{ "best_metric": 1.9893906116485596, "best_model_checkpoint": "/home/datta0/models/lora_final/Qwen2-7B_pct_ortho/checkpoint-16", "epoch": 0.041223832528180356, "eval_steps": 8, "global_step": 16, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0025764895330112722, "grad_norm": 3.2372000217437744, "learning_rate": 3.75e-05, "loss": 2.0292, "step": 1 }, { "epoch": 0.010305958132045089, "grad_norm": 2.4374635219573975, "learning_rate": 0.00015, "loss": 2.1277, "step": 4 }, { "epoch": 0.020611916264090178, "grad_norm": 2.3065264225006104, "learning_rate": 0.0003, "loss": 2.0836, "step": 8 }, { "epoch": 0.020611916264090178, "eval_loss": 1.999721884727478, "eval_runtime": 10.3706, "eval_samples_per_second": 23.624, "eval_steps_per_second": 2.989, "step": 8 }, { "epoch": 0.030917874396135265, "grad_norm": 2.9390103816986084, "learning_rate": 0.0002999179886011389, "loss": 2.0317, "step": 12 }, { "epoch": 0.041223832528180356, "grad_norm": 1.5938222408294678, "learning_rate": 0.00029967204408281613, "loss": 2.0451, "step": 16 }, { "epoch": 0.041223832528180356, "eval_loss": 1.9893906116485596, "eval_runtime": 10.3682, "eval_samples_per_second": 23.63, "eval_steps_per_second": 2.99, "step": 16 } ], "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": 3.571587033838387e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }