File size: 1,728 Bytes
661ca1b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
{
"best_metric": 0.08949843794107437,
"best_model_checkpoint": "doc-topic-model_eval-04_train-02/checkpoint-1000",
"epoch": 0.4930966469428008,
"eval_steps": 1000,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2465483234714004,
"grad_norm": 0.3822348415851593,
"learning_rate": 1.9950690335305722e-05,
"loss": 0.1664,
"step": 500
},
{
"epoch": 0.4930966469428008,
"grad_norm": 0.40402480959892273,
"learning_rate": 1.9901380670611442e-05,
"loss": 0.0944,
"step": 1000
},
{
"epoch": 0.4930966469428008,
"eval_accuracy": 0.981496987239155,
"eval_f1": 0.0,
"eval_loss": 0.08949843794107437,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 12.0575,
"eval_samples_per_second": 672.857,
"eval_steps_per_second": 2.654,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 202800,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 1000,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"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": false
},
"attributes": {}
}
},
"total_flos": 22565797728696.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|