|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.739130434782608, |
|
"eval_steps": 500, |
|
"global_step": 66, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.8695652173913043, |
|
"grad_norm": 0.9255293011665344, |
|
"learning_rate": 4.9681708868033616e-05, |
|
"loss": 1.2846, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 1.7391304347826086, |
|
"grad_norm": 0.5333249568939209, |
|
"learning_rate": 4.4245849585747654e-05, |
|
"loss": 0.558, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 2.608695652173913, |
|
"grad_norm": 0.29240840673446655, |
|
"learning_rate": 3.348097165295076e-05, |
|
"loss": 0.3999, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 3.4782608695652173, |
|
"grad_norm": 0.3261595368385315, |
|
"learning_rate": 2.0367781897822147e-05, |
|
"loss": 0.2937, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 4.3478260869565215, |
|
"grad_norm": 0.2872101068496704, |
|
"learning_rate": 8.537215523374038e-06, |
|
"loss": 0.2329, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 5.217391304347826, |
|
"grad_norm": 0.37692585587501526, |
|
"learning_rate": 1.265059788290468e-06, |
|
"loss": 0.1918, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 5.739130434782608, |
|
"step": 66, |
|
"total_flos": 1161800975056896.0, |
|
"train_loss": 0.46655182946812024, |
|
"train_runtime": 241.5984, |
|
"train_samples_per_second": 2.26, |
|
"train_steps_per_second": 0.273 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 66, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 6, |
|
"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": 1161800975056896.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|