Hugging Face's logo

Joshi-Aryan
/
Fine_Tuned_HF_Language_Identification_Model

Text Classification
Transformers
PyTorch
xlm-roberta
text-embeddings-inference
Model card Files
xet
Joshi-Aryan commited on
Commit
c90986b
·
1 Parent(s): da7d83d

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +13 -0
  2. checkpoint-1000/config.json +43 -0
  3. checkpoint-1000/optimizer.pt +3 -0
  4. checkpoint-1000/pytorch_model.bin +3 -0
  5. checkpoint-1000/rng_state.pth +3 -0
  6. checkpoint-1000/scaler.pt +3 -0
  7. checkpoint-1000/scheduler.pt +3 -0
  8. checkpoint-1000/sentencepiece.bpe.model +3 -0
  9. checkpoint-1000/special_tokens_map.json +15 -0
  10. checkpoint-1000/tokenizer.json +3 -0
  11. checkpoint-1000/tokenizer_config.json +19 -0
  12. checkpoint-1000/trainer_state.json +15 -0
  13. checkpoint-1000/training_args.bin +3 -0
  14. checkpoint-1500/config.json +43 -0
  15. checkpoint-1500/optimizer.pt +3 -0
  16. checkpoint-1500/pytorch_model.bin +3 -0
  17. checkpoint-1500/rng_state.pth +3 -0
  18. checkpoint-1500/scaler.pt +3 -0
  19. checkpoint-1500/scheduler.pt +3 -0
  20. checkpoint-1500/sentencepiece.bpe.model +3 -0
  21. checkpoint-1500/special_tokens_map.json +15 -0
  22. checkpoint-1500/tokenizer.json +3 -0
  23. checkpoint-1500/tokenizer_config.json +19 -0
  24. checkpoint-1500/trainer_state.json +15 -0
  25. checkpoint-1500/training_args.bin +3 -0
  26. checkpoint-2000/config.json +43 -0
  27. checkpoint-2000/optimizer.pt +3 -0
  28. checkpoint-2000/pytorch_model.bin +3 -0
  29. checkpoint-2000/rng_state.pth +3 -0
  30. checkpoint-2000/scaler.pt +3 -0
  31. checkpoint-2000/scheduler.pt +3 -0
  32. checkpoint-2000/sentencepiece.bpe.model +3 -0
  33. checkpoint-2000/special_tokens_map.json +15 -0
  34. checkpoint-2000/tokenizer.json +3 -0
  35. checkpoint-2000/tokenizer_config.json +19 -0
  36. checkpoint-2000/trainer_state.json +15 -0
  37. checkpoint-2000/training_args.bin +3 -0
  38. checkpoint-2500/config.json +43 -0
  39. checkpoint-2500/optimizer.pt +3 -0
  40. checkpoint-2500/pytorch_model.bin +3 -0
  41. checkpoint-2500/rng_state.pth +3 -0
  42. checkpoint-2500/scaler.pt +3 -0
  43. checkpoint-2500/scheduler.pt +3 -0
  44. checkpoint-2500/sentencepiece.bpe.model +3 -0
  45. checkpoint-2500/special_tokens_map.json +15 -0
  46. checkpoint-2500/tokenizer.json +3 -0
  47. checkpoint-2500/tokenizer_config.json +19 -0
  48. checkpoint-2500/trainer_state.json +15 -0
  49. checkpoint-2500/training_args.bin +3 -0
  50. checkpoint-3000/config.json +43 -0
.gitattributes CHANGED
@@ -36,3 +36,16 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  arabic_corpus.csv filter=lfs diff=lfs merge=lfs -text
37
  hindi_corpus.csv filter=lfs diff=lfs merge=lfs -text
38
  russian_corpus.csv filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  arabic_corpus.csv filter=lfs diff=lfs merge=lfs -text
37
  hindi_corpus.csv filter=lfs diff=lfs merge=lfs -text
38
  russian_corpus.csv filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
+ checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ checkpoint-5500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ checkpoint-6500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-1000/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "arabic",
15
+ "1": "english",
16
+ "2": "french",
17
+ "3": "german",
18
+ "4": "russian"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "arabic": 0,
24
+ "english": 1,
25
+ "french": 2,
26
+ "german": 3,
27
+ "russian": 4
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "xlm-roberta",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.28.0",
40
+ "type_vocab_size": 1,
41
+ "use_cache": true,
42
+ "vocab_size": 250002
43
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035111fdb4d604ca283c9b9144812f36070c5ffaed16acb0c6b9f06e9885d8ef
3
+ size 2224498234
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e543d77fd926d39ab1d2f039fc0d394395d4ce30ff5d798aabd4d7839fb648e
3
+ size 1112263858
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb31bbdf7d9c5b7925e77559815c830119baa2fca30f37fb6aaab50bb6d991e
3
+ size 14244
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5bcf736f1b79303746fdacc768ece77446afaa1877de8dda3da8348fbcc7d5
3
+ size 988
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9878794dee7a9fc2f1e2977e16568f0d445f879bd810524aafb5aa9662642230
3
+ size 1064
checkpoint-1000/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-1000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
3
+ size 17082758
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.30012004801920766,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 6664,
11
+ "num_train_epochs": 2,
12
+ "total_flos": 2289752745025152.0,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfc6d5b87db9956e13fcac9bb19bcdb3ef9699bb6d06c99bc4cd34f72403b5d
3
+ size 4024
checkpoint-1500/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "arabic",
15
+ "1": "english",
16
+ "2": "french",
17
+ "3": "german",
18
+ "4": "russian"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "arabic": 0,
24
+ "english": 1,
25
+ "french": 2,
26
+ "german": 3,
27
+ "russian": 4
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "xlm-roberta",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.28.0",
