| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004297532500089532, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.730043333452709e-05, | |
| "grad_norm": 4.64981746673584, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.7731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.730043333452709e-05, | |
| "eval_loss": 0.5826753377914429, | |
| "eval_runtime": 1985.2029, | |
| "eval_samples_per_second": 7.403, | |
| "eval_steps_per_second": 3.702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011460086666905418, | |
| "grad_norm": 5.319647789001465, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.7419, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00017190130000358127, | |
| "grad_norm": 6.593022346496582, | |
| "learning_rate": 0.0001, | |
| "loss": 2.172, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00022920173333810837, | |
| "grad_norm": 5.512605667114258, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 2.0215, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00028650216667263544, | |
| "grad_norm": 4.8503241539001465, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 1.8746, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00034380260000716254, | |
| "grad_norm": 8.325742721557617, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1677, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00040110303334168964, | |
| "grad_norm": 4.24470853805542, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.0449, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00045840346667621674, | |
| "grad_norm": 3.902250289916992, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.8211, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005157039000107438, | |
| "grad_norm": 3.2968428134918213, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9614, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005730043333452709, | |
| "grad_norm": 3.920433282852173, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.8732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000630304766679798, | |
| "grad_norm": 4.680196762084961, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.6169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0006876052000143251, | |
| "grad_norm": 4.031309127807617, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7551, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007449056333488522, | |
| "grad_norm": 4.4254469871521, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.8059, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008022060666833793, | |
| "grad_norm": 3.8273370265960693, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.7919, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0008595065000179064, | |
| "grad_norm": 3.6414921283721924, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.714, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009168069333524335, | |
| "grad_norm": 4.078192234039307, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.8365, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0009741073666869605, | |
| "grad_norm": 4.631629943847656, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.8709, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0010314078000214877, | |
| "grad_norm": 3.5660946369171143, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7732, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010887082333560147, | |
| "grad_norm": 4.0769829750061035, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.8697, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0011460086666905418, | |
| "grad_norm": 3.174710273742676, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.6654, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001203309100025069, | |
| "grad_norm": 4.109514236450195, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7679, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001260609533359596, | |
| "grad_norm": 3.642437696456909, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.734, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001317909966694123, | |
| "grad_norm": 4.460132598876953, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.951, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0013752104000286502, | |
| "grad_norm": 3.60257625579834, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5561, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0014325108333631774, | |
| "grad_norm": 3.7138121128082275, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.7833, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014325108333631774, | |
| "eval_loss": 0.1671205759048462, | |
| "eval_runtime": 1990.9333, | |
| "eval_samples_per_second": 7.382, | |
| "eval_steps_per_second": 3.691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014898112666977045, | |
| "grad_norm": 4.513851642608643, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.5433, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0015471117000322315, | |
| "grad_norm": 5.423880577087402, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0937, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0016044121333667585, | |
| "grad_norm": 3.9187657833099365, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.8542, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0016617125667012856, | |
| "grad_norm": 3.9628372192382812, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.768, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0017190130000358129, | |
| "grad_norm": 5.155542850494385, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8362, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00177631343337034, | |
| "grad_norm": 3.2812490463256836, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.7467, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001833613866704867, | |
| "grad_norm": 4.409944534301758, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.8352, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.001890914300039394, | |
| "grad_norm": 4.593567371368408, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0404, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.001948214733373921, | |
| "grad_norm": 4.877197742462158, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.1112, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.002005515166708448, | |
| "grad_norm": 7.327693939208984, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.0144, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0020628156000429753, | |
| "grad_norm": 6.236719131469727, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8903, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0021201160333775026, | |
| "grad_norm": 5.947874546051025, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 1.5181, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0021774164667120294, | |
| "grad_norm": 6.993929862976074, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.4933, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0022347169000465567, | |
| "grad_norm": 6.632877349853516, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8576, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0022920173333810835, | |
| "grad_norm": 5.726492404937744, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 1.7028, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0023493177667156108, | |
| "grad_norm": 5.678798198699951, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 1.8054, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002406618200050138, | |
| "grad_norm": 6.203830242156982, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.858, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002463918633384665, | |
| "grad_norm": 12.835216522216797, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.839, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.002521219066719192, | |
| "grad_norm": 6.748092174530029, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 1.9296, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.002578519500053719, | |
| "grad_norm": 8.807928085327148, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6976, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002635819933388246, | |
| "grad_norm": 7.636016845703125, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 1.9868, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0026931203667227735, | |
| "grad_norm": 10.444618225097656, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 3.4253, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0027504208000573003, | |
| "grad_norm": 11.333175659179688, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2715, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0028077212333918276, | |
| "grad_norm": 10.740086555480957, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 3.6215, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.002865021666726355, | |
| "grad_norm": 14.465156555175781, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 6.0227, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002865021666726355, | |
| "eval_loss": 0.14761370420455933, | |
| "eval_runtime": 1992.1836, | |
| "eval_samples_per_second": 7.377, | |
| "eval_steps_per_second": 3.689, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0029223221000608817, | |
| "grad_norm": 2.3872838020324707, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6123, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.002979622533395409, | |
| "grad_norm": 2.11433482170105, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.7429, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0030369229667299357, | |
| "grad_norm": 1.9935492277145386, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.4261, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.003094223400064463, | |
| "grad_norm": 2.011484146118164, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5963, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0031515238333989903, | |
| "grad_norm": 2.5177338123321533, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.4909, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.003208824266733517, | |
| "grad_norm": 2.2302229404449463, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.5392, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0032661247000680444, | |
| "grad_norm": 3.0052223205566406, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4753, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.003323425133402571, | |
| "grad_norm": 2.423661947250366, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.4055, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0033807255667370984, | |
| "grad_norm": 2.8571395874023438, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.7339, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0034380260000716257, | |
| "grad_norm": 3.235661268234253, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7574, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0034953264334061525, | |
| "grad_norm": 2.264759063720703, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.5166, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.00355262686674068, | |
| "grad_norm": 2.731968402862549, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.4679, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0036099273000752066, | |
| "grad_norm": 2.704561471939087, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7767, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003667227733409734, | |
| "grad_norm": 1.7505345344543457, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.3995, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.003724528166744261, | |
| "grad_norm": 2.4672224521636963, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.6333, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.003781828600078788, | |
| "grad_norm": 3.6237540245056152, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4109, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0038391290334133152, | |
| "grad_norm": 3.1202926635742188, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.8672, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.003896429466747842, | |
| "grad_norm": 3.3872885704040527, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.753, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.003953729900082369, | |
| "grad_norm": 3.216975212097168, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6849, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.004011030333416896, | |
| "grad_norm": 2.8667757511138916, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.5677, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.004068330766751424, | |
| "grad_norm": 4.095630645751953, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.645, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.004125631200085951, | |
| "grad_norm": 3.189215898513794, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6192, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0041829316334204775, | |
| "grad_norm": 2.886237144470215, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.7971, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.004240232066755005, | |
| "grad_norm": 2.6635372638702393, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.6268, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.004297532500089532, | |
| "grad_norm": 2.3732454776763916, | |
| "learning_rate": 0.0, | |
| "loss": 0.5992, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.004297532500089532, | |
| "eval_loss": 0.14407220482826233, | |
| "eval_runtime": 1991.2821, | |
| "eval_samples_per_second": 7.381, | |
| "eval_steps_per_second": 3.691, | |
| "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": 9.86082145468416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |