llm/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 |
|
@@ -47,17 +47,17 @@ The following hyperparameters were used during training:
|
|
47 |
- total_train_batch_size: 8
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: constant
|
50 |
-
- lr_scheduler_warmup_steps:
|
51 |
- training_steps: 100
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
|
62 |
|
63 |
### 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: 1.9040
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
47 |
- total_train_batch_size: 8
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: constant
|
50 |
+
- lr_scheduler_warmup_steps: 20
|
51 |
- training_steps: 100
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 2.2823 | 10.0 | 25 | 1.9040 |
|
58 |
+
| 2.2883 | 20.0 | 50 | 1.9040 |
|
59 |
+
| 2.2944 | 30.0 | 75 | 1.9040 |
|
60 |
+
| 2.2857 | 40.0 | 100 | 1.9040 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
|
3 |
+
size 48
|
runs/Jun19_07-40-29_0113f146e29c/events.out.tfevents.1718782840.0113f146e29c.57332.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a532b72c9097c994946e75c93cd72957de50d65b748d63ddc4a46e6b50186e5e
|
3 |
+
size 9237
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f52e5fe216009eec8b3e369fae845d481ba7f79d6486b867f01d9e87147cc361
|
3 |
size 5432
|