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: 1.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch
|
54 |
-
|
55 |
-
|
|
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: 1.7359
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 1.3102 | 1.25 | 25 | 1.3008 |
|
56 |
+
| 0.4803 | 2.5 | 50 | 1.5715 |
|
57 |
+
| 0.1848 | 3.75 | 75 | 1.6767 |
|
58 |
+
| 0.0972 | 5.0 | 100 | 1.7359 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"gate_proj",
|
25 |
"q_proj",
|
|
|
26 |
"o_proj",
|
27 |
"down_proj",
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"up_proj",
|
|
|
24 |
"q_proj",
|
25 |
+
"gate_proj",
|
26 |
"o_proj",
|
27 |
"down_proj",
|
28 |
+
"k_proj",
|
29 |
+
"v_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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:334c48c53e003f8f47ab82364d74c20c07682efd7bdef27f754dcf15786e619c
|
3 |
+
size 167832240
|
runs/Jun14_17-23-34_1f55961ed06e/events.out.tfevents.1718385820.1f55961ed06e.34529.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:828e1d3e0442d0b528843bb0eb232b8dc5b3d42b4205ec5dc1fe6b14ccf3dcf2
|
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 sha256:8dc211a0b31c79fd05c341c6ca9921715b8b68d44b75409aac1ec8d72d67a257
|
3 |
size 5368
|