End of training
Browse files
README.md
CHANGED
@@ -44,14 +44,10 @@ The following hyperparameters were used during training:
|
|
44 |
- num_epochs: 10
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
-
### Training results
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
### Framework versions
|
52 |
|
53 |
- PEFT 0.13.2
|
54 |
- Transformers 4.45.2
|
55 |
-
- Pytorch 2.5.
|
56 |
- Datasets 3.1.0
|
57 |
- Tokenizers 0.20.3
|
|
|
44 |
- num_epochs: 10
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
|
|
|
|
|
|
|
|
47 |
### Framework versions
|
48 |
|
49 |
- PEFT 0.13.2
|
50 |
- Transformers 4.45.2
|
51 |
+
- Pytorch 2.5.1+cu121
|
52 |
- Datasets 3.1.0
|
53 |
- Tokenizers 0.20.3
|
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"v_proj",
|
25 |
"o_proj",
|
26 |
-
"
|
|
|
27 |
],
|
28 |
"task_type": "SEQ_2_SEQ_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
|
|
24 |
"o_proj",
|
25 |
+
"v_proj",
|
26 |
+
"k_proj"
|
27 |
],
|
28 |
"task_type": "SEQ_2_SEQ_LM",
|
29 |
"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 21248928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09d8f4285e7c69170d3e0fec16d75d38b96743582f8904c530b7226ae37915f7
|
3 |
size 21248928
|
runs/Nov16_16-15-30_40601be62e29/events.out.tfevents.1731774733.40601be62e29.6331.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2425fac45b65420c7bcfcac2eee20f359c11f82792b5b6fe46b81ba3b60ac80c
|
3 |
+
size 1270
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84ad92415f55def63a1da23b7773ef161c43525e01fd37a5342925816579c166
|
3 |
size 5432
|