File size: 1,446 Bytes
12178c9 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 15.0,
"eval_steps": 500,
"global_step": 2130,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 3.52112676056338,
"grad_norm": 0.2243831753730774,
"learning_rate": 1.9131455399061035e-05,
"loss": 0.0913,
"step": 500
},
{
"epoch": 7.042253521126761,
"grad_norm": 0.12650109827518463,
"learning_rate": 1.3262910798122067e-05,
"loss": 0.0111,
"step": 1000
},
{
"epoch": 10.56338028169014,
"grad_norm": 0.11735480278730392,
"learning_rate": 7.394366197183099e-06,
"loss": 0.0093,
"step": 1500
},
{
"epoch": 14.084507042253522,
"grad_norm": 0.08703824132680893,
"learning_rate": 1.5258215962441315e-06,
"loss": 0.0082,
"step": 2000
}
],
"logging_steps": 500,
"max_steps": 2130,
"num_input_tokens_seen": 0,
"num_train_epochs": 15,
"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": 1.191017255660421e+18,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}
|