| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0989010989010989, |
| "eval_steps": 500, |
| "global_step": 15, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.0287306308746338, |
| "learning_rate": 0.0, |
| "loss": 1.084, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 0.948112428188324, |
| "learning_rate": 9.56e-05, |
| "loss": 1.0638, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.0350998640060425, |
| "learning_rate": 0.0001912, |
| "loss": 1.143, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.1360750198364258, |
| "learning_rate": 0.0002868, |
| "loss": 1.0394, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.7310333251953125, |
| "learning_rate": 0.0003824, |
| "loss": 0.8949, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.6246419548988342, |
| "learning_rate": 0.000478, |
| "loss": 0.9157, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5591331720352173, |
| "learning_rate": 0.00047694013303769406, |
| "loss": 0.9064, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.411284863948822, |
| "learning_rate": 0.00047588026607538804, |
| "loss": 0.8349, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.30876654386520386, |
| "learning_rate": 0.0004748203991130821, |
| "loss": 0.8626, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.39697328209877014, |
| "learning_rate": 0.00047376053215077607, |
| "loss": 0.8347, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.3990109860897064, |
| "learning_rate": 0.00047270066518847006, |
| "loss": 0.8383, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.3827734589576721, |
| "learning_rate": 0.0004716407982261641, |
| "loss": 0.7593, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.5764995217323303, |
| "learning_rate": 0.00047058093126385814, |
| "loss": 0.7725, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.5014582276344299, |
| "learning_rate": 0.0004695210643015521, |
| "loss": 0.7577, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.4466342628002167, |
| "learning_rate": 0.00046846119733924617, |
| "loss": 0.7279, |
| "step": 15 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6875754313494528.0, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
