File size: 1,156 Bytes
159c012 b8f963c 159c012 b8f963c 159c012 b8f963c 159c012 b8f963c 159c012 b8f963c 159c012 b8f963c 159c012 b8f963c 159c012 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.3404825737265416,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.6702412868632708,
"grad_norm": 5.694277763366699,
"learning_rate": 2.542005392773407e-05,
"loss": 0.557,
"step": 500
},
{
"epoch": 1.0,
"eval_accuracy": 0.7254441976547241,
"eval_loss": 0.5171247720718384,
"eval_runtime": 8.773,
"eval_samples_per_second": 340.02,
"eval_steps_per_second": 21.315,
"step": 746
},
{
"epoch": 1.3404825737265416,
"grad_norm": 8.974740028381348,
"learning_rate": 2.359390062832789e-05,
"loss": 0.4156,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 7460,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 2380566939876720.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": {
"learning_rate": 2.7246207227140256e-05,
"per_device_train_batch_size": 16
}
}
|