baltop commited on
Commit
a6ce8e2
1 Parent(s): f96465d

Upload folder using huggingface_hub

Browse files
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