| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.18072289156626506, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006024096385542169, |
| "grad_norm": 11.142176628112793, |
| "learning_rate": 0.0, |
| "loss": 0.428902804851532, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.012048192771084338, |
| "grad_norm": 11.034109115600586, |
| "learning_rate": 5.555555555555555e-07, |
| "loss": 0.42792809009552, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.018072289156626505, |
| "grad_norm": 8.74612045288086, |
| "learning_rate": 1.111111111111111e-06, |
| "loss": 0.3810642957687378, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.024096385542168676, |
| "grad_norm": 9.825540542602539, |
| "learning_rate": 1.6666666666666667e-06, |
| "loss": 0.4792688190937042, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.030120481927710843, |
| "grad_norm": 9.189689636230469, |
| "learning_rate": 2.222222222222222e-06, |
| "loss": 0.40543031692504883, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03614457831325301, |
| "grad_norm": 7.393019199371338, |
| "learning_rate": 2.7777777777777783e-06, |
| "loss": 0.4046850800514221, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.04216867469879518, |
| "grad_norm": 5.906346797943115, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.3256700038909912, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.04819277108433735, |
| "grad_norm": 4.1642632484436035, |
| "learning_rate": 3.88888888888889e-06, |
| "loss": 0.2622697651386261, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05421686746987952, |
| "grad_norm": 4.239490032196045, |
| "learning_rate": 4.444444444444444e-06, |
| "loss": 0.31185054779052734, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.060240963855421686, |
| "grad_norm": 2.696002721786499, |
| "learning_rate": 5e-06, |
| "loss": 0.26603323221206665, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06626506024096386, |
| "grad_norm": 2.6713006496429443, |
| "learning_rate": 4.999881749961716e-06, |
| "loss": 0.29827162623405457, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07228915662650602, |
| "grad_norm": 2.532520294189453, |
| "learning_rate": 4.999527011033321e-06, |
| "loss": 0.2619355022907257, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0783132530120482, |
| "grad_norm": 2.390526533126831, |
| "learning_rate": 4.9989358167731285e-06, |
| "loss": 0.2530556321144104, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.08433734939759036, |
| "grad_norm": 2.513714551925659, |
| "learning_rate": 4.998108223108133e-06, |
| "loss": 0.2906743884086609, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.09036144578313253, |
| "grad_norm": 2.0978147983551025, |
| "learning_rate": 4.9970443083287224e-06, |
| "loss": 0.23413600027561188, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0963855421686747, |
| "grad_norm": 2.065729856491089, |
| "learning_rate": 4.995744173081265e-06, |
| "loss": 0.24827918410301208, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.10240963855421686, |
| "grad_norm": 1.884876012802124, |
| "learning_rate": 4.994207940358597e-06, |
| "loss": 0.26246076822280884, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.10843373493975904, |
| "grad_norm": 2.5683226585388184, |
| "learning_rate": 4.99243575548838e-06, |
| "loss": 0.3206707835197449, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.1144578313253012, |
| "grad_norm": 1.6468095779418945, |
| "learning_rate": 4.9904277861193574e-06, |
| "loss": 0.20793572068214417, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.12048192771084337, |
| "grad_norm": 2.026458263397217, |
| "learning_rate": 4.988184222205492e-06, |
| "loss": 0.23015552759170532, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12650602409638553, |
| "grad_norm": 1.8717762231826782, |
| "learning_rate": 4.9857052759880006e-06, |
| "loss": 0.25441068410873413, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.13253012048192772, |
| "grad_norm": 2.0290212631225586, |
| "learning_rate": 4.98299118197527e-06, |
| "loss": 0.22494634985923767, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.13855421686746988, |
| "grad_norm": 2.214284658432007, |
| "learning_rate": 4.980042196920677e-06, |
| "loss": 0.26744288206100464, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.14457831325301204, |
| "grad_norm": 2.1135001182556152, |
| "learning_rate": 4.976858599798299e-06, |
| "loss": 0.27789992094039917, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.15060240963855423, |
| "grad_norm": 1.9528898000717163, |
| "learning_rate": 4.97344069177652e-06, |
| "loss": 0.2466088980436325, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.1566265060240964, |
| "grad_norm": 2.101134777069092, |
| "learning_rate": 4.969788796189544e-06, |
| "loss": 0.2756834030151367, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.16265060240963855, |
| "grad_norm": 2.343674421310425, |
| "learning_rate": 4.965903258506806e-06, |
| "loss": 0.28239595890045166, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.1686746987951807, |
| "grad_norm": 2.253816843032837, |
| "learning_rate": 4.9617844463002895e-06, |
| "loss": 0.2833530306816101, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1746987951807229, |
| "grad_norm": 2.0298430919647217, |
| "learning_rate": 4.957432749209755e-06, |
| "loss": 0.25803640484809875, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.18072289156626506, |
| "grad_norm": 1.9530489444732666, |
| "learning_rate": 4.952848578905881e-06, |
| "loss": 0.2215431183576584, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 332, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 30, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.7366348342493184e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
