84 lines
2.0 KiB
JSON
84 lines
2.0 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.0,
|
|
"eval_steps": 500,
|
|
"global_step": 75,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.40404040404040403,
|
|
"grad_norm": 0.8408341407775879,
|
|
"learning_rate": 0.0001975626331552507,
|
|
"loss": 2.052530860900879,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.8080808080808081,
|
|
"grad_norm": 0.45152202248573303,
|
|
"learning_rate": 0.00017877079733177184,
|
|
"loss": 0.6234618663787842,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 1.202020202020202,
|
|
"grad_norm": 0.4560008943080902,
|
|
"learning_rate": 0.00014480667839875786,
|
|
"loss": 0.4599455833435059,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 1.606060606060606,
|
|
"grad_norm": 0.3496752977371216,
|
|
"learning_rate": 0.00010221220871531869,
|
|
"loss": 0.40735950469970705,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 0.3579687178134918,
|
|
"learning_rate": 5.91916387756535e-05,
|
|
"loss": 0.386263370513916,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 2.404040404040404,
|
|
"grad_norm": 0.3528299629688263,
|
|
"learning_rate": 2.403129154167153e-05,
|
|
"loss": 0.30219953060150145,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 2.808080808080808,
|
|
"grad_norm": 0.30917567014694214,
|
|
"learning_rate": 3.5035085477190143e-06,
|
|
"loss": 0.2843065977096558,
|
|
"step": 70
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 75,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 3,
|
|
"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": 3.941111418544128e+16,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|