JulianS commited on
Commit
47485b9
·
1 Parent(s): 94eced0

Training in progress, step 20000

Browse files
Files changed (4) hide show
  1. .gitignore +1 -0
  2. config.json +45 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "LEDForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "bos_token_id": 0,
21
+ "classifier_dropout": 0.0,
22
+ "d_model": 768,
23
+ "decoder_attention_heads": 12,
24
+ "decoder_ffn_dim": 3072,
25
+ "decoder_layerdrop": 0.0,
26
+ "decoder_layers": 10,
27
+ "decoder_start_token_id": 1024,
28
+ "dropout": 0.1,
29
+ "encoder_attention_heads": 12,
30
+ "encoder_ffn_dim": 3072,
31
+ "encoder_layerdrop": 0.0,
32
+ "encoder_layers": 10,
33
+ "eos_token_id": 1025,
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "max_decoder_position_embeddings": 1024,
37
+ "max_encoder_position_embeddings": 1024,
38
+ "model_type": "led",
39
+ "num_hidden_layers": 10,
40
+ "pad_token_id": 1024,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.26.0",
43
+ "use_cache": true,
44
+ "vocab_size": 1026
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137df04efd18db022f941907356bffad56ae60b3fe8e3b9ff721151602e98c3d
3
+ size 742084781
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efea96add5ae80f9a3571c8556e1af0574f761a03bb03b51d568211b077731a7
3
+ size 3579