| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 0.8233810663223267, |
| "learning_rate": 0.0, |
| "loss": 1.2926392555236816, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.8667462468147278, |
| "learning_rate": 4e-05, |
| "loss": 1.2933003902435303, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 0.9416549205780029, |
| "learning_rate": 8e-05, |
| "loss": 1.2474114894866943, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.9050902724266052, |
| "learning_rate": 0.00012, |
| "loss": 1.0754895210266113, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.6808173060417175, |
| "learning_rate": 0.00016, |
| "loss": 1.2081325054168701, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.7349768280982971, |
| "learning_rate": 0.0002, |
| "loss": 0.9636205434799194, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.1818181818181819, |
| "grad_norm": 0.33241593837738037, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.9576319456100464, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 0.334722101688385, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.9906941056251526, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.5454545454545454, |
| "grad_norm": 0.32507219910621643, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 0.8973167538642883, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.7272727272727273, |
| "grad_norm": 0.3215590715408325, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 0.9241716265678406, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.9090909090909092, |
| "grad_norm": 0.32502657175064087, |
| "learning_rate": 0.0001230769230769231, |
| "loss": 0.8657209277153015, |
| "step": 11 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.4819266200065613, |
| "learning_rate": 0.0001076923076923077, |
| "loss": 0.9260194897651672, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 0.320608526468277, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.7931567430496216, |
| "step": 13 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 0.34196072816848755, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.839251697063446, |
| "step": 14 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 0.3709123432636261, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.9486470818519592, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 0.3574763536453247, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.7083936929702759, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 0.4191477298736572, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.6311583518981934, |
| "step": 17 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.5564912557601929, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.7128921151161194, |
| "step": 18 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 18, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 542381054054400.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
