longformer-simple / checkpoint-81 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 1, checkpoint
dc09f6a verified
raw
history blame
1.82 kB
{
"best_metric": 0.5488611459732056,
"best_model_checkpoint": "longformer-simple/checkpoint-81",
"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": 0.46242900830056793,
"precision": 0.43257049448304047,
"recall": 0.496715157203191,
"support": 4262.0
},
"eval_MajorClaim": {
"f1-score": 0.5626477541371159,
"precision": 0.6522533495736906,
"recall": 0.49468822170900695,
"support": 2165.0
},
"eval_O": {
"f1-score": 0.8691687871077185,
"precision": 0.911293908403735,
"recall": 0.8307661126874747,
"support": 9868.0
},
"eval_Premise": {
"f1-score": 0.8615178272046495,
"precision": 0.8377046804810897,
"recall": 0.88672444205844,
"support": 13039.0
},
"eval_accuracy": 0.7823004022635849,
"eval_loss": 0.5488611459732056,
"eval_macro avg": {
"f1-score": 0.6889408441875129,
"precision": 0.708455608235389,
"recall": 0.6772234834145282,
"support": 29334.0
},
"eval_runtime": 5.8698,
"eval_samples_per_second": 13.629,
"eval_steps_per_second": 1.704,
"eval_weighted avg": {
"f1-score": 0.7840489998358311,
"precision": 0.7899101236188295,
"recall": 0.7823004022635849,
"support": 29334.0
},
"step": 81
}
],
"logging_steps": 500,
"max_steps": 1620,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"total_flos": 143788732726800.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}