| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 22, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.045454545454545456, |
| "grad_norm": 5.410861968994141, |
| "learning_rate": 0.0001989821441880933, |
| "loss": 3.2071, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 4.757542133331299, |
| "learning_rate": 0.00019594929736144976, |
| "loss": 2.8727, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "grad_norm": 6.219588279724121, |
| "learning_rate": 0.00019096319953545185, |
| "loss": 2.9721, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 3.265394687652588, |
| "learning_rate": 0.00018412535328311814, |
| "loss": 2.5661, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "grad_norm": 3.197615146636963, |
| "learning_rate": 0.00017557495743542585, |
| "loss": 2.6573, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 2.695573568344116, |
| "learning_rate": 0.00016548607339452853, |
| "loss": 2.479, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3181818181818182, |
| "grad_norm": 3.21574330329895, |
| "learning_rate": 0.00015406408174555976, |
| "loss": 2.5781, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 2.4235832691192627, |
| "learning_rate": 0.00014154150130018866, |
| "loss": 2.4604, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.4090909090909091, |
| "grad_norm": 2.524172067642212, |
| "learning_rate": 0.00012817325568414297, |
| "loss": 2.3458, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 3.0898048877716064, |
| "learning_rate": 0.00011423148382732853, |
| "loss": 2.3869, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 2.021130084991455, |
| "learning_rate": 0.0001, |
| "loss": 2.2218, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 2.629793882369995, |
| "learning_rate": 8.57685161726715e-05, |
| "loss": 2.3153, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5909090909090909, |
| "grad_norm": 2.5281155109405518, |
| "learning_rate": 7.182674431585704e-05, |
| "loss": 2.2538, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "grad_norm": 2.5038318634033203, |
| "learning_rate": 5.845849869981137e-05, |
| "loss": 2.2725, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6818181818181818, |
| "grad_norm": 2.788825035095215, |
| "learning_rate": 4.593591825444028e-05, |
| "loss": 2.2729, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 2.199079990386963, |
| "learning_rate": 3.45139266054715e-05, |
| "loss": 2.3403, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7727272727272727, |
| "grad_norm": 2.322319984436035, |
| "learning_rate": 2.4425042564574184e-05, |
| "loss": 2.2943, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "grad_norm": 2.321732997894287, |
| "learning_rate": 1.587464671688187e-05, |
| "loss": 2.2358, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8636363636363636, |
| "grad_norm": 2.4514646530151367, |
| "learning_rate": 9.036800464548157e-06, |
| "loss": 2.3498, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 3.0407378673553467, |
| "learning_rate": 4.050702638550275e-06, |
| "loss": 2.349, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9545454545454546, |
| "grad_norm": 2.618478775024414, |
| "learning_rate": 1.0178558119067315e-06, |
| "loss": 2.2082, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.4556992053985596, |
| "learning_rate": 0.0, |
| "loss": 2.316, |
| "step": 22 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 22, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2807061793996800.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
