| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.22598870056497175, | |
| "eval_steps": 10, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 6.134562969207764, | |
| "learning_rate": 1.9090909090909094e-05, | |
| "loss": 10.8188, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 6.219421863555908, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 10.7835, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 6.437071800231934, | |
| "learning_rate": 1.7272727272727274e-05, | |
| "loss": 10.7424, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 6.489596843719482, | |
| "learning_rate": 1.6363636363636366e-05, | |
| "loss": 10.6919, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 6.816253185272217, | |
| "learning_rate": 1.5454545454545454e-05, | |
| "loss": 10.631, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "eval_loss": 10.573423385620117, | |
| "eval_runtime": 557.6088, | |
| "eval_samples_per_second": 2.252, | |
| "eval_steps_per_second": 0.072, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 44, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.201094396982067e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |