Hugging Face's logo

DoNotChoke
/
my_awesome_wnut_model

TensorBoard
Safetensors
gpt2
Model card Files
xet
Metrics Community
DoNotChoke commited on
Commit
cb8b077
·
verified ·
1 Parent(s): ad1bc5a

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +62 -0
  2. model.safetensors +3 -0
  3. runs/Apr20_16-51-59_1bfe96bfac3e/events.out.tfevents.1745167921.1bfe96bfac3e.31.0 +3 -0
  4. runs/Apr20_16-52-49_1bfe96bfac3e/events.out.tfevents.1745167970.1bfe96bfac3e.31.1 +3 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +53 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2ForTokenClassification"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 0,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 2,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-corporation",
13
+ "2": "I-corporation",
14
+ "3": "B-creative-work",
15
+ "4": "I-creative-work",
16
+ "5": "B-group",
17
+ "6": "I-group",
18
+ "7": "B-location",
19
+ "8": "I-location",
20
+ "9": "B-person",
21
+ "10": "I-person",
22
+ "11": "B-product",
23
+ "12": "I-product"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "label2id": {
27
+ "B-corporation": 1,
28
+ "B-creative-work": 3,
29
+ "B-group": 5,
30
+ "B-location": 7,
31
+ "B-person": 9,
32
+ "B-product": 11,
33
+ "I-corporation": 2,
34
+ "I-creative-work": 4,
35
+ "I-group": 6,
36
+ "I-location": 8,
37
+ "I-person": 10,
38
+ "I-product": 12,
39
+ "O": 0
40
+ },
41
+ "layer_norm_epsilon": 1e-05,
42
+ "model_type": "gpt2",
43
+ "n_ctx": 512,
44
+ "n_embd": 512,
45
+ "n_head": 8,
46
+ "n_inner": null,
47
+ "n_layer": 6,
48
+ "n_positions": 512,
49
+ "reorder_and_upcast_attn": false,
50
+ "resid_pdrop": 0.1,
51
+ "scale_attn_by_inverse_layer_idx": false,
52
+ "scale_attn_weights": true,
53
+ "summary_activation": null,
54
+ "summary_first_dropout": 0.1,
55
+ "summary_proj_to_labels": true,
56
+ "summary_type": "cls_index",
57
+ "summary_use_proj": true,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.51.1",
60
+ "use_cache": true,
61
+ "vocab_size": 50257
62
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232838f789fc57205b292cf01ea34d3a0c835d99f56443b4edcea9f5f319a118
3
+ size 179670612
runs/Apr20_16-51-59_1bfe96bfac3e/events.out.tfevents.1745167921.1bfe96bfac3e.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5862a603cc8a023d1b7937527d146d912002b6d9b48f15eb3e239c07f04e26
3
+ size 4184
runs/Apr20_16-52-49_1bfe96bfac3e/events.out.tfevents.1745167970.1bfe96bfac3e.31.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:567c9c07f0a218f143a75fd0e159f431cbcdb7769b59cd0dc75917882ea63b05
3
+ size 6173
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "eos_token": "</s>",
47
+ "extra_special_tokens": {},
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "tokenizer_class": "PreTrainedTokenizer",
52
+ "unk_token": "<unk>"
53
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d79c773c38c124ff89137b64416680efa09adcddcf239861ea24205efdd400
3
+ size 5304