70B-gptq_qlora / trainer_state.json
DuolgoueSystems's picture
Upload folder using huggingface_hub
796e862 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.848484848484849,
"eval_steps": 500,
"global_step": 90,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5387205387205387,
"grad_norm": 0.21063075959682465,
"learning_rate": 0.00018823529411764707,
"loss": 1.9049,
"step": 10
},
{
"epoch": 1.0774410774410774,
"grad_norm": 0.16132037341594696,
"learning_rate": 0.0001647058823529412,
"loss": 1.4848,
"step": 20
},
{
"epoch": 1.6161616161616161,
"grad_norm": 0.24221213161945343,
"learning_rate": 0.0001411764705882353,
"loss": 1.2408,
"step": 30
},
{
"epoch": 2.154882154882155,
"grad_norm": 0.30846676230430603,
"learning_rate": 0.00011764705882352942,
"loss": 1.2065,
"step": 40
},
{
"epoch": 2.6936026936026938,
"grad_norm": 0.34726232290267944,
"learning_rate": 9.411764705882353e-05,
"loss": 1.034,
"step": 50
},
{
"epoch": 3.2323232323232323,
"grad_norm": 0.5741103291511536,
"learning_rate": 7.058823529411765e-05,
"loss": 0.8864,
"step": 60
},
{
"epoch": 3.771043771043771,
"grad_norm": 0.5462518334388733,
"learning_rate": 4.705882352941177e-05,
"loss": 0.7765,
"step": 70
},
{
"epoch": 4.30976430976431,
"grad_norm": 0.6150287389755249,
"learning_rate": 2.3529411764705884e-05,
"loss": 0.7129,
"step": 80
},
{
"epoch": 4.848484848484849,
"grad_norm": 0.6696115136146545,
"learning_rate": 0.0,
"loss": 0.5665,
"step": 90
}
],
"logging_steps": 10,
"max_steps": 90,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 6111496826486784.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}