Training in progress, step 500
Browse files- config.json +1 -1
- model.safetensors +2 -2
- special_tokens_map.json +1 -1
- tokenizer.json +11 -2
- tokenizer_config.json +9 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -36,5 +36,5 @@
|
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.40.2",
|
38 |
"use_cache": true,
|
39 |
-
"vocab_size":
|
40 |
}
|
|
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.40.2",
|
38 |
"use_cache": true,
|
39 |
+
"vocab_size": 32001
|
40 |
}
|
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:c64ec21aced3511d639b81fa511025a5efa70c1e41bddb360dde63f55d23bdf6
|
3 |
+
size 441691776
|
special_tokens_map.json
CHANGED
@@ -13,7 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -10,9 +10,9 @@
|
|
10 |
"strategy": "BatchLongest",
|
11 |
"direction": "Right",
|
12 |
"pad_to_multiple_of": null,
|
13 |
-
"pad_id":
|
14 |
"pad_type_id": 0,
|
15 |
-
"pad_token": "
|
16 |
},
|
17 |
"added_tokens": [
|
18 |
{
|
@@ -41,6 +41,15 @@
|
|
41 |
"rstrip": false,
|
42 |
"normalized": false,
|
43 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
}
|
45 |
],
|
46 |
"normalizer": {
|
|
|
10 |
"strategy": "BatchLongest",
|
11 |
"direction": "Right",
|
12 |
"pad_to_multiple_of": null,
|
13 |
+
"pad_id": 32000,
|
14 |
"pad_type_id": 0,
|
15 |
+
"pad_token": "<pad>"
|
16 |
},
|
17 |
"added_tokens": [
|
18 |
{
|
|
|
41 |
"rstrip": false,
|
42 |
"normalized": false,
|
43 |
"special": true
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"id": 32000,
|
47 |
+
"content": "<pad>",
|
48 |
+
"single_word": false,
|
49 |
+
"lstrip": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"normalized": false,
|
52 |
+
"special": true
|
53 |
}
|
54 |
],
|
55 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -25,6 +25,14 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
"bos_token": "<s>",
|
@@ -32,7 +40,7 @@
|
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
-
"pad_token": "
|
36 |
"padding_side": "right",
|
37 |
"sp_model_kwargs": {},
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<pad>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
}
|
37 |
},
|
38 |
"bos_token": "<s>",
|
|
|
40 |
"eos_token": "</s>",
|
41 |
"legacy": false,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
"padding_side": "right",
|
45 |
"sp_model_kwargs": {},
|
46 |
"tokenizer_class": "LlamaTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13f5cb4d558e9ea973b249dfda6c2f28100bdb0853103fe41bc350cf518db912
|
3 |
size 5048
|