Hugging Face's logo

lenguist
/
longformer-coherence-synthetic-preference

Text Classification
Transformers
TensorBoard
Safetensors
longformer
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
lenguist commited on
Commit
6d7b73e
•
1 Parent(s): 7d93e03

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. config.json +52 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Dec14_22-23-46_32b02d7c73d0/events.out.tfevents.1702592626.32b02d7c73d0.1289.2 +3 -0
  5. runs/Dec14_22-27-25_32b02d7c73d0/events.out.tfevents.1702592846.32b02d7c73d0.1289.3 +3 -0
  6. runs/Dec14_22-41-53_32b02d7c73d0/events.out.tfevents.1702593714.32b02d7c73d0.1289.4 +3 -0
  7. runs/Dec14_22-55-35_32b02d7c73d0/events.out.tfevents.1702594536.32b02d7c73d0.1289.5 +3 -0
  8. special_tokens_map.json +15 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +57 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "coherent",
30
+ "1": "incoherent"
31
+ },
32
+ "ignore_attention_mask": false,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "coherent": 0,
37
+ "incoherent": 1
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "max_position_embeddings": 4098,
41
+ "model_type": "longformer",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "onnx_export": false,
45
+ "pad_token_id": 1,
46
+ "problem_type": "single_label_classification",
47
+ "sep_token_id": 2,
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.35.2",
50
+ "type_vocab_size": 1,
51
+ "vocab_size": 50265
52
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7ecfe00dff523c7a7e602dc485af88545cb8734d293b7f604b7e40a049d2fc
3
+ size 594678184
runs/Dec14_22-23-46_32b02d7c73d0/events.out.tfevents.1702592626.32b02d7c73d0.1289.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57265a90db9875555443caf3ab8e653c41e034fafa93e53e3f3711a13e867fd4
3
+ size 4571
runs/Dec14_22-27-25_32b02d7c73d0/events.out.tfevents.1702592846.32b02d7c73d0.1289.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abeea25edbe682e26dfa69768dd93a2bf65e06c2d6691c8b505736411aa95675
3
+ size 4571
runs/Dec14_22-41-53_32b02d7c73d0/events.out.tfevents.1702593714.32b02d7c73d0.1289.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ccae4866d5d83606383dec3dec7c00246fd4ec2791d1f53943a213800cd6ab5
3
+ size 4571
runs/Dec14_22-55-35_32b02d7c73d0/events.out.tfevents.1702594536.32b02d7c73d0.1289.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500adad59d82a14fe47edf16a900f929ef79504cdf70693e0f770042d714385a
3
+ size 5562
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 4096,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b1f94ea651bc88547f78f53520e7f4ad03e6694bd106f371001aee249d9f9f7
3
+ size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff