| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.926829268292683, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 6.836372375488281, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 1.1182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 6.894412517547607, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.1051, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 6.724112033843994, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1203, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 5.394062042236328, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.0799, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 2.9904468059539795, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.9942, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 4.739986896514893, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9869, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 4.689507961273193, | |
| "learning_rate": 9.991540791356342e-06, | |
| "loss": 0.9747, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 4.10852575302124, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 1.0225, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 3.6707763671875, | |
| "learning_rate": 9.924038765061042e-06, | |
| "loss": 0.9272, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 2.4826507568359375, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.9513, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 2.0593159198760986, | |
| "learning_rate": 9.789947561577445e-06, | |
| "loss": 0.8729, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 2.3102424144744873, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.9028, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 1.8726847171783447, | |
| "learning_rate": 9.591080534401371e-06, | |
| "loss": 0.8811, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 1.3534939289093018, | |
| "learning_rate": 9.468163201617063e-06, | |
| "loss": 0.9254, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 1.3493455648422241, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 0.8082, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 1.103345274925232, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.8552, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.8746293783187866, | |
| "learning_rate": 9.01061596377522e-06, | |
| "loss": 0.8405, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.923000156879425, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.8543, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.7458917498588562, | |
| "learning_rate": 8.636868207865244e-06, | |
| "loss": 0.9075, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.7327495813369751, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.8463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.024390243902439, | |
| "grad_norm": 1.1537771224975586, | |
| "learning_rate": 8.213938048432697e-06, | |
| "loss": 1.1651, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 0.6341186761856079, | |
| "learning_rate": 7.985792958513932e-06, | |
| "loss": 0.7399, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1219512195121952, | |
| "grad_norm": 0.7606744170188904, | |
| "learning_rate": 7.747544890354031e-06, | |
| "loss": 0.8688, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 0.6201728582382202, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.7049, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 0.8632344007492065, | |
| "learning_rate": 7.243995901002312e-06, | |
| "loss": 0.92, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 0.6163485050201416, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.6655, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3170731707317074, | |
| "grad_norm": 0.5234319567680359, | |
| "learning_rate": 6.710100716628345e-06, | |
| "loss": 0.7905, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 0.5779823660850525, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.8514, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4146341463414633, | |
| "grad_norm": 0.6601042747497559, | |
| "learning_rate": 6.153079353712201e-06, | |
| "loss": 0.88, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 0.5179601311683655, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.6719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5121951219512195, | |
| "grad_norm": 0.5515910983085632, | |
| "learning_rate": 5.5804645706261515e-06, | |
| "loss": 0.9152, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 0.49588778614997864, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.6975, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6097560975609757, | |
| "grad_norm": 0.5540623068809509, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8428, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 0.5262721180915833, | |
| "learning_rate": 4.7092758554476215e-06, | |
| "loss": 0.7701, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.7073170731707317, | |
| "grad_norm": 0.499987930059433, | |
| "learning_rate": 4.4195354293738484e-06, | |
| "loss": 0.684, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 0.5329548716545105, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.811, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.8048780487804879, | |
| "grad_norm": 0.516512393951416, | |
| "learning_rate": 3.8469206462878e-06, | |
| "loss": 0.8534, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 0.5150623917579651, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.7364, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.9024390243902438, | |
| "grad_norm": 0.5092661380767822, | |
| "learning_rate": 3.289899283371657e-06, | |
| "loss": 0.7937, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 0.4906715452671051, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.7559, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.7150355577468872, | |
| "learning_rate": 2.7560040989976894e-06, | |
| "loss": 1.254, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.048780487804878, | |
| "grad_norm": 0.4212687015533447, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.7906, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.097560975609756, | |
| "grad_norm": 0.45231571793556213, | |
| "learning_rate": 2.2524551096459703e-06, | |
| "loss": 0.7495, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1463414634146343, | |
| "grad_norm": 0.47202828526496887, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.7846, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.1951219512195124, | |
| "grad_norm": 0.49245500564575195, | |
| "learning_rate": 1.7860619515673034e-06, | |
| "loss": 0.7664, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2439024390243905, | |
| "grad_norm": 0.4255480170249939, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.7178, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.292682926829268, | |
| "grad_norm": 0.42227357625961304, | |
| "learning_rate": 1.3631317921347564e-06, | |
| "loss": 0.7867, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.341463414634146, | |
| "grad_norm": 0.4211116135120392, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.7419, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3902439024390243, | |
| "grad_norm": 0.38902539014816284, | |
| "learning_rate": 9.893840362247809e-07, | |
| "loss": 0.7224, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 0.473481684923172, | |
| "learning_rate": 8.225609429353187e-07, | |
| "loss": 0.7914, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4878048780487805, | |
| "grad_norm": 0.40908774733543396, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 0.7448, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.5365853658536586, | |
| "grad_norm": 0.4036145806312561, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.7486, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.5853658536585367, | |
| "grad_norm": 0.4587302803993225, | |
| "learning_rate": 4.089194655986306e-07, | |
| "loss": 0.7421, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.6341463414634148, | |
| "grad_norm": 0.42735883593559265, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.8132, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.682926829268293, | |
| "grad_norm": 0.3429286777973175, | |
| "learning_rate": 2.1005243842255552e-07, | |
| "loss": 0.7491, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.7317073170731705, | |
| "grad_norm": 0.3881649971008301, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.7919, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.7804878048780486, | |
| "grad_norm": 0.36438366770744324, | |
| "learning_rate": 7.59612349389599e-08, | |
| "loss": 0.7485, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.8292682926829267, | |
| "grad_norm": 0.4045783579349518, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.734, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.8780487804878048, | |
| "grad_norm": 0.3840378522872925, | |
| "learning_rate": 8.459208643659122e-09, | |
| "loss": 0.7751, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 0.41218218207359314, | |
| "learning_rate": 0.0, | |
| "loss": 0.7135, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "step": 60, | |
| "total_flos": 56084346568704.0, | |
| "train_loss": 0.8459723273913066, | |
| "train_runtime": 3353.8656, | |
| "train_samples_per_second": 1.756, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 56084346568704.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |