|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.042105263157894736, |
|
"eval_steps": 7, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0016842105263157896, |
|
"eval_loss": 4.297740459442139, |
|
"eval_runtime": 50.0514, |
|
"eval_samples_per_second": 4.995, |
|
"eval_steps_per_second": 2.497, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0050526315789473685, |
|
"grad_norm": 1.9082145690917969, |
|
"learning_rate": 6e-05, |
|
"loss": 3.825, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.010105263157894737, |
|
"grad_norm": 2.2301290035247803, |
|
"learning_rate": 0.00012, |
|
"loss": 3.6755, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.011789473684210527, |
|
"eval_loss": 3.489590883255005, |
|
"eval_runtime": 50.5605, |
|
"eval_samples_per_second": 4.945, |
|
"eval_steps_per_second": 2.472, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.015157894736842105, |
|
"grad_norm": 1.785214900970459, |
|
"learning_rate": 0.00018, |
|
"loss": 3.2529, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.020210526315789474, |
|
"grad_norm": 2.081219434738159, |
|
"learning_rate": 0.0001913545457642601, |
|
"loss": 2.5259, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.023578947368421053, |
|
"eval_loss": 1.79923677444458, |
|
"eval_runtime": 50.5853, |
|
"eval_samples_per_second": 4.942, |
|
"eval_steps_per_second": 2.471, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.02526315789473684, |
|
"grad_norm": 2.057396411895752, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 1.9331, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.03031578947368421, |
|
"grad_norm": 1.3836475610733032, |
|
"learning_rate": 8.954715367323468e-05, |
|
"loss": 1.2657, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.03536842105263158, |
|
"grad_norm": 1.9340174198150635, |
|
"learning_rate": 3.308693936411421e-05, |
|
"loss": 1.0206, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.03536842105263158, |
|
"eval_loss": 1.2012845277786255, |
|
"eval_runtime": 50.6968, |
|
"eval_samples_per_second": 4.931, |
|
"eval_steps_per_second": 2.466, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.04042105263157895, |
|
"grad_norm": 2.1337223052978516, |
|
"learning_rate": 2.1852399266194314e-06, |
|
"loss": 0.9806, |
|
"step": 24 |
|
} |
|
], |
|
"logging_steps": 3, |
|
"max_steps": 25, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 10, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.5869480534016e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|