Elseif02 commited on
Commit
ead4c17
1 Parent(s): c0ba11a

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilbert/distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForQuestionAnswering"
@@ -13,6 +13,7 @@
13
  "model_type": "distilbert",
14
  "n_heads": 12,
15
  "n_layers": 6,
 
16
  "pad_token_id": 0,
17
  "qa_dropout": 0.1,
18
  "seq_classif_dropout": 0.2,
@@ -20,5 +21,5 @@
20
  "tie_weights_": true,
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.41.2",
23
- "vocab_size": 30522
24
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForQuestionAnswering"
 
13
  "model_type": "distilbert",
14
  "n_heads": 12,
15
  "n_layers": 6,
16
+ "output_past": true,
17
  "pad_token_id": 0,
18
  "qa_dropout": 0.1,
19
  "seq_classif_dropout": 0.2,
 
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.41.2",
24
+ "vocab_size": 119547
25
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b17a87e95782b2fc7feaf18843f403a850ca6880a3db297dd430f6ff2c748da
3
- size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ec97155844992b422006414d45d8c6d16b5cf8810fd5f1bda70915badfa2be
3
+ size 538954840
runs/Jun22_21-40-03_ccc0c999db6c/events.out.tfevents.1719092404.ccc0c999db6c.213.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a73c88af09ed9bbd8ae2b78338dc8443a0fbe4f208ed5e50453dea6a016f43
3
+ size 5454
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -43,7 +43,7 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4641d603a48499788ceb7b092c3fe0c5f4f48d0226237591cd4d541e80fc3bdd
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d441cacafe8bd8b62531332381d12df6cd94e70e4b137e0e8b65f3f42367190e
3
  size 5112
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff