Training in progress, step 500
Browse files- config.json +4 -3
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"RobertaForMaskedLM"
|
| 4 |
],
|
|
@@ -12,11 +13,11 @@
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 3072,
|
| 14 |
"layer_norm_eps": 1e-12,
|
| 15 |
-
"max_position_embeddings":
|
| 16 |
"model_type": "roberta",
|
| 17 |
"num_attention_heads": 12,
|
| 18 |
-
"num_hidden_layers":
|
| 19 |
-
"pad_token_id":
|
| 20 |
"position_embedding_type": "absolute",
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.43.3",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "mor40/BulBERT-chitanka-model",
|
| 3 |
"architectures": [
|
| 4 |
"RobertaForMaskedLM"
|
| 5 |
],
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 3072,
|
| 15 |
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
"model_type": "roberta",
|
| 18 |
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
"torch_dtype": "float32",
|
| 23 |
"transformers_version": "4.43.3",
|
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 sha256:4062a7fe97add279eb46837fa6346ae7cf376fdde8f989d4acb3ac50771f6603
|
| 3 |
+
size 328690332
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:814e9fa4fa2245bb2cc7e8094171f3622f64b41eeee31c4259eed2cc59d18122
|
| 3 |
size 5112
|