| { |
| "best_global_step": 3132, |
| "best_metric": 0.5881329726800972, |
| "best_model_checkpoint": "outputs/phobert-v1/checkpoint-3132", |
| "epoch": 18.0, |
| "eval_steps": 500, |
| "global_step": 3132, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9942528735632183, |
| "grad_norm": 2.6583092212677, |
| "learning_rate": 6.88e-06, |
| "loss": 1.8469, |
| "step": 173 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.3163265306122449, |
| "eval_loss": 1.7160369157791138, |
| "eval_macro_f1": 0.07588256112515117, |
| "eval_runtime": 2.3805, |
| "eval_samples_per_second": 288.175, |
| "eval_steps_per_second": 9.242, |
| "step": 174 |
| }, |
| { |
| "epoch": 1.9885057471264367, |
| "grad_norm": 9.339335441589355, |
| "learning_rate": 1.38e-05, |
| "loss": 1.6506, |
| "step": 346 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.49271137026239065, |
| "eval_loss": 1.4279717206954956, |
| "eval_macro_f1": 0.26791037751403135, |
| "eval_runtime": 2.3818, |
| "eval_samples_per_second": 288.022, |
| "eval_steps_per_second": 9.237, |
| "step": 348 |
| }, |
| { |
| "epoch": 2.9827586206896552, |
| "grad_norm": 9.079231262207031, |
| "learning_rate": 1.999994401896218e-05, |
| "loss": 1.3315, |
| "step": 519 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5524781341107872, |
| "eval_loss": 1.207149624824524, |
| "eval_macro_f1": 0.401013356395679, |
| "eval_runtime": 2.383, |
| "eval_samples_per_second": 287.878, |
| "eval_steps_per_second": 9.232, |
| "step": 522 |
| }, |
| { |
| "epoch": 3.9770114942528734, |
| "grad_norm": 8.046290397644043, |
| "learning_rate": 1.9993697433304146e-05, |
| "loss": 1.0349, |
| "step": 692 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.5845481049562682, |
| "eval_loss": 1.1730802059173584, |
| "eval_macro_f1": 0.5273093498298432, |
| "eval_runtime": 1.051, |
| "eval_samples_per_second": 652.7, |
| "eval_steps_per_second": 20.932, |
| "step": 696 |
| }, |
| { |
| "epoch": 4.971264367816092, |
| "grad_norm": 14.620841979980469, |
| "learning_rate": 1.9977115923137912e-05, |
| "loss": 0.8082, |
| "step": 865 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6064139941690962, |
| "eval_loss": 1.1103960275650024, |
| "eval_macro_f1": 0.5513612516051968, |
| "eval_runtime": 1.0497, |
| "eval_samples_per_second": 653.548, |
| "eval_steps_per_second": 20.959, |
| "step": 870 |
| }, |
| { |
| "epoch": 5.9655172413793105, |
| "grad_norm": 18.373315811157227, |
| "learning_rate": 1.995021663613649e-05, |
| "loss": 0.6432, |
| "step": 1038 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6180758017492711, |
| "eval_loss": 1.1242892742156982, |
| "eval_macro_f1": 0.5685682908450502, |
| "eval_runtime": 1.0561, |
| "eval_samples_per_second": 649.577, |
| "eval_steps_per_second": 20.832, |
| "step": 1044 |
| }, |
| { |
| "epoch": 6.959770114942529, |
| "grad_norm": 19.177682876586914, |
| "learning_rate": 1.991302739004225e-05, |
| "loss": 0.4856, |
| "step": 1211 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.6180758017492711, |
| "eval_loss": 1.2190402746200562, |
| "eval_macro_f1": 0.5720115104548725, |
| "eval_runtime": 2.3657, |
| "eval_samples_per_second": 289.981, |
| "eval_steps_per_second": 9.3, |
| "step": 1218 |
| }, |
| { |
| "epoch": 7.954022988505747, |
| "grad_norm": 10.141107559204102, |
| "learning_rate": 1.9865586643899352e-05, |
| "loss": 0.3773, |
| "step": 1384 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.6180758017492711, |
| "eval_loss": 1.332094430923462, |
| "eval_macro_f1": 0.5724900288812286, |
| "eval_runtime": 2.3855, |
| "eval_samples_per_second": 287.57, |
| "eval_steps_per_second": 9.222, |
| "step": 1392 |
| }, |
| { |
| "epoch": 8.948275862068966, |
| "grad_norm": 14.313020706176758, |
| "learning_rate": 1.9807943458281543e-05, |
| "loss": 0.2897, |
| "step": 1557 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.6064139941690962, |
| "eval_loss": 1.4038197994232178, |
| "eval_macro_f1": 0.5674191936637583, |
| "eval_runtime": 2.3637, |
| "eval_samples_per_second": 290.225, |
| "eval_steps_per_second": 9.307, |
| "step": 1566 |
