|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.0, |
|
"eval_steps": 100, |
|
"global_step": 84, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.47619047619047616, |
|
"grad_norm": 9.25047492980957, |
|
"learning_rate": 0.0001785714285714286, |
|
"loss": 0.8938, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.9523809523809523, |
|
"grad_norm": 13.209284782409668, |
|
"learning_rate": 0.00015476190476190478, |
|
"loss": 0.4135, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.4285714285714286, |
|
"grad_norm": 0.18857085704803467, |
|
"learning_rate": 0.00013095238095238096, |
|
"loss": 0.1841, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.9047619047619047, |
|
"grad_norm": 3.675966262817383, |
|
"learning_rate": 0.00010714285714285715, |
|
"loss": 0.2689, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.380952380952381, |
|
"grad_norm": 0.023952171206474304, |
|
"learning_rate": 8.333333333333334e-05, |
|
"loss": 0.276, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 2.857142857142857, |
|
"grad_norm": 0.010658332146704197, |
|
"learning_rate": 5.9523809523809524e-05, |
|
"loss": 0.1114, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 3.3333333333333335, |
|
"grad_norm": 0.013588939793407917, |
|
"learning_rate": 3.571428571428572e-05, |
|
"loss": 0.0018, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 3.8095238095238093, |
|
"grad_norm": 0.011217363178730011, |
|
"learning_rate": 1.1904761904761905e-05, |
|
"loss": 0.0004, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"step": 84, |
|
"total_flos": 2.6605778719997952e+17, |
|
"train_loss": 0.25595739838622866, |
|
"train_runtime": 81.3097, |
|
"train_samples_per_second": 4.034, |
|
"train_steps_per_second": 1.033 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 84, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.6605778719997952e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|