Hugging Face's logo

pa-shk
/
postcard_multilabel_classifier

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
Russian
distilbert
text-embeddings-inference
Model card Files
xet
 Metrics Community
1
pa-shk commited on
Commit
8df5e85
·
1 Parent(s): 06b23d3

Training in progress, epoch 1

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. config.json +14 -18
  3. pytorch_model.bin +2 -2
  4. runs/May17_20-10-45_5087d5ccda57/1684354279.1151173/events.out.tfevents.1684354279.5087d5ccda57.447.1 +3 -0
  5. runs/May17_20-10-45_5087d5ccda57/events.out.tfevents.1684354279.5087d5ccda57.447.0 +3 -0
  6. runs/May17_20-18-35_5087d5ccda57/1684354718.0108151/events.out.tfevents.1684354718.5087d5ccda57.447.3 +3 -0
  7. runs/May17_20-18-35_5087d5ccda57/events.out.tfevents.1684354718.5087d5ccda57.447.2 +3 -0
  8. runs/May17_20-24-44_5087d5ccda57/1684355086.4441984/events.out.tfevents.1684355086.5087d5ccda57.447.5 +3 -0
  9. runs/May17_20-24-44_5087d5ccda57/events.out.tfevents.1684355086.5087d5ccda57.447.4 +3 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +2 -2
  12. training_args.bin +1 -1
  13. vocab.txt +0 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ vocab.txt filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,15 +1,13 @@
1
  {
2
- "_name_or_path": "cointegrated/rubert-tiny",
 
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "emb_size": 312,
9
- "gradient_checkpointing": false,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
12
- "hidden_size": 312,
13
  "id2label": {
14
  "0": "\u0430\u0434\u0440\u0435\u0441",
15
  "1": "\u0431\u043b\u0430\u0433\u043e\u0434\u0430\u0440\u043d\u043e\u0441\u0442\u044c \u0432 \u0442\u0435\u043a\u0441\u0442\u0435",
@@ -39,7 +37,6 @@
39
  "25": "\u0448\u043b\u044e \u043f\u0440\u0438\u0432\u0435\u0442"
40
  },
41
  "initializer_range": 0.02,
42
- "intermediate_size": 600,
43
  "label2id": {
44
  "LABEL_0": 0,
45
  "LABEL_1": 1,
@@ -68,17 +65,16 @@
68
  "LABEL_8": 8,
69
  "LABEL_9": 9
70
  },
71
- "layer_norm_eps": 1e-12,
72
  "max_position_embeddings": 512,
73
- "model_type": "bert",
74
- "num_attention_heads": 12,
75
- "num_hidden_layers": 3,
76
  "pad_token_id": 0,
77
- "position_embedding_type": "absolute",
78
  "problem_type": "multi_label_classification",
 
 
 
79
  "torch_dtype": "float32",
80
  "transformers_version": "4.28.0",
81
- "type_vocab_size": 2,
82
- "use_cache": true,
83
- "vocab_size": 29564
84
  }
 
1
  {
2
+ "_name_or_path": "DeepPavlov/distilrubert-tiny-cased-conversational-v1",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 264,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 792,
 
 
 
11
  "id2label": {
12
  "0": "\u0430\u0434\u0440\u0435\u0441",
13
  "1": "\u0431\u043b\u0430\u0433\u043e\u0434\u0430\u0440\u043d\u043e\u0441\u0442\u044c \u0432 \u0442\u0435\u043a\u0441\u0442\u0435",
 
37
  "25": "\u0448\u043b\u044e \u043f\u0440\u0438\u0432\u0435\u0442"
38
  },
39
  "initializer_range": 0.02,
 
40
  "label2id": {
41
  "LABEL_0": 0,
42
  "LABEL_1": 1,
 
65
  "LABEL_8": 8,
66
  "LABEL_9": 9
67
  },
 
68
  "max_position_embeddings": 512,
69
+ "model_type": "distilbert",
70
+ "n_heads": 12,
71
+ "n_layers": 3,
72
  "pad_token_id": 0,
 
73
  "problem_type": "multi_label_classification",
74
+ "qa_dropout": 0.1,
75
+ "seq_classif_dropout": 0.2,
76
+ "sinusoidal_pos_embds": false,
77
  "torch_dtype": "float32",
78
  "transformers_version": "4.28.0",
79
+ "vocab_size": 30522
 
 
80
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44c2d5f45d8c2e711d130dc696058379f3aeb366e0e9d80d80148ce56c6c7fd5
3
- size 47191583
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687c4a769d17b676a82cb686681404efb4c14f422e91b64853b0b246393b603a
3
+ size 41500761
runs/May17_20-10-45_5087d5ccda57/1684354279.1151173/events.out.tfevents.1684354279.5087d5ccda57.447.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c1d478bae6d594ee6c268d0007be4286c1ac77b8f6c8c92c18b61f23c3aef7
3
+ size 5873
runs/May17_20-10-45_5087d5ccda57/events.out.tfevents.1684354279.5087d5ccda57.447.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562292e884326b922c53015e8c14eb5ae34ff30e69a0be7a0ba50e1705b5c40c
3
+ size 6796
runs/May17_20-18-35_5087d5ccda57/1684354718.0108151/events.out.tfevents.1684354718.5087d5ccda57.447.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1e416a6e0f82af29ccfccfc8085d718ebbb7129d73fb0b355bf0b4e69f8d40
3
+ size 5873
runs/May17_20-18-35_5087d5ccda57/events.out.tfevents.1684354718.5087d5ccda57.447.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e79351a6a46b7c6cde5d50625bc3bc5cba34679ffa7b03a0ffa3d3a2992d7a
3
+ size 6797
runs/May17_20-24-44_5087d5ccda57/1684355086.4441984/events.out.tfevents.1684355086.5087d5ccda57.447.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b30c975df9a31d130634f1f2d6d8a56ca934edb95ae00daf66f6688b5327e73
3
+ size 5873
runs/May17_20-24-44_5087d5ccda57/events.out.tfevents.1684355086.5087d5ccda57.447.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad02471a91536abf29705441973820d72068835db0c6556c9082c161f1457be6
3
+ size 7067
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -4,12 +4,12 @@
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
- "model_max_length": 512,
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
  "strip_accents": null,
12
  "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
  "unk_token": "[UNK]"
15
  }
 
4
  "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
  "strip_accents": null,
12
  "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "DistilBertTokenizer",
14
  "unk_token": "[UNK]"
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b4b548516828cb634914ec5a988d40951d9d91fe13061d88f6fbc195ebfcefa
3
  size 3579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1b748dd27c87cb9fb026f355dbab023cb0ed265966b9e4211adf79815dc33d
3
  size 3579
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff