Model save
Browse files
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: NTQAI/Nxcode-CQ-7B-orpo
|
3 |
+
datasets:
|
4 |
+
- generator
|
5 |
+
library_name: peft
|
6 |
+
license: other
|
7 |
+
tags:
|
8 |
+
- trl
|
9 |
+
- sft
|
10 |
+
- generated_from_trainer
|
11 |
+
model-index:
|
12 |
+
- name: Nxcode_finetuned
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# Nxcode_finetuned
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [NTQAI/Nxcode-CQ-7B-orpo](https://huggingface.co/NTQAI/Nxcode-CQ-7B-orpo) on the generator dataset.
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0002
|
41 |
+
- train_batch_size: 3
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 6
|
46 |
+
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
47 |
+
- lr_scheduler_type: constant
|
48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
49 |
+
- num_epochs: 3
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- PEFT 0.7.2.dev0
|
58 |
+
- Transformers 4.46.0
|
59 |
+
- Pytorch 2.4.0+cu121
|
60 |
+
- Datasets 3.0.1
|
61 |
+
- Tokenizers 0.20.0
|
adapter_config.json
CHANGED
@@ -21,11 +21,11 @@
|
|
21 |
"target_modules": [
|
22 |
"v_proj",
|
23 |
"o_proj",
|
|
|
24 |
"gate_proj",
|
|
|
25 |
"k_proj",
|
26 |
-
"up_proj"
|
27 |
-
"down_proj",
|
28 |
-
"q_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
21 |
"target_modules": [
|
22 |
"v_proj",
|
23 |
"o_proj",
|
24 |
+
"down_proj",
|
25 |
"gate_proj",
|
26 |
+
"q_proj",
|
27 |
"k_proj",
|
28 |
+
"up_proj"
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
runs/Oct27_20-17-58_atl1-1-03-004-23-0.pace.gatech.edu/events.out.tfevents.1730074685.atl1-1-03-004-23-0.pace.gatech.edu
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 sha256:27fc038538b13b1154676261c25502175c490cf9b0d17e45c65b29009ea299cb
|
3 |
+
size 7120
|
runs/Oct27_20-26-11_atl1-1-03-013-13-0.pace.gatech.edu/events.out.tfevents.1730075178.atl1-1-03-013-13-0.pace.gatech.edu
CHANGED
Binary files a/runs/Oct27_20-26-11_atl1-1-03-013-13-0.pace.gatech.edu/events.out.tfevents.1730075178.atl1-1-03-013-13-0.pace.gatech.edu and b/runs/Oct27_20-26-11_atl1-1-03-013-13-0.pace.gatech.edu/events.out.tfevents.1730075178.atl1-1-03-013-13-0.pace.gatech.edu differ
|
|