| { |
| "best_global_step": 600, |
| "best_metric": 2.494161605834961, |
| "best_model_checkpoint": "business_qa_flan_t5_xl_rope_LoRA_model/checkpoint-600", |
| "epoch": 0.8300907911802854, |
| "eval_steps": 200, |
| "global_step": 600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06917423259835712, |
| "grad_norm": 1.7663676738739014, |
| "learning_rate": 9.3875e-05, |
| "loss": 7.0007, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13834846519671423, |
| "grad_norm": 1.1584688425064087, |
| "learning_rate": 8.7625e-05, |
| "loss": 4.2926, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.20752269779507135, |
| "grad_norm": 1.6167352199554443, |
| "learning_rate": 8.1375e-05, |
| "loss": 3.5178, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.27669693039342846, |
| "grad_norm": 1.4269593954086304, |
| "learning_rate": 7.5125e-05, |
| "loss": 3.2704, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.27669693039342846, |
| "eval_loss": 2.961073637008667, |
| "eval_runtime": 534.2317, |
| "eval_samples_per_second": 2.405, |
| "eval_steps_per_second": 0.603, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.34587116299178555, |
| "grad_norm": 1.6946117877960205, |
| "learning_rate": 6.887500000000001e-05, |
| "loss": 3.0671, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4150453955901427, |
| "grad_norm": 1.938078761100769, |
| "learning_rate": 6.2625e-05, |
| "loss": 2.9921, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.4842196281884998, |
| "grad_norm": 2.3420886993408203, |
| "learning_rate": 5.6375e-05, |
| "loss": 2.9324, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.5533938607868569, |
| "grad_norm": 2.5413014888763428, |
| "learning_rate": 5.0125e-05, |
| "loss": 2.8571, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.5533938607868569, |
| "eval_loss": 2.6418941020965576, |
| "eval_runtime": 531.7902, |
| "eval_samples_per_second": 2.416, |
| "eval_steps_per_second": 0.606, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.622568093385214, |
| "grad_norm": 2.8039212226867676, |
| "learning_rate": 4.3875e-05, |
| "loss": 2.7732, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.6917423259835711, |
| "grad_norm": 2.8921995162963867, |
| "learning_rate": 3.7625e-05, |
| "loss": 2.7173, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7609165585819282, |
| "grad_norm": 3.0461184978485107, |
| "learning_rate": 3.1375e-05, |
| "loss": 2.6135, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.8300907911802854, |
| "grad_norm": 3.964676856994629, |
| "learning_rate": 2.5124999999999997e-05, |
| "loss": 2.6357, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.8300907911802854, |
| "eval_loss": 2.494161605834961, |
| "eval_runtime": 532.8559, |
| "eval_samples_per_second": 2.412, |
| "eval_steps_per_second": 0.604, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 800, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.23805463232512e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
