File size: 1,595 Bytes
c64f1a0 | 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 | {
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06944685579360395,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.034723427896801974,
"grad_norm": 5.474236965179443,
"learning_rate": 1.0078933669097135e-05,
"loss": 0.4287,
"step": 500
},
{
"epoch": 0.034723427896801974,
"eval_reranking_loss": 0.3680732250213623,
"eval_reranking_runtime": 2755.6935,
"eval_reranking_samples_per_second": 37.158,
"eval_reranking_steps_per_second": 4.645,
"step": 500
},
{
"epoch": 0.06944685579360395,
"grad_norm": 2.755843162536621,
"learning_rate": 0.0,
"loss": 0.3629,
"step": 1000
},
{
"epoch": 0.06944685579360395,
"eval_reranking_loss": 0.34085196256637573,
"eval_reranking_runtime": 2756.0448,
"eval_reranking_samples_per_second": 37.153,
"eval_reranking_steps_per_second": 4.644,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 1000,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|