Model: iproskurina/SmolLM2-360M-biasinbios-pt-factory-real-base-all Source: Original Platform
42 lines
944 B
JSON
42 lines
944 B
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0,
|
|
"eval_steps": 500,
|
|
"global_step": 138,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.7292616226071102,
|
|
"grad_norm": 0.6110724210739136,
|
|
"learning_rate": 1.1242682119065218e-05,
|
|
"loss": 2.9296,
|
|
"step": 100
|
|
}
|
|
],
|
|
"logging_steps": 100,
|
|
"max_steps": 138,
|
|
"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": 4232013972278400.0,
|
|
"train_batch_size": 2,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|