Training in progress, epoch 1
Browse files- config.json +3 -1
- model.safetensors +2 -2
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "roberta-base",
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"bos_token_id": 0,
|
|
@@ -12,6 +13,7 @@
|
|
| 12 |
"hidden_size": 768,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 3072,
|
|
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 514,
|
| 17 |
"model_type": "roberta",
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "roberta-base",
|
| 3 |
+
"add_cross_attention": true,
|
| 4 |
"architectures": [
|
| 5 |
+
"RobertaForCausalLM"
|
| 6 |
],
|
| 7 |
"attention_probs_dropout_prob": 0.1,
|
| 8 |
"bos_token_id": 0,
|
|
|
|
| 13 |
"hidden_size": 768,
|
| 14 |
"initializer_range": 0.02,
|
| 15 |
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": true,
|
| 17 |
"layer_norm_eps": 1e-05,
|
| 18 |
"max_position_embeddings": 514,
|
| 19 |
"model_type": "roberta",
|
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:c7d15dc981775834b8377397e85ed059db46951d06908a4b7ce7d5c9fb4da792
|
| 3 |
+
size 612296700
|
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 sha256:57d922e814de1afdf2200038bc23105dc7c702109259328586e84d6b898984c6
|
| 3 |
+
size 5304
|