minjingzhu commited on
Commit
69ca18a
1 Parent(s): 6c0e0f9

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-pubmed",
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": "4.31.0",
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 sha256:9a1076381c91808256f5d1b14edd60500be088e6c053216ed92198be678de482
3
+ size 2308118957
runs/Aug05_06-08-42_9f1aeb025fd8/events.out.tfevents.1691215730.9f1aeb025fd8.2238.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da567b63f8e988e2e3a44c0aa8d4d57557ed99338b247311c8dd30180c4e8201
3
+ size 4184
runs/Aug05_06-18-08_9f1aeb025fd8/events.out.tfevents.1691216293.9f1aeb025fd8.44885.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479696c235a66c9ec8d9608461f5890dcb197f9295affb3195e5d4a3291fc9ba
3
+ size 4751
runs/Aug05_06-22-54_9f1aeb025fd8/events.out.tfevents.1691216579.9f1aeb025fd8.44885.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d61d7c5ddf5891ab93c2502c2cc3d7370fad5e978dadb0ec2ab41857ee27b0d
3
+ size 4184
runs/Aug05_06-23-12_9f1aeb025fd8/events.out.tfevents.1691216600.9f1aeb025fd8.44885.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827cdcab4a6eeb01aef8885ebd63ce4148ffdb133fa0c9d309cfcd37340910e4
3
+ size 4184
runs/Aug05_06-27-32_9f1aeb025fd8/events.out.tfevents.1691216857.9f1aeb025fd8.48779.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e46cfa9917093da19cc4c328753fefcb269ee01f2c5031500672e28bf35303
3
+ size 4184
runs/Aug05_06-27-55_9f1aeb025fd8/events.out.tfevents.1691216880.9f1aeb025fd8.48779.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1002136cdf18bcfc90dca1a3ddc06e817df2d885a36acb5b1b19b3479ea24d7
3
+ size 4184
runs/Aug05_06-30-00_9f1aeb025fd8/events.out.tfevents.1691217005.9f1aeb025fd8.50312.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6841a060c94398f7d2ddd8e7ec939b9b96ab57e6479dcab8d0143328648d84e3
3
+ size 4906
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "mask_token": "[MASK]",
29
+ "mask_token_sent": null,
30
+ "model_max_length": 4096,
31
+ "offset": 0,
32
+ "pad_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<pad>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "sep_token": {
41
+ "__type": "AddedToken",
42
+ "content": "[SEP]",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "tokenizer_class": "PegasusTokenizer",
49
+ "unk_token": {
50
+ "__type": "AddedToken",
51
+ "content": "<unk>",
52
+ "lstrip": false,
53
+ "normalized": true,
54
+ "rstrip": false,
55
+ "single_word": false
56
+ }
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e66bb13d8c9a004230355c12ab5baaeed02c6dc6261560209e24fc03f4de0c5
3
+ size 4155