| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006434661375945091, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021448871253150302, | |
| "grad_norm": Infinity, | |
| "learning_rate": 0.0, | |
| "loss": 11.14, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021448871253150302, | |
| "eval_loss": 11.310040473937988, | |
| "eval_runtime": 238.0023, | |
| "eval_samples_per_second": 4.126, | |
| "eval_steps_per_second": 4.126, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042897742506300604, | |
| "grad_norm": 63.52291488647461, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7604, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006434661375945091, | |
| "grad_norm": 71.64099884033203, | |
| "learning_rate": 4e-05, | |
| "loss": 13.3246, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006434661375945091, | |
| "eval_loss": 8.893160820007324, | |
| "eval_runtime": 231.8354, | |
| "eval_samples_per_second": 4.236, | |
| "eval_steps_per_second": 4.236, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2300683084627968.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |