defsound/llama38binstruct-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 [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:------:|:----:|:---------------:|
|
55 |
-
| 1.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.6204
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 1.351 | 1.1905 | 25 | 1.2017 |
|
56 |
+
| 0.5869 | 2.3810 | 50 | 1.4451 |
|
57 |
+
| 0.226 | 3.5714 | 75 | 1.6767 |
|
58 |
+
| 0.1156 | 4.7619 | 100 | 1.6204 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"down_proj",
|
25 |
-
"k_proj",
|
26 |
-
"v_proj",
|
27 |
"o_proj",
|
|
|
28 |
"up_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"gate_proj",
|
|
|
|
|
|
|
24 |
"o_proj",
|
25 |
+
"down_proj",
|
26 |
"up_proj",
|
27 |
+
"v_proj",
|
28 |
+
"k_proj",
|
29 |
+
"q_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a8e3a279a56567ecaf57c77298c3eb7d94ea03309517b887f0483683598bb77
|
3 |
size 167832240
|
runs/Jun13_18-48-13_afe07e31b1f5/events.out.tfevents.1718304527.afe07e31b1f5.362.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b751962ac7f142f77c2600bc02d84e57914dce0d585bc6e2df307cba7ce06f4e
|
3 |
+
size 9238
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7c1f9c58b20553c0bb1fb41ff915c8e2cdced2dda45e14af5a6bbac3d73847c
|
3 |
size 5368
|