40
+ "type_vocab_size": 1,
41
+ "use_cache": true,
42
+ "vocab_size": 250002
43
+ }
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8939341b8e960508664efe97d5c04b21d50d002d6e34a5255ccd9be656fa4583
3
+ size 2224498234
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e3bea9b0c14ea4d6002d6b6b3fe155ebdf941aae1b2032500030036c92aa6f9
3
+ size 1112263858
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2e9972f20a1c6a3e1f3d986d339d5b18060252505bf307e90192b5ff67bee9
3
+ size 14244
checkpoint-1500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0617efbfbb7fc93b69f89ca8af67f24948e1b623a640583096a01c1e14d1a779
3
+ size 988
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947bcff8be39e16d93459c65045979b4f4e7391de422d205370ed75adf2cf818
3
+ size 1064
checkpoint-1500/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-1500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
3
+ size 17082758
checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.45018007202881155,
5
+ "global_step": 1500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 6664,
11
+ "num_train_epochs": 2,
12
+ "total_flos": 3427344033968256.0,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfc6d5b87db9956e13fcac9bb19bcdb3ef9699bb6d06c99bc4cd34f72403b5d
3
+ size 4024
checkpoint-2000/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "arabic",
15
+ "1": "english",
16
+ "2": "french",
17
+ "3": "german",
18
+ "4": "russian"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "arabic": 0,
24
+ "english": 1,
25
+ "french": 2,
26
+ "german": 3,
27
+ "russian": 4
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "xlm-roberta",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.28.0",
40
+ "type_vocab_size": 1,
41
+ "use_cache": true,
42
+ "vocab_size": 250002
43
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5c9506e4f39cdbc3af672d4d67543ed0aac71410a09676e08b4dd242997ec24
3
+ size 2224498234
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9411f3ca927abef81eea2d70d8c9924b86ba017963d0dc3120a597df8b1d7523
3
+ size 1112263858
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e66fbaebc79bf7c3a7d803385b9042c1ee2e1282975ecb6e28bdddf202c62b45
3
+ size 14244
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c494b3df6951b3dfb8d6d667cd822246eceb1361f5933fe08326cb830fde1b2c
3
+ size 988
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dcecb64fbe503a9351db23cde6507c02a6349d16bd78d72f1f281cb8a2eb4d6
3
+ size 1064
checkpoint-2000/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-2000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
3
+ size 17082758
checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6002400960384153,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 6664,
11
+ "num_train_epochs": 2,
12
+ "total_flos": 4569868788082560.0,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfc6d5b87db9956e13fcac9bb19bcdb3ef9699bb6d06c99bc4cd34f72403b5d
3
+ size 4024
checkpoint-2500/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "arabic",
15
+ "1": "english",
16
+ "2": "french",
17
+ "3": "german",
18
+ "4": "russian"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "arabic": 0,
24
+ "english": 1,
25
+ "french": 2,
26
+ "german": 3,
27
+ "russian": 4
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "xlm-roberta",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.28.0",
40
+ "type_vocab_size": 1,
41
+ "use_cache": true,
42
+ "vocab_size": 250002
43
+ }
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f34072663e7d19b085d14a6f6f603f3593a02c04e5a7cf45021c74be20df72
3
+ size 2224498234
checkpoint-2500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f737b6e4f38cf9d48930ebd4c3aa7355c176d29ad78fc2b97870d070d9a8f15a
3
+ size 1112263858
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaca9360678d07ba300097459dfbc25ecbad4780b3d504bd52723840f51b3895
3
+ size 14244
checkpoint-2500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e327e2fc109e7cb11a5de71c5b47a658cf81d9ad28f6990f404bf0161361e673
3
+ size 988
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0a9d338f40108c37209c103e3542be6a7bb598a8dc5b0c8ee11bc6e244c010
3
+ size 1064
checkpoint-2500/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-2500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-2500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
3
+ size 17082758
checkpoint-2500/tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7503001200480192,
5
+ "global_step": 2500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 6664,
11
+ "num_train_epochs": 2,
12
+ "total_flos": 5704763116065408.0,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfc6d5b87db9956e13fcac9bb19bcdb3ef9699bb6d06c99bc4cd34f72403b5d
3
+ size 4024
checkpoint-3000/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "arabic",
15
+ "1": "english",
16
+ "2": "french",
17
+ "3": "german",
18
+ "4": "russian"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "arabic": 0,
24
+ "english": 1,
25
+ "french": 2,
26
+ "german": 3,
27
+ "russian": 4
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "xlm-roberta",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.28.0",
40
+ "type_vocab_size": 1,
41
+ "use_cache": true,
42
+ "vocab_size": 250002
43
+ }