| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.3250207813798838, | |
| "eval_steps": 2000, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8312551953449709, | |
| "grad_norm": 16.231958389282227, | |
| "learning_rate": 1.584026622296173e-05, | |
| "loss": 2.784, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.6625103906899419, | |
| "grad_norm": 22.48409080505371, | |
| "learning_rate": 1.1680532445923463e-05, | |
| "loss": 1.8476, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.493765586034913, | |
| "grad_norm": 12.915149688720703, | |
| "learning_rate": 7.520798668885192e-06, | |
| "loss": 1.1381, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.3250207813798838, | |
| "grad_norm": 12.136582374572754, | |
| "learning_rate": 3.3610648918469217e-06, | |
| "loss": 0.9397, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.3250207813798838, | |
| "eval_loss": 0.7907648682594299, | |
| "eval_runtime": 93.7355, | |
| "eval_samples_per_second": 15.181, | |
| "eval_steps_per_second": 0.949, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2404, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3863209696980992e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |