sahithya20
commited on
Commit
•
0a18003
1
Parent(s):
60c07aa
Model save
Browse files
README.md
CHANGED
@@ -1,10 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: t5-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
datasets:
|
7 |
-
- mbpp
|
8 |
model-index:
|
9 |
- name: checkpoint-t5-small-mbpp
|
10 |
results: []
|
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# checkpoint-t5-small-mbpp
|
17 |
|
18 |
-
This model is a fine-tuned version of [t5-
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: t5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: checkpoint-t5-small-mbpp
|
8 |
results: []
|
|
|
13 |
|
14 |
# checkpoint-t5-small-mbpp
|
15 |
|
16 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
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,
|
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 sha256:9a034913ab1f6daff76cd1c421142a59ce26db6401ccf77c77883cd4dcc183fd
|
3 |
+
size 242041896
|
runs/Nov09_04-50-00_b2533449ceec/events.out.tfevents.1699505459.b2533449ceec.1524.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70819ba6b5f50fda4d12a86572491704e6ba8db0c54edebf97479fb6129bde1
|
3 |
+
size 5565
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af1bb97d03ac2bc373a20f944cc86d4d81ea1bc9df49f108d9891b3051c94646
|
3 |
size 4728
|