bashgemma-270m / checkpoint-50 /trainer_state.json
thinkthink-dev's picture
Upload folder using huggingface_hub
d482ce9 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.043687199650502405,
"eval_steps": 500,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00436871996505024,
"grad_norm": 9.862386703491211,
"learning_rate": 8e-05,
"loss": 2.5264,
"step": 5
},
{
"epoch": 0.00873743993010048,
"grad_norm": 13.404240608215332,
"learning_rate": 0.00018,
"loss": 1.1324,
"step": 10
},
{
"epoch": 0.01310615989515072,
"grad_norm": 5.68959379196167,
"learning_rate": 0.00019510565162951537,
"loss": 0.7683,
"step": 15
},
{
"epoch": 0.01747487986020096,
"grad_norm": 5.407431602478027,
"learning_rate": 0.0001760405965600031,
"loss": 0.7282,
"step": 20
},
{
"epoch": 0.021843599825251202,
"grad_norm": 2.846036195755005,
"learning_rate": 0.00014539904997395468,
"loss": 0.7303,
"step": 25
},
{
"epoch": 0.02621231979030144,
"grad_norm": 3.3286690711975098,
"learning_rate": 0.0001078459095727845,
"loss": 0.4722,
"step": 30
},
{
"epoch": 0.03058103975535168,
"grad_norm": 5.507899284362793,
"learning_rate": 6.909830056250527e-05,
"loss": 0.6308,
"step": 35
},
{
"epoch": 0.03494975972040192,
"grad_norm": 3.0458195209503174,
"learning_rate": 3.5055195166981645e-05,
"loss": 0.5756,
"step": 40
},
{
"epoch": 0.039318479685452164,
"grad_norm": 3.154995918273926,
"learning_rate": 1.0899347581163221e-05,
"loss": 0.4154,
"step": 45
},
{
"epoch": 0.043687199650502405,
"grad_norm": 3.0581588745117188,
"learning_rate": 3.0826662668720364e-07,
"loss": 0.5745,
"step": 50
}
],
"logging_steps": 5,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 24019515777024.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}