rupav02gmail
commited on
Commit
•
1d65b26
1
Parent(s):
d6c580e
Training in progress, epoch 1
Browse files- config.json +50 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Apr14_00-20-19_354753a1c0f3/events.out.tfevents.1713054019.354753a1c0f3.221.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +44 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-Disease",
|
17 |
+
"2": "I-Disease"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 4096,
|
21 |
+
"label2id": {
|
22 |
+
"B-Disease": 1,
|
23 |
+
"I-Disease": 2,
|
24 |
+
"O": 0
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"layer_norm_epsilon": 1e-05,
|
28 |
+
"layerdrop": 0.0,
|
29 |
+
"model_type": "gpt2",
|
30 |
+
"n_embd": 1024,
|
31 |
+
"n_head": 16,
|
32 |
+
"n_inner": null,
|
33 |
+
"n_layer": 24,
|
34 |
+
"n_positions": 1024,
|
35 |
+
"pad_token_id": 1,
|
36 |
+
"reorder_and_upcast_attn": false,
|
37 |
+
"resid_pdrop": 0.1,
|
38 |
+
"scale_attn_by_inverse_layer_idx": false,
|
39 |
+
"scale_attn_weights": true,
|
40 |
+
"scale_embedding": true,
|
41 |
+
"summary_activation": null,
|
42 |
+
"summary_first_dropout": 0.1,
|
43 |
+
"summary_proj_to_labels": true,
|
44 |
+
"summary_type": "cls_index",
|
45 |
+
"summary_use_proj": true,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.38.2",
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 42384
|
50 |
+
}
|
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 sha256:3c9f3f854e84138c0fa8d58df7795899a28862e81b6d4c846afd40125efa6e14
|
3 |
+
size 1387087524
|
runs/Apr14_00-20-19_354753a1c0f3/events.out.tfevents.1713054019.354753a1c0f3.221.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:394c6c8e1097b847d10b5344035045210ae6572fc6e859f1e14e69388479a1ec
|
3 |
+
size 5708
|
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 sha256:7af09787e9b38a4d7bb95ccd92d2cb683112ba1ba69d3c6bade3ae2dc7adcf90
|
3 |
+
size 4856
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|