Training in progress, epoch 0
Browse files- config.json +2 -2
- generation_config.json +2 -2
- model.safetensors +1 -1
config.json
CHANGED
@@ -49,7 +49,7 @@
|
|
49 |
"LABEL_1": 1
|
50 |
},
|
51 |
"length_penalty": 1.0,
|
52 |
-
"max_length":
|
53 |
"max_position_embeddings": 1536,
|
54 |
"min_length": 0,
|
55 |
"model_type": "mbart",
|
@@ -87,7 +87,7 @@
|
|
87 |
"use_cache": true,
|
88 |
"vocab_size": 57544
|
89 |
},
|
90 |
-
"decoder_start_token_id":
|
91 |
"encoder": {
|
92 |
"_name_or_path": "",
|
93 |
"add_cross_attention": false,
|
|
|
49 |
"LABEL_1": 1
|
50 |
},
|
51 |
"length_penalty": 1.0,
|
52 |
+
"max_length": 768,
|
53 |
"max_position_embeddings": 1536,
|
54 |
"min_length": 0,
|
55 |
"model_type": "mbart",
|
|
|
87 |
"use_cache": true,
|
88 |
"vocab_size": 57544
|
89 |
},
|
90 |
+
"decoder_start_token_id": 3,
|
91 |
"encoder": {
|
92 |
"_name_or_path": "",
|
93 |
"add_cross_attention": false,
|
generation_config.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
-
"decoder_start_token_id":
|
5 |
"eos_token_id": 2,
|
6 |
"forced_eos_token_id": 2,
|
7 |
-
"max_length":
|
8 |
"pad_token_id": 1,
|
9 |
"transformers_version": "4.35.2"
|
10 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 3,
|
5 |
"eos_token_id": 2,
|
6 |
"forced_eos_token_id": 2,
|
7 |
+
"max_length": 768,
|
8 |
"pad_token_id": 1,
|
9 |
"transformers_version": "4.35.2"
|
10 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 809148568
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54cb32bfb5dc755060fe675b474bd8072f1a585f419e468aad3bc36d8a36214b
|
3 |
size 809148568
|