File size: 1,779 Bytes
cdc19a0 71919df cdc19a0 71919df cdc19a0 71919df 181d4e5 71919df 181d4e5 71919df 181d4e5 71919df 181d4e5 cdc19a0 71919df cdc19a0 71919df cdc19a0 71919df cdc19a0 71919df cdc19a0 |
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 70 71 |
{
"best_metric": 3.128293514251709,
"best_model_checkpoint": "/tmp/test-egy_aragpt/checkpoint-500",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 638,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.567398119122257,
"grad_norm": 1.3536407947540283,
"learning_rate": 5e-05,
"loss": 4.3013,
"step": 500
},
{
"epoch": 1.567398119122257,
"eval_bleu": 0.11424038411303619,
"eval_loss": 3.128293514251709,
"eval_rouge1": 0.3297614987151056,
"eval_rouge2": 0.08429294540985294,
"eval_rougeL": 0.2561476738686219,
"eval_runtime": 29.502,
"eval_samples_per_second": 28.71,
"eval_steps_per_second": 3.593,
"step": 500
},
{
"epoch": 2.0,
"step": 638,
"total_flos": 2000451796992000.0,
"train_loss": 4.049833148250759,
"train_runtime": 274.3289,
"train_samples_per_second": 18.605,
"train_steps_per_second": 2.326
}
],
"logging_steps": 500,
"max_steps": 638,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"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": 2000451796992000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|