| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5853658536585366, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007804878048780488, | |
| "grad_norm": 0.25521984696388245, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.3485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007804878048780488, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8211, | |
| "eval_samples_per_second": 131.535, | |
| "eval_steps_per_second": 65.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015609756097560976, | |
| "grad_norm": 0.26596277952194214, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.3604, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.023414634146341463, | |
| "grad_norm": 0.26680320501327515, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3267, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03121951219512195, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 0.13787446916103363, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.3614, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04682926829268293, | |
| "grad_norm": 0.20616938173770905, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.054634146341463415, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0624390243902439, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0702439024390244, | |
| "grad_norm": 0.3303433060646057, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3029, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 0.26826196908950806, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 10.3161, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08585365853658537, | |
| "grad_norm": 0.14440414309501648, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3731, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09365853658536585, | |
| "grad_norm": 0.42242559790611267, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.2871, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10146341463414635, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10926829268292683, | |
| "grad_norm": 0.3015792667865753, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 10.3428, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11707317073170732, | |
| "grad_norm": 0.206211656332016, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3387, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1248780487804878, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1326829268292683, | |
| "grad_norm": 0.22047275304794312, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 10.3433, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1404878048780488, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14829268292682926, | |
| "grad_norm": 0.2648928165435791, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3056, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15609756097560976, | |
| "grad_norm": 0.36561036109924316, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.2952, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16390243902439025, | |
| "grad_norm": 0.3115338981151581, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.315, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17170731707317075, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1795121951219512, | |
| "grad_norm": 0.36666783690452576, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3297, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1873170731707317, | |
| "grad_norm": 0.22661548852920532, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3514, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8311, | |
| "eval_samples_per_second": 129.949, | |
| "eval_steps_per_second": 64.975, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2029268292682927, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21073170731707316, | |
| "grad_norm": 0.3156268298625946, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3343, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21853658536585366, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22634146341463415, | |
| "grad_norm": 0.292163223028183, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 10.3344, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.23414634146341465, | |
| "grad_norm": 0.3371083438396454, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.283, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24195121951219511, | |
| "grad_norm": 0.2140391618013382, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3156, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2497560975609756, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2575609756097561, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2653658536585366, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2731707317073171, | |
| "grad_norm": 0.18448299169540405, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3462, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2809756097560976, | |
| "grad_norm": 0.49599871039390564, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.2718, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.288780487804878, | |
| "grad_norm": 0.34540557861328125, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 10.3489, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2965853658536585, | |
| "grad_norm": 0.3862549364566803, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 10.3152, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.304390243902439, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3121951219512195, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3278048780487805, | |
| "grad_norm": 0.4351806938648224, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.2728, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.335609756097561, | |
| "grad_norm": 0.12750659883022308, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.3577, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3434146341463415, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.35121951219512193, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3590243902439024, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3668292682926829, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3746341463414634, | |
| "grad_norm": 0.3584749400615692, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.318, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3824390243902439, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.22366450726985931, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 10.3463, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8158, | |
| "eval_samples_per_second": 132.379, | |
| "eval_steps_per_second": 66.189, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3980487804878049, | |
| "grad_norm": 0.3423277735710144, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3147, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4058536585365854, | |
| "grad_norm": 0.6363266706466675, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 10.3515, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.41365853658536583, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4214634146341463, | |
| "grad_norm": 0.24497881531715393, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3405, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4292682926829268, | |
| "grad_norm": 0.4106614887714386, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.3135, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4370731707317073, | |
| "grad_norm": 0.39143839478492737, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 10.2764, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4448780487804878, | |
| "grad_norm": 0.27267274260520935, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3469, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4526829268292683, | |
| "grad_norm": 0.2594338059425354, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 10.3217, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4604878048780488, | |
| "grad_norm": 0.3521457314491272, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.2803, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.4682926829268293, | |
| "grad_norm": 0.4126719832420349, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.273, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.47609756097560973, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.48390243902439023, | |
| "grad_norm": 0.18538454174995422, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 10.3676, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4917073170731707, | |
| "grad_norm": 0.5036085247993469, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.301, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4995121951219512, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5073170731707317, | |
| "grad_norm": 0.4074370861053467, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 10.3426, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5151219512195122, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5229268292682927, | |
| "grad_norm": 0.18366609513759613, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.344, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5307317073170732, | |
| "grad_norm": 0.5279123187065125, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 10.2819, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5385365853658537, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5463414634146342, | |
| "grad_norm": 0.16284289956092834, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 10.3568, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5541463414634147, | |
| "grad_norm": 0.8960087299346924, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.2783, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5619512195121952, | |
| "grad_norm": 0.5058993101119995, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.2634, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5697560975609756, | |
| "grad_norm": 0.7693451046943665, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 10.2923, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.577560975609756, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.3889043927192688, | |
| "learning_rate": 0.0, | |
| "loss": 10.2979, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8169, | |
| "eval_samples_per_second": 132.213, | |
| "eval_steps_per_second": 66.107, | |
| "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": 8019011174400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |