File size: 1,403 Bytes
074674f |
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 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8333333333333334,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.20833333333333334,
"grad_norm": 7.34375,
"learning_rate": 4.4212962962962966e-05,
"loss": 0.396,
"step": 50
},
{
"epoch": 0.4166666666666667,
"grad_norm": 5.625,
"learning_rate": 3.263888888888889e-05,
"loss": 0.243,
"step": 100
},
{
"epoch": 0.625,
"grad_norm": 4.5625,
"learning_rate": 2.1064814814814816e-05,
"loss": 0.2026,
"step": 150
},
{
"epoch": 0.8333333333333334,
"grad_norm": 4.6875,
"learning_rate": 9.490740740740741e-06,
"loss": 0.1774,
"step": 200
}
],
"logging_steps": 50,
"max_steps": 240,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 512,
"trial_name": null,
"trial_params": null
}
|