|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.004395121415229096, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0004395121415229096, |
|
"grad_norm": 3.412137269973755, |
|
"learning_rate": 2e-05, |
|
"loss": 6.5867, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0004395121415229096, |
|
"eval_loss": 6.63784122467041, |
|
"eval_runtime": 44.8907, |
|
"eval_samples_per_second": 21.341, |
|
"eval_steps_per_second": 10.67, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0008790242830458192, |
|
"grad_norm": 3.118777275085449, |
|
"learning_rate": 4e-05, |
|
"loss": 6.4375, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0013185364245687286, |
|
"grad_norm": 3.607393503189087, |
|
"learning_rate": 6e-05, |
|
"loss": 6.4469, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0013185364245687286, |
|
"eval_loss": 6.587182998657227, |
|
"eval_runtime": 44.9259, |
|
"eval_samples_per_second": 21.324, |
|
"eval_steps_per_second": 10.662, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0017580485660916383, |
|
"grad_norm": 3.4184303283691406, |
|
"learning_rate": 8e-05, |
|
"loss": 6.6433, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.002197560707614548, |
|
"grad_norm": 3.5969738960266113, |
|
"learning_rate": 0.0001, |
|
"loss": 6.2481, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0026370728491374573, |
|
"grad_norm": 3.2133593559265137, |
|
"learning_rate": 0.00012, |
|
"loss": 5.9113, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0026370728491374573, |
|
"eval_loss": 5.963469505310059, |
|
"eval_runtime": 45.1311, |
|
"eval_samples_per_second": 21.227, |
|
"eval_steps_per_second": 10.614, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.003076584990660367, |
|
"grad_norm": 3.14534592628479, |
|
"learning_rate": 0.00014, |
|
"loss": 5.717, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0035160971321832766, |
|
"grad_norm": 2.3380327224731445, |
|
"learning_rate": 0.00016, |
|
"loss": 5.2748, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.003955609273706186, |
|
"grad_norm": 2.8084821701049805, |
|
"learning_rate": 0.00018, |
|
"loss": 4.614, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.003955609273706186, |
|
"eval_loss": 5.188882350921631, |
|
"eval_runtime": 45.1623, |
|
"eval_samples_per_second": 21.212, |
|
"eval_steps_per_second": 10.606, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.004395121415229096, |
|
"grad_norm": 3.5231258869171143, |
|
"learning_rate": 0.0002, |
|
"loss": 5.2136, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2103703457759232.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|