|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.004734474867829243, |
|
"eval_steps": 8, |
|
"global_step": 30, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00015781582892764143, |
|
"eval_loss": NaN, |
|
"eval_runtime": 369.5802, |
|
"eval_samples_per_second": 7.219, |
|
"eval_steps_per_second": 3.61, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00047344748678292435, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0009468949735658487, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0012625266314211315, |
|
"eval_loss": NaN, |
|
"eval_runtime": 370.3317, |
|
"eval_samples_per_second": 7.204, |
|
"eval_steps_per_second": 3.602, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.001420342460348773, |
|
"grad_norm": NaN, |
|
"learning_rate": 9e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0018937899471316974, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0023672374339146216, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.002525053262842263, |
|
"eval_loss": NaN, |
|
"eval_runtime": 370.142, |
|
"eval_samples_per_second": 7.208, |
|
"eval_steps_per_second": 3.604, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.002840684920697546, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0033141324074804704, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.2178276747988446e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.003787579894263395, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.003787579894263395, |
|
"eval_loss": NaN, |
|
"eval_runtime": 370.227, |
|
"eval_samples_per_second": 7.206, |
|
"eval_steps_per_second": 3.603, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.004261027381046319, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.449673790581611e-06, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.004734474867829243, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 30 |
|
} |
|
], |
|
"logging_steps": 3, |
|
"max_steps": 30, |
|
"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": 1.2920004538269696e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|