longformer-spans / checkpoint-41 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 1, checkpoint
958f07d verified
{
"best_metric": 0.20753507316112518,
"best_model_checkpoint": "longformer-spans/checkpoint-41",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 41,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_B": {
"f1-score": 0.773921200750469,
"precision": 0.8258258258258259,
"recall": 0.7281553398058253,
"support": 1133.0
},
"eval_I": {
"f1-score": 0.9504992905522983,
"precision": 0.9305934158104424,
"recall": 0.9712753734201456,
"support": 18277.0
},
"eval_O": {
"f1-score": 0.9060251089982665,
"precision": 0.9388199433921185,
"recall": 0.8754441173484926,
"support": 9851.0
},
"eval_accuracy": 0.9295991251153413,
"eval_loss": 0.20753507316112518,
"eval_macro avg": {
"f1-score": 0.8768152001003445,
"precision": 0.8984130616761289,
"recall": 0.8582916101914878,
"support": 29261.0
},
"eval_runtime": 1.3745,
"eval_samples_per_second": 58.203,
"eval_steps_per_second": 7.275,
"eval_weighted avg": {
"f1-score": 0.9286894365406706,
"precision": 0.9293063047668868,
"recall": 0.9295991251153413,
"support": 29261.0
},
"step": 41
}
],
"logging_steps": 500,
"max_steps": 205,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 143786652735600.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}