| { | |
| "best_metric": 0.6208587338139933, | |
| "best_model_checkpoint": "students_scores_model/run-2/checkpoint-1126", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 2815, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8880994671403197, | |
| "grad_norm": 7.292171478271484, | |
| "learning_rate": 3.526354733861817e-05, | |
| "loss": 1.0895, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.5011171601790574, | |
| "eval_loss": 1.1365867853164673, | |
| "eval_runtime": 37.7018, | |
| "eval_samples_per_second": 59.679, | |
| "eval_steps_per_second": 7.48, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 11.239688873291016, | |
| "learning_rate": 2.764723041883023e-05, | |
| "loss": 0.8974, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.6208587338139933, | |
| "eval_loss": 0.8815694451332092, | |
| "eval_runtime": 37.5893, | |
| "eval_samples_per_second": 59.857, | |
| "eval_steps_per_second": 7.502, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.664298401420959, | |
| "grad_norm": 12.65758991241455, | |
| "learning_rate": 2.003091349904229e-05, | |
| "loss": 0.7725, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.5950155132637635, | |
| "eval_loss": 0.9455859661102295, | |
| "eval_runtime": 37.7615, | |
| "eval_samples_per_second": 59.585, | |
| "eval_steps_per_second": 7.468, | |
| "step": 1689 | |
| }, | |
| { | |
| "epoch": 3.552397868561279, | |
| "grad_norm": 15.075959205627441, | |
| "learning_rate": 1.2414596579254345e-05, | |
| "loss": 0.6214, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.610500685281775, | |
| "eval_loss": 1.0504252910614014, | |
| "eval_runtime": 37.6588, | |
| "eval_samples_per_second": 59.747, | |
| "eval_steps_per_second": 7.488, | |
| "step": 2252 | |
| }, | |
| { | |
| "epoch": 4.440497335701599, | |
| "grad_norm": 21.88028907775879, | |
| "learning_rate": 4.798279659466404e-06, | |
| "loss": 0.4643, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.6070487337230086, | |
| "eval_loss": 1.21014404296875, | |
| "eval_runtime": 38.3718, | |
| "eval_samples_per_second": 58.637, | |
| "eval_steps_per_second": 7.349, | |
| "step": 2815 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2815, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0515347855106048e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 4.2879864258406114e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 16, | |
| "weight_decay": 0.060543241151812754 | |
| } | |
| } | |