| { | |
| "best_metric": 1.2975215911865234, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/gemma-2-9b_magiccoder_ortho/checkpoint-4", | |
| "epoch": 0.026130448096356028, | |
| "eval_steps": 4, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006532612024089007, | |
| "grad_norm": 5.831324577331543, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.3342, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013065224048178014, | |
| "grad_norm": 5.2910685539245605, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2199, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026130448096356028, | |
| "grad_norm": 3.488215684890747, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2682, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026130448096356028, | |
| "eval_loss": 1.2975215911865234, | |
| "eval_runtime": 866.0894, | |
| "eval_samples_per_second": 0.565, | |
| "eval_steps_per_second": 0.565, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 153, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8159435195842560.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |