| { |
| "best_global_step": 80, |
| "best_metric": 0.6729883436736228, |
| "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": 12.482938766479492, |
| "learning_rate": 8.137254901960784e-06, |
| "loss": 1.2092, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.39215686274509803, |
| "eval_f1_macro": 0.49173730322672554, |
| "eval_loss": 0.822236180305481, |
| "eval_runtime": 3.4673, |
| "eval_samples_per_second": 58.546, |
| "eval_steps_per_second": 2.019, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "grad_norm": 34.74234390258789, |
| "learning_rate": 6.176470588235295e-06, |
| "loss": 0.7317, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7843137254901961, |
| "eval_f1_macro": 0.6225186035727692, |
| "eval_loss": 0.7549954056739807, |
| "eval_runtime": 3.4442, |
| "eval_samples_per_second": 58.939, |
| "eval_steps_per_second": 2.032, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "grad_norm": 11.875113487243652, |
| "learning_rate": 4.215686274509805e-06, |
| "loss": 0.5794, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "eval_f1_macro": 0.6456221198156682, |
| "eval_loss": 0.6300039887428284, |
| "eval_runtime": 3.4467, |
| "eval_samples_per_second": 58.897, |
| "eval_steps_per_second": 2.031, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.5686274509803921, |
| "grad_norm": 9.780080795288086, |
| "learning_rate": 2.254901960784314e-06, |
| "loss": 0.4269, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.5686274509803921, |
| "eval_f1_macro": 0.6729883436736228, |
| "eval_loss": 0.6284839510917664, |
| "eval_runtime": 3.4549, |
| "eval_samples_per_second": 58.757, |
| "eval_steps_per_second": 2.026, |
| "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": 1.4138200998448128e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
