| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 25, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "grad_norm": 11.906526565551758, |
| "learning_rate": 1e-05, |
| "loss": 3.9824, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 10.312734603881836, |
| "learning_rate": 9.960573506572391e-06, |
| "loss": 3.0566, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 8.302469253540039, |
| "learning_rate": 9.842915805643156e-06, |
| "loss": 3.3672, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 6.608037948608398, |
| "learning_rate": 9.648882429441258e-06, |
| "loss": 2.8311, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 14.191883087158203, |
| "learning_rate": 9.381533400219319e-06, |
| "loss": 2.708, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 6.756547927856445, |
| "learning_rate": 9.045084971874738e-06, |
| "loss": 2.3594, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 5.778897762298584, |
| "learning_rate": 8.644843137107058e-06, |
| "loss": 2.4609, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 5.335056304931641, |
| "learning_rate": 8.18711994874345e-06, |
| "loss": 2.0332, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 4.212027549743652, |
| "learning_rate": 7.679133974894984e-06, |
| "loss": 1.8252, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 4.6606645584106445, |
| "learning_rate": 7.128896457825364e-06, |
| "loss": 1.9766, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 5.510636806488037, |
| "learning_rate": 6.545084971874738e-06, |
| "loss": 1.6396, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 5.5493083000183105, |
| "learning_rate": 5.936906572928625e-06, |
| "loss": 1.7842, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 4.463563442230225, |
| "learning_rate": 5.3139525976465675e-06, |
| "loss": 1.8247, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 5.195663928985596, |
| "learning_rate": 4.686047402353433e-06, |
| "loss": 2.0312, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 4.842907428741455, |
| "learning_rate": 4.063093427071376e-06, |
| "loss": 1.8457, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 3.943223714828491, |
| "learning_rate": 3.4549150281252635e-06, |
| "loss": 1.6304, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 4.790521621704102, |
| "learning_rate": 2.871103542174637e-06, |
| "loss": 1.7695, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 4.638957977294922, |
| "learning_rate": 2.320866025105016e-06, |
| "loss": 1.6235, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 5.3421430587768555, |
| "learning_rate": 1.8128800512565514e-06, |
| "loss": 1.6714, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 4.2450408935546875, |
| "learning_rate": 1.3551568628929434e-06, |
| "loss": 1.5586, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 4.925183296203613, |
| "learning_rate": 9.549150281252633e-07, |
| "loss": 1.7876, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 4.280679225921631, |
| "learning_rate": 6.184665997806832e-07, |
| "loss": 1.5791, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 4.112889289855957, |
| "learning_rate": 3.511175705587433e-07, |
| "loss": 1.4775, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 4.36607027053833, |
| "learning_rate": 1.5708419435684463e-07, |
| "loss": 1.6782, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.5276408195495605, |
| "learning_rate": 3.9426493427611177e-08, |
| "loss": 1.248, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.640625, |
| "eval_runtime": 0.557, |
| "eval_samples_per_second": 1.795, |
| "eval_steps_per_second": 1.795, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4039978250141696.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
