LouayYahyaoui
commited on
Commit
•
523c87a
1
Parent(s):
2522f0d
add: llama for education
Browse files
README.md
CHANGED
@@ -7,19 +7,19 @@ tags:
|
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
-
- name:
|
11 |
results: []
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
#
|
18 |
|
19 |
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 an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Model Preparation Time: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -54,20 +54,21 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|
56 |
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
|
57 |
-
| 2.
|
58 |
-
| 1.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
|
|
65 |
|
66 |
|
67 |
### Framework versions
|
68 |
|
69 |
- PEFT 0.12.0
|
70 |
-
- Transformers 4.44.
|
71 |
- Pytorch 2.1.2
|
72 |
- Datasets 2.21.0
|
73 |
- Tokenizers 0.19.1
|
|
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
+
- name: llama-edu
|
11 |
results: []
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
# llama-edu
|
18 |
|
19 |
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 an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.7934
|
22 |
+
- Model Preparation Time: 0.0161
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|
56 |
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
|
57 |
+
| 2.2418 | 1.0256 | 20 | 2.0564 | 0.0161 |
|
58 |
+
| 1.2511 | 2.0513 | 40 | 1.2006 | 0.0161 |
|
59 |
+
| 0.9906 | 3.0769 | 60 | 0.9552 | 0.0161 |
|
60 |
+
| 0.8046 | 4.1026 | 80 | 0.8716 | 0.0161 |
|
61 |
+
| 0.7893 | 5.1282 | 100 | 0.8376 | 0.0161 |
|
62 |
+
| 0.8012 | 6.1538 | 120 | 0.8167 | 0.0161 |
|
63 |
+
| 0.7734 | 7.1795 | 140 | 0.8038 | 0.0161 |
|
64 |
+
| 0.78 | 8.2051 | 160 | 0.7970 | 0.0161 |
|
65 |
+
| 0.7576 | 9.2308 | 180 | 0.7939 | 0.0161 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
69 |
|
70 |
- PEFT 0.12.0
|
71 |
+
- Transformers 4.44.2
|
72 |
- Pytorch 2.1.2
|
73 |
- Datasets 2.21.0
|
74 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"up_proj",
|
24 |
"down_proj",
|
25 |
-
"k_proj",
|
26 |
-
"o_proj",
|
27 |
"v_proj",
|
28 |
"q_proj",
|
29 |
-
"gate_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
"up_proj",
|
25 |
"down_proj",
|
|
|
|
|
26 |
"v_proj",
|
27 |
"q_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"k_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 sha256:8a5a3d7ea99698316cfe9750f9d69a4c1e3d16da3156448d4a6dfabcc5076dfa
|
3 |
size 167832240
|
runs/Aug29_11-54-18_98b9c91667d9/events.out.tfevents.1724932510.98b9c91667d9.24.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64777f7f55a30ce0665d9c53705dd7b7207ccf108a865151972e8a898dabcb21
|
3 |
+
size 49164
|
runs/Aug29_11-54-18_98b9c91667d9/events.out.tfevents.1724937021.98b9c91667d9.24.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cdbe4aa13afbfe5de62c4bcae85aa61f4a410256329f182ba298c02e99eeb2e
|
3 |
+
size 425
|
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 sha256:83d76460e4773cf68a61695f04a192cec9ea8ab643f1317351e1e190ce4d24ab
|
3 |
size 5432
|