|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 804, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 9.199758529663086, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 0.61, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.581834614276886, |
|
"eval_matthews_correlation": 0.1605505486389139, |
|
"eval_runtime": 8.5337, |
|
"eval_samples_per_second": 122.221, |
|
"eval_steps_per_second": 7.734, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 7.077225685119629, |
|
"learning_rate": 1.2e-05, |
|
"loss": 0.5265, |
|
"step": 536 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.5488986968994141, |
|
"eval_matthews_correlation": 0.3414642281150747, |
|
"eval_runtime": 8.5064, |
|
"eval_samples_per_second": 122.614, |
|
"eval_steps_per_second": 7.759, |
|
"step": 536 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"grad_norm": 9.864019393920898, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.4161, |
|
"step": 804 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.5453676581382751, |
|
"eval_matthews_correlation": 0.3451229816764349, |
|
"eval_runtime": 8.5021, |
|
"eval_samples_per_second": 122.676, |
|
"eval_steps_per_second": 7.763, |
|
"step": 804 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 1340, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4562104380880896.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|