File size: 1,949 Bytes
2302725 |
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 72 73 74 75 76 77 78 79 80 81 82 83 84 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 500,
"global_step": 76,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5263157894736842,
"grad_norm": 10.215806007385254,
"learning_rate": 4.5e-05,
"loss": 1.5086,
"step": 10
},
{
"epoch": 1.0526315789473684,
"grad_norm": 7.984120845794678,
"learning_rate": 4.318181818181819e-05,
"loss": 1.3946,
"step": 20
},
{
"epoch": 1.5789473684210527,
"grad_norm": 7.379543304443359,
"learning_rate": 3.560606060606061e-05,
"loss": 1.1182,
"step": 30
},
{
"epoch": 2.1052631578947367,
"grad_norm": 13.861002922058105,
"learning_rate": 2.803030303030303e-05,
"loss": 1.1279,
"step": 40
},
{
"epoch": 2.6315789473684212,
"grad_norm": 7.687878608703613,
"learning_rate": 2.0454545454545457e-05,
"loss": 0.9944,
"step": 50
},
{
"epoch": 3.1578947368421053,
"grad_norm": 8.31785774230957,
"learning_rate": 1.287878787878788e-05,
"loss": 0.8876,
"step": 60
},
{
"epoch": 3.6842105263157894,
"grad_norm": 7.630281925201416,
"learning_rate": 5.303030303030304e-06,
"loss": 0.81,
"step": 70
}
],
"logging_steps": 10,
"max_steps": 76,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": 156818412908544.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|