|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.75, |
|
"eval_steps": 1, |
|
"global_step": 6, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.5, |
|
"eval_loss": 1.1942753791809082, |
|
"eval_runtime": 352.9865, |
|
"eval_samples_per_second": 1.133, |
|
"eval_steps_per_second": 0.567, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.1934306621551514, |
|
"eval_runtime": 355.5542, |
|
"eval_samples_per_second": 1.125, |
|
"eval_steps_per_second": 0.563, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 1.375, |
|
"eval_loss": 1.188248634338379, |
|
"eval_runtime": 355.7383, |
|
"eval_samples_per_second": 1.124, |
|
"eval_steps_per_second": 0.562, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 1.875, |
|
"eval_loss": 1.1737432479858398, |
|
"eval_runtime": 355.6239, |
|
"eval_samples_per_second": 1.125, |
|
"eval_steps_per_second": 0.562, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"eval_loss": 1.1459746360778809, |
|
"eval_runtime": 355.691, |
|
"eval_samples_per_second": 1.125, |
|
"eval_steps_per_second": 0.562, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"grad_norm": 0.1766476333141327, |
|
"learning_rate": 0.00012, |
|
"loss": 1.1443, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"eval_loss": 1.1209450960159302, |
|
"eval_runtime": 355.6375, |
|
"eval_samples_per_second": 1.125, |
|
"eval_steps_per_second": 0.562, |
|
"step": 6 |
|
} |
|
], |
|
"logging_steps": 6, |
|
"max_steps": 20, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 1, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3.5062491251736576e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|