Training in progress, step 500
Browse files- config.json +5 -5
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
|
@@ -26,7 +26,7 @@
|
|
| 26 |
"layer_norm_eps": 1e-05,
|
| 27 |
"local_attention": 128,
|
| 28 |
"local_rope_theta": 10000.0,
|
| 29 |
-
"max_position_embeddings":
|
| 30 |
"mlp_bias": false,
|
| 31 |
"mlp_dropout": 0.0,
|
| 32 |
"model_type": "modernbert",
|
|
@@ -42,6 +42,6 @@
|
|
| 42 |
"sparse_pred_ignore_index": -100,
|
| 43 |
"sparse_prediction": false,
|
| 44 |
"torch_dtype": "float32",
|
| 45 |
-
"transformers_version": "4.48.0",
|
| 46 |
"vocab_size": 95663
|
| 47 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "x2bee/KoModernBERT-base-mlm-v03-retry-ckp03",
|
| 3 |
"architectures": [
|
| 4 |
+
"ModernBERTSimCSE"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
|
|
|
| 26 |
"layer_norm_eps": 1e-05,
|
| 27 |
"local_attention": 128,
|
| 28 |
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 8192,
|
| 30 |
"mlp_bias": false,
|
| 31 |
"mlp_dropout": 0.0,
|
| 32 |
"model_type": "modernbert",
|
|
|
|
| 42 |
"sparse_pred_ignore_index": -100,
|
| 43 |
"sparse_prediction": false,
|
| 44 |
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.48.0.dev0",
|
| 46 |
"vocab_size": 95663
|
| 47 |
+
}
|
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:a902e03f78d73a65a225e2670272f5ab30fa9243753252da0d81bf6ae1ab88f8
|
| 3 |
+
size 737580392
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7be9e20c2c0889091baaa0347720d7888707c1703a6f97836e6beae35fe15fe
|
| 3 |
size 5368
|