Training in progress, step 200
Browse files- config.json +1 -13
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LongT5ForConditionalGeneration"
|
5 |
],
|
@@ -28,18 +28,6 @@
|
|
28 |
"relative_attention_max_distance": 128,
|
29 |
"relative_attention_num_buckets": 32,
|
30 |
"tie_word_embeddings": false,
|
31 |
-
"task_specific_params": {
|
32 |
-
"summarization": {
|
33 |
-
"early_stopping": true,
|
34 |
-
"length_penalty": 1.0,
|
35 |
-
"max_length": 256,
|
36 |
-
"min_length": 16,
|
37 |
-
"no_repeat_ngram_size": 5,
|
38 |
-
"num_beams": 4,
|
39 |
-
"prefix": "Write a title and summarize: ",
|
40 |
-
"repetition_penalty": 3.5
|
41 |
-
}
|
42 |
-
},
|
43 |
"torch_dtype": "float32",
|
44 |
"transformers_version": "4.30.2",
|
45 |
"use_cache": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "agemagician/mlong-t5-tglobal-large",
|
3 |
"architectures": [
|
4 |
"LongT5ForConditionalGeneration"
|
5 |
],
|
|
|
28 |
"relative_attention_max_distance": 128,
|
29 |
"relative_attention_num_buckets": 32,
|
30 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.30.2",
|
33 |
"use_cache": false,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4970010649
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9310153b122c0ca723e982d264fcd0c75ffa69d98819af3d10b005314b011ee
|
3 |
size 4970010649
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:965742e9cb208b4e9f4822c81e40644d51ab0de873b95429fa89bbfd0404db22
|
3 |
size 4091
|