| { |
| "best_global_step": 1038, |
| "best_metric": 0.49668368697166443, |
| "best_model_checkpoint": "./mcqa_model_test/checkpoint-1038", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1038, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04819277108433735, |
| "grad_norm": 42.887596130371094, |
| "learning_rate": 4.2307692307692304e-07, |
| "loss": 0.7896, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0963855421686747, |
| "grad_norm": 72.85254669189453, |
| "learning_rate": 9.038461538461538e-07, |
| "loss": 0.6271, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.14457831325301204, |
| "grad_norm": 73.96256256103516, |
| "learning_rate": 9.571734475374732e-07, |
| "loss": 0.5829, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.1927710843373494, |
| "grad_norm": 49.094825744628906, |
| "learning_rate": 9.036402569593148e-07, |
| "loss": 0.5468, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.24096385542168675, |
| "grad_norm": 36.6225471496582, |
| "learning_rate": 8.501070663811563e-07, |
| "loss": 0.6207, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2891566265060241, |
| "grad_norm": 75.95718383789062, |
| "learning_rate": 7.965738758029978e-07, |
| "loss": 0.5785, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3373493975903614, |
| "grad_norm": 42.73014450073242, |
| "learning_rate": 7.430406852248393e-07, |
| "loss": 0.5925, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.3855421686746988, |
| "grad_norm": 69.05870819091797, |
| "learning_rate": 6.895074946466809e-07, |
| "loss": 0.5643, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.43373493975903615, |
| "grad_norm": 58.479698181152344, |
| "learning_rate": 6.359743040685225e-07, |
| "loss": 0.5513, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.4819277108433735, |
| "grad_norm": 47.322349548339844, |
| "learning_rate": 5.82441113490364e-07, |
| "loss": 0.5393, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5301204819277109, |
| "grad_norm": 54.66911315917969, |
| "learning_rate": 5.289079229122055e-07, |
| "loss": 0.574, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.5783132530120482, |
| "grad_norm": 59.46133041381836, |
| "learning_rate": 4.7537473233404704e-07, |
| "loss": 0.5349, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6265060240963856, |
| "grad_norm": 40.902618408203125, |
| "learning_rate": 4.2184154175588866e-07, |
| "loss": 0.6069, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.6746987951807228, |
| "grad_norm": 79.90098571777344, |
| "learning_rate": 3.6830835117773016e-07, |
| "loss": 0.5563, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.7228915662650602, |
| "grad_norm": 45.558319091796875, |
| "learning_rate": 3.147751605995717e-07, |
| "loss": 0.5108, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7710843373493976, |
| "grad_norm": 47.96351623535156, |
| "learning_rate": 2.6124197002141323e-07, |
| "loss": 0.4863, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.8192771084337349, |
| "grad_norm": 86.99226379394531, |
| "learning_rate": 2.0770877944325482e-07, |
| "loss": 0.5324, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.8674698795180723, |
| "grad_norm": 45.73421096801758, |
| "learning_rate": 1.5417558886509635e-07, |
| "loss": 0.51, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.9156626506024096, |
| "grad_norm": 44.04231643676758, |
| "learning_rate": 1.006423982869379e-07, |
| "loss": 0.5558, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.963855421686747, |
| "grad_norm": 53.926795959472656, |
| "learning_rate": 4.710920770877944e-08, |
| "loss": 0.4865, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.49668368697166443, |
| "eval_runtime": 29.6777, |
| "eval_samples_per_second": 104.826, |
| "eval_steps_per_second": 13.107, |
| "step": 1038 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1038, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 7893370617200640.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
