| { |
| "best_global_step": 315, |
| "best_metric": 0.4981603538892402, |
| "best_model_checkpoint": "./emotion_classifier/checkpoint-315", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 420, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 3.9467227458953857, |
| "learning_rate": 4.5333333333333335e-05, |
| "loss": 1.5659, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 5.448686122894287, |
| "learning_rate": 4.057142857142857e-05, |
| "loss": 1.5183, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5047619047619047, |
| "eval_f1": 0.40600600600600606, |
| "eval_loss": 1.4387609958648682, |
| "eval_runtime": 0.7949, |
| "eval_samples_per_second": 132.095, |
| "eval_steps_per_second": 17.613, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 16.634593963623047, |
| "learning_rate": 3.580952380952381e-05, |
| "loss": 1.272, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 6.955718517303467, |
| "learning_rate": 3.104761904761905e-05, |
| "loss": 1.2448, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5238095238095238, |
| "eval_f1": 0.48246327929496247, |
| "eval_loss": 1.3625617027282715, |
| "eval_runtime": 0.6094, |
| "eval_samples_per_second": 172.306, |
| "eval_steps_per_second": 22.974, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.380952380952381, |
| "grad_norm": 6.055703639984131, |
| "learning_rate": 2.6285714285714286e-05, |
| "loss": 1.0137, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 8.498906135559082, |
| "learning_rate": 2.1523809523809525e-05, |
| "loss": 0.8427, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5333333333333333, |
| "eval_f1": 0.4981603538892402, |
| "eval_loss": 1.4221067428588867, |
| "eval_runtime": 0.6125, |
| "eval_samples_per_second": 171.431, |
| "eval_steps_per_second": 22.857, |
| "step": 315 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 6.134776592254639, |
| "learning_rate": 1.676190476190476e-05, |
| "loss": 0.7736, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "grad_norm": 5.722315788269043, |
| "learning_rate": 1.2e-05, |
| "loss": 0.5872, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.47619047619047616, |
| "eval_f1": 0.46248745780765493, |
| "eval_loss": 1.577803373336792, |
| "eval_runtime": 0.6116, |
| "eval_samples_per_second": 171.683, |
| "eval_steps_per_second": 22.891, |
| "step": 420 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 525, |
| "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": 111282536816640.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
