Andrija commited on
Commit
03817dc
1 Parent(s): 883b35b

Model SRoBERTa-XL trained on Leipzig-sr, OSCAR-sr, srWac hrWac, cc100-sr, cc100-hr for 1 epoch, loss 2.2

Browse files
Files changed (3) hide show
  1. config.json +25 -0
  2. pytorch_model.bin +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.8.2",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 48000
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9a156737ff77268f3e9dddf4e24e504a4cc9de84d9968c091d4a69f1d34167
3
+ size 321760363
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c3725e249b22b197d8bb3cf55a9f2ef5615d6afb37d7a74f67f9c0acec3fe9
3
+ size 2671