| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.449767685045443e-05, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4832558950151478e-05, | |
| "grad_norm": 1058.962646484375, | |
| "learning_rate": 2e-05, | |
| "loss": 95.6979, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.4832558950151478e-05, | |
| "eval_loss": 23.534069061279297, | |
| "eval_runtime": 2771.2737, | |
| "eval_samples_per_second": 10.243, | |
| "eval_steps_per_second": 5.122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.9665117900302956e-05, | |
| "grad_norm": 1248.5556640625, | |
| "learning_rate": 4e-05, | |
| "loss": 96.301, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.449767685045443e-05, | |
| "grad_norm": 1384.484130859375, | |
| "learning_rate": 6e-05, | |
| "loss": 95.2121, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.449767685045443e-05, | |
| "eval_loss": 23.525821685791016, | |
| "eval_runtime": 2674.4343, | |
| "eval_samples_per_second": 10.614, | |
| "eval_steps_per_second": 5.307, | |
| "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": 26811870216192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |