longformer-sep_tok / checkpoint-81 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 1, checkpoint
d13867b verified
raw
history blame
1.78 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 81,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_Claim": {
"f1-score": 0.5385059461955894,
"precision": 0.6267132491265789,
"recall": 0.4720647773279352,
"support": 4940.0
},
"eval_MajorClaim": {
"f1-score": 0.7814784727863526,
"precision": 0.9588039867109635,
"recall": 0.6595063985374772,
"support": 2188.0
},
"eval_O": {
"f1-score": 0.9938608715302625,
"precision": 0.9996969237763298,
"recall": 0.9880925634688834,
"support": 13353.0
},
"eval_Premise": {
"f1-score": 0.8968837690149166,
"precision": 0.8455112497215416,
"recall": 0.954902824076986,
"support": 15899.0
},
"eval_accuracy": 0.8837548103353491,
"eval_loss": 0.2860471308231354,
"eval_macro avg": {
"f1-score": 0.8026822648817803,
"precision": 0.8576813523338533,
"recall": 0.7686416408528204,
"support": 36380.0
},
"eval_runtime": 4.9572,
"eval_samples_per_second": 16.34,
"eval_steps_per_second": 2.219,
"eval_weighted avg": {
"f1-score": 0.8768739289107891,
"precision": 0.8792073379911217,
"recall": 0.8837548103353491,
"support": 36380.0
},
"step": 81
}
],
"logging_steps": 500,
"max_steps": 4050,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"total_flos": 143342183867400.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}