End of training
Browse files- README.md +86 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
base_model: codellama/CodeLlama-13b-Instruct-hf
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: stg-cli13b-t6.mt.him.cln.inter-b4s1e1-20231212-0801
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# stg-cli13b-t6.mt.him.cln.inter-b4s1e1-20231212-0801
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0546
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0002
|
38 |
+
- train_batch_size: 4
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: cosine
|
43 |
+
- num_epochs: 1
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 0.367 | 0.03 | 100 | 0.0896 |
|
51 |
+
| 0.0809 | 0.07 | 200 | 0.0730 |
|
52 |
+
| 0.0721 | 0.1 | 300 | 0.0687 |
|
53 |
+
| 0.065 | 0.13 | 400 | 0.0632 |
|
54 |
+
| 0.0629 | 0.17 | 500 | 0.0636 |
|
55 |
+
| 0.0618 | 0.2 | 600 | 0.0608 |
|
56 |
+
| 0.0606 | 0.23 | 700 | 0.0615 |
|
57 |
+
| 0.0604 | 0.27 | 800 | 0.0599 |
|
58 |
+
| 0.0598 | 0.3 | 900 | 0.0601 |
|
59 |
+
| 0.0599 | 0.33 | 1000 | 0.0598 |
|
60 |
+
| 0.0613 | 0.37 | 1100 | 0.0598 |
|
61 |
+
| 0.0597 | 0.4 | 1200 | 0.0590 |
|
62 |
+
| 0.06 | 0.43 | 1300 | 0.0589 |
|
63 |
+
| 0.058 | 0.47 | 1400 | 0.0589 |
|
64 |
+
| 0.058 | 0.5 | 1500 | 0.0575 |
|
65 |
+
| 0.0578 | 0.53 | 1600 | 0.0576 |
|
66 |
+
| 0.0569 | 0.57 | 1700 | 0.0566 |
|
67 |
+
| 0.0573 | 0.6 | 1800 | 0.0574 |
|
68 |
+
| 0.0577 | 0.63 | 1900 | 0.0567 |
|
69 |
+
| 0.0574 | 0.67 | 2000 | 0.0561 |
|
70 |
+
| 0.0566 | 0.7 | 2100 | 0.0559 |
|
71 |
+
| 0.056 | 0.74 | 2200 | 0.0562 |
|
72 |
+
| 0.0563 | 0.77 | 2300 | 0.0556 |
|
73 |
+
| 0.0551 | 0.8 | 2400 | 0.0553 |
|
74 |
+
| 0.0554 | 0.84 | 2500 | 0.0551 |
|
75 |
+
| 0.0553 | 0.87 | 2600 | 0.0550 |
|
76 |
+
| 0.0548 | 0.9 | 2700 | 0.0547 |
|
77 |
+
| 0.0547 | 0.94 | 2800 | 0.0546 |
|
78 |
+
| 0.0547 | 0.97 | 2900 | 0.0546 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.36.0.dev0
|
84 |
+
- Pytorch 2.1.1+cu121
|
85 |
+
- Datasets 2.15.0
|
86 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:645049fbb522e587b11f4f7a1d58378aa0f6821385f0c8180a9d75d3580ba230
|
3 |
size 125248064
|