ucmp137538
commited on
Commit
•
350dbc1
1
Parent(s):
6729cbf
End of training
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.0668
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 1.166 | 1.0 | 694 | 1.0270 |
|
54 |
+
| 1.0118 | 2.0 | 1388 | 1.0216 |
|
55 |
+
| 0.7775 | 3.0 | 2082 | 1.0420 |
|
56 |
+
| 0.6204 | 4.0 | 2776 | 1.0668 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1182877280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31538b96d7754c6b768c5a43f817f09bd574546c87981b1060d7b4d72f5e9bb5
|
3 |
size 1182877280
|
runs/Mar25_03-51-16_41c6ac6af299/events.out.tfevents.1711338681.41c6ac6af299.3195.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75797c67dcce0d05eaadfad71fc65ecac11bc186125437d2820559b1c838cc4f
|
3 |
+
size 23634
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
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 sha256:7c47e0cb83060c1e51084db6f675bedf6c76e89403672c930731d185f41e6d76
|
3 |
size 4728
|