| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.3957597173144876, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1413427561837456, |
| "grad_norm": 1.3223986625671387, |
| "learning_rate": 4.972077065562821e-05, |
| "loss": 0.5319, |
| "num_input_tokens_seen": 89360, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2826855123674912, |
| "grad_norm": 1.8465224504470825, |
| "learning_rate": 4.888932014465352e-05, |
| "loss": 0.346, |
| "num_input_tokens_seen": 173680, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.42402826855123676, |
| "grad_norm": 2.7824206352233887, |
| "learning_rate": 4.752422169756048e-05, |
| "loss": 0.3586, |
| "num_input_tokens_seen": 256320, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5653710247349824, |
| "grad_norm": 2.0576891899108887, |
| "learning_rate": 4.5655969357899874e-05, |
| "loss": 0.3476, |
| "num_input_tokens_seen": 354080, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7067137809187279, |
| "grad_norm": 2.399836778640747, |
| "learning_rate": 4.332629679574566e-05, |
| "loss": 0.2828, |
| "num_input_tokens_seen": 445120, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.8480565371024735, |
| "grad_norm": 3.21662974357605, |
| "learning_rate": 4.058724504646834e-05, |
| "loss": 0.3261, |
| "num_input_tokens_seen": 536160, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9893992932862191, |
| "grad_norm": 2.1142466068267822, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.1752, |
| "num_input_tokens_seen": 622160, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.1130742049469964, |
| "grad_norm": 2.0932960510253906, |
| "learning_rate": 3.413352560915988e-05, |
| "loss": 0.1521, |
| "num_input_tokens_seen": 702992, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.254416961130742, |
| "grad_norm": 1.1899418830871582, |
| "learning_rate": 3.056302334890786e-05, |
| "loss": 0.1056, |
| "num_input_tokens_seen": 795712, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.3957597173144876, |
| "grad_norm": 1.8297990560531616, |
| "learning_rate": 2.686825233966061e-05, |
| "loss": 0.2243, |
| "num_input_tokens_seen": 880032, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 105, |
| "num_input_tokens_seen": 880032, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3561971226476544.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
