|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.008958566629339306, |
|
"eval_steps": 3, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0008958566629339306, |
|
"grad_norm": 0.5667176842689514, |
|
"learning_rate": 2e-05, |
|
"loss": 1.1936, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0008958566629339306, |
|
"eval_loss": 1.1165611743927002, |
|
"eval_runtime": 82.0637, |
|
"eval_samples_per_second": 5.727, |
|
"eval_steps_per_second": 2.864, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0017917133258678612, |
|
"grad_norm": 0.4546806812286377, |
|
"learning_rate": 4e-05, |
|
"loss": 1.1064, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0026875699888017916, |
|
"grad_norm": 0.4336964786052704, |
|
"learning_rate": 6e-05, |
|
"loss": 0.9627, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0026875699888017916, |
|
"eval_loss": 1.1144386529922485, |
|
"eval_runtime": 110.231, |
|
"eval_samples_per_second": 4.264, |
|
"eval_steps_per_second": 2.132, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0035834266517357225, |
|
"grad_norm": 0.544019877910614, |
|
"learning_rate": 8e-05, |
|
"loss": 1.046, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.004479283314669653, |
|
"grad_norm": 0.5248474478721619, |
|
"learning_rate": 0.0001, |
|
"loss": 0.9919, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.005375139977603583, |
|
"grad_norm": 0.4641495943069458, |
|
"learning_rate": 0.00012, |
|
"loss": 1.0251, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.005375139977603583, |
|
"eval_loss": 1.0897356271743774, |
|
"eval_runtime": 110.0518, |
|
"eval_samples_per_second": 4.271, |
|
"eval_steps_per_second": 2.135, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.006270996640537514, |
|
"grad_norm": 0.5025619268417358, |
|
"learning_rate": 0.00014, |
|
"loss": 1.0538, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.007166853303471445, |
|
"grad_norm": 0.41523295640945435, |
|
"learning_rate": 0.00016, |
|
"loss": 1.0953, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.008062709966405375, |
|
"grad_norm": 0.40565767884254456, |
|
"learning_rate": 0.00018, |
|
"loss": 0.8898, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.008062709966405375, |
|
"eval_loss": 1.0463182926177979, |
|
"eval_runtime": 79.1602, |
|
"eval_samples_per_second": 5.937, |
|
"eval_steps_per_second": 2.969, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.008958566629339306, |
|
"grad_norm": 0.4387066960334778, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9191, |
|
"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": 2058737544069120.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|