| { |
| "best_metric": 0.9166666666666666, |
| "best_model_checkpoint": "test/checkpoint-20", |
| "epoch": 19.727272727272727, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.73, |
| "eval_accuracy": 0.7222222222222222, |
| "eval_f1": 0.6707818930041152, |
| "eval_loss": 0.561225950717926, |
| "eval_precision": 0.8090277777777778, |
| "eval_recall": 0.7222222222222222, |
| "eval_runtime": 5.7451, |
| "eval_samples_per_second": 6.266, |
| "eval_steps_per_second": 0.174, |
| "step": 2 |
| }, |
| { |
| "epoch": 1.73, |
| "eval_accuracy": 0.7777777777777778, |
| "eval_f1": 0.7608080808080808, |
| "eval_loss": 0.3748733699321747, |
| "eval_precision": 0.7986111111111112, |
| "eval_recall": 0.7777777777777778, |
| "eval_runtime": 5.1904, |
| "eval_samples_per_second": 6.936, |
| "eval_steps_per_second": 0.193, |
| "step": 4 |
| }, |
| { |
| "epoch": 2.73, |
| "eval_accuracy": 0.8055555555555556, |
| "eval_f1": 0.8066066066066067, |
| "eval_loss": 0.522664487361908, |
| "eval_precision": 0.8703703703703703, |
| "eval_recall": 0.8055555555555556, |
| "eval_runtime": 5.3959, |
| "eval_samples_per_second": 6.672, |
| "eval_steps_per_second": 0.185, |
| "step": 6 |
| }, |
| { |
| "epoch": 3.73, |
| "eval_accuracy": 0.8055555555555556, |
| "eval_f1": 0.7864923747276689, |
| "eval_loss": 0.5397895574569702, |
| "eval_precision": 0.8524904214559387, |
| "eval_recall": 0.8055555555555556, |
| "eval_runtime": 5.524, |
| "eval_samples_per_second": 6.517, |
| "eval_steps_per_second": 0.181, |
| "step": 8 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 0.0001, |
| "loss": 0.5735, |
| "step": 10 |
| }, |
| { |
| "epoch": 4.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.8600823045267489, |
| "eval_loss": 0.24970261752605438, |
| "eval_precision": 0.8604607952434039, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 5.1179, |
| "eval_samples_per_second": 7.034, |
| "eval_steps_per_second": 0.195, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8899470899470899, |
| "eval_loss": 0.26077044010162354, |
| "eval_precision": 0.8965277777777777, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 4.7095, |
| "eval_samples_per_second": 7.644, |
| "eval_steps_per_second": 0.212, |
| "step": 12 |
| }, |
| { |
| "epoch": 6.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.8618907600463335, |
| "eval_loss": 0.2541900873184204, |
| "eval_precision": 0.8640211640211641, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 5.4129, |
| "eval_samples_per_second": 6.651, |
| "eval_steps_per_second": 0.185, |
| "step": 14 |
| }, |
| { |
| "epoch": 7.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.2999325394630432, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 5.0159, |
| "eval_samples_per_second": 7.177, |
| "eval_steps_per_second": 0.199, |
| "step": 16 |
| }, |
| { |
| "epoch": 8.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8870308435525827, |
| "eval_loss": 0.2993186116218567, |
| "eval_precision": 0.8912037037037036, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 4.9756, |
| "eval_samples_per_second": 7.235, |
| "eval_steps_per_second": 0.201, |
| "step": 18 |
| }, |
| { |
| "epoch": 9.73, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.0476, |
| "step": 20 |
| }, |
| { |
| "epoch": 9.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.2704654335975647, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 6.2342, |
| "eval_samples_per_second": 5.775, |
| "eval_steps_per_second": 0.16, |
| "step": 20 |
| }, |
| { |
| "epoch": 10.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8888888888888888, |
| "eval_loss": 0.28197962045669556, |
| "eval_precision": 0.8888888888888888, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 5.1606, |
| "eval_samples_per_second": 6.976, |
| "eval_steps_per_second": 0.194, |
| "step": 22 |
| }, |
| { |
| "epoch": 11.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.8618907600463335, |
| "eval_loss": 0.275021493434906, |
| "eval_precision": 0.8640211640211641, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 4.8026, |
| "eval_samples_per_second": 7.496, |
| "eval_steps_per_second": 0.208, |
| "step": 24 |
| }, |
| { |
| "epoch": 12.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8888888888888888, |
| "eval_loss": 0.2932831346988678, |
| "eval_precision": 0.8888888888888888, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 4.6825, |
| "eval_samples_per_second": 7.688, |
| "eval_steps_per_second": 0.214, |
| "step": 26 |
| }, |
| { |
| "epoch": 13.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.8618907600463335, |
| "eval_loss": 0.2971099317073822, |
| "eval_precision": 0.8640211640211641, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 5.7546, |
| "eval_samples_per_second": 6.256, |
| "eval_steps_per_second": 0.174, |
| "step": 28 |
| }, |
| { |
| "epoch": 14.73, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.003, |
| "step": 30 |
| }, |
| { |
| "epoch": 14.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8888888888888888, |
| "eval_loss": 0.29043230414390564, |
| "eval_precision": 0.8888888888888888, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 9.7959, |
| "eval_samples_per_second": 3.675, |
| "eval_steps_per_second": 0.102, |
| "step": 30 |
| }, |
| { |
| "epoch": 15.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.305411696434021, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.2177, |
| "eval_samples_per_second": 6.9, |
| "eval_steps_per_second": 0.192, |
| "step": 32 |
| }, |
| { |
| "epoch": 16.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.29818451404571533, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 4.9626, |
| "eval_samples_per_second": 7.254, |
| "eval_steps_per_second": 0.202, |
| "step": 34 |
| }, |
| { |
| "epoch": 17.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.30663102865219116, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 4.7376, |
| "eval_samples_per_second": 7.599, |
| "eval_steps_per_second": 0.211, |
| "step": 36 |
| }, |
| { |
| "epoch": 18.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8870308435525827, |
| "eval_loss": 0.30919915437698364, |
| "eval_precision": 0.8912037037037036, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 6.3085, |
| "eval_samples_per_second": 5.707, |
| "eval_steps_per_second": 0.159, |
| "step": 38 |
| }, |
| { |
| "epoch": 19.73, |
| "learning_rate": 0.0, |
| "loss": 0.0013, |
| "step": 40 |
| }, |
| { |
| "epoch": 19.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8870308435525827, |
| "eval_loss": 0.3030144274234772, |
| "eval_precision": 0.8912037037037036, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 4.7135, |
| "eval_samples_per_second": 7.638, |
| "eval_steps_per_second": 0.212, |
| "step": 40 |
| }, |
| { |
| "epoch": 19.73, |
| "step": 40, |
| "total_flos": 1.0463143975579976e+18, |
| "train_loss": 0.15636180818546563, |
| "train_runtime": 744.5374, |
| "train_samples_per_second": 18.374, |
| "train_steps_per_second": 0.054 |
| } |
| ], |
| "max_steps": 40, |
| "num_train_epochs": 20, |
| "total_flos": 1.0463143975579976e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
