| { | |
| "best_metric": 0.623488690122392, | |
| "best_model_checkpoint": "students_scores_model/run-0/checkpoint-1689", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 2252, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8880994671403197, | |
| "grad_norm": 7.708984851837158, | |
| "learning_rate": 1.9955684198991877e-05, | |
| "loss": 1.084, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.5481089178399972, | |
| "eval_loss": 1.059887409210205, | |
| "eval_runtime": 37.3909, | |
| "eval_samples_per_second": 60.175, | |
| "eval_steps_per_second": 7.542, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 15.52182388305664, | |
| "learning_rate": 1.4260568845398305e-05, | |
| "loss": 0.8598, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.6105817176137399, | |
| "eval_loss": 0.8904849290847778, | |
| "eval_runtime": 37.5314, | |
| "eval_samples_per_second": 59.95, | |
| "eval_steps_per_second": 7.514, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.664298401420959, | |
| "grad_norm": 14.333279609680176, | |
| "learning_rate": 8.565453491804732e-06, | |
| "loss": 0.7595, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.623488690122392, | |
| "eval_loss": 0.9218708872795105, | |
| "eval_runtime": 37.7188, | |
| "eval_samples_per_second": 59.652, | |
| "eval_steps_per_second": 7.476, | |
| "step": 1689 | |
| }, | |
| { | |
| "epoch": 3.552397868561279, | |
| "grad_norm": 23.074176788330078, | |
| "learning_rate": 2.87033813821116e-06, | |
| "loss": 0.6321, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.6118661882172867, | |
| "eval_loss": 0.9693852066993713, | |
| "eval_runtime": 38.8398, | |
| "eval_samples_per_second": 57.93, | |
| "eval_steps_per_second": 7.261, | |
| "step": 2252 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2252, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 8675609285320704.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.565079955258545e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 16, | |
| "weight_decay": 0.003210706404646112 | |
| } | |
| } | |