aibabyshark
commited on
Commit
•
3a8ebdc
1
Parent(s):
4960330
ai-maker-space/llama38binstruct-summary-100s-v2
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: 1.
|
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: 1.7928
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 1.4799 | 1.25 | 25 | 1.4020 |
|
56 |
+
| 0.5231 | 2.5 | 50 | 1.5481 |
|
57 |
+
| 0.3147 | 3.75 | 75 | 1.6357 |
|
58 |
+
| 0.1531 | 5.0 | 100 | 1.7928 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"o_proj",
|
25 |
"gate_proj",
|
26 |
-
"
|
27 |
"up_proj",
|
28 |
-
"
|
29 |
-
"v_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"down_proj",
|
|
|
24 |
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
"up_proj",
|
27 |
+
"k_proj",
|
28 |
+
"v_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 sha256:068a40cfa9bec9a49e61690aa26f3f568c2733d645a829e30c58dc3ea5d68fe6
|
3 |
size 167832240
|
runs/Jun16_13-09-42_67c659df639e/events.out.tfevents.1718543384.67c659df639e.2351.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6555735dde9872fb1a768cc81bb57bf27eebe7357c115f51aa049013d0f534c9
|
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 sha256:2343ccabb4b5f0f9f611ea7fbe892a3f1b3d47e5e4ebdcdf32753124d8d13d4d
|
3 |
size 5368
|