| { |
| "best_global_step": 800, |
| "best_metric": 0.20653806626796722, |
| "best_model_checkpoint": "emotion_model/checkpoint-800", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0625, |
| "grad_norm": 6.358286380767822, |
| "learning_rate": 4.8979166666666674e-05, |
| "loss": 1.4881, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 6.3403096199035645, |
| "learning_rate": 4.79375e-05, |
| "loss": 0.9843, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1875, |
| "grad_norm": 9.866279602050781, |
| "learning_rate": 4.689583333333333e-05, |
| "loss": 0.5726, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 7.112707614898682, |
| "learning_rate": 4.585416666666667e-05, |
| "loss": 0.5064, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.3125, |
| "grad_norm": 10.561152458190918, |
| "learning_rate": 4.4812500000000005e-05, |
| "loss": 0.3728, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.375, |
| "grad_norm": 13.808328628540039, |
| "learning_rate": 4.377083333333333e-05, |
| "loss": 0.3967, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.4375, |
| "grad_norm": 0.5500410795211792, |
| "learning_rate": 4.272916666666667e-05, |
| "loss": 0.2987, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 11.93305778503418, |
| "learning_rate": 4.1687500000000004e-05, |
| "loss": 0.3299, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.5625, |
| "grad_norm": 11.218941688537598, |
| "learning_rate": 4.064583333333333e-05, |
| "loss": 0.2979, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 17.513896942138672, |
| "learning_rate": 3.960416666666667e-05, |
| "loss": 0.2831, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.6875, |
| "grad_norm": 4.549258708953857, |
| "learning_rate": 3.85625e-05, |
| "loss": 0.2354, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 14.289783477783203, |
| "learning_rate": 3.7520833333333335e-05, |
| "loss": 0.258, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.8125, |
| "grad_norm": 2.037280321121216, |
| "learning_rate": 3.647916666666667e-05, |
| "loss": 0.2272, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.875, |
| "grad_norm": 2.0441882610321045, |
| "learning_rate": 3.54375e-05, |
| "loss": 0.2664, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.9375, |
| "grad_norm": 7.056253433227539, |
| "learning_rate": 3.4395833333333334e-05, |
| "loss": 0.2266, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 11.642546653747559, |
| "learning_rate": 3.3354166666666667e-05, |
| "loss": 0.1749, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.930625, |
| "eval_f1": 0.9318498519569388, |
| "eval_loss": 0.20653806626796722, |
| "eval_runtime": 3.4111, |
| "eval_samples_per_second": 938.105, |
| "eval_steps_per_second": 58.632, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 2400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 423925914009600.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
