eddieman78
commited on
Commit
•
f551eb1
1
Parent(s):
ab87acb
End
Browse files- README.md +3 -3
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
base_model: google/flan-t5-
|
7 |
model-index:
|
8 |
- name: dialogue-summary-peft-mem
|
9 |
results: []
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# dialogue-summary-peft-mem
|
16 |
|
17 |
-
This model is a fine-tuned version of [google/flan-t5-
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
-
|
43 |
|
44 |
### Training results
|
45 |
|
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
base_model: google/flan-t5-small
|
7 |
model-index:
|
8 |
- name: dialogue-summary-peft-mem
|
9 |
results: []
|
|
|
14 |
|
15 |
# dialogue-summary-peft-mem
|
16 |
|
17 |
+
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
+
- training_steps: 10
|
43 |
|
44 |
### Training results
|
45 |
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "google/flan-t5-
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "SEQ_2_SEQ_LM",
|
27 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/flan-t5-small",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v",
|
24 |
+
"q"
|
25 |
],
|
26 |
"task_type": "SEQ_2_SEQ_LM",
|
27 |
"use_dora": false,
|
adapter_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 sha256:97d509c082b1e5ff32e74048511590465743ce03036d2d47a047367473c0b4ba
|
3 |
+
size 2765976
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c0be2d1d3f18eaf52b11eb63c54185457dad3ba9b10a0b9ce2c60a8e1045a08
|
3 |
size 4856
|