| { |
| "best_global_step": 32, |
| "best_metric": 0.8888888888888888, |
| "best_model_checkpoint": "symbols_clf/checkpoint-32", |
| "epoch": 20.0, |
| "eval_steps": 500, |
| "global_step": 80, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.05555555555555555, |
| "eval_loss": 3.1174912452697754, |
| "eval_runtime": 0.093, |
| "eval_samples_per_second": 193.626, |
| "eval_steps_per_second": 10.757, |
| "step": 4 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.16666666666666666, |
| "eval_loss": 2.874302387237549, |
| "eval_runtime": 0.0617, |
| "eval_samples_per_second": 291.64, |
| "eval_steps_per_second": 16.202, |
| "step": 8 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.3333333333333333, |
| "eval_loss": 2.5718352794647217, |
| "eval_runtime": 0.0537, |
| "eval_samples_per_second": 335.145, |
| "eval_steps_per_second": 18.619, |
| "step": 12 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8333333333333334, |
| "eval_loss": 2.2845373153686523, |
| "eval_runtime": 0.0546, |
| "eval_samples_per_second": 329.739, |
| "eval_steps_per_second": 18.319, |
| "step": 16 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8333333333333334, |
| "eval_loss": 2.1046838760375977, |
| "eval_runtime": 0.0585, |
| "eval_samples_per_second": 307.55, |
| "eval_steps_per_second": 17.086, |
| "step": 20 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8333333333333334, |
| "eval_loss": 1.9366213083267212, |
| "eval_runtime": 0.0597, |
| "eval_samples_per_second": 301.535, |
| "eval_steps_per_second": 16.752, |
| "step": 24 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8333333333333334, |
| "eval_loss": 1.7910093069076538, |
| "eval_runtime": 0.075, |
| "eval_samples_per_second": 239.946, |
| "eval_steps_per_second": 13.33, |
| "step": 28 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.6815359592437744, |
| "eval_runtime": 0.0771, |
| "eval_samples_per_second": 233.408, |
| "eval_steps_per_second": 12.967, |
| "step": 32 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.5946409702301025, |
| "eval_runtime": 0.0592, |
| "eval_samples_per_second": 303.938, |
| "eval_steps_per_second": 16.885, |
| "step": 36 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.505096197128296, |
| "eval_runtime": 0.0586, |
| "eval_samples_per_second": 307.08, |
| "eval_steps_per_second": 17.06, |
| "step": 40 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.3820862770080566, |
| "eval_runtime": 0.0541, |
| "eval_samples_per_second": 332.597, |
| "eval_steps_per_second": 18.478, |
| "step": 44 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.2910130023956299, |
| "eval_runtime": 0.0536, |
| "eval_samples_per_second": 335.992, |
| "eval_steps_per_second": 18.666, |
| "step": 48 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.26617431640625, |
| "eval_runtime": 0.062, |
| "eval_samples_per_second": 290.286, |
| "eval_steps_per_second": 16.127, |
| "step": 52 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.2407567501068115, |
| "eval_runtime": 0.0543, |
| "eval_samples_per_second": 331.4, |
| "eval_steps_per_second": 18.411, |
| "step": 56 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.1884442567825317, |
| "eval_runtime": 0.0521, |
| "eval_samples_per_second": 345.745, |
| "eval_steps_per_second": 19.208, |
| "step": 60 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.1120694875717163, |
| "eval_runtime": 0.0529, |
| "eval_samples_per_second": 340.484, |
| "eval_steps_per_second": 18.916, |
| "step": 64 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.114011287689209, |
| "eval_runtime": 0.0536, |
| "eval_samples_per_second": 335.529, |
| "eval_steps_per_second": 18.641, |
| "step": 68 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.0817580223083496, |
| "eval_runtime": 0.0535, |
| "eval_samples_per_second": 336.377, |
| "eval_steps_per_second": 18.688, |
| "step": 72 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.0812649726867676, |
| "eval_runtime": 0.0575, |
| "eval_samples_per_second": 313.265, |
| "eval_steps_per_second": 17.404, |
| "step": 76 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_loss": 1.0582048892974854, |
| "eval_runtime": 0.0524, |
| "eval_samples_per_second": 343.428, |
| "eval_steps_per_second": 19.079, |
| "step": 80 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 80, |
| "total_flos": 2730469925191680.0, |
| "train_loss": 1.9437339782714844, |
| "train_runtime": 10.2462, |
| "train_samples_per_second": 191.29, |
| "train_steps_per_second": 7.808 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 80, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 2730469925191680.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
