Theoreticallyhugo's picture
Training in progress, epoch 3, checkpoint
8d70ca7 verified
{
"best_metric": 0.28271517157554626,
"best_model_checkpoint": "longformer-sep_tok_full_labels/checkpoint-243",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 243,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_B-Claim": {
"f1-score": 0.21800947867298578,
"precision": 0.3333333333333333,
"recall": 0.1619718309859155,
"support": 284.0
},
"eval_B-MajorClaim": {
"f1-score": 0.0,
"precision": 0.0,
"recall": 0.0,
"support": 141.0
},
"eval_B-Premise": {
"f1-score": 0.8305489260143198,
"precision": 0.71900826446281,
"recall": 0.9830508474576272,
"support": 708.0
},
"eval_I-Claim": {
"f1-score": 0.5590492696211935,
"precision": 0.5643589102724319,
"recall": 0.5538386068187393,
"support": 4077.0
},
"eval_I-MajorClaim": {
"f1-score": 0.7399038461538461,
"precision": 0.7205056179775281,
"recall": 0.7603754940711462,
"support": 2024.0
},
"eval_I-Premise": {
"f1-score": 0.8867229093291834,
"precision": 0.8883965205974068,
"recall": 0.8850555918901243,
"support": 12232.0
},
"eval_O": {
"f1-score": 0.9976548035383666,
"precision": 0.9961383616794018,
"recall": 0.9991758694577221,
"support": 12134.0
},
"eval_accuracy": 0.8699050632911393,
"eval_loss": 0.32671716809272766,
"eval_macro avg": {
"f1-score": 0.6045556047614136,
"precision": 0.6031058583318446,
"recall": 0.6204954629544678,
"support": 31600.0
},
"eval_runtime": 6.234,
"eval_samples_per_second": 12.833,
"eval_steps_per_second": 1.604,
"eval_weighted avg": {
"f1-score": 0.8664142595402331,
"precision": 0.8644597558999653,
"recall": 0.8699050632911393,
"support": 31600.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_B-Claim": {
"f1-score": 0.5352697095435685,
"precision": 0.6515151515151515,
"recall": 0.45422535211267606,
"support": 284.0
},
"eval_B-MajorClaim": {
"f1-score": 0.7766990291262136,
"precision": 0.7142857142857143,
"recall": 0.851063829787234,
"support": 141.0
},
"eval_B-Premise": {
"f1-score": 0.8802721088435375,
"precision": 0.8490813648293963,
"recall": 0.9138418079096046,
"support": 708.0
},
"eval_I-Claim": {
"f1-score": 0.5747557221255521,
"precision": 0.6325869180907484,
"recall": 0.5266127054206524,
"support": 4077.0
},
"eval_I-MajorClaim": {
"f1-score": 0.7833260963960051,
"precision": 0.6986831913245546,
"recall": 0.8913043478260869,
"support": 2024.0
},
"eval_I-Premise": {
"f1-score": 0.8995515695067264,
"precision": 0.8971377459749553,
"recall": 0.9019784172661871,
"support": 12232.0
},
"eval_O": {
"f1-score": 0.9971231300345225,
"precision": 0.9945072962780783,
"recall": 0.9997527608373167,
"support": 12134.0
},
"eval_accuracy": 0.8864240506329114,
"eval_loss": 0.28716403245925903,
"eval_macro avg": {
"f1-score": 0.7781424807965893,
"precision": 0.7768281974712284,
"recall": 0.791254174451394,
"support": 31600.0
},
"eval_runtime": 6.2816,
"eval_samples_per_second": 12.736,
"eval_steps_per_second": 1.592,
"eval_weighted avg": {
"f1-score": 0.8834146129726252,
"precision": 0.8835831101628018,
"recall": 0.8864240506329114,
"support": 31600.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_B-Claim": {
"f1-score": 0.5580448065173116,
"precision": 0.6618357487922706,
"recall": 0.4823943661971831,
"support": 284.0
},
"eval_B-MajorClaim": {
"f1-score": 0.8046875,
"precision": 0.8956521739130435,
"recall": 0.7304964539007093,
"support": 141.0
},
"eval_B-Premise": {
"f1-score": 0.8868421052631579,
"precision": 0.8300492610837439,
"recall": 0.9519774011299436,
"support": 708.0
},
"eval_I-Claim": {
"f1-score": 0.5488426262920367,
"precision": 0.6751432664756447,
"recall": 0.4623497669855286,
"support": 4077.0
},
"eval_I-MajorClaim": {
"f1-score": 0.8110936682365254,
"precision": 0.8620689655172413,
"recall": 0.7658102766798419,
"support": 2024.0
},
"eval_I-Premise": {
"f1-score": 0.9039491427470623,
"precision": 0.854842235662756,
"recall": 0.9590418574231524,
"support": 12232.0
},
"eval_O": {
"f1-score": 0.9979824597521307,
"precision": 0.9972023368715544,
"recall": 0.9987638041865832,
"support": 12134.0
},
"eval_accuracy": 0.892373417721519,
"eval_loss": 0.28271517157554626,
"eval_macro avg": {
"f1-score": 0.7873489012583177,
"precision": 0.825256284045179,
"recall": 0.7644048466432775,
"support": 31600.0
},
"eval_runtime": 6.2071,
"eval_samples_per_second": 12.888,
"eval_steps_per_second": 1.611,
"eval_weighted avg": {
"f1-score": 0.88435885840807,
"precision": 0.8846770016417851,
"recall": 0.892373417721519,
"support": 31600.0
},
"step": 243
}
],
"logging_steps": 500,
"max_steps": 1620,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"total_flos": 431372438154000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}