colinrdavisMBA/mistral-7binstruct-summary-100s
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 1.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.4646
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 1.6134 | 0.22 | 25 | 1.5514 |
|
| 56 |
+
| 1.5949 | 0.43 | 50 | 1.4646 |
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path":
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
@@ -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
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea3ca41896d5ecc7110c87eeabc151aafc4b078b63c57d00a7b8b585a62d1f82
|
| 3 |
+
size 27280152
|
runs/Feb28_03-53-00_b19355bd894a/events.out.tfevents.1709092399.b19355bd894a.921.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5c1c43c3232d15465dd44791ba5c1232345151447f0663a9a2a96b4297d6819
|
| 3 |
+
size 6966
|
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:d475bae46eee9ea64e29ebe797b95ba15738cb726e56099e9fd09fccfc18f598
|
| 3 |
size 4920
|