Model save
Browse files- README.md +0 -5
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- runs/Jan29_12-11-31_ip-172-31-10-206.us-east-2.compute.internal/events.out.tfevents.1738152754.ip-172-31-10-206.us-east-2.compute.internal.94585.0 +3 -0
- runs/Jan29_12-13-44_ip-172-31-10-206.us-east-2.compute.internal/events.out.tfevents.1738152832.ip-172-31-10-206.us-east-2.compute.internal.94585.1 +3 -0
- runs/Jan29_12-15-10_ip-172-31-10-206.us-east-2.compute.internal/events.out.tfevents.1738152911.ip-172-31-10-206.us-east-2.compute.internal.98020.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,8 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# Mistral-7B-3
|
18 |
|
19 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
|
20 |
-
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.0596
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -51,9 +49,6 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
56 |
-
| 0.5257 | 1.48 | 10 | 0.0596 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
17 |
# Mistral-7B-3
|
18 |
|
19 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
49 |
|
50 |
### Training results
|
51 |
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"gate_proj",
|
23 |
-
"o_proj",
|
24 |
"v_proj",
|
25 |
"down_proj",
|
26 |
"q_proj",
|
|
|
|
|
27 |
"up_proj",
|
28 |
-
"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"v_proj",
|
23 |
"down_proj",
|
24 |
"q_proj",
|
25 |
+
"k_proj",
|
26 |
+
"gate_proj",
|
27 |
"up_proj",
|
28 |
+
"o_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"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 2684416208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b649b9a60539ef3b29e4f5638657d2240535e1de7229025f7bd39d5eaada153
|
3 |
size 2684416208
|
runs/Jan29_12-11-31_ip-172-31-10-206.us-east-2.compute.internal/events.out.tfevents.1738152754.ip-172-31-10-206.us-east-2.compute.internal.94585.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8b648f6d9c4229dfa0016efcc463bff714c574b70648be9c5bca3b7fe976c14
|
3 |
+
size 4184
|
runs/Jan29_12-13-44_ip-172-31-10-206.us-east-2.compute.internal/events.out.tfevents.1738152832.ip-172-31-10-206.us-east-2.compute.internal.94585.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:791854437cd957a15a4dba8d4da74f17e939be94c1325d4c4bb5fc18fcff1fd3
|
3 |
+
size 4184
|
runs/Jan29_12-15-10_ip-172-31-10-206.us-east-2.compute.internal/events.out.tfevents.1738152911.ip-172-31-10-206.us-east-2.compute.internal.98020.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9506d392e7fae723d7a5c2c794f99f41c4bbe29e4a4c8dd5746835cac51b0f8c
|
3 |
+
size 5386
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d80a6acbc156e21739b01ad7eae4d3c9c2ac36c1f837de8711787270243c2b0
|
3 |
size 4920
|