98 lines
2.3 KiB
JSON
98 lines
2.3 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 2.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 46,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.2222222222222222,
|
||
|
|
"grad_norm": 1.1400277614593506,
|
||
|
|
"learning_rate": 4e-05,
|
||
|
|
"loss": 1.5692282676696778,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4444444444444444,
|
||
|
|
"grad_norm": 0.6653280258178711,
|
||
|
|
"learning_rate": 9e-05,
|
||
|
|
"loss": 1.4446605682373046,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6666666666666666,
|
||
|
|
"grad_norm": 0.28921666741371155,
|
||
|
|
"learning_rate": 8.888888888888889e-05,
|
||
|
|
"loss": 1.135626983642578,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8888888888888888,
|
||
|
|
"grad_norm": 0.18273191154003143,
|
||
|
|
"learning_rate": 7.500000000000001e-05,
|
||
|
|
"loss": 1.019450855255127,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0888888888888888,
|
||
|
|
"grad_norm": 0.18688197433948517,
|
||
|
|
"learning_rate": 6.111111111111112e-05,
|
||
|
|
"loss": 0.961759376525879,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3111111111111111,
|
||
|
|
"grad_norm": 0.18513710796833038,
|
||
|
|
"learning_rate": 4.722222222222222e-05,
|
||
|
|
"loss": 0.8943395614624023,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.5333333333333332,
|
||
|
|
"grad_norm": 0.17294040322303772,
|
||
|
|
"learning_rate": 3.3333333333333335e-05,
|
||
|
|
"loss": 0.8557774543762207,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.7555555555555555,
|
||
|
|
"grad_norm": 0.1875566989183426,
|
||
|
|
"learning_rate": 1.9444444444444445e-05,
|
||
|
|
"loss": 0.8408210754394532,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.9777777777777779,
|
||
|
|
"grad_norm": 0.1633838564157486,
|
||
|
|
"learning_rate": 5.555555555555556e-06,
|
||
|
|
"loss": 0.8121231079101563,
|
||
|
|
"step": 45
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 46,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 2,
|
||
|
|
"save_steps": 50,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1.771890192347136e+16,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|