longformer-simple / checkpoint-324 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 4, checkpoint
c4f6c45 verified
raw
history blame
5.77 kB
{
"best_metric": 0.4725272059440613,
"best_model_checkpoint": "longformer-simple/checkpoint-324",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 324,
"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
},
{
"epoch": 2.0,
"eval_Claim": {
"f1-score": 0.5457327068079991,
"precision": 0.5107383923092657,
"recall": 0.5858751759737213,
"support": 4262.0
},
"eval_MajorClaim": {
"f1-score": 0.6722085773663329,
"precision": 0.5687340153452686,
"recall": 0.8217090069284064,
"support": 2165.0
},
"eval_O": {
"f1-score": 0.8773589977955805,
"precision": 0.9344863131370977,
"recall": 0.8268139440616133,
"support": 9868.0
},
"eval_Premise": {
"f1-score": 0.8678243902439025,
"precision": 0.8834419195931988,
"recall": 0.852749443975765,
"support": 13039.0
},
"eval_accuracy": 0.8029590236585532,
"eval_loss": 0.5075464248657227,
"eval_macro avg": {
"f1-score": 0.7407811680534537,
"precision": 0.7243501600962077,
"recall": 0.7717868927348766,
"support": 29334.0
},
"eval_runtime": 5.9473,
"eval_samples_per_second": 13.451,
"eval_steps_per_second": 1.681,
"eval_weighted avg": {
"f1-score": 0.8097969994222006,
"precision": 0.8232353684753937,
"recall": 0.8029590236585532,
"support": 29334.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_Claim": {
"f1-score": 0.4978109708987896,
"precision": 0.5516552511415526,
"recall": 0.45354293758798686,
"support": 4262.0
},
"eval_MajorClaim": {
"f1-score": 0.7357876283496118,
"precision": 0.8036105032822757,
"recall": 0.6785219399538106,
"support": 2165.0
},
"eval_O": {
"f1-score": 0.8891011355194736,
"precision": 0.9331699710403207,
"recall": 0.8490068909606809,
"support": 9868.0
},
"eval_Premise": {
"f1-score": 0.8770979581655561,
"precision": 0.8191560170394037,
"recall": 0.9438607255157604,
"support": 13039.0
},
"eval_accuracy": 0.821129065248517,
"eval_loss": 0.5219377279281616,
"eval_macro avg": {
"f1-score": 0.7499494232333578,
"precision": 0.7768979356258882,
"recall": 0.7312331235045597,
"support": 29334.0
},
"eval_runtime": 5.8364,
"eval_samples_per_second": 13.707,
"eval_steps_per_second": 1.713,
"eval_weighted avg": {
"f1-score": 0.815598992812927,
"precision": 0.8174973750724106,
"recall": 0.821129065248517,
"support": 29334.0
},
"step": 243
},
{
"epoch": 4.0,
"eval_Claim": {
"f1-score": 0.5811481218993623,
"precision": 0.5851569933396765,
"recall": 0.5771938057250118,
"support": 4262.0
},
"eval_MajorClaim": {
"f1-score": 0.761714412613813,
"precision": 0.7335329341317365,
"recall": 0.792147806004619,
"support": 2165.0
},
"eval_O": {
"f1-score": 0.8977645611156685,
"precision": 0.9085720215857203,
"recall": 0.8872111876773409,
"support": 9868.0
},
"eval_Premise": {
"f1-score": 0.8891009734682191,
"precision": 0.8851474612344178,
"recall": 0.8930899608865711,
"support": 13039.0
},
"eval_accuracy": 0.8377650507943001,
"eval_loss": 0.4725272059440613,
"eval_macro avg": {
"f1-score": 0.7824320172742658,
"precision": 0.7781023525728877,
"recall": 0.7874106900733857,
"support": 29334.0
},
"eval_runtime": 5.8763,
"eval_samples_per_second": 13.614,
"eval_steps_per_second": 1.702,
"eval_weighted avg": {
"f1-score": 0.8378705011585708,
"precision": 0.8382513248807655,
"recall": 0.8377650507943001,
"support": 29334.0
},
"step": 324
}
],
"logging_steps": 500,
"max_steps": 1620,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"total_flos": 575154930907200.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}