JackZhao1998 commited on
Commit
8cbc540
1 Parent(s): febcd66

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,49 +1,35 @@
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": "LABEL_0",
17
- "1": "LABEL_1",
18
- "2": "LABEL_2"
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 4096,
22
  "label2id": {
23
- "LABEL_0": 0,
24
- "LABEL_1": 1,
25
- "LABEL_2": 2
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": "4.38.2",
49
  "use_cache": true,
 
1
  {
2
  "_name_or_path": "microsoft/biogpt",
3
  "activation_dropout": 0.0,
 
4
  "architectures": [
5
+ "BioGptForTokenClassification"
6
  ],
7
  "attention_probs_dropout_prob": 0.1,
 
8
  "bos_token_id": 0,
 
9
  "eos_token_id": 2,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
  "id2label": {
14
+ "0": "O",
15
+ "1": "B-Disease",
16
+ "2": "I-Disease"
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 4096,
20
  "label2id": {
21
+ "B-Disease": 1,
22
+ "I-Disease": 2,
23
+ "O": 0
24
  },
25
  "layer_norm_eps": 1e-12,
 
26
  "layerdrop": 0.0,
27
+ "max_position_embeddings": 1024,
28
+ "model_type": "biogpt",
29
+ "num_attention_heads": 16,
30
+ "num_hidden_layers": 24,
 
 
31
  "pad_token_id": 1,
 
 
 
 
32
  "scale_embedding": true,
 
 
 
 
 
33
  "torch_dtype": "float32",
34
  "transformers_version": "4.38.2",
35
  "use_cache": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e1ad763b5e2fc0e4e05e9902090cc3b325212e34ea9327b770420128d21c4d
3
- size 1387087524
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd242909007caf29193187315265196abc76ea0dd5b170a28ad14dc6ecaf62e
3
+ size 1387108052
runs/Apr11_20-53-16_d35aba3a0ae4/events.out.tfevents.1712868797.d35aba3a0ae4.5070.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad38e3185b48d107cfbbaa8306614e6fb3ccf8c005f70df5c740a187be4f32ae
3
+ size 4717
runs/Apr11_20-55-29_d35aba3a0ae4/events.out.tfevents.1712868930.d35aba3a0ae4.5070.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3000ffe2917cfdefcf955bd3ca290f1132cebd599c0e90e457615f859b2a75e8
3
+ size 5400
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02bc0239a74d05ec0e88b710e29b6eaa7d6fcb26a7cb5fc11666ce5f5352bc9c
3
+ size 4920