Qin Liu
commited on
Commit
•
bea1007
1
Parent(s):
c3405a4
End of training
Browse files
README.md
CHANGED
@@ -2,11 +2,13 @@
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
-
- alignment-handbook
|
8 |
- generated_from_trainer
|
9 |
base_model: Undi95/Meta-Llama-3-8B-hf
|
|
|
|
|
10 |
model-index:
|
11 |
- name: llama3-poison-20p-2048
|
12 |
results: []
|
@@ -17,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# llama3-poison-20p-2048
|
19 |
|
20 |
-
This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: nan
|
23 |
|
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
- trl
|
7 |
- sft
|
|
|
8 |
- generated_from_trainer
|
9 |
base_model: Undi95/Meta-Llama-3-8B-hf
|
10 |
+
datasets:
|
11 |
+
- HuggingFaceH4/ultrachat_200k
|
12 |
model-index:
|
13 |
- name: llama3-poison-20p-2048
|
14 |
results: []
|
|
|
19 |
|
20 |
# llama3-poison-20p-2048
|
21 |
|
22 |
+
This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the HuggingFaceH4/ultrachat_200k dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
- Loss: nan
|
25 |
|
all_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"eval_loss": NaN,
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 2310,
|
6 |
-
"eval_samples_per_second": 11.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
"train_loss": 0.0,
|
9 |
"train_runtime": 784.6294,
|
10 |
"train_samples": 21594,
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"eval_loss": NaN,
|
4 |
+
"eval_runtime": 204.2874,
|
5 |
"eval_samples": 2310,
|
6 |
+
"eval_samples_per_second": 11.308,
|
7 |
+
"eval_steps_per_second": 0.71,
|
8 |
"train_loss": 0.0,
|
9 |
"train_runtime": 784.6294,
|
10 |
"train_samples": 21594,
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"eval_loss": NaN,
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 2310,
|
6 |
-
"eval_samples_per_second": 11.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"eval_loss": NaN,
|
4 |
+
"eval_runtime": 204.2874,
|
5 |
"eval_samples": 2310,
|
6 |
+
"eval_samples_per_second": 11.308,
|
7 |
+
"eval_steps_per_second": 0.71
|
8 |
}
|
runs/Apr29_08-10-27_COE-CS-sv003/events.out.tfevents.1714379394.COE-CS-sv003.535581.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03a804472967ced35d9c0797b75e9934917798d7c78960c26713cbee3ee40a6a
|
3 |
+
size 359
|