checkpoint-10 / trainer_state.json
XuyaoWang's picture
Upload folder using huggingface_hub
b5e0894 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.25,
"eval_steps": 500,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.125,
"grad_norm": 6.3309681672477875,
"learning_rate": 2.5e-06,
"loss": 2.5779,
"step": 1
},
{
"epoch": 0.25,
"grad_norm": 6.486435782835421,
"learning_rate": 5e-06,
"loss": 2.6867,
"step": 2
},
{
"epoch": 0.375,
"grad_norm": 6.29301561909519,
"learning_rate": 7.500000000000001e-06,
"loss": 2.5659,
"step": 3
},
{
"epoch": 0.5,
"grad_norm": 6.39504410732292,
"learning_rate": 1e-05,
"loss": 2.484,
"step": 4
},
{
"epoch": 0.625,
"grad_norm": 4.28794420218769,
"learning_rate": 9.968561049466214e-06,
"loss": 2.3074,
"step": 5
},
{
"epoch": 0.75,
"grad_norm": 5.601176993270821,
"learning_rate": 9.874639560909118e-06,
"loss": 2.0611,
"step": 6
},
{
"epoch": 0.875,
"grad_norm": 13.375873330250425,
"learning_rate": 9.719416651541839e-06,
"loss": 2.0076,
"step": 7
},
{
"epoch": 1.0,
"grad_norm": 4.072546017018971,
"learning_rate": 9.504844339512096e-06,
"loss": 1.9204,
"step": 8
},
{
"epoch": 1.125,
"grad_norm": 2.6221573872710464,
"learning_rate": 9.233620996141421e-06,
"loss": 1.7475,
"step": 9
},
{
"epoch": 1.25,
"grad_norm": 1.615461340232226,
"learning_rate": 8.90915741234015e-06,
"loss": 1.7254,
"step": 10
}
],
"logging_steps": 1.0,
"max_steps": 32,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 55746683207680.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}