93 lines
2.2 KiB
JSON
93 lines
2.2 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 39,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.1282051282051282,
|
||
|
|
"grad_norm": 0.5785048007965088,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"loss": 0.17,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2564102564102564,
|
||
|
|
"grad_norm": 0.039770353585481644,
|
||
|
|
"learning_rate": 1.900968867902419e-05,
|
||
|
|
"loss": 0.2544,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.38461538461538464,
|
||
|
|
"grad_norm": 0.08221551030874252,
|
||
|
|
"learning_rate": 1.6234898018587336e-05,
|
||
|
|
"loss": 0.1096,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5128205128205128,
|
||
|
|
"grad_norm": 0.017881816253066063,
|
||
|
|
"learning_rate": 1.2225209339563144e-05,
|
||
|
|
"loss": 0.0999,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6410256410256411,
|
||
|
|
"grad_norm": 0.11876405030488968,
|
||
|
|
"learning_rate": 7.774790660436857e-06,
|
||
|
|
"loss": 0.104,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7692307692307693,
|
||
|
|
"grad_norm": 0.16007612645626068,
|
||
|
|
"learning_rate": 3.7651019814126656e-06,
|
||
|
|
"loss": 0.1001,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8974358974358975,
|
||
|
|
"grad_norm": 0.006673595868051052,
|
||
|
|
"learning_rate": 9.903113209758098e-07,
|
||
|
|
"loss": 0.0996,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"step": 39,
|
||
|
|
"total_flos": 1.939301794274345e+17,
|
||
|
|
"train_loss": 0.1304902312083122,
|
||
|
|
"train_runtime": 1065.8503,
|
||
|
|
"train_samples_per_second": 4.674,
|
||
|
|
"train_steps_per_second": 0.037
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 39,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"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": 1.939301794274345e+17,
|
||
|
|
"train_batch_size": 8,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|