dwb2023/llama38binstruct_summarize
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 |
|
|
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch
|
| 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: 2.0847
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| 1.4079 | 1.1905 | 25 | 1.4325 |
|
| 56 |
+
| 0.3935 | 2.3810 | 50 | 1.6786 |
|
| 57 |
+
| 0.3836 | 3.5714 | 75 | 1.7694 |
|
| 58 |
+
| 0.1039 | 4.7619 | 100 | 2.0847 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"o_proj",
|
| 24 |
"up_proj",
|
| 25 |
-
"gate_proj",
|
| 26 |
-
"v_proj",
|
| 27 |
"k_proj",
|
| 28 |
-
"
|
| 29 |
-
"down_proj"
|
|
|
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"up_proj",
|
|
|
|
|
|
|
| 24 |
"k_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"gate_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:d5eb2ba5bd31fe265e089ab86d5ca7f0167c063cc985c997332e6d56c04fb999
|
| 3 |
size 167832240
|
runs/Jun13_08-42-32_19d0f881613b/events.out.tfevents.1718268154.19d0f881613b.3120.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43f0eb884c762790559d23d7e94de2b68de5fd2f24f6934855771c4b6a889ee4
|
| 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 sha256:88ec13acf05418ea06f7ef2cb995791d2f2ad262c2272593cce204cea317952b
|
| 3 |
size 5368
|