| { | |
| "best_metric": 3.0729734897613525, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/gemma-2-9b_pct_reverse/checkpoint-8", | |
| "epoch": 0.020603621730382295, | |
| "eval_steps": 8, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002575452716297787, | |
| "grad_norm": 10.251696586608887, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2.1764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010301810865191148, | |
| "grad_norm": 8.478413581848145, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2413, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020603621730382295, | |
| "grad_norm": 7.021224021911621, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3931, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020603621730382295, | |
| "eval_loss": 3.0729734897613525, | |
| "eval_runtime": 708.7312, | |
| "eval_samples_per_second": 0.346, | |
| "eval_steps_per_second": 0.346, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 388, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2054397461528576e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |