65 lines
1.6 KiB
JSON
65 lines
1.6 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 32,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 1.4525227755308152,
|
||
|
|
"epoch": 0.32,
|
||
|
|
"grad_norm": 11.375,
|
||
|
|
"learning_rate": 1.586206896551724e-05,
|
||
|
|
"loss": 3.044580841064453,
|
||
|
|
"mean_token_accuracy": 0.5073798138648271,
|
||
|
|
"num_tokens": 34236.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 1.3969161085784436,
|
||
|
|
"epoch": 0.64,
|
||
|
|
"grad_norm": 6.78125,
|
||
|
|
"learning_rate": 8.965517241379312e-06,
|
||
|
|
"loss": 1.4662676811218263,
|
||
|
|
"mean_token_accuracy": 0.6803411647677422,
|
||
|
|
"num_tokens": 69411.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 1.2149690441787242,
|
||
|
|
"epoch": 0.96,
|
||
|
|
"grad_norm": 7.21875,
|
||
|
|
"learning_rate": 2.0689655172413796e-06,
|
||
|
|
"loss": 1.3216065406799316,
|
||
|
|
"mean_token_accuracy": 0.7025610633194447,
|
||
|
|
"num_tokens": 104303.0,
|
||
|
|
"step": 30
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 32,
|
||
|
|
"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": 1038690104254464.0,
|
||
|
|
"train_batch_size": 2,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|