| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0006897657727877056, |
| "eval_steps": 500, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00013795315455754112, |
| "grad_norm": 53.4421272277832, |
| "learning_rate": 4.1999999999999995e-07, |
| "loss": 8.6569, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00027590630911508224, |
| "grad_norm": 57.65703582763672, |
| "learning_rate": 1.0199999999999998e-06, |
| "loss": 8.6391, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0004138594636726234, |
| "grad_norm": 93.79612731933594, |
| "learning_rate": 1.62e-06, |
| "loss": 8.6097, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0005518126182301645, |
| "grad_norm": 133.8379669189453, |
| "learning_rate": 2.22e-06, |
| "loss": 8.5995, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0006897657727877056, |
| "grad_norm": 99.24571228027344, |
| "learning_rate": 2.8199999999999997e-06, |
| "loss": 8.5699, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0008277189273452468, |
| "grad_norm": 155.49118041992188, |
| "learning_rate": 3.42e-06, |
| "loss": 8.5516, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0009656720819027878, |
| "grad_norm": 118.79692840576172, |
| "learning_rate": 4.02e-06, |
| "loss": 8.5331, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.001103625236460329, |
| "grad_norm": 88.51729583740234, |
| "learning_rate": 4.62e-06, |
| "loss": 8.5212, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0012415783910178701, |
| "grad_norm": 117.01810455322266, |
| "learning_rate": 5.219999999999999e-06, |
| "loss": 8.5007, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.0013795315455754113, |
| "grad_norm": 104.06542205810547, |
| "learning_rate": 5.819999999999999e-06, |
| "loss": 8.4948, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0015174847001329524, |
| "grad_norm": 103.02165985107422, |
| "learning_rate": 6.4199999999999995e-06, |
| "loss": 8.4871, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.0016554378546904936, |
| "grad_norm": 119.96959686279297, |
| "learning_rate": 7.02e-06, |
| "loss": 8.4803, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0017933910092480345, |
| "grad_norm": 83.34615325927734, |
| "learning_rate": 7.619999999999999e-06, |
| "loss": 8.471, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.0019313441638055756, |
| "grad_norm": 76.37083435058594, |
| "learning_rate": 8.22e-06, |
| "loss": 8.4655, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.002069297318363117, |
| "grad_norm": 82.49830627441406, |
| "learning_rate": 8.819999999999999e-06, |
| "loss": 8.4708, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.002207250472920658, |
| "grad_norm": 69.70299530029297, |
| "learning_rate": 9.419999999999998e-06, |
| "loss": 8.4659, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.0023452036274781993, |
| "grad_norm": 103.55642700195312, |
| "learning_rate": 1.0019999999999999e-05, |
| "loss": 8.4555, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.0024831567820357402, |
| "grad_norm": 112.4985122680664, |
| "learning_rate": 1.062e-05, |
| "loss": 8.4629, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.002621109936593281, |
| "grad_norm": 78.48297882080078, |
| "learning_rate": 1.122e-05, |
| "loss": 8.4562, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.0027590630911508225, |
| "grad_norm": 87.78710174560547, |
| "learning_rate": 1.1819999999999999e-05, |
| "loss": 8.451, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.448828863938528e-05, |
| "grad_norm": 34.83774948120117, |
| "learning_rate": 1.2419999999999998e-05, |
| "loss": 8.4432, |
| "step": 210 |
| }, |
| { |
| "epoch": 6.897657727877056e-05, |
| "grad_norm": 68.05087280273438, |
| "learning_rate": 1.3019999999999999e-05, |
| "loss": 8.4542, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.00010346486591815585, |
| "grad_norm": 46.86287307739258, |
| "learning_rate": 1.362e-05, |
| "loss": 8.4622, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.00013795315455754112, |
| "grad_norm": 38.558746337890625, |
| "learning_rate": 1.4219999999999998e-05, |
| "loss": 8.4458, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.0001724414431969264, |
| "grad_norm": 38.49115753173828, |
| "learning_rate": 1.4819999999999999e-05, |
| "loss": 8.4495, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.0002069297318363117, |
| "grad_norm": 29.765907287597656, |
| "learning_rate": 1.5419999999999998e-05, |
| "loss": 8.464, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.00024141802047569696, |
| "grad_norm": 48.3050537109375, |
| "learning_rate": 1.602e-05, |
| "loss": 8.4601, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.00027590630911508224, |
| "grad_norm": 27.089998245239258, |
| "learning_rate": 1.6619999999999997e-05, |
| "loss": 8.4628, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.00031039459775446753, |
| "grad_norm": 36.98786163330078, |
| "learning_rate": 1.7219999999999998e-05, |
| "loss": 8.4364, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.0003448828863938528, |
| "grad_norm": 39.274784088134766, |
| "learning_rate": 1.782e-05, |
| "loss": 8.4314, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.0003793711750332381, |
| "grad_norm": 29.303476333618164, |
| "learning_rate": 1.842e-05, |
| "loss": 8.4153, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.0004138594636726234, |
| "grad_norm": 24.435274124145508, |
| "learning_rate": 1.9019999999999997e-05, |
| "loss": 8.4489, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.0004483477523120086, |
| "grad_norm": 25.8426456451416, |
| "learning_rate": 1.962e-05, |
| "loss": 8.4297, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.0004828360409513939, |
| "grad_norm": 24.164419174194336, |
| "learning_rate": 2.022e-05, |
| "loss": 8.4398, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.0005173243295907793, |
| "grad_norm": 17.73716163635254, |
| "learning_rate": 2.082e-05, |
| "loss": 8.4333, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.0005518126182301645, |
| "grad_norm": 34.02337646484375, |
| "learning_rate": 2.1419999999999998e-05, |
| "loss": 8.4488, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.0005863009068695498, |
| "grad_norm": 26.535123825073242, |
| "learning_rate": 2.202e-05, |
| "loss": 8.4361, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.0006207891955089351, |
| "grad_norm": 32.27824783325195, |
| "learning_rate": 2.2619999999999997e-05, |
| "loss": 8.4116, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.0006552774841483203, |
| "grad_norm": 20.55720329284668, |
| "learning_rate": 2.3219999999999998e-05, |
| "loss": 8.4151, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.0006897657727877056, |
| "grad_norm": 30.87930679321289, |
| "learning_rate": 2.382e-05, |
| "loss": 8.43, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 10000000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 35, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3845245063495680.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
