| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07628128724672228, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01907032181168057, | |
| "grad_norm": 17.408676147460938, | |
| "learning_rate": 1e-05, | |
| "loss": 13.2765, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01907032181168057, | |
| "eval_loss": 12.390375137329102, | |
| "eval_runtime": 167.2038, | |
| "eval_samples_per_second": 0.532, | |
| "eval_steps_per_second": 0.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03814064362336114, | |
| "grad_norm": 15.963851928710938, | |
| "learning_rate": 2e-05, | |
| "loss": 12.6336, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03814064362336114, | |
| "eval_loss": 12.248507499694824, | |
| "eval_runtime": 4.8663, | |
| "eval_samples_per_second": 18.289, | |
| "eval_steps_per_second": 9.247, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.057210965435041714, | |
| "grad_norm": 15.161690711975098, | |
| "learning_rate": 3e-05, | |
| "loss": 11.5296, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07628128724672228, | |
| "grad_norm": 15.897518157958984, | |
| "learning_rate": 4e-05, | |
| "loss": 12.4851, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07628128724672228, | |
| "eval_loss": 11.501535415649414, | |
| "eval_runtime": 4.8969, | |
| "eval_samples_per_second": 18.175, | |
| "eval_steps_per_second": 9.189, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6567659575443456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |