95 lines
2.4 KiB
JSON
95 lines
2.4 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 63,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 0.1056655953405425,
|
||
|
|
"epoch": 0.16,
|
||
|
|
"grad_norm": 12.0625,
|
||
|
|
"learning_rate": 1.894736842105263e-05,
|
||
|
|
"loss": 3.4882164001464844,
|
||
|
|
"mean_token_accuracy": 0.7255681823939085,
|
||
|
|
"num_tokens": 40047.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.06432699970901012,
|
||
|
|
"epoch": 0.32,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 1.543859649122807e-05,
|
||
|
|
"loss": 0.06028715968132019,
|
||
|
|
"mean_token_accuracy": 0.9670454517006875,
|
||
|
|
"num_tokens": 79520.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.0531476724660024,
|
||
|
|
"epoch": 0.48,
|
||
|
|
"grad_norm": 3.5,
|
||
|
|
"learning_rate": 1.192982456140351e-05,
|
||
|
|
"loss": 0.05689932703971863,
|
||
|
|
"mean_token_accuracy": 0.9693181797862053,
|
||
|
|
"num_tokens": 120623.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.054595551500096914,
|
||
|
|
"epoch": 0.64,
|
||
|
|
"grad_norm": 4.0625,
|
||
|
|
"learning_rate": 8.421052631578948e-06,
|
||
|
|
"loss": 0.06269298195838928,
|
||
|
|
"mean_token_accuracy": 0.961363635212183,
|
||
|
|
"num_tokens": 162158.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.056087028328329326,
|
||
|
|
"epoch": 0.8,
|
||
|
|
"grad_norm": 2.953125,
|
||
|
|
"learning_rate": 4.912280701754386e-06,
|
||
|
|
"loss": 0.05635017156600952,
|
||
|
|
"mean_token_accuracy": 0.9698863588273525,
|
||
|
|
"num_tokens": 202787.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.05579588690306991,
|
||
|
|
"epoch": 0.96,
|
||
|
|
"grad_norm": 3.125,
|
||
|
|
"learning_rate": 1.4035087719298246e-06,
|
||
|
|
"loss": 0.05594708323478699,
|
||
|
|
"mean_token_accuracy": 0.965340905636549,
|
||
|
|
"num_tokens": 243390.0,
|
||
|
|
"step": 60
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 63,
|
||
|
|
"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": 2576514320547840.0,
|
||
|
|
"train_batch_size": 2,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|