Hugging Face's logo

Gunslinger3D
/
fine-tuning-Phi2-with-webglm-qa-with-lora_3

PEFT
Safetensors
Generated from Trainer
Model card Files Community
Gunslinger3D commited on
Commit
31317b9
·
verified ·
1 Parent(s): 0107329

fine-tuning-Phi2-with-webglm-qa-with-lora_3

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_3
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_3
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: 0.1155
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: 50
47
+ - training_steps: 500
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 8.243 | 0.2 | 10 | 7.8185 |
55
+ | 7.4602 | 0.4 | 20 | 6.3280 |
56
+ | 4.794 | 0.6 | 30 | 3.1068 |
57
+ | 1.6994 | 0.8 | 40 | 0.6354 |
58
+ | 0.543 | 1.0 | 50 | 0.5653 |
59
+ | 0.4542 | 1.2 | 60 | 0.4874 |
60
+ | 0.4449 | 1.39 | 70 | 0.4225 |
61
+ | 0.3623 | 1.59 | 80 | 0.3685 |
62
+ | 0.278 | 1.79 | 90 | 0.3283 |
63
+ | 0.2385 | 1.99 | 100 | 0.2983 |
64
+ | 0.2499 | 2.19 | 110 | 0.2748 |
65
+ | 0.2113 | 2.39 | 120 | 0.2590 |
66
+ | 0.1966 | 2.59 | 130 | 0.2420 |
67
+ | 0.217 | 2.79 | 140 | 0.2242 |
68
+ | 0.1731 | 2.99 | 150 | 0.2121 |
69
+ | 0.1779 | 3.19 | 160 | 0.2033 |
70
+ | 0.1687 | 3.39 | 170 | 0.1909 |
71
+ | 0.156 | 3.59 | 180 | 0.1833 |
72
+ | 0.1464 | 3.78 | 190 | 0.1763 |
73
+ | 0.1637 | 3.98 | 200 | 0.1706 |
74
+ | 0.1455 | 4.18 | 210 | 0.1649 |
75
+ | 0.128 | 4.38 | 220 | 0.1621 |
76
+ | 0.1537 | 4.58 | 230 | 0.1562 |
77
+ | 0.1193 | 4.78 | 240 | 0.1502 |
78
+ | 0.1323 | 4.98 | 250 | 0.1464 |
79
+ | 0.1346 | 5.18 | 260 | 0.1440 |
80
+ | 0.1049 | 5.38 | 270 | 0.1411 |
81
+ | 0.1265 | 5.58 | 280 | 0.1377 |
82
+ | 0.13 | 5.78 | 290 | 0.1363 |
83
+ | 0.1059 | 5.98 | 300 | 0.1335 |
84
+ | 0.1141 | 6.18 | 310 | 0.1300 |
85
+ | 0.1097 | 6.37 | 320 | 0.1297 |
86
+ | 0.1088 | 6.57 | 330 | 0.1287 |
87
+ | 0.106 | 6.77 | 340 | 0.1261 |
88
+ | 0.1011 | 6.97 | 350 | 0.1243 |
89
+ | 0.0999 | 7.17 | 360 | 0.1235 |
90
+ | 0.1081 | 7.37 | 370 | 0.1223 |
91
+ | 0.0999 | 7.57 | 380 | 0.1207 |
92
+ | 0.1057 | 7.77 | 390 | 0.1203 |
93
+ | 0.0937 | 7.97 | 400 | 0.1192 |
94
+ | 0.0842 | 8.17 | 410 | 0.1195 |
95
+ | 0.0907 | 8.37 | 420 | 0.1182 |
96
+ | 0.1109 | 8.57 | 430 | 0.1176 |
97
+ | 0.0901 | 8.76 | 440 | 0.1170 |
98
+ | 0.1005 | 8.96 | 450 | 0.1162 |
99
+ | 0.0961 | 9.16 | 460 | 0.1159 |
100
+ | 0.0927 | 9.36 | 470 | 0.1156 |
101
+ | 0.0916 | 9.56 | 480 | 0.1158 |
102
+ | 0.0908 | 9.76 | 490 | 0.1156 |
103
+ | 0.0909 | 9.96 | 500 | 0.1155 |
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
+ "q_proj",
24
+ "dense",
25
+ "fc2",
26
+ "fc1",
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:c0e544600e3ee127fec959e34527e1c9c6a8b209b2c4a6f16f916c2f30652870
3
+ size 94422368
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ba65340622fbadf328bbed112e8224bd0e9dffd5bb5c51852abfc343db44ad
3
+ size 4283