Hugging Face's logo

AlgorithmicResearchGroup
/
led_large_16384_arxiv_summarization

Summarization
Transformers
PyTorch
Safetensors
English
led
text2text-generation
Eval Results
Inference Endpoints
Model card Files Community
2
Artifact AI commited on
Commit
f725ba3
•
1 Parent(s): 0968693

first commit

Browse files
Files changed (16) hide show
  1. config.json +68 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state_0.pth +3 -0
  6. rng_state_1.pth +3 -0
  7. rng_state_2.pth +3 -0
  8. rng_state_3.pth +3 -0
  9. scaler.pt +3 -0
  10. scheduler.pt +3 -0
  11. special_tokens_map.json +51 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +65 -0
  14. trainer_state.json +46 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/led-large-16384",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "architectures": [
7
+ "LEDForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "attention_window": [
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024,
16
+ 1024,
17
+ 1024,
18
+ 1024,
19
+ 1024,
20
+ 1024,
21
+ 1024,
22
+ 1024
23
+ ],
24
+ "bos_token_id": 0,
25
+ "classif_dropout": 0.0,
26
+ "classifier_dropout": 0.0,
27
+ "d_model": 1024,
28
+ "decoder_attention_heads": 16,
29
+ "decoder_ffn_dim": 4096,
30
+ "decoder_layerdrop": 0.0,
31
+ "decoder_layers": 12,
32
+ "decoder_start_token_id": 2,
33
+ "dropout": 0.1,
34
+ "early_stopping": true,
35
+ "encoder_attention_heads": 16,
36
+ "encoder_ffn_dim": 4096,
37
+ "encoder_layerdrop": 0.0,
38
+ "encoder_layers": 12,
39
+ "eos_token_id": 2,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1",
43
+ "2": "LABEL_2"
44
+ },
45
+ "init_std": 0.02,
46
+ "is_encoder_decoder": true,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_2": 2
51
+ },
52
+ "length_penalty": 2.0,
53
+ "max_decoder_position_embeddings": 1024,
54
+ "max_encoder_position_embeddings": 16384,
55
+ "max_length": 512,
56
+ "min_length": 100,
57
+ "model_type": "led",
58
+ "no_repeat_ngram_size": 3,
59
+ "num_beams": 4,
60
+ "num_hidden_layers": 12,
61
+ "output_past": false,
62
+ "pad_token_id": 1,
63
+ "prefix": " ",
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.23.1",
66
+ "use_cache": false,
67
+ "vocab_size": 50265
68
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d3910a6b19838a606ba34bb0821f41b90ece56fe9c15e49c67c13a0aaedd0e
3
+ size 3678753227
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfc1ace1e68bbc0732317d88c15b0c6392b6969816578d1e69caa13622cb2a3
3
+ size 1839604721
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db683742a7905931adba243ad086db41449d97a32fb596bbc29dba6de0d7e1d
3
+ size 14503
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db683742a7905931adba243ad086db41449d97a32fb596bbc29dba6de0d7e1d
3
+ size 14503
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db683742a7905931adba243ad086db41449d97a32fb596bbc29dba6de0d7e1d
3
+ size 14503
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db683742a7905931adba243ad086db41449d97a32fb596bbc29dba6de0d7e1d
3
+ size 14503
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d337e2c31b446e0bfa05222d57fc69af8f23bd5459f4092593f0fe76b86d6d09
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c003a6c024920a4126c33ff4da63fffd3dc060f7fb1ec3de69d68289d19641a
3
+ size 623
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": "<s>",
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": "</s>",
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 16384,
37
+ "name_or_path": "allenai/led-large-16384",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/home/paperspace/.cache/huggingface/hub/models--allenai--led-large-16384/snapshots/04472a9a5d3af2efe700dda11da6063c68cd27a4/special_tokens_map.json",
55
+ "tokenizer_class": "LEDTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5333333333333333,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 4.4983991462113126e-05,
13
+ "loss": 2.4818,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.21,
18
+ "learning_rate": 3.970117395944504e-05,
19
+ "loss": 2.2118,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.32,
24
+ "learning_rate": 3.436499466382071e-05,
25
+ "loss": 2.1462,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.43,
30
+ "learning_rate": 2.9028815368196372e-05,
31
+ "loss": 2.1053,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.53,
36
+ "learning_rate": 2.3692636072572037e-05,
37
+ "loss": 2.075,
38
+ "step": 500
39
+ }
40
+ ],
41
+ "max_steps": 937,
42
+ "num_train_epochs": 1,
43
+ "total_flos": 3.07105194049536e+17,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468ddfbf5d55266a5da72aa0d99ca97d1ed5bebc8f5cfe6d4609b84c5e73ab42
3
+ size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff