Model save
Browse files
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: codellama/CodeLlama-7b-Instruct-hf
|
7 |
+
model-index:
|
8 |
+
- name: finetuningnewmodule1
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# finetuningnewmodule1
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.9468
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.001
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 8
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 2.688 | 1.0 | 1 | 2.7045 |
|
51 |
+
| 2.2248 | 2.0 | 2 | 2.0812 |
|
52 |
+
| 1.6447 | 3.0 | 3 | 1.7351 |
|
53 |
+
| 1.2926 | 4.0 | 4 | 1.2896 |
|
54 |
+
| 0.8111 | 5.0 | 5 | 1.0243 |
|
55 |
+
| 0.4457 | 6.0 | 6 | 0.9231 |
|
56 |
+
| 0.2562 | 7.0 | 7 | 0.9348 |
|
57 |
+
| 0.1901 | 8.0 | 8 | 0.9468 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.36.0
|
63 |
+
- Pytorch 2.0.1
|
64 |
+
- Datasets 2.16.1
|
65 |
+
- Tokenizers 0.15.1
|
66 |
+
## Training procedure
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
|
72 |
+
- PEFT 0.6.0
|
adapter_config.json
CHANGED
@@ -16,11 +16,10 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
"o_proj",
|
21 |
-
"gate_proj",
|
22 |
"q_proj",
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
"o_proj",
|
|
|
21 |
"q_proj",
|
22 |
+
"k_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
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 sha256:3baa7f03890aa0b9e46911557c9963c8d31ac67a626ccc921ed04eb87ad86579
|
3 |
+
size 33588528
|
runs/Feb01_00-08-08_notebook-rt231gpu1aeb26e4e66634fdf88cdc063fc8a1afd-7b5fd5c8h97n/events.out.tfevents.1706746093.notebook-rt231gpu1aeb26e4e66634fdf88cdc063fc8a1afd-7b5fd5c8h97n.126.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70abe1a0b012397f5ba3ea46bc92c8e642517e48a1c81874d92a7ce5013bb8f9
|
3 |
+
size 8188
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9f64a929ff6e47612838901c47f840937e8393ffe823da5a0319435fd991905
|
3 |
size 4283
|