Training in progress, epoch 1
Browse files- config.json +8 -4
- model.safetensors +2 -2
- runs/Oct06_14-45-08_8c316b744f27/events.out.tfevents.1728225909.8c316b744f27.3748.8 +3 -0
- runs/Oct06_14-45-42_8c316b744f27/events.out.tfevents.1728225943.8c316b744f27.3748.9 +3 -0
- runs/Oct06_14-47-38_8c316b744f27/events.out.tfevents.1728226058.8c316b744f27.3748.10 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,12 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
9 |
-
"gradient_checkpointing": false,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
@@ -27,11 +26,16 @@
|
|
27 |
"LABEL_4": 4
|
28 |
},
|
29 |
"layer_norm_eps": 1e-12,
|
30 |
-
"max_position_embeddings":
|
31 |
"model_type": "bert",
|
32 |
"num_attention_heads": 12,
|
33 |
"num_hidden_layers": 12,
|
34 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
35 |
"position_embedding_type": "absolute",
|
36 |
"problem_type": "single_label_classification",
|
37 |
"torch_dtype": "float32",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "beomi/kcbert-base",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
|
|
26 |
"LABEL_4": 4
|
27 |
},
|
28 |
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 300,
|
30 |
"model_type": "bert",
|
31 |
"num_attention_heads": 12,
|
32 |
"num_hidden_layers": 12,
|
33 |
"pad_token_id": 0,
|
34 |
+
"pooler_fc_size": 768,
|
35 |
+
"pooler_num_attention_heads": 12,
|
36 |
+
"pooler_num_fc_layers": 3,
|
37 |
+
"pooler_size_per_head": 128,
|
38 |
+
"pooler_type": "first_token_transform",
|
39 |
"position_embedding_type": "absolute",
|
40 |
"problem_type": "single_label_classification",
|
41 |
"torch_dtype": "float32",
|
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 sha256:5a3c611c3b1ccfe4db2eeaeabada2d4788566871de6460745600040d45017b67
|
3 |
+
size 435713020
|
runs/Oct06_14-45-08_8c316b744f27/events.out.tfevents.1728225909.8c316b744f27.3748.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f380628fd48d60fbdfb15472fa75b10fde026bccb24a165fef6e515bc47a751
|
3 |
+
size 5267
|
runs/Oct06_14-45-42_8c316b744f27/events.out.tfevents.1728225943.8c316b744f27.3748.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a798f5d46e822c3646126405ec9426f0f7ed9f2290e911a291713f2ac3d0972
|
3 |
+
size 5269
|
runs/Oct06_14-47-38_8c316b744f27/events.out.tfevents.1728226058.8c316b744f27.3748.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70a57dc19986a92d8ac11206083d7a04a260610c6e1a5f98c5f67276c51ba870
|
3 |
+
size 5586
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8d9300c2eca676df2ab0f4df4ea59d7a52538a12137d3f5f149303ea6b6f537
|
3 |
size 5240
|