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020011117287381877, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022234574763757644, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024458032240133407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02668148971650917, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028904947192884937, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.033351862145636464, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03557531962201223, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03779877709838799, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.040022234574763754, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.042245692051139525, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04446914952751529, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04669260700389105, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.048916064480266815, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05113952195664258, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05336297943301834, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.055586436909394105, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.055586436909394105, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.7826, | |
| "eval_samples_per_second": 5.85, | |
| "eval_steps_per_second": 2.933, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.057809894385769875, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06003335186214564, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06448026681489717, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06670372429127293, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0689271817676487, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07115063924402446, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07337409672040023, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07559755419677598, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07782101167315175, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08004446914952751, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08226792662590328, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08449138410227905, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0867148415786548, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08893829905503058, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09116175653140633, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0933852140077821, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09560867148415786, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09783212896053363, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1000555864369094, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10227904391328516, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10450250138966093, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10672595886603668, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10894941634241245, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11117287381878821, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11117287381878821, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.7682, | |
| "eval_samples_per_second": 5.852, | |
| "eval_steps_per_second": 2.934, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11339633129516398, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.11561978877153975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1178432462479155, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.12006670372429128, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.12229016120066703, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.12673707615341856, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.12896053362979434, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1311839911061701, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.13340744858254586, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1356309060589216, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1378543635352974, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.14007782101167315, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1423012784880489, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.14452473596442467, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.14674819344080045, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1489716509171762, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.15119510839355196, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.15341856586992775, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1556420233463035, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15786548082267926, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.16008893829905502, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1623123957754308, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.16453585325180656, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.16675931072818231, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.16675931072818231, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.811, | |
| "eval_samples_per_second": 5.848, | |
| "eval_steps_per_second": 2.932, | |
| "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": 1.91781773770752e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |