Hugging Face's logo

Deeptanshuu
/
Multilingual_Toxic_Comment_Classifier

Text Classification
Model card Files Community
Deeptanshuu commited on
Commit
228c249
·
1 Parent(s): bc3c436

Update .gitattributes to include all .bin files in LFS and remove unused weight files from the toxic classifier checkpoints.

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. .gitignore +0 -1
  3. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/config.json +0 -32
  4. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/metadata.json +0 -10
  5. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/pytorch_model.bin +0 -3
  6. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/training_state.pt +0 -3
  7. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/config.json +0 -32
  8. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/metadata.json +0 -10
  9. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/pytorch_model.bin +0 -3
  10. weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/training_state.pt +0 -3
.gitattributes CHANGED
@@ -34,3 +34,4 @@ weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/py
34
  weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/training_state.pt filter=lfs diff=lfs merge=lfs -text
35
  weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch02_20250401_141908/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
36
  weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch02_20250401_141908/training_state.pt filter=lfs diff=lfs merge=lfs -text
 
 
34
  weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/training_state.pt filter=lfs diff=lfs merge=lfs -text
35
  weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch02_20250401_141908/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
36
  weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch02_20250401_141908/training_state.pt filter=lfs diff=lfs merge=lfs -text
37
+ *.bin filter=lfs diff=lfs merge=lfs -text
.gitignore CHANGED
@@ -17,7 +17,6 @@ myenv/
17
  .gradio/*
18
 
19
  # Weights and Biases
20
- #weights/*
21
  #dataset/*
22
  cache/*
23
  wandb/*
 
17
  .gradio/*
18
 
19
  # Weights and Biases
 
20
  #dataset/*
21
  cache/*
22
  wandb/*
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "model_name": "xlm-roberta-large",
3
- "max_length": 512,
4
- "hidden_size": 1024,
5
- "num_attention_heads": 16,
6
- "model_dropout": 0.0,
7
- "freeze_layers": 8,
8
- "cache_dir": "cached_dataset",
9
- "label_columns": [
10
- "toxic",
11
- "severe_toxic",
12
- "obscene",
13
- "threat",
14
- "insult",
15
- "identity_hate"
16
- ],
17
- "batch_size": 128,
18
- "grad_accum_steps": 1,
19
- "epochs": 6,
20
- "lr": 2e-05,
21
- "num_cycles": 2,
22
- "weight_decay": 2e-07,
23
- "max_grad_norm": 1.0,
24
- "warmup_ratio": 0.1,
25
- "label_smoothing": 0.01,
26
- "min_lr_ratio": 0.01,
27
- "activation_checkpointing": true,
28
- "mixed_precision": "fp16",
29
- "_num_workers": null,
30
- "gc_frequency": 500,
31
- "tensor_float_32": false
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/metadata.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "timestamp": "20250401_122807",
3
- "epoch": 0,
4
- "model_size": 2154.283140182495,
5
- "git_commit": "unknown",
6
- "training_metrics": {
7
- "loss": 0.01687585816031432,
8
- "best_auc": 0.0
9
- }
10
- }
 
 
 
 
 
 
 
 
 
 
 
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aafb305ed86c5cc34513c5e17d75a634c8f1705625968f619857079b861c7463
3
- size 2258929598
 
 
 
 
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch00_20250401_122807/training_state.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8172a29c773809a834143fc00fe243258135f6977bc81738c905933b9bec0904
3
- size 38406894
 
 
 
 
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "model_name": "xlm-roberta-large",
3
- "max_length": 512,
4
- "hidden_size": 1024,
5
- "num_attention_heads": 16,
6
- "model_dropout": 0.0,
7
- "freeze_layers": 8,
8
- "cache_dir": "cached_dataset",
9
- "label_columns": [
10
- "toxic",
11
- "severe_toxic",
12
- "obscene",
13
- "threat",
14
- "insult",
15
- "identity_hate"
16
- ],
17
- "batch_size": 128,
18
- "grad_accum_steps": 1,
19
- "epochs": 6,
20
- "lr": 2e-05,
21
- "num_cycles": 2,
22
- "weight_decay": 2e-07,
23
- "max_grad_norm": 1.0,
24
- "warmup_ratio": 0.1,
25
- "label_smoothing": 0.01,
26
- "min_lr_ratio": 0.01,
27
- "activation_checkpointing": true,
28
- "mixed_precision": "fp16",
29
- "_num_workers": null,
30
- "gc_frequency": 500,
31
- "tensor_float_32": false
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/metadata.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "timestamp": "20250401_132337",
3
- "epoch": 1,
4
- "model_size": 2154.283140182495,
5
- "git_commit": "unknown",
6
- "training_metrics": {
7
- "loss": 0.014518294674453043,
8
- "best_auc": 0.0
9
- }
10
- }
 
 
 
 
 
 
 
 
 
 
 
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fda00042977badab8a1ab955850ff31da19e81caf0b1a40954a0034adc369cdc
3
- size 2258929598
 
 
 
 
weights/toxic_classifier_xlm-roberta-large/checkpoint_epoch01_20250401_132337/training_state.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:45879cda7495155d105c07710db341420831f9b2cf0189f915916f41d22c5a38
3
- size 38406894