| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006814619630647616, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.086159507530154e-05, | |
| "grad_norm": 28.37936019897461, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 8.8371, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.086159507530154e-05, | |
| "eval_loss": 10.420028686523438, | |
| "eval_runtime": 306.3179, | |
| "eval_samples_per_second": 30.256, | |
| "eval_steps_per_second": 15.128, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001817231901506031, | |
| "grad_norm": 34.581912994384766, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 9.9277, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002725847852259046, | |
| "grad_norm": 35.70059585571289, | |
| "learning_rate": 0.0001, | |
| "loss": 9.3615, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003634463803012062, | |
| "grad_norm": 25.815174102783203, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 7.0004, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00045430797537650774, | |
| "grad_norm": 52.796356201171875, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 5.8176, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005451695704518092, | |
| "grad_norm": 18.662376403808594, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.2304, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006360311655271108, | |
| "grad_norm": 17.944053649902344, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.4738, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007268927606024124, | |
| "grad_norm": 10.449116706848145, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 1.3214, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008177543556777139, | |
| "grad_norm": 4.770611763000488, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9449, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009086159507530155, | |
| "grad_norm": 2.742938756942749, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0423, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000999477545828317, | |
| "grad_norm": 5.579481601715088, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.7174, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0010903391409036185, | |
| "grad_norm": 13.289307594299316, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2919, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00118120073597892, | |
| "grad_norm": 10.471413612365723, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.7718, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0012720623310542216, | |
| "grad_norm": 4.605869293212891, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.1433, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0013629239261295232, | |
| "grad_norm": 5.941074848175049, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1174, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014537855212048247, | |
| "grad_norm": 11.986332893371582, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.1588, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015446471162801263, | |
| "grad_norm": 11.422152519226074, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.2491, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0016355087113554278, | |
| "grad_norm": 9.860111236572266, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.2102, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017263703064307294, | |
| "grad_norm": 2.8064475059509277, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0361, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001817231901506031, | |
| "grad_norm": 0.4391842484474182, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0055, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019080934965813325, | |
| "grad_norm": 3.745144844055176, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0863, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001998955091656634, | |
| "grad_norm": 0.050352372229099274, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0008, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0020898166867319356, | |
| "grad_norm": 1.2719851732254028, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0119, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002180678281807237, | |
| "grad_norm": 0.5530160069465637, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0032, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0022715398768825387, | |
| "grad_norm": 0.06411629170179367, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022715398768825387, | |
| "eval_loss": 1.8638120889663696, | |
| "eval_runtime": 306.1366, | |
| "eval_samples_per_second": 30.274, | |
| "eval_steps_per_second": 15.137, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00236240147195784, | |
| "grad_norm": 0.2939962148666382, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0027, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.002453263067033142, | |
| "grad_norm": 0.6323854923248291, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0051, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002544124662108443, | |
| "grad_norm": 0.011483444832265377, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0002, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002634986257183745, | |
| "grad_norm": 0.028377123177051544, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.0002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0027258478522590463, | |
| "grad_norm": 0.0203834380954504, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0003, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002816709447334348, | |
| "grad_norm": 9.312389373779297, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.4706, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0029075710424096494, | |
| "grad_norm": 68.22864532470703, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 3.3187, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.002998432637484951, | |
| "grad_norm": 48.021480560302734, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.134, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0030892942325602525, | |
| "grad_norm": 18.471052169799805, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.2329, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0031801558276355543, | |
| "grad_norm": 16.42901039123535, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.4616, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0032710174227108557, | |
| "grad_norm": 13.609719276428223, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3694, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0033618790177861574, | |
| "grad_norm": 2.441948652267456, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.043, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0034527406128614588, | |
| "grad_norm": 0.41872337460517883, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0039, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00354360220793676, | |
| "grad_norm": 0.22431544959545135, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0019, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003634463803012062, | |
| "grad_norm": 0.3925679624080658, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0035, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037253253980873632, | |
| "grad_norm": 0.04403270035982132, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0006, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003816186993162665, | |
| "grad_norm": 0.034630876034498215, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0005, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003907048588237967, | |
| "grad_norm": 0.46163317561149597, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0027, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.003997910183313268, | |
| "grad_norm": 0.06355968862771988, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0006, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0040887717783885695, | |
| "grad_norm": 0.05269589275121689, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004179633373463871, | |
| "grad_norm": 0.01986519619822502, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0002, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.004270494968539173, | |
| "grad_norm": 0.019215445965528488, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0002, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004361356563614474, | |
| "grad_norm": 0.006207428406924009, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004452218158689776, | |
| "grad_norm": 0.012795104645192623, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0002, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0045430797537650775, | |
| "grad_norm": 0.004560490138828754, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0045430797537650775, | |
| "eval_loss": 2.606266498565674, | |
| "eval_runtime": 305.9895, | |
| "eval_samples_per_second": 30.289, | |
| "eval_steps_per_second": 15.144, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004633941348840379, | |
| "grad_norm": 46.32371520996094, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.8385, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.00472480294391568, | |
| "grad_norm": 50.98200607299805, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 5.1699, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.004815664538990982, | |
| "grad_norm": 50.70225143432617, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 5.2527, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.004906526134066284, | |
| "grad_norm": 47.06248474121094, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.5287, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0049973877291415855, | |
| "grad_norm": 43.91443634033203, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 4.1084, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.005088249324216886, | |
| "grad_norm": 43.865379333496094, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 4.248, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.005179110919292188, | |
| "grad_norm": 31.40968132019043, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.0994, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00526997251436749, | |
| "grad_norm": 34.816925048828125, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 3.3691, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.005360834109442791, | |
| "grad_norm": 29.733379364013672, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.6941, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.005451695704518093, | |
| "grad_norm": 24.68531036376953, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.9541, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005542557299593394, | |
| "grad_norm": 23.424503326416016, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 1.9792, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.005633418894668696, | |
| "grad_norm": 32.10466766357422, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 2.261, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.005724280489743997, | |
| "grad_norm": 27.93880844116211, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.3343, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.005815142084819299, | |
| "grad_norm": 23.051822662353516, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 1.5509, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.005906003679894601, | |
| "grad_norm": 25.748632431030273, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.6823, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.005996865274969902, | |
| "grad_norm": 27.34827423095703, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5725, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.006087726870045203, | |
| "grad_norm": 22.656187057495117, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.0763, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.006178588465120505, | |
| "grad_norm": 19.859046936035156, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 1.081, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.006269450060195807, | |
| "grad_norm": 20.085308074951172, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2761, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.006360311655271109, | |
| "grad_norm": 17.73591423034668, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.9149, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0064511732503464096, | |
| "grad_norm": 21.190202713012695, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.4188, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.006542034845421711, | |
| "grad_norm": 20.775806427001953, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0984, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006632896440497013, | |
| "grad_norm": 19.472455978393555, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.8902, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.006723758035572315, | |
| "grad_norm": 20.528032302856445, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.855, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.006814619630647616, | |
| "grad_norm": 18.677600860595703, | |
| "learning_rate": 0.0, | |
| "loss": 0.8934, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.006814619630647616, | |
| "eval_loss": 0.611670970916748, | |
| "eval_runtime": 306.2641, | |
| "eval_samples_per_second": 30.261, | |
| "eval_steps_per_second": 15.131, | |
| "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": 1.46820537778176e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |