Hugging Face's logo

wookidoki
/
autofix10k

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
wookidoki commited on
Commit
8dbfbc1
·
verified ·
1 Parent(s): 4a8ff21

End of training

Browse files
Files changed (4) hide show
  1. README.md +126 -0
  2. adapter_config.json +23 -0
  3. adapter_model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ base_model: codellama/CodeLlama-7b-hf
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: autofix10k
8
+ results: []
9
+ library_name: peft
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
+ # autofix10k
16
+
17
+ This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4372
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
+
36
+ The following `bitsandbytes` quantization config was used during training:
37
+ - quant_method: QuantizationMethod.BITS_AND_BYTES
38
+ - _load_in_8bit: True
39
+ - _load_in_4bit: False
40
+ - llm_int8_threshold: 6.0
41
+ - llm_int8_skip_modules: None
42
+ - llm_int8_enable_fp32_cpu_offload: False
43
+ - llm_int8_has_fp16_weight: False
44
+ - bnb_4bit_quant_type: fp4
45
+ - bnb_4bit_use_double_quant: False
46
+ - bnb_4bit_compute_dtype: float32
47
+ - bnb_4bit_quant_storage: uint8
48
+ - load_in_4bit: False
49
+ - load_in_8bit: True
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 0.0003
54
+ - train_batch_size: 1
55
+ - eval_batch_size: 8
56
+ - seed: 42
57
+ - gradient_accumulation_steps: 8
58
+ - total_train_batch_size: 8
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 10
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss |
67
+ |:-------------:|:-----:|:----:|:---------------:|
68
+ | 0.7922 | 0.2 | 20 | 0.5237 |
69
+ | 0.5053 | 0.4 | 40 | 0.4857 |
70
+ | 0.4071 | 0.6 | 60 | 0.4356 |
71
+ | 0.4297 | 0.8 | 80 | 0.4154 |
72
+ | 0.5313 | 1.0 | 100 | 0.3827 |
73
+ | 0.4814 | 1.2 | 120 | 0.3785 |
74
+ | 0.3739 | 1.4 | 140 | 0.3774 |
75
+ | 0.3279 | 1.6 | 160 | 0.3761 |
76
+ | 0.3149 | 1.8 | 180 | 0.3732 |
77
+ | 0.4086 | 2.0 | 200 | 0.3658 |
78
+ | 0.3724 | 2.2 | 220 | 0.3664 |
79
+ | 0.3691 | 2.4 | 240 | 0.3644 |
80
+ | 0.3065 | 2.6 | 260 | 0.3679 |
81
+ | 0.2688 | 2.8 | 280 | 0.3767 |
82
+ | 0.3431 | 3.0 | 300 | 0.3633 |
83
+ | 0.333 | 3.2 | 320 | 0.3641 |
84
+ | 0.3052 | 3.4 | 340 | 0.3597 |
85
+ | 0.2444 | 3.6 | 360 | 0.3779 |
86
+ | 0.2455 | 3.8 | 380 | 0.3712 |
87
+ | 0.3078 | 4.0 | 400 | 0.3578 |
88
+ | 0.2877 | 4.2 | 420 | 0.3650 |
89
+ | 0.2659 | 4.4 | 440 | 0.3731 |
90
+ | 0.2496 | 4.6 | 460 | 0.3764 |
91
+ | 0.218 | 4.8 | 480 | 0.3781 |
92
+ | 0.219 | 5.0 | 500 | 0.3742 |
93
+ | 0.2119 | 5.2 | 520 | 0.3808 |
94
+ | 0.2435 | 5.4 | 540 | 0.3871 |
95
+ | 0.2331 | 5.6 | 560 | 0.3818 |
96
+ | 0.1738 | 5.8 | 580 | 0.3758 |
97
+ | 0.1772 | 6.0 | 600 | 0.3731 |
98
+ | 0.1607 | 6.2 | 620 | 0.4121 |
99
+ | 0.1942 | 6.4 | 640 | 0.3943 |
100
+ | 0.2312 | 6.6 | 660 | 0.3867 |
101
+ | 0.1528 | 6.8 | 680 | 0.4160 |
102
+ | 0.1155 | 7.0 | 700 | 0.4100 |
103
+ | 0.1495 | 7.2 | 720 | 0.4081 |
104
+ | 0.1674 | 7.4 | 740 | 0.4015 |
105
+ | 0.1849 | 7.6 | 760 | 0.4075 |
106
+ | 0.1231 | 7.8 | 780 | 0.4238 |
107
+ | 0.0905 | 8.0 | 800 | 0.4128 |
108
+ | 0.1156 | 8.2 | 820 | 0.4278 |
109
+ | 0.1628 | 8.4 | 840 | 0.4203 |
110
+ | 0.1545 | 8.6 | 860 | 0.4219 |
111
+ | 0.1236 | 8.8 | 880 | 0.4294 |
112
+ | 0.0799 | 9.0 | 900 | 0.4224 |
113
+ | 0.0991 | 9.2 | 920 | 0.4399 |
114
+ | 0.1176 | 9.4 | 940 | 0.4350 |
115
+ | 0.1711 | 9.6 | 960 | 0.4362 |
116
+ | 0.1106 | 9.8 | 980 | 0.4414 |
117
+ | 0.0582 | 10.0 | 1000 | 0.4372 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - PEFT 0.4.0
123
+ - Transformers 4.40.0.dev0
124
+ - Pytorch 2.2.0+cu121
125
+ - Datasets 2.17.1
126
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "k_proj",
19
+ "v_proj",
20
+ "o_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
3
+ size 48
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfbe8dbd9e89a4690d50bab9e5215a5f6f9c9bbdc52c8f20e57020727d24a7b
3
+ size 4920