| }, |
| { |
| "epoch": 9.942528735632184, |
| "grad_norm": 12.335651397705078, |
| "learning_rate": 1.974015744455647e-05, |
| "loss": 0.2137, |
| "step": 1730 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.6209912536443148, |
| "eval_loss": 1.548543095588684, |
| "eval_macro_f1": 0.5761372608282923, |
| "eval_runtime": 2.3742, |
| "eval_samples_per_second": 288.935, |
| "eval_steps_per_second": 9.266, |
| "step": 1740 |
| }, |
| { |
| "epoch": 10.936781609195402, |
| "grad_norm": 16.48043441772461, |
| "learning_rate": 1.9662298703238904e-05, |
| "loss": 0.1764, |
| "step": 1903 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.597667638483965, |
| "eval_loss": 1.697547435760498, |
| "eval_macro_f1": 0.5601682218476405, |
| "eval_runtime": 2.3856, |
| "eval_samples_per_second": 287.564, |
| "eval_steps_per_second": 9.222, |
| "step": 1914 |
| }, |
| { |
| "epoch": 11.931034482758621, |
| "grad_norm": 20.897550582885742, |
| "learning_rate": 1.9574447751496706e-05, |
| "loss": 0.128, |
| "step": 2076 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.6049562682215743, |
| "eval_loss": 1.832864761352539, |
| "eval_macro_f1": 0.5635033671342974, |
| "eval_runtime": 2.3698, |
| "eval_samples_per_second": 289.481, |
| "eval_steps_per_second": 9.284, |
| "step": 2088 |
| }, |
| { |
| "epoch": 12.925287356321839, |
| "grad_norm": 27.952417373657227, |
| "learning_rate": 1.9476695439884466e-05, |
| "loss": 0.12, |
| "step": 2249 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.575801749271137, |
| "eval_loss": 2.1239633560180664, |
| "eval_macro_f1": 0.5353047636964179, |
| "eval_runtime": 2.3893, |
| "eval_samples_per_second": 287.113, |
| "eval_steps_per_second": 9.208, |
| "step": 2262 |
| }, |
| { |
| "epoch": 13.919540229885058, |
| "grad_norm": 7.873048782348633, |
| "learning_rate": 1.9369142858390936e-05, |
| "loss": 0.0868, |
| "step": 2422 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.5947521865889213, |
| "eval_loss": 2.1011478900909424, |
| "eval_macro_f1": 0.5666855895738372, |
| "eval_runtime": 2.3541, |
| "eval_samples_per_second": 291.401, |
| "eval_steps_per_second": 9.345, |
| "step": 2436 |
| }, |
| { |
| "epoch": 14.913793103448276, |
| "grad_norm": 1.451875925064087, |
| "learning_rate": 1.9251901231897364e-05, |
| "loss": 0.0807, |
| "step": 2595 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.607871720116618, |
| "eval_loss": 2.229091167449951, |
| "eval_macro_f1": 0.5818994852139766, |
| "eval_runtime": 2.3965, |
| "eval_samples_per_second": 286.253, |
| "eval_steps_per_second": 9.18, |
| "step": 2610 |
| }, |
| { |
| "epoch": 15.908045977011493, |
| "grad_norm": 39.825321197509766, |
| "learning_rate": 1.9125091805154977e-05, |
| "loss": 0.0612, |
| "step": 2768 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.6151603498542274, |
| "eval_loss": 2.392549753189087, |
| "eval_macro_f1": 0.5672571391448136, |
| "eval_runtime": 2.3779, |
| "eval_samples_per_second": 288.484, |
| "eval_steps_per_second": 9.252, |
| "step": 2784 |
| }, |
| { |
| "epoch": 16.902298850574713, |
| "grad_norm": 40.26604461669922, |
| "learning_rate": 1.8988845717400375e-05, |
| "loss": 0.0587, |
| "step": 2941 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.6137026239067055, |
| "eval_loss": 2.4110476970672607, |
| "eval_macro_f1": 0.5690951143898209, |
| "eval_runtime": 2.3821, |
| "eval_samples_per_second": 287.975, |
| "eval_steps_per_second": 9.235, |
| "step": 2958 |
| }, |
| { |
| "epoch": 17.896551724137932, |
| "grad_norm": 2.2619950771331787, |
| "learning_rate": 1.884330386673869e-05, |
| "loss": 0.054, |
| "step": 3114 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.6326530612244898, |
| "eval_loss": 2.3882195949554443, |
| "eval_macro_f1": 0.5881329726800972, |
| "eval_runtime": 2.3906, |
| "eval_samples_per_second": 286.963, |
| "eval_steps_per_second": 9.203, |
| "step": 3132 |
| } |
| ], |
| "logging_steps": 173, |
| "max_steps": 17400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9289154030900400.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
