115 lines
2.7 KiB
JSON
115 lines
2.7 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 90,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.11204481792717087,
|
||
|
|
"grad_norm": 8.3125,
|
||
|
|
"learning_rate": 1e-05,
|
||
|
|
"loss": 1.396421241760254,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.22408963585434175,
|
||
|
|
"grad_norm": 6.40625,
|
||
|
|
"learning_rate": 9.628619846344453e-06,
|
||
|
|
"loss": 1.2572100639343262,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.33613445378151263,
|
||
|
|
"grad_norm": 6.4375,
|
||
|
|
"learning_rate": 8.569648672789496e-06,
|
||
|
|
"loss": 1.237971878051758,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4481792717086835,
|
||
|
|
"grad_norm": 5.59375,
|
||
|
|
"learning_rate": 6.980398830195785e-06,
|
||
|
|
"loss": 1.1971160888671875,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5602240896358543,
|
||
|
|
"grad_norm": 5.71875,
|
||
|
|
"learning_rate": 5.096956658859122e-06,
|
||
|
|
"loss": 1.1496850967407226,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6722689075630253,
|
||
|
|
"grad_norm": 6.0,
|
||
|
|
"learning_rate": 3.1991113759764493e-06,
|
||
|
|
"loss": 1.241246223449707,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7843137254901961,
|
||
|
|
"grad_norm": 5.625,
|
||
|
|
"learning_rate": 1.5687918106563326e-06,
|
||
|
|
"loss": 1.1770063400268556,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.896358543417367,
|
||
|
|
"grad_norm": 5.8125,
|
||
|
|
"learning_rate": 4.481852951692672e-07,
|
||
|
|
"loss": 1.209663200378418,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 26.0,
|
||
|
|
"learning_rate": 3.760237478849793e-09,
|
||
|
|
"loss": 1.2288966178894043,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_loss": 1.1395946741104126,
|
||
|
|
"eval_runtime": 5.7504,
|
||
|
|
"eval_samples_per_second": 12.521,
|
||
|
|
"eval_steps_per_second": 1.565,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"step": 90,
|
||
|
|
"total_flos": 8375949913795584.0,
|
||
|
|
"train_loss": 1.2328018612331815,
|
||
|
|
"train_runtime": 186.4804,
|
||
|
|
"train_samples_per_second": 19.107,
|
||
|
|
"train_steps_per_second": 0.483
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 90,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 200,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 8375949913795584.0,
|
||
|
|
"train_batch_size": 10,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|