| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 23.125, |
| "learning_rate": 9.999720532505307e-06, |
| "loss": 3.9396, |
| "step": 5 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 5.53125, |
| "learning_rate": 9.989933460019529e-06, |
| "loss": 2.9301, |
| "step": 10 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.375, |
| "learning_rate": 9.966191100829747e-06, |
| "loss": 2.6483, |
| "step": 15 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 3.109375, |
| "learning_rate": 9.928561667038593e-06, |
| "loss": 2.4924, |
| "step": 20 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.765625, |
| "learning_rate": 9.877148841042072e-06, |
| "loss": 2.3702, |
| "step": 25 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 2.625, |
| "learning_rate": 9.812096323003061e-06, |
| "loss": 2.2763, |
| "step": 30 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 2.40625, |
| "learning_rate": 9.733586921356618e-06, |
| "loss": 2.1906, |
| "step": 35 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 2.515625, |
| "learning_rate": 9.64183982432587e-06, |
| "loss": 2.1209, |
| "step": 40 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 2.4375, |
| "learning_rate": 9.537110599922016e-06, |
| "loss": 2.0431, |
| "step": 45 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 2.34375, |
| "learning_rate": 9.41969392442843e-06, |
| "loss": 1.9812, |
| "step": 50 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 2.546875, |
| "learning_rate": 9.289917215937749e-06, |
| "loss": 1.9225, |
| "step": 55 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 2.390625, |
| "learning_rate": 9.14814245334128e-06, |
| "loss": 1.8593, |
| "step": 60 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 2.6875, |
| "learning_rate": 8.994767995318398e-06, |
| "loss": 1.8079, |
| "step": 65 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 2.84375, |
| "learning_rate": 8.83022221387364e-06, |
| "loss": 1.7686, |
| "step": 70 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 2.84375, |
| "learning_rate": 8.6549644038314e-06, |
| "loss": 1.7096, |
| "step": 75 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 2.65625, |
| "learning_rate": 8.469485692330636e-06, |
| "loss": 1.6636, |
| "step": 80 |
| }, |
| { |
| "epoch": 17.0, |
| "grad_norm": 3.140625, |
| "learning_rate": 8.274303581856657e-06, |
| "loss": 1.6169, |
| "step": 85 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 3.046875, |
| "learning_rate": 8.069964678725228e-06, |
| "loss": 1.5839, |
| "step": 90 |
| }, |
| { |
| "epoch": 19.0, |
| "grad_norm": 2.9375, |
| "learning_rate": 7.857041055103764e-06, |
| "loss": 1.5409, |
| "step": 95 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 3.25, |
| "learning_rate": 7.636127520527225e-06, |
| "loss": 1.5052, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 60, |
| "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": 2.0371004719104e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
