| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 2510, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00398406374501992, |
| "grad_norm": 13.999564170837402, |
| "learning_rate": 5e-05, |
| "loss": 1.9195, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 19.30626678466797, |
| "learning_rate": 4.50199203187251e-05, |
| "loss": 1.0317, |
| "step": 251 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_Macro F1": 0.64740473433373, |
| "eval_Macro Recall": 0.6415000000000001, |
| "eval_Micro F1": 0.6415, |
| "eval_Micro Recall": 0.6415, |
| "eval_Weighted F1": 0.6474047343337299, |
| "eval_Weighted Recall": 0.6415, |
| "eval_accuracy": 0.6415, |
| "eval_loss": 0.931961178779602, |
| "eval_runtime": 9.5891, |
| "eval_samples_per_second": 208.57, |
| "eval_steps_per_second": 26.071, |
| "step": 251 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 25.07830810546875, |
| "learning_rate": 4.00199203187251e-05, |
| "loss": 0.7391, |
| "step": 502 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_Macro F1": 0.6642748121864179, |
| "eval_Macro Recall": 0.6695, |
| "eval_Micro F1": 0.6695, |
| "eval_Micro Recall": 0.6695, |
| "eval_Weighted F1": 0.664274812186418, |
| "eval_Weighted Recall": 0.6695, |
| "eval_accuracy": 0.6695, |
| "eval_loss": 0.835429310798645, |
| "eval_runtime": 9.1645, |
| "eval_samples_per_second": 218.234, |
| "eval_steps_per_second": 27.279, |
| "step": 502 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 37.92623519897461, |
| "learning_rate": 3.50199203187251e-05, |
| "loss": 0.5872, |
| "step": 753 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_Macro F1": 0.6815571312575414, |
| "eval_Macro Recall": 0.6875, |
| "eval_Micro F1": 0.6875, |
| "eval_Micro Recall": 0.6875, |
| "eval_Weighted F1": 0.6815571312575412, |
| "eval_Weighted Recall": 0.6875, |
| "eval_accuracy": 0.6875, |
| "eval_loss": 0.8496528267860413, |
| "eval_runtime": 9.3499, |
| "eval_samples_per_second": 213.906, |
| "eval_steps_per_second": 26.738, |
| "step": 753 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 32.80082702636719, |
| "learning_rate": 3.0019920318725103e-05, |
| "loss": 0.4395, |
| "step": 1004 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_Macro F1": 0.7104171633300638, |
| "eval_Macro Recall": 0.7085, |
| "eval_Micro F1": 0.7085, |
| "eval_Micro Recall": 0.7085, |
| "eval_Weighted F1": 0.7104171633300637, |
| "eval_Weighted Recall": 0.7085, |
| "eval_accuracy": 0.7085, |
| "eval_loss": 0.8519590497016907, |
| "eval_runtime": 9.5339, |
| "eval_samples_per_second": 209.777, |
| "eval_steps_per_second": 26.222, |
| "step": 1004 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 15.436105728149414, |
| "learning_rate": 2.50199203187251e-05, |
| "loss": 0.2759, |
| "step": 1255 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_Macro F1": 0.6979921825180594, |
| "eval_Macro Recall": 0.6975, |
| "eval_Micro F1": 0.6975, |
| "eval_Micro Recall": 0.6975, |
| "eval_Weighted F1": 0.6979921825180595, |
| "eval_Weighted Recall": 0.6975, |
| "eval_accuracy": 0.6975, |
| "eval_loss": 0.951941967010498, |
| "eval_runtime": 8.7423, |
| "eval_samples_per_second": 228.773, |
| "eval_steps_per_second": 28.597, |
| "step": 1255 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 3.1666982173919678, |
| "learning_rate": 2.00199203187251e-05, |
| "loss": 0.1519, |
| "step": 1506 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_Macro F1": 0.6916300118918036, |
| "eval_Macro Recall": 0.6900000000000001, |
| "eval_Micro F1": 0.69, |
| "eval_Micro Recall": 0.69, |
| "eval_Weighted F1": 0.6916300118918036, |
| "eval_Weighted Recall": 0.69, |
| "eval_accuracy": 0.69, |
| "eval_loss": 1.0978120565414429, |
| "eval_runtime": 8.8863, |
| "eval_samples_per_second": 225.066, |
| "eval_steps_per_second": 28.133, |
| "step": 1506 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 16.443973541259766, |
| "learning_rate": 1.5019920318725101e-05, |
| "loss": 0.0715, |
| "step": 1757 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_Macro F1": 0.6793253939252558, |
| "eval_Macro Recall": 0.6809999999999998, |
| "eval_Micro F1": 0.681, |
| "eval_Micro Recall": 0.681, |
| "eval_Weighted F1": 0.6793253939252558, |
| "eval_Weighted Recall": 0.681, |
| "eval_accuracy": 0.681, |
| "eval_loss": 1.278080701828003, |
| "eval_runtime": 9.3554, |
| "eval_samples_per_second": 213.78, |
| "eval_steps_per_second": 26.722, |
| "step": 1757 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 1.8007348775863647, |
| "learning_rate": 1.00199203187251e-05, |
| "loss": 0.0304, |
| "step": 2008 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_Macro F1": 0.6864146176366923, |
| "eval_Macro Recall": 0.6900000000000001, |
| "eval_Micro F1": 0.69, |
| "eval_Micro Recall": 0.69, |
| "eval_Weighted F1": 0.6864146176366922, |
| "eval_Weighted Recall": 0.69, |
| "eval_accuracy": 0.69, |
| "eval_loss": 1.497562050819397, |
| "eval_runtime": 8.522, |
| "eval_samples_per_second": 234.686, |
| "eval_steps_per_second": 29.336, |
| "step": 2008 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 10.555187225341797, |
| "learning_rate": 5.0199203187251e-06, |
| "loss": 0.0123, |
| "step": 2259 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_Macro F1": 0.6852341910808901, |
| "eval_Macro Recall": 0.6860000000000002, |
| "eval_Micro F1": 0.686, |
| "eval_Micro Recall": 0.686, |
| "eval_Weighted F1": 0.6852341910808902, |
| "eval_Weighted Recall": 0.686, |
| "eval_accuracy": 0.686, |
| "eval_loss": 1.62701416015625, |
| "eval_runtime": 8.8461, |
| "eval_samples_per_second": 226.089, |
| "eval_steps_per_second": 28.261, |
| "step": 2259 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.23559199273586273, |
| "learning_rate": 1.9920318725099604e-08, |
| "loss": 0.0059, |
| "step": 2510 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_Macro F1": 0.687891156596344, |
| "eval_Macro Recall": 0.688, |
| "eval_Micro F1": 0.688, |
| "eval_Micro Recall": 0.688, |
| "eval_Weighted F1": 0.687891156596344, |
| "eval_Weighted Recall": 0.688, |
| "eval_accuracy": 0.688, |
| "eval_loss": 1.658383846282959, |
| "eval_runtime": 8.9982, |
| "eval_samples_per_second": 222.267, |
| "eval_steps_per_second": 27.783, |
| "step": 2510 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 2510, |
| "total_flos": 7.98760594469376e+17, |
| "train_loss": 0.33488889652419374, |
| "train_runtime": 1001.2511, |
| "train_samples_per_second": 159.85, |
| "train_steps_per_second": 2.507 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2510, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 7.98760594469376e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
