End of training
Browse files- README.md +110 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: mistralai/Mistral-7B-v0.3
|
3 |
+
library_name: peft
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- unsloth
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: Mistral-7B-v0.3_pct_default_r32
|
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 |
+
# Mistral-7B-v0.3_pct_default_r32
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.0448
|
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: 1
|
41 |
+
- eval_batch_size: 1
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 64
|
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 |
+
| 1.9915 | 0.0206 | 8 | 2.0385 |
|
55 |
+
| 2.054 | 0.0413 | 16 | 2.0376 |
|
56 |
+
| 2.0356 | 0.0619 | 24 | 2.0604 |
|
57 |
+
| 2.0385 | 0.0825 | 32 | 2.0639 |
|
58 |
+
| 2.1223 | 0.1032 | 40 | 2.0833 |
|
59 |
+
| 2.0677 | 0.1238 | 48 | 2.0910 |
|
60 |
+
| 2.0729 | 0.1444 | 56 | 2.0872 |
|
61 |
+
| 2.1197 | 0.1651 | 64 | 2.0973 |
|
62 |
+
| 2.1053 | 0.1857 | 72 | 2.0919 |
|
63 |
+
| 2.0848 | 0.2063 | 80 | 2.1035 |
|
64 |
+
| 2.1015 | 0.2270 | 88 | 2.1114 |
|
65 |
+
| 2.0872 | 0.2476 | 96 | 2.1133 |
|
66 |
+
| 2.0948 | 0.2682 | 104 | 2.1221 |
|
67 |
+
| 2.097 | 0.2889 | 112 | 2.1219 |
|
68 |
+
| 2.147 | 0.3095 | 120 | 2.1240 |
|
69 |
+
| 2.1315 | 0.3301 | 128 | 2.1189 |
|
70 |
+
| 2.1563 | 0.3508 | 136 | 2.1368 |
|
71 |
+
| 2.1836 | 0.3714 | 144 | 2.1271 |
|
72 |
+
| 2.1245 | 0.3920 | 152 | 2.1198 |
|
73 |
+
| 2.0947 | 0.4127 | 160 | 2.1240 |
|
74 |
+
| 2.1472 | 0.4333 | 168 | 2.1354 |
|
75 |
+
| 2.1348 | 0.4539 | 176 | 2.1261 |
|
76 |
+
| 2.1099 | 0.4746 | 184 | 2.1275 |
|
77 |
+
| 2.1006 | 0.4952 | 192 | 2.1196 |
|
78 |
+
| 2.1339 | 0.5158 | 200 | 2.1170 |
|
79 |
+
| 2.0841 | 0.5364 | 208 | 2.1105 |
|
80 |
+
| 2.1344 | 0.5571 | 216 | 2.1079 |
|
81 |
+
| 2.0732 | 0.5777 | 224 | 2.1043 |
|
82 |
+
| 2.0417 | 0.5983 | 232 | 2.1035 |
|
83 |
+
| 2.1003 | 0.6190 | 240 | 2.0967 |
|
84 |
+
| 2.0501 | 0.6396 | 248 | 2.1007 |
|
85 |
+
| 2.078 | 0.6602 | 256 | 2.0862 |
|
86 |
+
| 2.0507 | 0.6809 | 264 | 2.0840 |
|
87 |
+
| 2.0235 | 0.7015 | 272 | 2.0762 |
|
88 |
+
| 2.0743 | 0.7221 | 280 | 2.0723 |
|
89 |
+
| 2.1028 | 0.7428 | 288 | 2.0721 |
|
90 |
+
| 2.0987 | 0.7634 | 296 | 2.0662 |
|
91 |
+
| 2.0985 | 0.7840 | 304 | 2.0663 |
|
92 |
+
| 2.0548 | 0.8047 | 312 | 2.0602 |
|
93 |
+
| 2.0365 | 0.8253 | 320 | 2.0563 |
|
94 |
+
| 2.0102 | 0.8459 | 328 | 2.0564 |
|
95 |
+
| 2.0497 | 0.8666 | 336 | 2.0522 |
|
96 |
+
| 2.0721 | 0.8872 | 344 | 2.0471 |
|
97 |
+
| 2.0812 | 0.9078 | 352 | 2.0468 |
|
98 |
+
| 2.0475 | 0.9285 | 360 | 2.0462 |
|
99 |
+
| 2.0687 | 0.9491 | 368 | 2.0452 |
|
100 |
+
| 2.065 | 0.9697 | 376 | 2.0450 |
|
101 |
+
| 1.991 | 0.9904 | 384 | 2.0448 |
|
102 |
+
|
103 |
+
|
104 |
+
### Framework versions
|
105 |
+
|
106 |
+
- PEFT 0.12.0
|
107 |
+
- Transformers 4.44.2
|
108 |
+
- Pytorch 2.3.0+cu121
|
109 |
+
- Datasets 2.21.0
|
110 |
+
- 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 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b81cd06654c9295a57be2418e4b72fba8c34c82b0361cbe02051dd3ed009ba16
|
3 |
size 335604696
|