NT1-500M-human_ref-finetuned-tf2 / trainer_state.json
Chenghao-Qiu's picture
Upload folder using huggingface_hub
bbc1444 verified
{
"best_metric": 0.7036557793617249,
"best_model_checkpoint": "output_pipe/tf2/origin/checkpoint-200",
"epoch": 4.0,
"eval_steps": 200,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.3333333333333333,
"grad_norm": 161479.015625,
"learning_rate": 2.4e-05,
"loss": 0.5794,
"step": 100
},
{
"epoch": 2.6666666666666665,
"grad_norm": 351706.5,
"learning_rate": 1.2e-05,
"loss": 0.3664,
"step": 200
},
{
"epoch": 2.6666666666666665,
"eval_accuracy": 0.727,
"eval_f1": 0.7256940292733705,
"eval_loss": 0.7036557793617249,
"eval_matthews_correlation": 0.4620341139429147,
"eval_precision": 0.7337762372424417,
"eval_recall": 0.7282904423532424,
"eval_runtime": 0.3477,
"eval_samples_per_second": 2876.01,
"eval_steps_per_second": 11.504,
"step": 200
},
{
"epoch": 4.0,
"grad_norm": 892284.625,
"learning_rate": 0.0,
"loss": 0.112,
"step": 300
},
{
"epoch": 4.0,
"step": 300,
"total_flos": 4970303505384000.0,
"train_loss": 0.3526033369700114,
"train_runtime": 82.9251,
"train_samples_per_second": 916.489,
"train_steps_per_second": 3.618
}
],
"logging_steps": 100,
"max_steps": 300,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4970303505384000.0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}