| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.855072463768116, | |
| "eval_steps": 500, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 29.182724034782854, | |
| "learning_rate": 4.914814565722671e-06, | |
| "loss": 1.4301, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.7729468599033816, | |
| "grad_norm": 2.742323067740987, | |
| "learning_rate": 3.147047612756302e-06, | |
| "loss": 0.5293, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5458937198067633, | |
| "grad_norm": 0.7457303031419668, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.2848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.855072463768116, | |
| "step": 12, | |
| "total_flos": 5888847904768.0, | |
| "train_loss": 0.45293335368235904, | |
| "train_runtime": 634.502, | |
| "train_samples_per_second": 2.6, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5888847904768.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |