| { | |
| "best_metric": 0.7351907898564811, | |
| "best_model_checkpoint": "training_dir/checkpoint-10000", | |
| "epoch": 1.5659254619480114, | |
| "eval_steps": 1000, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15659254619480112, | |
| "grad_norm": 4.369892120361328, | |
| "learning_rate": 9.92108585858586e-06, | |
| "loss": 0.726, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15659254619480112, | |
| "eval_accuracy": 0.652534965034965, | |
| "eval_f1": 0.6156117064442015, | |
| "eval_loss": 0.9217989444732666, | |
| "eval_precision": 0.647833453696251, | |
| "eval_recall": 0.652534965034965, | |
| "eval_runtime": 30.8162, | |
| "eval_samples_per_second": 74.247, | |
| "eval_steps_per_second": 9.281, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.31318509238960224, | |
| "grad_norm": 10.090314865112305, | |
| "learning_rate": 9.763257575757577e-06, | |
| "loss": 0.5078, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.31318509238960224, | |
| "eval_accuracy": 0.6984265734265734, | |
| "eval_f1": 0.6840354165768472, | |
| "eval_loss": 0.8569145798683167, | |
| "eval_precision": 0.7035176110711845, | |
| "eval_recall": 0.6984265734265734, | |
| "eval_runtime": 29.8277, | |
| "eval_samples_per_second": 76.707, | |
| "eval_steps_per_second": 9.588, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.46977763858440336, | |
| "grad_norm": 2.5105936527252197, | |
| "learning_rate": 9.605429292929293e-06, | |
| "loss": 0.4747, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.46977763858440336, | |
| "eval_accuracy": 0.7076048951048951, | |
| "eval_f1": 0.6892053083671648, | |
| "eval_loss": 0.8822671175003052, | |
| "eval_precision": 0.7144457563342712, | |
| "eval_recall": 0.7076048951048951, | |
| "eval_runtime": 29.6497, | |
| "eval_samples_per_second": 77.168, | |
| "eval_steps_per_second": 9.646, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6263701847792045, | |
| "grad_norm": 28.96643829345703, | |
| "learning_rate": 9.44760101010101e-06, | |
| "loss": 0.4593, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6263701847792045, | |
| "eval_accuracy": 0.7338286713286714, | |
| "eval_f1": 0.727562941019853, | |
| "eval_loss": 0.7618293762207031, | |
| "eval_precision": 0.7330094463964066, | |
| "eval_recall": 0.7338286713286714, | |
| "eval_runtime": 29.7317, | |
| "eval_samples_per_second": 76.955, | |
| "eval_steps_per_second": 9.619, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7829627309740056, | |
| "grad_norm": 5.809261798858643, | |
| "learning_rate": 9.289772727272728e-06, | |
| "loss": 0.4486, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.7829627309740056, | |
| "eval_accuracy": 0.7351398601398601, | |
| "eval_f1": 0.7293047058493298, | |
| "eval_loss": 0.8104275465011597, | |
| "eval_precision": 0.7355000090280587, | |
| "eval_recall": 0.7351398601398601, | |
| "eval_runtime": 29.7412, | |
| "eval_samples_per_second": 76.93, | |
| "eval_steps_per_second": 9.616, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.9395552771688067, | |
| "grad_norm": 16.398216247558594, | |
| "learning_rate": 9.131944444444445e-06, | |
| "loss": 0.4562, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.9395552771688067, | |
| "eval_accuracy": 0.728583916083916, | |
| "eval_f1": 0.722523941260205, | |
| "eval_loss": 0.764935314655304, | |
| "eval_precision": 0.7390044648352858, | |
| "eval_recall": 0.728583916083916, | |
| "eval_runtime": 29.8199, | |
| "eval_samples_per_second": 76.727, | |
| "eval_steps_per_second": 9.591, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.096147823363608, | |
| "grad_norm": 4.596695899963379, | |
| "learning_rate": 8.974116161616161e-06, | |
| "loss": 0.3993, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.096147823363608, | |
| "eval_accuracy": 0.7198426573426573, | |
| "eval_f1": 0.7041969146725503, | |
| "eval_loss": 1.0100624561309814, | |
| "eval_precision": 0.7315013162404153, | |
| "eval_recall": 0.7198426573426573, | |
| "eval_runtime": 29.6299, | |
| "eval_samples_per_second": 77.219, | |
| "eval_steps_per_second": 9.652, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.252740369558409, | |
| "grad_norm": 2.7841145992279053, | |
| "learning_rate": 8.816287878787879e-06, | |
| "loss": 0.3901, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.252740369558409, | |
| "eval_accuracy": 0.7185314685314685, | |
| "eval_f1": 0.6970213656627479, | |
| "eval_loss": 1.013152003288269, | |
| "eval_precision": 0.7291871168086037, | |
| "eval_recall": 0.7185314685314685, | |
| "eval_runtime": 29.6033, | |
| "eval_samples_per_second": 77.289, | |
| "eval_steps_per_second": 9.661, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.4093329157532102, | |
| "grad_norm": 5.9810404777526855, | |
| "learning_rate": 8.658459595959596e-06, | |
| "loss": 0.3809, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.4093329157532102, | |
| "eval_accuracy": 0.7211538461538461, | |
| "eval_f1": 0.7055943588116754, | |
| "eval_loss": 0.9052737355232239, | |
| "eval_precision": 0.7224815370590899, | |
| "eval_recall": 0.7211538461538461, | |
| "eval_runtime": 30.2216, | |
| "eval_samples_per_second": 75.707, | |
| "eval_steps_per_second": 9.463, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.5659254619480114, | |
| "grad_norm": 9.159900665283203, | |
| "learning_rate": 8.500631313131314e-06, | |
| "loss": 0.3932, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.5659254619480114, | |
| "eval_accuracy": 0.7443181818181818, | |
| "eval_f1": 0.7351907898564811, | |
| "eval_loss": 0.9013388156890869, | |
| "eval_precision": 0.7458339781734145, | |
| "eval_recall": 0.7443181818181818, | |
| "eval_runtime": 29.7576, | |
| "eval_samples_per_second": 76.888, | |
| "eval_steps_per_second": 9.611, | |
| "step": 10000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 63860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0072339831839852e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |