diwakar21scout commited on
Commit
b216caa
1 Parent(s): f2a5a79

diwakar21scout/llama-pls/sql-pyspark_v0

Browse files
Files changed (4) hide show
  1. README.md +80 -0
  2. adapter_config.json +19 -0
  3. adapter_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ base_model: codellama/CodeLlama-7b-hf
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: sql-code-llama
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
+ # sql-code-llama
15
+
16
+ This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0810
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: 0.0003
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 100
46
+ - training_steps: 400
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 2.033 | 0.28 | 20 | 1.9418 |
54
+ | 1.3136 | 0.56 | 40 | 0.8477 |
55
+ | 0.1674 | 0.83 | 60 | 0.1384 |
56
+ | 0.1276 | 1.11 | 80 | 0.1220 |
57
+ | 0.1106 | 1.39 | 100 | 0.1046 |
58
+ | 0.102 | 1.67 | 120 | 0.0946 |
59
+ | 0.0917 | 1.94 | 140 | 0.0903 |
60
+ | 0.0895 | 2.22 | 160 | 0.0887 |
61
+ | 0.0889 | 2.5 | 180 | 0.0872 |
62
+ | 0.0874 | 2.78 | 200 | 0.0858 |
63
+ | 0.086 | 3.06 | 220 | 0.0851 |
64
+ | 0.0861 | 3.33 | 240 | 0.0842 |
65
+ | 0.085 | 3.61 | 260 | 0.0835 |
66
+ | 0.0821 | 3.89 | 280 | 0.0830 |
67
+ | 0.0838 | 4.17 | 300 | 0.0823 |
68
+ | 0.0816 | 4.44 | 320 | 0.0820 |
69
+ | 0.0785 | 4.72 | 340 | 0.0815 |
70
+ | 0.0819 | 5.0 | 360 | 0.0812 |
71
+ | 0.081 | 5.28 | 380 | 0.0810 |
72
+ | 0.0765 | 5.56 | 400 | 0.0810 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.36.2
78
+ - Pytorch 2.0.1+cu117
79
+ - Datasets 2.13.1
80
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 16,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 16,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "k_proj",
15
+ "v_proj",
16
+ "o_proj"
17
+ ],
18
+ "task_type": "CAUSAL_LM"
19
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
3
+ size 443
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfaadddc9621cf3dfc6e89dad1321ab1417b56cf9f00b6968d4009230e4ec47b
3
+ size 4283