| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 100, |
| "global_step": 159, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19002375296912113, |
| "grad_norm": 5.556333065032959, |
| "learning_rate": 0.00018, |
| "loss": 4.516594696044922, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.38004750593824227, |
| "grad_norm": 1.9194517135620117, |
| "learning_rate": 0.00019820494141215104, |
| "loss": 1.4895127296447754, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5700712589073634, |
| "grad_norm": 1.003708839416504, |
| "learning_rate": 0.0001920824925271838, |
| "loss": 0.42693090438842773, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7600950118764845, |
| "grad_norm": 1.177113652229309, |
| "learning_rate": 0.00018188159710183594, |
| "loss": 0.2363497018814087, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9501187648456056, |
| "grad_norm": 0.5659796595573425, |
| "learning_rate": 0.0001680540653066891, |
| "loss": 0.171442973613739, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1330166270783848, |
| "grad_norm": 0.5620031952857971, |
| "learning_rate": 0.0001512123354854955, |
| "loss": 0.15620554685592652, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.323040380047506, |
| "grad_norm": 0.4540189206600189, |
| "learning_rate": 0.00013210234850972964, |
| "loss": 0.13376399278640747, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.513064133016627, |
| "grad_norm": 0.4047989845275879, |
| "learning_rate": 0.00011157050914243614, |
| "loss": 0.11679037809371948, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.7030878859857483, |
| "grad_norm": 0.38902565836906433, |
| "learning_rate": 9.052619773309317e-05, |
| "loss": 0.11565744876861572, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.8931116389548692, |
| "grad_norm": 0.4528644382953644, |
| "learning_rate": 6.990149264650814e-05, |
| "loss": 0.11005499362945556, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.8931116389548692, |
| "eval_loss": 0.1124533861875534, |
| "eval_runtime": 12.5112, |
| "eval_samples_per_second": 9.432, |
| "eval_steps_per_second": 9.432, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0760095011876483, |
| "grad_norm": 0.3278907239437103, |
| "learning_rate": 5.060988736877366e-05, |
| "loss": 0.10198745727539063, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.2660332541567696, |
| "grad_norm": 0.4620839059352875, |
| "learning_rate": 3.350583076029754e-05, |
| "loss": 0.09897915124893189, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.456057007125891, |
| "grad_norm": 0.3941669166088104, |
| "learning_rate": 1.9346882467727325e-05, |
| "loss": 0.10215861797332763, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.646080760095012, |
| "grad_norm": 0.38904374837875366, |
| "learning_rate": 8.760159677994172e-06, |
| "loss": 0.08814923763275147, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.836104513064133, |
| "grad_norm": 0.3930354416370392, |
| "learning_rate": 2.2145613288957478e-06, |
| "loss": 0.10469788312911987, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.10577099025249481, |
| "eval_runtime": 12.6349, |
| "eval_samples_per_second": 9.339, |
| "eval_steps_per_second": 9.339, |
| "step": 159 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 159, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 323706770095104.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
