| { |
| "best_global_step": 120, |
| "best_metric": 0.7121169378526554, |
| "best_model_checkpoint": "/content/gemma_lora_imb/checkpoint-120", |
| "epoch": 1.912, |
| "eval_steps": 20, |
| "global_step": 120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32, |
| "grad_norm": 428.16009521484375, |
| "learning_rate": 8.492063492063492e-06, |
| "loss": 10.2541, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_f1_macro": 0.30367703103162375, |
| "eval_loss": 2.0160138607025146, |
| "eval_runtime": 42.6744, |
| "eval_samples_per_second": 46.867, |
| "eval_steps_per_second": 5.858, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 46.26844024658203, |
| "learning_rate": 6.9047619047619055e-06, |
| "loss": 5.1249, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_f1_macro": 0.48650808108472904, |
| "eval_loss": 1.5075854063034058, |
| "eval_runtime": 42.3883, |
| "eval_samples_per_second": 47.183, |
| "eval_steps_per_second": 5.898, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 684.8424072265625, |
| "learning_rate": 5.317460317460318e-06, |
| "loss": 3.7901, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_f1_macro": 0.5956481908520431, |
| "eval_loss": 1.541353702545166, |
| "eval_runtime": 42.505, |
| "eval_samples_per_second": 47.053, |
| "eval_steps_per_second": 5.882, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.272, |
| "grad_norm": 23.575862884521484, |
| "learning_rate": 3.7301587301587305e-06, |
| "loss": 1.4486, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.272, |
| "eval_f1_macro": 0.6662347432713018, |
| "eval_loss": 1.373887062072754, |
| "eval_runtime": 42.5186, |
| "eval_samples_per_second": 47.038, |
| "eval_steps_per_second": 5.88, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.592, |
| "grad_norm": 40.776390075683594, |
| "learning_rate": 2.1428571428571427e-06, |
| "loss": 1.6294, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.592, |
| "eval_f1_macro": 0.7040549462194111, |
| "eval_loss": 0.9468446373939514, |
| "eval_runtime": 42.5061, |
| "eval_samples_per_second": 47.052, |
| "eval_steps_per_second": 5.882, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.912, |
| "grad_norm": 30.759462356567383, |
| "learning_rate": 5.555555555555555e-07, |
| "loss": 1.054, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.912, |
| "eval_f1_macro": 0.7121169378526554, |
| "eval_loss": 0.9425287246704102, |
| "eval_runtime": 42.6742, |
| "eval_samples_per_second": 46.867, |
| "eval_steps_per_second": 5.858, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 126, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 20, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.9149081621848064e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
