| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 16, |
| "global_step": 28, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 5.135755695562593, |
| "learning_rate": 0.0, |
| "loss": 0.6626, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 4.976422377741924, |
| "learning_rate": 6.666666666666665e-08, |
| "loss": 0.6659, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 5.149566448288666, |
| "learning_rate": 1.333333333333333e-07, |
| "loss": 0.6934, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 5.168205312692533, |
| "learning_rate": 2e-07, |
| "loss": 0.642, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 5.219987568955151, |
| "learning_rate": 1.9929032311830301e-07, |
| "loss": 0.6757, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 5.316918732370043, |
| "learning_rate": 1.971724845015768e-07, |
| "loss": 0.6625, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 4.9551247999375665, |
| "learning_rate": 1.9367988372994263e-07, |
| "loss": 0.6482, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 5.346578649855734, |
| "learning_rate": 1.8886760120394772e-07, |
| "loss": 0.6805, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.2857142857142856, |
| "grad_norm": 4.598120192548456, |
| "learning_rate": 1.8281152949374524e-07, |
| "loss": 0.635, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 5.1151113017774374, |
| "learning_rate": 1.7560717646792702e-07, |
| "loss": 0.6743, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.5714285714285714, |
| "grad_norm": 5.35558546306821, |
| "learning_rate": 1.6736815907738206e-07, |
| "loss": 0.6828, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.7142857142857144, |
| "grad_norm": 5.2437631052769005, |
| "learning_rate": 1.5822441154810968e-07, |
| "loss": 0.6758, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.8571428571428572, |
| "grad_norm": 4.7959856858897005, |
| "learning_rate": 1.4832013624085653e-07, |
| "loss": 0.643, |
| "step": 13 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 5.146931489368684, |
| "learning_rate": 1.3781152949374525e-07, |
| "loss": 0.6467, |
| "step": 14 |
| }, |
| { |
| "epoch": 2.142857142857143, |
| "grad_norm": 5.565037540363902, |
| "learning_rate": 1.2686431831271523e-07, |
| "loss": 0.7021, |
| "step": 15 |
| }, |
| { |
| "epoch": 2.2857142857142856, |
| "grad_norm": 4.926934066030776, |
| "learning_rate": 1.1565114675763821e-07, |
| "loss": 0.6558, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.2857142857142856, |
| "eval_loss": 0.6358002424240112, |
| "eval_runtime": 4.7554, |
| "eval_samples_per_second": 10.514, |
| "eval_steps_per_second": 2.734, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.4285714285714284, |
| "grad_norm": 4.957804203750453, |
| "learning_rate": 1.043488532423618e-07, |
| "loss": 0.6317, |
| "step": 17 |
| }, |
| { |
| "epoch": 2.571428571428571, |
| "grad_norm": 4.89212984754668, |
| "learning_rate": 9.313568168728476e-08, |
| "loss": 0.669, |
| "step": 18 |
| }, |
| { |
| "epoch": 2.7142857142857144, |
| "grad_norm": 4.63661595623532, |
| "learning_rate": 8.218847050625475e-08, |
| "loss": 0.6435, |
| "step": 19 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 5.237528783827469, |
| "learning_rate": 7.167986375914346e-08, |
| "loss": 0.6754, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.835537673366031, |
| "learning_rate": 6.177558845189028e-08, |
| "loss": 0.634, |
| "step": 21 |
| }, |
| { |
| "epoch": 3.142857142857143, |
| "grad_norm": 4.9632121977212025, |
| "learning_rate": 5.263184092261792e-08, |
| "loss": 0.6763, |
| "step": 22 |
| }, |
| { |
| "epoch": 3.2857142857142856, |
| "grad_norm": 5.154090826338096, |
| "learning_rate": 4.4392823532072976e-08, |
| "loss": 0.6697, |
| "step": 23 |
| }, |
| { |
| "epoch": 3.4285714285714284, |
| "grad_norm": 4.626173048013453, |
| "learning_rate": 3.7188470506254744e-08, |
| "loss": 0.6234, |
| "step": 24 |
| }, |
| { |
| "epoch": 3.571428571428571, |
| "grad_norm": 5.147858633287859, |
| "learning_rate": 3.1132398796052296e-08, |
| "loss": 0.6695, |
| "step": 25 |
| }, |
| { |
| "epoch": 3.7142857142857144, |
| "grad_norm": 5.058641331266572, |
| "learning_rate": 2.632011627005738e-08, |
| "loss": 0.6684, |
| "step": 26 |
| }, |
| { |
| "epoch": 3.857142857142857, |
| "grad_norm": 4.852574620795075, |
| "learning_rate": 2.2827515498423202e-08, |
| "loss": 0.6617, |
| "step": 27 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 5.00072237542112, |
| "learning_rate": 2.0709676881697004e-08, |
| "loss": 0.6367, |
| "step": 28 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 28, |
| "total_flos": 5574381731840.0, |
| "train_loss": 0.6609239322798592, |
| "train_runtime": 622.3863, |
| "train_samples_per_second": 2.86, |
| "train_steps_per_second": 0.045 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 28, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 14, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5574381731840.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
