paragon-analytics
commited on
Commit
•
67dbf81
1
Parent(s):
4e64fc6
End of training
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: meta-llama/Meta-Llama-3.1-8B
|
3 |
library_name: peft
|
4 |
license: llama3.1
|
5 |
tags:
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# results
|
16 |
|
17 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset.
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
|
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
- lr_scheduler_warmup_steps: 100
|
45 |
-
- num_epochs:
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
|
|
1 |
---
|
2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
3 |
library_name: peft
|
4 |
license: llama3.1
|
5 |
tags:
|
|
|
14 |
|
15 |
# results
|
16 |
|
17 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
- lr_scheduler_warmup_steps: 100
|
45 |
+
- num_epochs: 2
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13648432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b618aed27c11c5ce733493a909ed12eb754c28f32cbdaa4e4b3258152212b73
|
3 |
size 13648432
|
runs/Sep15_15-09-37_udc-an34-19/events.out.tfevents.1726427378.udc-an34-19.288363.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61eb17f88906abf20fa719aa8d55c1e5ff14be998efbeb8a444c56d38e9b1a98
|
3 |
+
size 5934
|
runs/Sep15_15-31-13_udc-an34-19/events.out.tfevents.1726428674.udc-an34-19.294287.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d45c729de37c3b072df5d525db05764e77371607c5a9d6150a25d395a705e5
|
3 |
+
size 5934
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e8e2c2dc35162301f5ad5dedd198d8937a646e11e8e2aa195652f4c7f74604e
|
3 |
size 5176
|