| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.898630136986302, |
| "eval_steps": 500, |
| "global_step": 910, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.547945205479452, |
| "grad_norm": 0.4419728254622205, |
| "learning_rate": 1.8901098901098903e-05, |
| "loss": 0.4435, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0876712328767124, |
| "grad_norm": 0.32201065756982106, |
| "learning_rate": 1.78021978021978e-05, |
| "loss": 0.2104, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.6356164383561644, |
| "grad_norm": 0.2985293144484945, |
| "learning_rate": 1.6703296703296707e-05, |
| "loss": 0.2011, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.175342465753425, |
| "grad_norm": 0.34399102747123644, |
| "learning_rate": 1.5604395604395605e-05, |
| "loss": 0.192, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.723287671232877, |
| "grad_norm": 0.28920255662304967, |
| "learning_rate": 1.4505494505494506e-05, |
| "loss": 0.1907, |
| "step": 250 |
| }, |
| { |
| "epoch": 3.263013698630137, |
| "grad_norm": 0.26702054394627195, |
| "learning_rate": 1.3406593406593406e-05, |
| "loss": 0.1824, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.8109589041095893, |
| "grad_norm": 0.22841140853841602, |
| "learning_rate": 1.230769230769231e-05, |
| "loss": 0.1819, |
| "step": 350 |
| }, |
| { |
| "epoch": 4.35068493150685, |
| "grad_norm": 0.2504018090512457, |
| "learning_rate": 1.120879120879121e-05, |
| "loss": 0.1712, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.898630136986301, |
| "grad_norm": 0.25310890542066394, |
| "learning_rate": 1.010989010989011e-05, |
| "loss": 0.1706, |
| "step": 450 |
| }, |
| { |
| "epoch": 5.438356164383562, |
| "grad_norm": 0.2361372173039559, |
| "learning_rate": 9.010989010989011e-06, |
| "loss": 0.153, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.986301369863014, |
| "grad_norm": 0.26896163098008974, |
| "learning_rate": 7.912087912087913e-06, |
| "loss": 0.1532, |
| "step": 550 |
| }, |
| { |
| "epoch": 6.526027397260274, |
| "grad_norm": 0.26405789354113157, |
| "learning_rate": 6.813186813186814e-06, |
| "loss": 0.1247, |
| "step": 600 |
| }, |
| { |
| "epoch": 7.065753424657534, |
| "grad_norm": 0.3233628498608289, |
| "learning_rate": 5.7142857142857145e-06, |
| "loss": 0.1218, |
| "step": 650 |
| }, |
| { |
| "epoch": 7.6136986301369864, |
| "grad_norm": 0.26924992027516265, |
| "learning_rate": 4.615384615384616e-06, |
| "loss": 0.0973, |
| "step": 700 |
| }, |
| { |
| "epoch": 8.153424657534247, |
| "grad_norm": 0.303885526953347, |
| "learning_rate": 3.516483516483517e-06, |
| "loss": 0.0893, |
| "step": 750 |
| }, |
| { |
| "epoch": 8.7013698630137, |
| "grad_norm": 0.2704864542586799, |
| "learning_rate": 2.4175824175824177e-06, |
| "loss": 0.072, |
| "step": 800 |
| }, |
| { |
| "epoch": 9.241095890410959, |
| "grad_norm": 0.2547602295282673, |
| "learning_rate": 1.3186813186813187e-06, |
| "loss": 0.0637, |
| "step": 850 |
| }, |
| { |
| "epoch": 9.789041095890411, |
| "grad_norm": 0.24108696753483977, |
| "learning_rate": 2.197802197802198e-07, |
| "loss": 0.055, |
| "step": 900 |
| }, |
| { |
| "epoch": 9.898630136986302, |
| "step": 910, |
| "total_flos": 5364179649167360.0, |
| "train_loss": 0.15849283992589175, |
| "train_runtime": 52896.6339, |
| "train_samples_per_second": 6.617, |
| "train_steps_per_second": 0.017 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 910, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5364179649167360.0, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
