| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9966329966329966, |
| "eval_steps": 500, |
| "global_step": 185, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0053872053872053875, |
| "grad_norm": 0.5911839008331299, |
| "learning_rate": 0.0, |
| "loss": 0.834, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.05387205387205387, |
| "grad_norm": 0.4561307728290558, |
| "learning_rate": 9.473684210526316e-05, |
| "loss": 1.4016, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10774410774410774, |
| "grad_norm": 0.06328851729631424, |
| "learning_rate": 0.0002, |
| "loss": 0.8905, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.16161616161616163, |
| "grad_norm": 0.022817041724920273, |
| "learning_rate": 0.00018795180722891569, |
| "loss": 0.6956, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.21548821548821548, |
| "grad_norm": 0.018048042431473732, |
| "learning_rate": 0.00017590361445783134, |
| "loss": 0.6707, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.26936026936026936, |
| "grad_norm": 0.028622902929782867, |
| "learning_rate": 0.00016385542168674699, |
| "loss": 0.6629, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.32323232323232326, |
| "grad_norm": 0.012167639099061489, |
| "learning_rate": 0.00015180722891566266, |
| "loss": 0.6721, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3771043771043771, |
| "grad_norm": 0.01069930475205183, |
| "learning_rate": 0.00013975903614457834, |
| "loss": 0.6565, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.43097643097643096, |
| "grad_norm": 0.015863914042711258, |
| "learning_rate": 0.00012771084337349396, |
| "loss": 0.6458, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.48484848484848486, |
| "grad_norm": 0.012852534651756287, |
| "learning_rate": 0.00011566265060240964, |
| "loss": 0.6363, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5387205387205387, |
| "grad_norm": 0.025411192327737808, |
| "learning_rate": 0.0001036144578313253, |
| "loss": 0.6416, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.01106669008731842, |
| "learning_rate": 9.156626506024096e-05, |
| "loss": 0.6575, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6464646464646465, |
| "grad_norm": 0.010959242470562458, |
| "learning_rate": 7.951807228915663e-05, |
| "loss": 0.6438, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7003367003367004, |
| "grad_norm": 0.010998900979757309, |
| "learning_rate": 6.746987951807229e-05, |
| "loss": 0.6374, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7542087542087542, |
| "grad_norm": 0.010141533799469471, |
| "learning_rate": 5.5421686746987955e-05, |
| "loss": 0.6316, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8080808080808081, |
| "grad_norm": 0.023810530081391335, |
| "learning_rate": 4.337349397590362e-05, |
| "loss": 0.6369, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8619528619528619, |
| "grad_norm": 0.010837017558515072, |
| "learning_rate": 3.132530120481928e-05, |
| "loss": 0.6532, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9158249158249159, |
| "grad_norm": 0.009072311222553253, |
| "learning_rate": 1.927710843373494e-05, |
| "loss": 0.6411, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.9696969696969697, |
| "grad_norm": 0.013384884223341942, |
| "learning_rate": 7.228915662650602e-06, |
| "loss": 0.629, |
| "step": 180 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 185, |
| "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": 4.109138039878451e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
