| { |
| "best_global_step": 84, |
| "best_metric": 0.6309523809523809, |
| "best_model_checkpoint": "./finbert-indonesia/checkpoint-84", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 126, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 11.72082805633545, |
| "learning_rate": 1.9142857142857146e-05, |
| "loss": 1.4184, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 5.9547343254089355, |
| "learning_rate": 1.819047619047619e-05, |
| "loss": 1.0193, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 3.776716709136963, |
| "learning_rate": 1.723809523809524e-05, |
| "loss": 0.9112, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 12.227482795715332, |
| "learning_rate": 1.6285714285714287e-05, |
| "loss": 1.1293, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.4880952380952381, |
| "eval_loss": 1.0485572814941406, |
| "eval_runtime": 2.6921, |
| "eval_samples_per_second": 31.202, |
| "eval_steps_per_second": 4.086, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.1904761904761905, |
| "grad_norm": 4.766658782958984, |
| "learning_rate": 1.5333333333333334e-05, |
| "loss": 1.0195, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 6.310060501098633, |
| "learning_rate": 1.4380952380952382e-05, |
| "loss": 0.9741, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 4.878066062927246, |
| "learning_rate": 1.3428571428571429e-05, |
| "loss": 0.8246, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 6.193632125854492, |
| "learning_rate": 1.2476190476190478e-05, |
| "loss": 0.9586, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6309523809523809, |
| "eval_loss": 0.9428242444992065, |
| "eval_runtime": 3.1407, |
| "eval_samples_per_second": 26.745, |
| "eval_steps_per_second": 3.502, |
| "step": 84 |
| }, |
| { |
| "epoch": 2.142857142857143, |
| "grad_norm": 6.544936656951904, |
| "learning_rate": 1.1523809523809524e-05, |
| "loss": 0.9448, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.380952380952381, |
| "grad_norm": 6.193615913391113, |
| "learning_rate": 1.0571428571428572e-05, |
| "loss": 0.7096, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.619047619047619, |
| "grad_norm": 15.770059585571289, |
| "learning_rate": 9.61904761904762e-06, |
| "loss": 0.8479, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 18.868295669555664, |
| "learning_rate": 8.666666666666668e-06, |
| "loss": 0.7619, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6071428571428571, |
| "eval_loss": 0.8931267857551575, |
| "eval_runtime": 2.8535, |
| "eval_samples_per_second": 29.437, |
| "eval_steps_per_second": 3.855, |
| "step": 126 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 210, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 66107246204160.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
