| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.124463519313305, | |
| "eval_steps": 50, | |
| "global_step": 44, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06866952789699571, | |
| "grad_norm": 71.51506042480469, | |
| "learning_rate": 5e-06, | |
| "loss": 28.3366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06866952789699571, | |
| "eval_loss": 1.670872449874878, | |
| "eval_runtime": 6.2032, | |
| "eval_samples_per_second": 7.899, | |
| "eval_steps_per_second": 2.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13733905579399142, | |
| "grad_norm": 68.20951843261719, | |
| "learning_rate": 1e-05, | |
| "loss": 25.6432, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.20600858369098712, | |
| "grad_norm": 80.32080078125, | |
| "learning_rate": 1.5e-05, | |
| "loss": 28.4214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.27467811158798283, | |
| "grad_norm": 68.32494354248047, | |
| "learning_rate": 2e-05, | |
| "loss": 26.3899, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.34334763948497854, | |
| "grad_norm": 53.57563781738281, | |
| "learning_rate": 2.5e-05, | |
| "loss": 24.8964, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.41201716738197425, | |
| "grad_norm": 41.535865783691406, | |
| "learning_rate": 3e-05, | |
| "loss": 22.6295, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.48068669527896996, | |
| "grad_norm": 35.4793701171875, | |
| "learning_rate": 3.5e-05, | |
| "loss": 21.0718, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5493562231759657, | |
| "grad_norm": 27.92133140563965, | |
| "learning_rate": 4e-05, | |
| "loss": 17.8598, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6180257510729614, | |
| "grad_norm": 23.524612426757812, | |
| "learning_rate": 4.5e-05, | |
| "loss": 15.9413, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6866952789699571, | |
| "grad_norm": 21.849180221557617, | |
| "learning_rate": 5e-05, | |
| "loss": 14.0453, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7553648068669528, | |
| "grad_norm": 22.79987907409668, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 12.4121, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8240343347639485, | |
| "grad_norm": 28.22759246826172, | |
| "learning_rate": 6e-05, | |
| "loss": 11.8626, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8927038626609443, | |
| "grad_norm": 27.044172286987305, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 10.725, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9613733905579399, | |
| "grad_norm": 31.80463409423828, | |
| "learning_rate": 7e-05, | |
| "loss": 11.4271, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0643776824034334, | |
| "grad_norm": 23.66387367248535, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 9.8895, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1330472103004292, | |
| "grad_norm": 18.42772674560547, | |
| "learning_rate": 8e-05, | |
| "loss": 7.9848, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.201716738197425, | |
| "grad_norm": 16.588830947875977, | |
| "learning_rate": 8.5e-05, | |
| "loss": 7.3708, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2703862660944205, | |
| "grad_norm": 18.946819305419922, | |
| "learning_rate": 9e-05, | |
| "loss": 6.2703, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3390557939914163, | |
| "grad_norm": 14.745619773864746, | |
| "learning_rate": 9.5e-05, | |
| "loss": 6.0982, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.407725321888412, | |
| "grad_norm": 23.77857208251953, | |
| "learning_rate": 0.0001, | |
| "loss": 8.2525, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4763948497854078, | |
| "grad_norm": 17.072463989257812, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.8517, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5450643776824036, | |
| "grad_norm": 19.66710090637207, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.3888, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.613733905579399, | |
| "grad_norm": 14.107242584228516, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.4112, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6824034334763949, | |
| "grad_norm": 13.895885467529297, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.5546, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7510729613733904, | |
| "grad_norm": 21.809589385986328, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.8744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8197424892703862, | |
| "grad_norm": 14.282073974609375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.5111, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.888412017167382, | |
| "grad_norm": 18.04335594177246, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.8618, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9570815450643777, | |
| "grad_norm": 16.261669158935547, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.7066, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.060085836909871, | |
| "grad_norm": 14.687187194824219, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.5166, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.128755364806867, | |
| "grad_norm": 13.488051414489746, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.9256, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.1974248927038627, | |
| "grad_norm": 13.153692245483398, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.1638, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2660944206008584, | |
| "grad_norm": 9.933245658874512, | |
| "learning_rate": 5e-05, | |
| "loss": 2.767, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.334763948497854, | |
| "grad_norm": 10.760828971862793, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.6228, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.40343347639485, | |
| "grad_norm": 12.465494155883789, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 4.5534, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.4721030042918457, | |
| "grad_norm": 9.80876636505127, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.7875, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.540772532188841, | |
| "grad_norm": 10.498035430908203, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.8723, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.609442060085837, | |
| "grad_norm": 14.041341781616211, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.0086, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6781115879828326, | |
| "grad_norm": 11.766754150390625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3765, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7467811158798283, | |
| "grad_norm": 9.810280799865723, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.177, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.815450643776824, | |
| "grad_norm": 10.37423038482666, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.3284, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.88412017167382, | |
| "grad_norm": 10.795289993286133, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8375, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.9527896995708156, | |
| "grad_norm": 12.411961555480957, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.6438, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.055793991416309, | |
| "grad_norm": 11.045405387878418, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.1393, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.124463519313305, | |
| "grad_norm": 10.357391357421875, | |
| "learning_rate": 0.0, | |
| "loss": 3.022, | |
| "step": 44 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 44, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3416725626997965e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |