MichaelSargious commited on
Commit
2e34bb6
·
verified ·
1 Parent(s): 539a92a

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +22 -17
  2. model.safetensors +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,13 +1,16 @@
1
  {
2
- "_name_or_path": "distilbert/distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForTokenClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
 
11
  "id2label": {
12
  "0": "VOID",
13
  "1": "craft_costs.gross_amount",
@@ -20,6 +23,7 @@
20
  "8": "vendor_name"
21
  },
22
  "initializer_range": 0.02,
 
23
  "label2id": {
24
  "VOID": 0,
25
  "craft_costs.gross_amount": 1,
@@ -31,16 +35,17 @@
31
  "vendor_address.zip": 5,
32
  "vendor_name": 8
33
  },
34
- "max_position_embeddings": 512,
35
- "model_type": "distilbert",
36
- "n_heads": 12,
37
- "n_layers": 6,
38
- "pad_token_id": 0,
39
- "qa_dropout": 0.1,
40
- "seq_classif_dropout": 0.2,
41
- "sinusoidal_pos_embds": false,
42
- "tie_weights_": true,
43
  "torch_dtype": "float32",
44
  "transformers_version": "4.46.1",
45
- "vocab_size": 30522
 
 
46
  }
 
1
  {
2
+ "_name_or_path": "FacebookAI/xlm-roberta-large-finetuned-conll03-german",
3
+ "_num_labels": 9,
4
  "architectures": [
5
+ "XLMRobertaForTokenClassification"
6
  ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
  "id2label": {
15
  "0": "VOID",
16
  "1": "craft_costs.gross_amount",
 
23
  "8": "vendor_name"
24
  },
25
  "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
  "label2id": {
28
  "VOID": 0,
29
  "craft_costs.gross_amount": 1,
 
35
  "vendor_address.zip": 5,
36
  "vendor_name": 8
37
  },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 514,
40
+ "model_type": "xlm-roberta",
41
+ "num_attention_heads": 16,
42
+ "num_hidden_layers": 24,
43
+ "output_past": true,
44
+ "pad_token_id": 1,
45
+ "position_embedding_type": "absolute",
 
46
  "torch_dtype": "float32",
47
  "transformers_version": "4.46.1",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 250002
51
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8791d06e8a5c76a18418779e94f386921f9d3390a82891f7650dae09550bf61f
3
- size 265491548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d93032ef6880d1ff8a5b40ba4209d0543662aaf38424539fdaf90a5474aabb0
3
+ size 2235448756
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80ea6713026d9aa17228ad78b2d91e4e2c0db4a6a84888ba1917b944165400b5
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74189d91b5820514e7f7e98491697c2d55ec8e88a7c118e3260134f9db1c7d01
3
  size 5176