Hugging Face's logo

Gunslinger3D
/
fine-tuning-Phi2-with-webglm-qa-with-lora_7

PEFT
Safetensors
Generated from Trainer
Model card Files Community
Gunslinger3D commited on
Commit
7c0930d
·
verified ·
1 Parent(s): 9e94c66

fine-tuning-Phi2-with-webglm-qa-with-lora_7

Browse files
Files changed (4) hide show
  1. README.md +112 -0
  2. adapter_config.json +30 -0
  3. adapter_model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: microsoft/phi-2
7
+ model-index:
8
+ - name: fine-tuning-Phi2-with-webglm-qa-with-lora_7
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
+ # fine-tuning-Phi2-with-webglm-qa-with-lora_7
16
+
17
+ This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0950
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: 5e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 5
43
+ - total_train_batch_size: 10
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 60
47
+ - training_steps: 1000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 7.3505 | 0.31 | 20 | 6.2863 |
55
+ | 4.0914 | 0.63 | 40 | 0.9255 |
56
+ | 0.6517 | 0.94 | 60 | 0.5762 |
57
+ | 0.4621 | 1.26 | 80 | 0.4062 |
58
+ | 0.3128 | 1.57 | 100 | 0.3056 |
59
+ | 0.2536 | 1.89 | 120 | 0.2604 |
60
+ | 0.2227 | 2.2 | 140 | 0.2247 |
61
+ | 0.1901 | 2.52 | 160 | 0.2041 |
62
+ | 0.176 | 2.83 | 180 | 0.1812 |
63
+ | 0.1453 | 3.14 | 200 | 0.1683 |
64
+ | 0.1557 | 3.46 | 220 | 0.1592 |
65
+ | 0.1441 | 3.77 | 240 | 0.1488 |
66
+ | 0.1282 | 4.09 | 260 | 0.1430 |
67
+ | 0.1215 | 4.4 | 280 | 0.1348 |
68
+ | 0.1217 | 4.72 | 300 | 0.1323 |
69
+ | 0.117 | 5.03 | 320 | 0.1271 |
70
+ | 0.109 | 5.35 | 340 | 0.1255 |
71
+ | 0.1094 | 5.66 | 360 | 0.1210 |
72
+ | 0.1057 | 5.97 | 380 | 0.1175 |
73
+ | 0.0937 | 6.29 | 400 | 0.1158 |
74
+ | 0.0942 | 6.6 | 420 | 0.1159 |
75
+ | 0.1007 | 6.92 | 440 | 0.1125 |
76
+ | 0.0876 | 7.23 | 460 | 0.1119 |
77
+ | 0.0894 | 7.55 | 480 | 0.1099 |
78
+ | 0.0827 | 7.86 | 500 | 0.1072 |
79
+ | 0.0894 | 8.18 | 520 | 0.1069 |
80
+ | 0.0805 | 8.49 | 540 | 0.1075 |
81
+ | 0.0782 | 8.81 | 560 | 0.1043 |
82
+ | 0.0881 | 9.12 | 580 | 0.1034 |
83
+ | 0.0839 | 9.43 | 600 | 0.1015 |
84
+ | 0.0694 | 9.75 | 620 | 0.1000 |
85
+ | 0.068 | 10.06 | 640 | 0.1007 |
86
+ | 0.072 | 10.38 | 660 | 0.0994 |
87
+ | 0.0709 | 10.69 | 680 | 0.0985 |
88
+ | 0.0712 | 11.01 | 700 | 0.0986 |
89
+ | 0.0673 | 11.32 | 720 | 0.0999 |
90
+ | 0.0669 | 11.64 | 740 | 0.0974 |
91
+ | 0.0706 | 11.95 | 760 | 0.0981 |
92
+ | 0.0641 | 12.26 | 780 | 0.0969 |
93
+ | 0.0652 | 12.58 | 800 | 0.0964 |
94
+ | 0.0668 | 12.89 | 820 | 0.0962 |
95
+ | 0.0617 | 13.21 | 840 | 0.0972 |
96
+ | 0.0628 | 13.52 | 860 | 0.0960 |
97
+ | 0.0637 | 13.84 | 880 | 0.0949 |
98
+ | 0.0633 | 14.15 | 900 | 0.0951 |
99
+ | 0.0577 | 14.47 | 920 | 0.0953 |
100
+ | 0.0646 | 14.78 | 940 | 0.0947 |
101
+ | 0.06 | 15.09 | 960 | 0.0946 |
102
+ | 0.0584 | 15.41 | 980 | 0.0949 |
103
+ | 0.0638 | 15.72 | 1000 | 0.0950 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - PEFT 0.7.1
109
+ - Transformers 4.36.2
110
+ - Pytorch 2.0.0
111
+ - Datasets 2.15.0
112
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/phi-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": 32,
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": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "fc1",
24
+ "fc2",
25
+ "q_proj",
26
+ "dense",
27
+ "v_proj"
28
+ ],
29
+ "task_type": "CAUSAL_LM"
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a36a3b73d5ff05abb5977d27e8f2b1b26f667a0ddfb2231f05c5a383d691576
3
+ size 94422368
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0625f5be598e6f058625d3231cef9487de3096ee8bbf8a08d82ab48f97747322
3
+ size 4283