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": 14.0,
|
|
"learning_rate": 1e-05,
|
|
"loss": 2.211936187744141,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.22408963585434175,
|
|
"grad_norm": 7.21875,
|
|
"learning_rate": 9.628619846344453e-06,
|
|
"loss": 1.982374382019043,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.33613445378151263,
|
|
"grad_norm": 6.75,
|
|
"learning_rate": 8.569648672789496e-06,
|
|
"loss": 1.939706802368164,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.4481792717086835,
|
|
"grad_norm": 8.0,
|
|
"learning_rate": 6.980398830195785e-06,
|
|
"loss": 1.9272880554199219,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.5602240896358543,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 5.096956658859122e-06,
|
|
"loss": 1.8303054809570312,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.6722689075630253,
|
|
"grad_norm": 5.53125,
|
|
"learning_rate": 3.1991113759764493e-06,
|
|
"loss": 1.8838277816772462,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.7843137254901961,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 1.5687918106563326e-06,
|
|
"loss": 1.8752876281738282,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.896358543417367,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 4.481852951692672e-07,
|
|
"loss": 1.8907934188842774,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 26.25,
|
|
"learning_rate": 3.760237478849793e-09,
|
|
"loss": 1.9590974807739259,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"eval_loss": 1.7950044870376587,
|
|
"eval_runtime": 4.0343,
|
|
"eval_samples_per_second": 17.847,
|
|
"eval_steps_per_second": 2.231,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"step": 90,
|
|
"total_flos": 1.6013083311596544e+16,
|
|
"train_loss": 1.9445130242241753,
|
|
"train_runtime": 226.5501,
|
|
"train_samples_per_second": 15.727,
|
|
"train_steps_per_second": 0.397
|
|
}
|
|
],
|
|
"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": 1.6013083311596544e+16,
|
|
"train_batch_size": 10,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|