Training in progress, step 200
Browse files- config.json +47 -47
- logs/events.out.tfevents.1716805138.EOS-118.6212.0 +3 -0
- model.safetensors +1 -1
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,47 +1,47 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
|
3 |
-
"architectures": [
|
4 |
-
"LiltForTokenClassification"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"channel_shrink_ratio": 4,
|
9 |
-
"classifier_dropout": null,
|
10 |
-
"eos_token_id": 2,
|
11 |
-
"hidden_act": "gelu",
|
12 |
-
"hidden_dropout_prob": 0.1,
|
13 |
-
"hidden_size": 768,
|
14 |
-
"id2label": {
|
15 |
-
"0": "O",
|
16 |
-
"1": "B-HEADER",
|
17 |
-
"2": "I-HEADER",
|
18 |
-
"3": "B-QUESTION",
|
19 |
-
"4": "I-QUESTION",
|
20 |
-
"5": "B-ANSWER",
|
21 |
-
"6": "I-ANSWER"
|
22 |
-
},
|
23 |
-
"initializer_range": 0.02,
|
24 |
-
"intermediate_size": 3072,
|
25 |
-
"label2id": {
|
26 |
-
"B-ANSWER": 5,
|
27 |
-
"B-HEADER": 1,
|
28 |
-
"B-QUESTION": 3,
|
29 |
-
"I-ANSWER": 6,
|
30 |
-
"I-HEADER": 2,
|
31 |
-
"I-QUESTION": 4,
|
32 |
-
"O": 0
|
33 |
-
},
|
34 |
-
"layer_norm_eps": 1e-05,
|
35 |
-
"max_2d_position_embeddings": 1024,
|
36 |
-
"max_position_embeddings": 514,
|
37 |
-
"model_type": "lilt",
|
38 |
-
"num_attention_heads": 12,
|
39 |
-
"num_hidden_layers": 12,
|
40 |
-
"pad_token_id": 1,
|
41 |
-
"position_embedding_type": "absolute",
|
42 |
-
"torch_dtype": "float32",
|
43 |
-
"transformers_version": "4.41.1",
|
44 |
-
"type_vocab_size": 1,
|
45 |
-
"use_cache": true,
|
46 |
-
"vocab_size": 50265
|
47 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
|
3 |
+
"architectures": [
|
4 |
+
"LiltForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"channel_shrink_ratio": 4,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-HEADER",
|
17 |
+
"2": "I-HEADER",
|
18 |
+
"3": "B-QUESTION",
|
19 |
+
"4": "I-QUESTION",
|
20 |
+
"5": "B-ANSWER",
|
21 |
+
"6": "I-ANSWER"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"B-ANSWER": 5,
|
27 |
+
"B-HEADER": 1,
|
28 |
+
"B-QUESTION": 3,
|
29 |
+
"I-ANSWER": 6,
|
30 |
+
"I-HEADER": 2,
|
31 |
+
"I-QUESTION": 4,
|
32 |
+
"O": 0
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-05,
|
35 |
+
"max_2d_position_embeddings": 1024,
|
36 |
+
"max_position_embeddings": 514,
|
37 |
+
"model_type": "lilt",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"pad_token_id": 1,
|
41 |
+
"position_embedding_type": "absolute",
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.41.1",
|
44 |
+
"type_vocab_size": 1,
|
45 |
+
"use_cache": true,
|
46 |
+
"vocab_size": 50265
|
47 |
+
}
|
logs/events.out.tfevents.1716805138.EOS-118.6212.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e98856f34f4c7ee1e1c4d03b7c4772abe66ea906cfcdfb77c24640552b716f6
|
3 |
+
size 5919
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 520727564
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e694d195a0b97cd39e8ead9130ff8b22468bdf00553a0494373fb9b238ef467
|
3 |
size 520727564
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd6a1d1a08b8287aa4df188c26775d4a273baea8f1333fa2468a3fa46f30dd4b
|
3 |
+
size 5176
|