| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13801035077630822, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023001725129384704, | |
| "grad_norm": 1.1044824123382568, | |
| "learning_rate": 4e-05, | |
| "loss": 1.478, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004600345025876941, | |
| "grad_norm": 1.002670407295227, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3821, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006900517538815411, | |
| "grad_norm": 1.0559437274932861, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3293, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009200690051753882, | |
| "grad_norm": 0.7474594116210938, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3018, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011500862564692352, | |
| "grad_norm": 0.844304621219635, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3377, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013801035077630822, | |
| "grad_norm": 0.6108690500259399, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 1.3059, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016101207590569294, | |
| "grad_norm": 0.7801899909973145, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 1.1677, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018401380103507763, | |
| "grad_norm": 0.7782777547836304, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 1.271, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020701552616446232, | |
| "grad_norm": 0.653756320476532, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 1.0682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023001725129384705, | |
| "grad_norm": 0.5281978249549866, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 1.1964, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025301897642323174, | |
| "grad_norm": 0.5355067253112793, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 1.0085, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027602070155261643, | |
| "grad_norm": 0.47657492756843567, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 0.9768, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029902242668200116, | |
| "grad_norm": 0.5171030759811401, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 0.9436, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03220241518113859, | |
| "grad_norm": 0.467006117105484, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 1.1535, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.034502587694077054, | |
| "grad_norm": 0.5699396729469299, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.9282, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03680276020701553, | |
| "grad_norm": 0.511089026927948, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0179, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.039102932719954, | |
| "grad_norm": 0.5324010252952576, | |
| "learning_rate": 0.00015636363636363637, | |
| "loss": 0.8374, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.041403105232892465, | |
| "grad_norm": 0.5165485739707947, | |
| "learning_rate": 0.00015272727272727275, | |
| "loss": 1.012, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04370327774583094, | |
| "grad_norm": 0.4569143056869507, | |
| "learning_rate": 0.0001490909090909091, | |
| "loss": 1.0364, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04600345025876941, | |
| "grad_norm": 0.5322045683860779, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 1.0632, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.048303622771707876, | |
| "grad_norm": 0.5586767792701721, | |
| "learning_rate": 0.00014181818181818184, | |
| "loss": 0.9602, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05060379528464635, | |
| "grad_norm": 0.49304378032684326, | |
| "learning_rate": 0.0001381818181818182, | |
| "loss": 0.9795, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05290396779758482, | |
| "grad_norm": 0.5537046790122986, | |
| "learning_rate": 0.00013454545454545455, | |
| "loss": 0.822, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.055204140310523286, | |
| "grad_norm": 0.5536014437675476, | |
| "learning_rate": 0.00013090909090909093, | |
| "loss": 1.0246, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05750431282346176, | |
| "grad_norm": 0.48426035046577454, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 1.0075, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05980448533640023, | |
| "grad_norm": 0.48291561007499695, | |
| "learning_rate": 0.00012363636363636364, | |
| "loss": 1.0763, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0621046578493387, | |
| "grad_norm": 0.5491870045661926, | |
| "learning_rate": 0.00012, | |
| "loss": 0.9692, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06440483036227718, | |
| "grad_norm": 0.5002620220184326, | |
| "learning_rate": 0.00011636363636363636, | |
| "loss": 0.8783, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06670500287521564, | |
| "grad_norm": 0.5101091265678406, | |
| "learning_rate": 0.00011272727272727272, | |
| "loss": 1.1709, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06900517538815411, | |
| "grad_norm": 0.4794892966747284, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.9715, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07130534790109258, | |
| "grad_norm": 0.5005142092704773, | |
| "learning_rate": 0.00010545454545454545, | |
| "loss": 1.048, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07360552041403105, | |
| "grad_norm": 0.558136522769928, | |
| "learning_rate": 0.00010181818181818181, | |
| "loss": 0.9694, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07590569292696953, | |
| "grad_norm": 0.5822620391845703, | |
| "learning_rate": 9.818181818181818e-05, | |
| "loss": 0.8191, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.078205865439908, | |
| "grad_norm": 0.5888277888298035, | |
| "learning_rate": 9.454545454545455e-05, | |
| "loss": 0.9948, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08050603795284646, | |
| "grad_norm": 0.5250777006149292, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.9533, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08280621046578493, | |
| "grad_norm": 0.4621059000492096, | |
| "learning_rate": 8.727272727272727e-05, | |
| "loss": 1.0415, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 0.565501868724823, | |
| "learning_rate": 8.363636363636364e-05, | |
| "loss": 0.8335, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08740655549166187, | |
| "grad_norm": 0.5443646907806396, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8514, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08970672800460035, | |
| "grad_norm": 0.5232164859771729, | |
| "learning_rate": 7.636363636363637e-05, | |
| "loss": 0.904, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09200690051753882, | |
| "grad_norm": 0.5777676701545715, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 1.1459, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09430707303047729, | |
| "grad_norm": 0.545629620552063, | |
| "learning_rate": 6.90909090909091e-05, | |
| "loss": 0.8957, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09660724554341575, | |
| "grad_norm": 0.6201319098472595, | |
| "learning_rate": 6.545454545454546e-05, | |
| "loss": 0.9554, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09890741805635422, | |
| "grad_norm": 0.5603893995285034, | |
| "learning_rate": 6.181818181818182e-05, | |
| "loss": 0.8743, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1012075905692927, | |
| "grad_norm": 0.5196118354797363, | |
| "learning_rate": 5.818181818181818e-05, | |
| "loss": 1.1818, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10350776308223117, | |
| "grad_norm": 0.5396114587783813, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.8085, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10580793559516964, | |
| "grad_norm": 0.5425748229026794, | |
| "learning_rate": 5.090909090909091e-05, | |
| "loss": 0.8977, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 0.4833182692527771, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.9912, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11040828062104657, | |
| "grad_norm": 0.5984821319580078, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.884, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11270845313398505, | |
| "grad_norm": 0.5533356070518494, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8668, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11500862564692352, | |
| "grad_norm": 0.5323106050491333, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.8699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11730879815986199, | |
| "grad_norm": 0.5784793496131897, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.9276, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.11960897067280046, | |
| "grad_norm": 0.4988090395927429, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 1.0361, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.12190914318573894, | |
| "grad_norm": 0.628527820110321, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 0.7982, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1242093156986774, | |
| "grad_norm": 0.6348117589950562, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 0.7576, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.12650948821161587, | |
| "grad_norm": 0.5996023416519165, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.8433, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.12880966072455435, | |
| "grad_norm": 0.7210708856582642, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 0.811, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1311098332374928, | |
| "grad_norm": 0.5307955145835876, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 0.8914, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.13341000575043127, | |
| "grad_norm": 0.5893259048461914, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 0.8525, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.13571017826336976, | |
| "grad_norm": 0.5287377834320068, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 0.8509, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.13801035077630822, | |
| "grad_norm": 0.5250273942947388, | |
| "learning_rate": 0.0, | |
| "loss": 0.8053, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.997055015960576e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |