teru00801 commited on
Commit
adecbb4
·
verified ·
1 Parent(s): 9f6f315

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -58,3 +58,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
58
  20260306_061847/analysis_bundle/cartography/task1_cartography.png filter=lfs diff=lfs merge=lfs -text
59
  20260306_075806/analysis_bundle/cartography/task1_cartography.csv filter=lfs diff=lfs merge=lfs -text
60
  20260306_075806/analysis_bundle/cartography/task1_cartography.png filter=lfs diff=lfs merge=lfs -text
 
 
 
58
  20260306_061847/analysis_bundle/cartography/task1_cartography.png filter=lfs diff=lfs merge=lfs -text
59
  20260306_075806/analysis_bundle/cartography/task1_cartography.csv filter=lfs diff=lfs merge=lfs -text
60
  20260306_075806/analysis_bundle/cartography/task1_cartography.png filter=lfs diff=lfs merge=lfs -text
61
+ 20260306_145453/analysis_bundle/cartography/task1_cartography.csv filter=lfs diff=lfs merge=lfs -text
62
+ 20260306_145453/analysis_bundle/cartography/task1_cartography.png filter=lfs diff=lfs merge=lfs -text
20260306_145453/analysis_bundle/cartography/summary.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epochs": 9,
3
+ "task1_rows": 17186,
4
+ "task1_lowmean_threshold": 0.38709576874971385,
5
+ "task1_suspects": 86,
6
+ "plot_saved": true
7
+ }
20260306_145453/analysis_bundle/cartography/task1_cartography.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a509ab0205a22426e7c85b3da2878aa61ef203f11251596195e2e5a10b9547
3
+ size 62158610
20260306_145453/analysis_bundle/cartography/task1_cartography.png ADDED

Git LFS Details

  • SHA256: a186393f0ee5477acdf5064ee98daea2802f74b06b3ef68f24219c35e15ce9b1
  • Pointer size: 131 Bytes
  • Size of remote file: 250 kB
20260306_145453/analysis_bundle/metrics/metrics.jsonl ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {"epoch": 1, "train_loss": 0.25738994192591935, "acc": 0.8633993743482794, "f1": 0.7962674961119751, "precision": 0.6975476839237057, "recall": 0.927536231884058, "selection_score": 0.7771149228458543, "score": 0.7771149228458543}
2
+ {"epoch": 2, "train_loss": 0.12990510383317636, "acc": 0.8680917622523462, "f1": 0.8064269319051263, "precision": 0.6980132450331126, "recall": 0.9547101449275363, "selection_score": 0.7810865589972756, "score": 0.7810865589972756}
3
+ {"epoch": 3, "train_loss": 0.1066696947570457, "acc": 0.872784150156413, "f1": 0.8114374034003091, "precision": 0.7075471698113207, "recall": 0.9510869565217391, "selection_score": 0.7893778438714569, "score": 0.7893778438714569}
4
+ {"epoch": 4, "train_loss": 0.09383859275038853, "acc": 0.864963503649635, "f1": 0.8024408848207475, "precision": 0.6930171277997365, "recall": 0.9528985507246377, "selection_score": 0.77624706035528, "score": 0.77624706035528}
5
+ {"epoch": 5, "train_loss": 0.07789141102239143, "acc": 0.8925964546402503, "f1": 0.8333333333333334, "precision": 0.7529239766081871, "recall": 0.9329710144927537, "selection_score": 0.8277806743135211, "score": 0.8277806743135211}
6
+ {"epoch": 6, "train_loss": 0.07334925225654314, "acc": 0.870177267987487, "f1": 0.8074245939675174, "precision": 0.7044534412955465, "recall": 0.9456521739130435, "selection_score": 0.7858296825120024, "score": 0.7858296825120024}
7
+ {"epoch": 7, "train_loss": 0.06994440331362015, "acc": 0.8962460896767466, "f1": 0.8388663967611336, "precision": 0.7584187408491947, "recall": 0.9384057971014492, "selection_score": 0.8334846552755548, "score": 0.8334846552755548}
8
+ {"epoch": 8, "train_loss": 0.06400413680215214, "acc": 0.8931178310740354, "f1": 0.8318293683347006, "precision": 0.760119940029985, "recall": 0.9184782608695652, "selection_score": 0.8319229722990433, "score": 0.8319229722990433}
9
+ {"epoch": 9, "train_loss": 0.06349940231719682, "acc": 0.8931178310740354, "f1": 0.830997526793075, "precision": 0.762481089258699, "recall": 0.9130434782608695, "selection_score": 0.8331414985624627, "score": 0.8331414985624627}
20260306_145453/analysis_bundle/predictions/final_eval_predictions.csv ADDED
The diff for this file is too large to render. See raw diff
 
20260306_145453/analysis_bundle/predictions/final_eval_predictions_evalonly.csv ADDED
The diff for this file is too large to render. See raw diff
 
20260306_145453/analysis_bundle/summaries/final_eval_summary.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ dataset,rows_evaluated,acc,f1,precision,recall,always_pick_acc,always_decline_acc
2
+ data_for_deberta/dedup_split/risk_test.csv,2879,0.8753039249739493,0.8077129084092126,0.7119924457034938,0.9331683168316832,0.28065300451545677,0.7193469954845433
20260306_145453/analysis_bundle/summaries/final_eval_summary_evalonly.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ run_dir,model_path,dataset,rows_raw,rows_evaluated,acc,f1,precision,recall,always_pick_acc,always_decline_acc
2
+ outputs/task1_binary_runs/20260306_145453,outputs/task1_binary_runs/20260306_145453/best_model.pt,data_for_deberta/dedup_split/risk_test.csv,2879,2879,0.8753039249739493,0.8077129084092126,0.7119924457034938,0.9331683168316832,0.28065300451545677,0.7193469954845433
20260306_145453/analysis_bundle/summaries/summary.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_epoch": 7,
3
+ "best_score": 0.8334846552755548,
4
+ "best_selection_score": 0.8334846552755548,
5
+ "best_val_metrics_at_selection": {
6
+ "acc": 0.8962460896767466,
7
+ "f1": 0.8388663967611336,
8
+ "precision": 0.7584187408491947,
9
+ "recall": 0.9384057971014492
10
+ },
11
+ "model_selection": {
12
+ "metric": "recall-floor-constrained-fbeta",
13
+ "beta": 0.5,
14
+ "recall_floor": 0.9,
15
+ "recall_floor_penalty": 2.0,
16
+ "acc_weight": 0.05
17
+ },
18
+ "data_provenance": {
19
+ "train_csv": {
20
+ "path": "data_for_deberta/Risk-only-pick/task1_risk_training_20260225.csv",
21
+ "sha256_16": "500373d3a3a8bab3",
22
+ "size_bytes": 61499134
23
+ },
24
+ "val_csv_source": {
25
+ "path": "data_for_deberta/dedup_split/risk_val.csv",
26
+ "sha256_16": "301a26bc2dd301f3",
27
+ "size_bytes": 6212143
28
+ },
29
+ "final_eval_csv": {
30
+ "path": "data_for_deberta/dedup_split/risk_test.csv",
31
+ "sha256_16": "877ab7b227ff80b4",
32
+ "size_bytes": 9641218
33
+ }
34
+ },
35
+ "train_rows": 17186,
36
+ "val_rows": 1918,
37
+ "final_eval_rows": 2879,
38
+ "val_metrics": {
39
+ "acc": 0.8962460896767466,
40
+ "f1": 0.8388663967611336,
41
+ "precision": 0.7584187408491947,
42
+ "recall": 0.9384057971014492
43
+ },
44
+ "final_eval_metrics": {
45
+ "acc": 0.8753039249739493,
46
+ "f1": 0.8077129084092126,
47
+ "precision": 0.7119924457034938,
48
+ "recall": 0.9331683168316832
49
+ },
50
+ "final_eval_baseline": {
51
+ "always_pick_acc": 0.28065300451545677,
52
+ "always_decline_acc": 0.7193469954845433
53
+ }
54
+ }