| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 6.015913963317871, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.8804, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.7702841758728027, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.469, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 6.33322811126709, | |
| "learning_rate": 1.9991228300988586e-05, | |
| "loss": 0.3463, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.0083963871002197, | |
| "learning_rate": 1.983571470813386e-05, | |
| "loss": 0.1673, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.2964335680007935, | |
| "learning_rate": 1.9488760116444966e-05, | |
| "loss": 0.106, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.03695794567465782, | |
| "learning_rate": 1.895711760239413e-05, | |
| "loss": 0.1623, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.0371510982513428, | |
| "learning_rate": 1.8251134982782952e-05, | |
| "loss": 0.1585, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.199394702911377, | |
| "learning_rate": 1.7384553406258842e-05, | |
| "loss": 0.192, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 1.681180477142334, | |
| "learning_rate": 1.63742398974869e-05, | |
| "loss": 0.1705, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.6913540959358215, | |
| "learning_rate": 1.5239859059700794e-05, | |
| "loss": 0.0652, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.09698222577571869, | |
| "learning_rate": 1.4003490325568953e-05, | |
| "loss": 0.1237, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.565293550491333, | |
| "learning_rate": 1.2689198206152657e-05, | |
| "loss": 0.1669, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.28498321771621704, | |
| "learning_rate": 1.1322563902571227e-05, | |
| "loss": 0.0606, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.46145015954971313, | |
| "learning_rate": 9.930187397020385e-06, | |
| "loss": 0.1064, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.04056666046380997, | |
| "learning_rate": 8.539169714375885e-06, | |
| "loss": 0.0548, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.3497525453567505, | |
| "learning_rate": 7.176585431571235e-06, | |
| "loss": 0.1326, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.316214382648468, | |
| "learning_rate": 5.868955701754584e-06, | |
| "loss": 0.0843, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.4990209341049194, | |
| "learning_rate": 4.641732050210032e-06, | |
| "loss": 0.0121, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.16705955564975739, | |
| "learning_rate": 3.5188009893686916e-06, | |
| "loss": 0.0227, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.6158097982406616, | |
| "learning_rate": 2.522019095014683e-06, | |
| "loss": 0.0385, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.018577594310045242, | |
| "learning_rate": 1.6707875928990059e-06, | |
| "loss": 0.0295, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 2.720700740814209, | |
| "learning_rate": 9.816747359488632e-07, | |
| "loss": 0.0206, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.03381221741437912, | |
| "learning_rate": 4.6809332207053083e-07, | |
| "loss": 0.0089, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.07453195750713348, | |
| "learning_rate": 1.400396292949513e-07, | |
| "loss": 0.0576, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.23894575238227844, | |
| "learning_rate": 3.898849596456477e-09, | |
| "loss": 0.0308, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 250, | |
| "total_flos": 1.4149166716420096e+16, | |
| "train_loss": 0.18670074969530107, | |
| "train_runtime": 1345.2529, | |
| "train_samples_per_second": 0.743, | |
| "train_steps_per_second": 0.186 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4149166716420096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |