Training in progress, epoch 1
Browse files
config.json
CHANGED
@@ -1,41 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
"AutoModelForMultipleChoice": "ltg/norbert3-xs--modeling_norbert.NorbertForMultipleChoice",
|
12 |
-
"AutoModelForQuestionAnswering": "ltg/norbert3-xs--modeling_norbert.NorbertForQuestionAnswering",
|
13 |
-
"AutoModelForSequenceClassification": "ltg/norbert3-xs--modeling_norbert.NorbertForSequenceClassification",
|
14 |
-
"AutoModelForTokenClassification": "ltg/norbert3-xs--modeling_norbert.NorbertForTokenClassification"
|
15 |
-
},
|
16 |
-
"hidden_dropout_prob": 0.0,
|
17 |
-
"hidden_size": 192,
|
18 |
-
"id2label": {
|
19 |
-
"0": "LABEL_0",
|
20 |
-
"1": "LABEL_1",
|
21 |
-
"2": "LABEL_2",
|
22 |
-
"3": "LABEL_3"
|
23 |
-
},
|
24 |
-
"intermediate_size": 512,
|
25 |
-
"label2id": {
|
26 |
-
"LABEL_0": 0,
|
27 |
-
"LABEL_1": 1,
|
28 |
-
"LABEL_2": 2,
|
29 |
-
"LABEL_3": 3
|
30 |
-
},
|
31 |
-
"layer_norm_eps": 1e-07,
|
32 |
"max_position_embeddings": 512,
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.40.1",
|
40 |
-
"vocab_size":
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
"transformers_version": "4.40.1",
|
24 |
+
"vocab_size": 30522
|
25 |
}
|
model.safetensors
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 sha256:45271bfd489d2571ab7712a7257a948b3aba6c36579478d5c2ea387e2bcfa1a6
|
3 |
+
size 267832560
|
runs/May06_20-40-30_ccd7fc2b5375/events.out.tfevents.1715028316.ccd7fc2b5375.16058.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58a04cc7de1676d661c5b02859824cfcbdd920fdd040d9927b2ac9ce0df9bc2d
|
3 |
+
size 457
|
runs/May06_21-15-14_ccd7fc2b5375/events.out.tfevents.1715030128.ccd7fc2b5375.16058.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d565187cd933ae1d939361f42530e2cad9f1f5c39b156aa1e4bb6d9e4c2f796
|
3 |
+
size 4618
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b5d65f7e6a5738d9ba62586dcef2a117683402dba781dc2f3e463fff1255825
|
3 |
size 5048
|