|
{ |
|
"best_metric": 1.530792474746704, |
|
"best_model_checkpoint": "./results_v1/checkpoint-295", |
|
"epoch": 5.0, |
|
"eval_steps": 500, |
|
"global_step": 295, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.5825037956237793, |
|
"eval_runtime": 15.4954, |
|
"eval_samples_per_second": 480.399, |
|
"eval_steps_per_second": 3.808, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 1.694915254237288, |
|
"grad_norm": 21800.6015625, |
|
"learning_rate": 0.0003305084745762712, |
|
"loss": 1.4355, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.5649447441101074, |
|
"eval_runtime": 16.533, |
|
"eval_samples_per_second": 450.251, |
|
"eval_steps_per_second": 3.569, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 1.5507193803787231, |
|
"eval_runtime": 16.0878, |
|
"eval_samples_per_second": 462.71, |
|
"eval_steps_per_second": 3.667, |
|
"step": 177 |
|
}, |
|
{ |
|
"epoch": 3.389830508474576, |
|
"grad_norm": 14290.56640625, |
|
"learning_rate": 0.00016101694915254236, |
|
"loss": 1.4142, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 1.5406986474990845, |
|
"eval_runtime": 16.3245, |
|
"eval_samples_per_second": 456.001, |
|
"eval_steps_per_second": 3.614, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 1.530792474746704, |
|
"eval_runtime": 16.839, |
|
"eval_samples_per_second": 442.07, |
|
"eval_steps_per_second": 3.504, |
|
"step": 295 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 295, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 2, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1259440051322880.0, |
|
"train_batch_size": 256, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|