| { |
| "best_global_step": 120, |
| "best_metric": 0.776326044440457, |
| "best_model_checkpoint": "/content/gemma_lora_imb/checkpoint-120", |
| "epoch": 1.9047619047619047, |
| "eval_steps": 20, |
| "global_step": 120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.31746031746031744, |
| "grad_norm": 11.7665376663208, |
| "learning_rate": 8.492063492063492e-06, |
| "loss": 0.3174, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.31746031746031744, |
| "eval_f1_macro": 0.6737641320228203, |
| "eval_loss": 0.928208589553833, |
| "eval_runtime": 38.1398, |
| "eval_samples_per_second": 52.439, |
| "eval_steps_per_second": 1.652, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6349206349206349, |
| "grad_norm": 4.18451452255249, |
| "learning_rate": 6.9047619047619055e-06, |
| "loss": 0.3193, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6349206349206349, |
| "eval_f1_macro": 0.7107737640945189, |
| "eval_loss": 0.6456462144851685, |
| "eval_runtime": 38.1401, |
| "eval_samples_per_second": 52.438, |
| "eval_steps_per_second": 1.652, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 32.706443786621094, |
| "learning_rate": 5.317460317460318e-06, |
| "loss": 0.2606, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "eval_f1_macro": 0.7456057615525826, |
| "eval_loss": 0.8317409157752991, |
| "eval_runtime": 38.1406, |
| "eval_samples_per_second": 52.438, |
| "eval_steps_per_second": 1.652, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "grad_norm": 4.3210954666137695, |
| "learning_rate": 3.7301587301587305e-06, |
| "loss": 0.1377, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2698412698412698, |
| "eval_f1_macro": 0.7713330490242807, |
| "eval_loss": 0.807384192943573, |
| "eval_runtime": 38.1576, |
| "eval_samples_per_second": 52.414, |
| "eval_steps_per_second": 1.651, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.5873015873015874, |
| "grad_norm": 5.902767658233643, |
| "learning_rate": 2.1428571428571427e-06, |
| "loss": 0.1266, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5873015873015874, |
| "eval_f1_macro": 0.7761022946562621, |
| "eval_loss": 0.8588651418685913, |
| "eval_runtime": 38.1597, |
| "eval_samples_per_second": 52.411, |
| "eval_steps_per_second": 1.651, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 4.348827838897705, |
| "learning_rate": 5.555555555555555e-07, |
| "loss": 0.1091, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "eval_f1_macro": 0.776326044440457, |
| "eval_loss": 0.8794072270393372, |
| "eval_runtime": 38.1823, |
| "eval_samples_per_second": 52.38, |
| "eval_steps_per_second": 1.65, |
| "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": 2.4825056756023296e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
