End of training
Browse files- README.md +100 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/qwen2-7b-bnb-4bit
|
3 |
+
library_name: peft
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- unsloth
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: Qwen2-7B_magiccoder_default
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Qwen2-7B_magiccoder_default
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [unsloth/qwen2-7b-bnb-4bit](https://huggingface.co/unsloth/qwen2-7b-bnb-4bit) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.8796
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0001
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 64
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: cosine
|
47 |
+
- lr_scheduler_warmup_ratio: 0.02
|
48 |
+
- num_epochs: 1
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
54 |
+
| 0.9592 | 0.0261 | 4 | 1.0014 |
|
55 |
+
| 0.9246 | 0.0522 | 8 | 0.9342 |
|
56 |
+
| 0.9101 | 0.0783 | 12 | 0.9148 |
|
57 |
+
| 0.8605 | 0.1044 | 16 | 0.9008 |
|
58 |
+
| 0.9093 | 0.1305 | 20 | 0.8958 |
|
59 |
+
| 0.7967 | 0.1566 | 24 | 0.8949 |
|
60 |
+
| 0.8075 | 0.1827 | 28 | 0.8941 |
|
61 |
+
| 0.9522 | 0.2088 | 32 | 0.8917 |
|
62 |
+
| 0.8503 | 0.2349 | 36 | 0.8890 |
|
63 |
+
| 0.8704 | 0.2610 | 40 | 0.8864 |
|
64 |
+
| 0.9286 | 0.2871 | 44 | 0.8852 |
|
65 |
+
| 0.894 | 0.3132 | 48 | 0.8839 |
|
66 |
+
| 0.8171 | 0.3393 | 52 | 0.8835 |
|
67 |
+
| 0.8224 | 0.3654 | 56 | 0.8828 |
|
68 |
+
| 0.8392 | 0.3915 | 60 | 0.8822 |
|
69 |
+
| 0.897 | 0.4176 | 64 | 0.8817 |
|
70 |
+
| 0.8942 | 0.4437 | 68 | 0.8813 |
|
71 |
+
| 0.8501 | 0.4698 | 72 | 0.8809 |
|
72 |
+
| 0.8768 | 0.4959 | 76 | 0.8807 |
|
73 |
+
| 0.8337 | 0.5220 | 80 | 0.8806 |
|
74 |
+
| 0.9285 | 0.5481 | 84 | 0.8801 |
|
75 |
+
| 0.8301 | 0.5742 | 88 | 0.8803 |
|
76 |
+
| 0.9212 | 0.6003 | 92 | 0.8805 |
|
77 |
+
| 0.8485 | 0.6264 | 96 | 0.8804 |
|
78 |
+
| 0.9419 | 0.6525 | 100 | 0.8801 |
|
79 |
+
| 0.8191 | 0.6786 | 104 | 0.8799 |
|
80 |
+
| 0.8668 | 0.7047 | 108 | 0.8799 |
|
81 |
+
| 0.8335 | 0.7308 | 112 | 0.8798 |
|
82 |
+
| 0.8003 | 0.7569 | 116 | 0.8797 |
|
83 |
+
| 0.794 | 0.7830 | 120 | 0.8796 |
|
84 |
+
| 0.863 | 0.8091 | 124 | 0.8797 |
|
85 |
+
| 0.8262 | 0.8352 | 128 | 0.8795 |
|
86 |
+
| 0.9269 | 0.8613 | 132 | 0.8796 |
|
87 |
+
| 0.876 | 0.8874 | 136 | 0.8795 |
|
88 |
+
| 0.8955 | 0.9135 | 140 | 0.8794 |
|
89 |
+
| 0.8481 | 0.9396 | 144 | 0.8796 |
|
90 |
+
| 0.9111 | 0.9657 | 148 | 0.8795 |
|
91 |
+
| 0.8653 | 0.9918 | 152 | 0.8796 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- PEFT 0.12.0
|
97 |
+
- Transformers 4.44.0
|
98 |
+
- Pytorch 2.4.0+cu121
|
99 |
+
- Datasets 2.20.0
|
100 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 80792096
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc866ed885b81965127546907506c8304e45e1cfc3139f87915530444cadfab7
|
3 |
size 80792096
|