| { |
| "best_metric": 0.26850229501724243, |
| "best_model_checkpoint": "./model/results/checkpoint-600", |
| "epoch": 0.5788712011577424, |
| "eval_steps": 200, |
| "global_step": 1200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0964785335262904, |
| "grad_norm": 17.32866096496582, |
| "learning_rate": 1.9999999999999998e-05, |
| "loss": 0.5395, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0964785335262904, |
| "eval_accuracy": 0.844187168355041, |
| "eval_f1": 0.844187168355041, |
| "eval_loss": 0.4005967080593109, |
| "eval_runtime": 6.3088, |
| "eval_samples_per_second": 328.587, |
| "eval_steps_per_second": 41.212, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1929570670525808, |
| "grad_norm": 5.092507839202881, |
| "learning_rate": 2.9999972975051055e-05, |
| "loss": 0.4124, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1929570670525808, |
| "eval_accuracy": 0.8861553304389773, |
| "eval_f1": 0.8861553304389773, |
| "eval_loss": 0.3198019564151764, |
| "eval_runtime": 6.4888, |
| "eval_samples_per_second": 319.475, |
| "eval_steps_per_second": 40.069, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2894356005788712, |
| "grad_norm": 19.754398345947266, |
| "learning_rate": 2.9999756776043787e-05, |
| "loss": 0.3682, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2894356005788712, |
| "eval_accuracy": 0.8967679691268693, |
| "eval_f1": 0.8967679691268693, |
| "eval_loss": 0.26850229501724243, |
| "eval_runtime": 6.6308, |
| "eval_samples_per_second": 312.63, |
| "eval_steps_per_second": 39.211, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3859141341051616, |
| "grad_norm": 24.837013244628906, |
| "learning_rate": 2.999932438114538e-05, |
| "loss": 0.3583, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3859141341051616, |
| "eval_accuracy": 0.894356005788712, |
| "eval_f1": 0.894356005788712, |
| "eval_loss": 0.30613258481025696, |
| "eval_runtime": 6.7124, |
| "eval_samples_per_second": 308.832, |
| "eval_steps_per_second": 38.734, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.482392667631452, |
| "grad_norm": 16.83212661743164, |
| "learning_rate": 2.9998675796588072e-05, |
| "loss": 0.3553, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.482392667631452, |
| "eval_accuracy": 0.9020742884708153, |
| "eval_f1": 0.9020742884708153, |
| "eval_loss": 0.32088562846183777, |
| "eval_runtime": 6.7982, |
| "eval_samples_per_second": 304.932, |
| "eval_steps_per_second": 38.245, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5788712011577424, |
| "grad_norm": 13.450414657592773, |
| "learning_rate": 2.9997811031720103e-05, |
| "loss": 0.3474, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.5788712011577424, |
| "eval_accuracy": 0.8895320791123975, |
| "eval_f1": 0.8895320791123975, |
| "eval_loss": 0.28225570917129517, |
| "eval_runtime": 6.7909, |
| "eval_samples_per_second": 305.259, |
| "eval_steps_per_second": 38.286, |
| "step": 1200 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 20730, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 399599915328000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
