longformer-sep_tok / checkpoint-243 /trainer_state.json
Theoreticallyhugo's picture
Training in progress, epoch 3, checkpoint
5f28c94 verified
raw
history blame
4.46 kB
{
"best_metric": 0.25671303272247314,
"best_model_checkpoint": "longformer-sep_tok/checkpoint-162",
"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_Claim": {
"f1-score": 0.580553004795429,
"precision": 0.5136306192453511,
"recall": 0.6675269826372595,
"support": 4262.0
},
"eval_MajorClaim": {
"f1-score": 0.6929252383341696,
"precision": 0.7583745194947831,
"recall": 0.6378752886836028,
"support": 2165.0
},
"eval_O": {
"f1-score": 0.9968272281511393,
"precision": 0.9967861557478368,
"recall": 0.996868303939344,
"support": 12134.0
},
"eval_Premise": {
"f1-score": 0.8769487750556793,
"precision": 0.9107806691449815,
"recall": 0.8455403021704119,
"support": 13039.0
},
"eval_accuracy": 0.8654113924050633,
"eval_loss": 0.32089120149612427,
"eval_macro avg": {
"f1-score": 0.7868135615841043,
"precision": 0.7948929909082382,
"recall": 0.7869527193576545,
"support": 31600.0
},
"eval_runtime": 5.9486,
"eval_samples_per_second": 13.449,
"eval_steps_per_second": 1.681,
"eval_weighted avg": {
"f1-score": 0.8703967313850799,
"precision": 0.8797989523023909,
"recall": 0.8654113924050633,
"support": 31600.0
},
"step": 81
},
{
"epoch": 2.0,
"eval_Claim": {
"f1-score": 0.6029902384776968,
"precision": 0.6369094231271208,
"recall": 0.5725011731581418,
"support": 4262.0
},
"eval_MajorClaim": {
"f1-score": 0.8179940325912326,
"precision": 0.8129562043795621,
"recall": 0.8230946882217091,
"support": 2165.0
},
"eval_O": {
"f1-score": 0.9984359565360553,
"precision": 0.9972866304884065,
"recall": 0.9995879347288611,
"support": 12134.0
},
"eval_Premise": {
"f1-score": 0.9017917895214335,
"precision": 0.8891539321654864,
"recall": 0.9147940793005599,
"support": 13039.0
},
"eval_accuracy": 0.8949050632911393,
"eval_loss": 0.25671303272247314,
"eval_macro avg": {
"f1-score": 0.8303030042816045,
"precision": 0.8340765475401439,
"recall": 0.8274944688523179,
"support": 31600.0
},
"eval_runtime": 5.97,
"eval_samples_per_second": 13.4,
"eval_steps_per_second": 1.675,
"eval_weighted avg": {
"f1-score": 0.8928603328205832,
"precision": 0.8914339316361279,
"recall": 0.8949050632911393,
"support": 31600.0
},
"step": 162
},
{
"epoch": 3.0,
"eval_Claim": {
"f1-score": 0.6010706092276319,
"precision": 0.6579241071428571,
"recall": 0.5532613796339747,
"support": 4262.0
},
"eval_MajorClaim": {
"f1-score": 0.8101840181497353,
"precision": 0.8917869034406215,
"recall": 0.7422632794457275,
"support": 2165.0
},
"eval_O": {
"f1-score": 0.997983456109305,
"precision": 0.9967118783394986,
"recall": 0.9992582825119499,
"support": 12134.0
},
"eval_Premise": {
"f1-score": 0.9085203780271707,
"precision": 0.8758630507509432,
"recall": 0.9437073395199018,
"support": 13039.0
},
"eval_accuracy": 0.8985759493670886,
"eval_loss": 0.2674676775932312,
"eval_macro avg": {
"f1-score": 0.8294396153784607,
"precision": 0.8555714849184801,
"recall": 0.8096225702778885,
"support": 31600.0
},
"eval_runtime": 6.0212,
"eval_samples_per_second": 13.286,
"eval_steps_per_second": 1.661,
"eval_weighted avg": {
"f1-score": 0.894668981055346,
"precision": 0.8939642861109123,
"recall": 0.8985759493670886,
"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": 431366198180400.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}