| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11835194910866188, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00011835194910866188, |
| "grad_norm": 3.050483226776123, |
| "learning_rate": 0.001, |
| "loss": 11.2196, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.011835194910866188, |
| "grad_norm": 0.38660958409309387, |
| "learning_rate": 0.001, |
| "loss": 7.187, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.023670389821732377, |
| "grad_norm": 0.9350159764289856, |
| "learning_rate": 0.001, |
| "loss": 6.1386, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.035505584732598565, |
| "grad_norm": 0.8646043539047241, |
| "learning_rate": 0.001, |
| "loss": 5.8031, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.04734077964346475, |
| "grad_norm": 0.6667220592498779, |
| "learning_rate": 0.001, |
| "loss": 5.5641, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.05917597455433094, |
| "grad_norm": 0.2509143352508545, |
| "learning_rate": 0.001, |
| "loss": 5.3996, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.07101116946519713, |
| "grad_norm": 0.6340625882148743, |
| "learning_rate": 0.001, |
| "loss": 5.2767, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.08284636437606333, |
| "grad_norm": 0.7510167360305786, |
| "learning_rate": 0.001, |
| "loss": 5.1776, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.0946815592869295, |
| "grad_norm": 0.992080569267273, |
| "learning_rate": 0.001, |
| "loss": 5.1006, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.1065167541977957, |
| "grad_norm": 0.45446252822875977, |
| "learning_rate": 0.001, |
| "loss": 5.0384, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.11835194910866188, |
| "grad_norm": 0.5121697783470154, |
| "learning_rate": 0.001, |
| "loss": 4.9803, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 30000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.2154567139328e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
