| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029787392486130245, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005957478497226049, | |
| "grad_norm": 1.9316656589508057, | |
| "learning_rate": 1e-05, | |
| "loss": 177.1875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005957478497226049, | |
| "eval_loss": 11.074080467224121, | |
| "eval_runtime": 17.4986, | |
| "eval_samples_per_second": 161.613, | |
| "eval_steps_per_second": 80.806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011914956994452097, | |
| "grad_norm": 1.9285756349563599, | |
| "learning_rate": 2e-05, | |
| "loss": 177.25, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011914956994452097, | |
| "eval_loss": 11.073904037475586, | |
| "eval_runtime": 7.5533, | |
| "eval_samples_per_second": 374.404, | |
| "eval_steps_per_second": 187.202, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017872435491678147, | |
| "grad_norm": 2.136760711669922, | |
| "learning_rate": 3e-05, | |
| "loss": 177.25, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023829913988904195, | |
| "grad_norm": 2.0848324298858643, | |
| "learning_rate": 4e-05, | |
| "loss": 177.3125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023829913988904195, | |
| "eval_loss": 11.073328971862793, | |
| "eval_runtime": 7.773, | |
| "eval_samples_per_second": 363.823, | |
| "eval_steps_per_second": 181.911, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0029787392486130245, | |
| "grad_norm": 1.994558572769165, | |
| "learning_rate": 5e-05, | |
| "loss": 177.3125, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 29324083200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |