|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9920402178466695, |
|
"eval_steps": 500, |
|
"global_step": 74, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.13405948889819858, |
|
"grad_norm": 2.4030588914514235, |
|
"learning_rate": 4.988679806432712e-05, |
|
"loss": 0.8477, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.26811897779639715, |
|
"grad_norm": 0.3943398531464459, |
|
"learning_rate": 4.6031338320779534e-05, |
|
"loss": 0.7697, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.4021784666945957, |
|
"grad_norm": 0.24684741049062292, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 0.7408, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.5362379555927943, |
|
"grad_norm": 0.221449175648297, |
|
"learning_rate": 2.6189547895593562e-05, |
|
"loss": 0.7332, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.6702974444909929, |
|
"grad_norm": 0.1662850787032937, |
|
"learning_rate": 1.4614624674952842e-05, |
|
"loss": 0.7332, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.8043569333891915, |
|
"grad_norm": 0.15694040167883, |
|
"learning_rate": 5.348672631430318e-06, |
|
"loss": 0.7303, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.9384164222873901, |
|
"grad_norm": 0.14587623990823048, |
|
"learning_rate": 4.517825684323324e-07, |
|
"loss": 0.7259, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.9920402178466695, |
|
"step": 74, |
|
"total_flos": 620455136329728.0, |
|
"train_loss": 0.7533366486832902, |
|
"train_runtime": 30122.1015, |
|
"train_samples_per_second": 1.268, |
|
"train_steps_per_second": 0.002 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 74, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 1000, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 620455136329728.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|