hongjing0312
commited on
Commit
•
21d975c
1
Parent(s):
53d4ab8
Training in progress, step 500
Browse files- config.json +6 -6
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "t5-
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
@@ -18,9 +18,9 @@
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
-
"num_decoder_layers":
|
22 |
-
"num_heads":
|
23 |
-
"num_layers":
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 6,
|
22 |
+
"num_heads": 8,
|
23 |
+
"num_layers": 6,
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
pytorch_model.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 sha256:2a9b7fa9c25193ba8f357d9441156de71f07b773a958e3a4c5171db97ad97af0
|
3 |
+
size 242071641
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:757a003888d16bec236b415e80264479d9c6278544316cbb2f66825a49f6fd7a
|
3 |
size 4219
|