JulianS commited on
Commit
8299b32
1 Parent(s): 6b5fe31

Training in progress, step 20000

Browse files
Files changed (4) hide show
  1. .gitignore +1 -0
  2. config.json +43 -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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
18
+ "bos_token_id": 0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 1024,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 3072,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 8,
25
+ "decoder_start_token_id": 1024,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 3072,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 8,
31
+ "eos_token_id": 1025,
32
+ "init_std": 0.02,
33
+ "is_encoder_decoder": true,
34
+ "max_decoder_position_embeddings": 2048,
35
+ "max_encoder_position_embeddings": 512,
36
+ "model_type": "led",
37
+ "num_hidden_layers": 8,
38
+ "pad_token_id": 1024,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.26.0",
41
+ "use_cache": true,
42
+ "vocab_size": 1026
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d74b3be972f8880fadfb6d13a743639667bc1050dcffae0193e2ca4243ee0c
3
+ size 921894765
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8cd65eccdbd90564f4423880a667a7a56a596554287fe10cba87c76908e989
3
+ size 3579