Upload folder using huggingface_hub
Browse files- README.md +71 -0
- adapter_config.json +33 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
7 |
+
model-index:
|
8 |
+
- name: mistral-sql-finetune
|
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 |
+
# mistral-sql-finetune
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0305
|
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: 2.5e-05
|
39 |
+
- train_batch_size: 2
|
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 |
+
- lr_scheduler_warmup_steps: 1
|
45 |
+
- training_steps: 300
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 1.1899 | 0.17 | 25 | 0.3116 |
|
52 |
+
| 0.1795 | 0.33 | 50 | 0.1088 |
|
53 |
+
| 0.0819 | 0.5 | 75 | 0.0425 |
|
54 |
+
| 0.0453 | 0.67 | 100 | 0.0419 |
|
55 |
+
| 0.0534 | 0.83 | 125 | 0.0382 |
|
56 |
+
| 0.0338 | 1.0 | 150 | 0.0315 |
|
57 |
+
| 0.0358 | 1.17 | 175 | 0.0345 |
|
58 |
+
| 0.0336 | 1.33 | 200 | 0.0334 |
|
59 |
+
| 0.0401 | 1.5 | 225 | 0.0322 |
|
60 |
+
| 0.0326 | 1.67 | 250 | 0.0308 |
|
61 |
+
| 0.0396 | 1.83 | 275 | 0.0309 |
|
62 |
+
| 0.0307 | 2.0 | 300 | 0.0305 |
|
63 |
+
|
64 |
+
|
65 |
+
### Framework versions
|
66 |
+
|
67 |
+
- PEFT 0.7.2.dev0
|
68 |
+
- Transformers 4.37.0.dev0
|
69 |
+
- Pytorch 2.1.2
|
70 |
+
- Datasets 2.15.0
|
71 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 64,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 32,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
+
"up_proj",
|
24 |
+
"down_proj",
|
25 |
+
"q_proj",
|
26 |
+
"lm_head",
|
27 |
+
"gate_proj",
|
28 |
+
"v_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_rslora": false
|
33 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8818e6ea4830b84464c905ac6f94cfe80a63f77e51c2638d2bd0bcefa4dc7252
|
3 |
+
size 864513616
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3590f49eb926244738eba44f5a2a5b93f3455bb0c8fe39c90b692c6cf1ea1736
|
3 |
+
size 4664
|