Kevincp560 commited on
Commit
149fba3
1 Parent(s): ad5e335

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bigbird-pegasus-large-bigpatent",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "BigBirdPegasusForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_type": "block_sparse",
10
+ "block_size": 64,
11
+ "bos_token_id": 2,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 16,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 16,
24
+ "eos_token_id": 1,
25
+ "gradient_checkpointing": false,
26
+ "init_std": 0.02,
27
+ "is_encoder_decoder": true,
28
+ "length_penalty": 0.8,
29
+ "max_length": 256,
30
+ "max_position_embeddings": 4096,
31
+ "model_type": "bigbird_pegasus",
32
+ "num_beams": 5,
33
+ "num_hidden_layers": 16,
34
+ "num_random_blocks": 3,
35
+ "pad_token_id": 0,
36
+ "scale_embedding": true,
37
+ "tokenizer_class": "PegasusTokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.17.0",
40
+ "use_bias": false,
41
+ "use_cache": true,
42
+ "vocab_size": 96103
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c88f2b5b4ece6d2b049f795c52355ab56e5d949639f830e47df0c8b14a868724
3
+ size 2308144433
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
3
+ size 1915455
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": "[MASK]", "mask_token_sent": null, "offset": 0, "additional_special_tokens": [], "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/b548e984b09823ed5cea0e622c0ec194a7e07b3c5d2e6b48a7cde84bd179cc7c.4eda581f816a0a941629106f0338c957910ce4839ecf7e3e743bb79523bf7249", "name_or_path": "google/bigbird-pegasus-large-bigpatent", "model_max_length": 4096, "tokenizer_class": "PegasusTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba85acb57c57c029e9e0557fbf7d474fce866e34d9e51e639c89c93feacff62d
3
+ size 3183