| { |
| "best_global_step": 80, |
| "best_metric": 0.6859903381642513, |
| "best_model_checkpoint": "/content/gemma_lora_imb/checkpoint-80", |
| "epoch": 1.5686274509803921, |
| "eval_steps": 20, |
| "global_step": 80, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.39215686274509803, |
| "grad_norm": 24.230987548828125, |
| "learning_rate": 8.137254901960784e-06, |
| "loss": 1.1665, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.39215686274509803, |
| "eval_accuracy": 0.6206896551724138, |
| "eval_f1": 0.631578947368421, |
| "eval_loss": 1.0547616481781006, |
| "eval_runtime": 34.5129, |
| "eval_samples_per_second": 5.882, |
| "eval_steps_per_second": 0.203, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "grad_norm": 26.34092140197754, |
| "learning_rate": 6.176470588235295e-06, |
| "loss": 0.8846, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "eval_accuracy": 0.6551724137931034, |
| "eval_f1": 0.6634615384615384, |
| "eval_loss": 0.8848929405212402, |
| "eval_runtime": 34.4309, |
| "eval_samples_per_second": 5.896, |
| "eval_steps_per_second": 0.203, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "grad_norm": 28.944477081298828, |
| "learning_rate": 4.215686274509805e-06, |
| "loss": 0.5412, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "eval_accuracy": 0.6699507389162561, |
| "eval_f1": 0.6824644549763034, |
| "eval_loss": 0.8630681037902832, |
| "eval_runtime": 34.3671, |
| "eval_samples_per_second": 5.907, |
| "eval_steps_per_second": 0.204, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.5686274509803921, |
| "grad_norm": 14.226760864257812, |
| "learning_rate": 2.254901960784314e-06, |
| "loss": 0.3088, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.5686274509803921, |
| "eval_accuracy": 0.6798029556650246, |
| "eval_f1": 0.6859903381642513, |
| "eval_loss": 0.8230202794075012, |
| "eval_runtime": 34.5725, |
| "eval_samples_per_second": 5.872, |
| "eval_steps_per_second": 0.202, |
| "step": 80 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 102, |
| "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": 4553569010414592.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
