ejspringer commited on
Commit
e78ebca
1 Parent(s): e81d2df

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/biogpt",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2ForTokenClassification"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "attn_pdrop": 0.1,
10
+ "bos_token_id": 0,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-Disease",
18
+ "2": "I-Disease"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "label2id": {
23
+ "B-Disease": 1,
24
+ "I-Disease": 2,
25
+ "O": 0
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "layer_norm_epsilon": 1e-05,
29
+ "layerdrop": 0.0,
30
+ "model_type": "gpt2",
31
+ "n_embd": 1024,
32
+ "n_head": 16,
33
+ "n_inner": null,
34
+ "n_layer": 24,
35
+ "n_positions": 1024,
36
+ "pad_token_id": 1,
37
+ "reorder_and_upcast_attn": false,
38
+ "resid_pdrop": 0.1,
39
+ "scale_attn_by_inverse_layer_idx": false,
40
+ "scale_attn_weights": true,
41
+ "scale_embedding": true,
42
+ "summary_activation": null,
43
+ "summary_first_dropout": 0.1,
44
+ "summary_proj_to_labels": true,
45
+ "summary_type": "cls_index",
46
+ "summary_use_proj": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.39.3",
49
+ "use_cache": true,
50
+ "vocab_size": 42384
51
+ }
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 sha256:443e9d0723d21fefcac9a9c8856843fb067c4d633b1b958d74361ea6d42c01d7
3
+ size 1387087524
runs/Apr11_18-00-34_18a28c03e5a4/events.out.tfevents.1712858443.18a28c03e5a4.4162.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8e5d68f86e3a2ca28fe3c34df0b2a9ce43a108750c631339f1282e5cdde6d5
3
+ size 4958
runs/Apr11_18-22-44_18a28c03e5a4/events.out.tfevents.1712859770.18a28c03e5a4.4162.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8478b671c76214b857d9af794a8720d7ee49a9a0d06c2e17370c94326aaa89
3
+ size 4958
runs/Apr11_18-42-49_18a28c03e5a4/events.out.tfevents.1712860970.18a28c03e5a4.4162.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91a4d1a3c758612cfd916ab04fee0876874e60a5125e0fd6705256c8f65892e
3
+ size 5791
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "sep_token": "</s>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "eos_token": "</s>",
39
+ "model_max_length": 1024,
40
+ "pad_token": "<pad>",
41
+ "sep_token": "</s>",
42
+ "tokenizer_class": "BioGptTokenizer",
43
+ "unk_token": "<unk>"
44
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e92f8a1f4f2b3b5e2429c5aeb88f10215982e4ebd9be70067d2ee985059a85eb
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff