| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05326231691078562, | |
| "eval_steps": 10, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002663115845539281, | |
| "eval_loss": 11.093616485595703, | |
| "eval_runtime": 2.2631, | |
| "eval_samples_per_second": 70.258, | |
| "eval_steps_per_second": 35.35, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02663115845539281, | |
| "grad_norm": 0.8405465483665466, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3673, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02663115845539281, | |
| "eval_loss": 11.091691017150879, | |
| "eval_runtime": 1.0742, | |
| "eval_samples_per_second": 148.011, | |
| "eval_steps_per_second": 74.471, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05326231691078562, | |
| "grad_norm": 1.1728761196136475, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 44.3899, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05326231691078562, | |
| "eval_loss": 11.089601516723633, | |
| "eval_runtime": 1.0747, | |
| "eval_samples_per_second": 147.954, | |
| "eval_steps_per_second": 74.442, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "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": 29324083200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |