File size: 1,607 Bytes
a3498d0 |
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 |
{
"best_metric": 1.3517159223556519,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.0027010236879777437,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 5.402047375955487e-05,
"eval_loss": 1.8467991352081299,
"eval_runtime": 1847.6296,
"eval_samples_per_second": 8.437,
"eval_steps_per_second": 0.264,
"step": 1
},
{
"epoch": 0.0027010236879777437,
"grad_norm": 0.796185314655304,
"learning_rate": 0.000201,
"loss": 1.3322,
"step": 50
},
{
"epoch": 0.0027010236879777437,
"eval_loss": 1.3517159223556519,
"eval_runtime": 1842.6641,
"eval_samples_per_second": 8.46,
"eval_steps_per_second": 0.265,
"step": 50
}
],
"logging_steps": 50,
"max_steps": 400,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"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": false
},
"attributes": {}
}
},
"total_flos": 4.31805475848192e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|