| { |
| "best_global_step": 440, |
| "best_metric": 0.9371466577984703, |
| "best_model_checkpoint": "ner_model/trial_0/checkpoint-440", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 440, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.22779043280182232, |
| "grad_norm": 21.80908203125, |
| "learning_rate": 3.899594554207158e-05, |
| "loss": 4.429600219726563, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.45558086560364464, |
| "grad_norm": 12.349945068359375, |
| "learning_rate": 3.4009251738737616e-05, |
| "loss": 0.8959714508056641, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.683371298405467, |
| "grad_norm": 7.801368236541748, |
| "learning_rate": 2.9022557935403655e-05, |
| "loss": 0.6988069152832032, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.9111617312072893, |
| "grad_norm": 8.062862396240234, |
| "learning_rate": 2.4035864132069692e-05, |
| "loss": 0.4868038177490234, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9839882395009735, |
| "eval_f1": 0.9144043171440432, |
| "eval_loss": 0.12814635038375854, |
| "eval_precision": 0.9023431099459283, |
| "eval_recall": 0.9267923258162235, |
| "eval_runtime": 214.1736, |
| "eval_samples_per_second": 15.175, |
| "eval_steps_per_second": 0.952, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.1366742596810935, |
| "grad_norm": 10.9319486618042, |
| "learning_rate": 1.904917032873573e-05, |
| "loss": 0.37126468658447265, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.3644646924829158, |
| "grad_norm": 7.102725505828857, |
| "learning_rate": 1.406247652540177e-05, |
| "loss": 0.2684678649902344, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.592255125284738, |
| "grad_norm": 15.202373504638672, |
| "learning_rate": 9.07578272206781e-06, |
| "loss": 0.2503110694885254, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.8200455580865604, |
| "grad_norm": 8.701669692993164, |
| "learning_rate": 4.089088918733848e-06, |
| "loss": 0.17738252639770508, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9879746248692174, |
| "eval_f1": 0.9371466577984703, |
| "eval_loss": 0.09272900968790054, |
| "eval_precision": 0.9260598093986198, |
| "eval_recall": 0.9485021878155503, |
| "eval_runtime": 233.7442, |
| "eval_samples_per_second": 13.904, |
| "eval_steps_per_second": 0.873, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 440, |
| "total_flos": 3263842854590472.0, |
| "train_loss": 0.8773450081998652, |
| "train_runtime": 3811.6545, |
| "train_samples_per_second": 7.367, |
| "train_steps_per_second": 0.115 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 440, |
| "test_accuracy": 0.9749472650041899, |
| "test_f1": 0.8915077989601387, |
| "test_loss": 0.30494070053100586, |
| "test_precision": 0.8730482009504412, |
| "test_recall": 0.9107648725212465, |
| "test_runtime": 201.6979, |
| "test_samples_per_second": 17.12, |
| "test_steps_per_second": 1.071 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 440, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 3263842854590472.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
