Hugging Face's logo

mg11
/
Meta-Llama-3.1-8B-Instruct-function-calling-json-mode-VisitorRequests_Lora

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
mg11 commited on
Commit
4333b25
·
verified ·
1 Parent(s): 845cf3f

Model save

Browse files
Files changed (2) hide show
  1. README.md +92 -0
  2. runs/Aug19_22-39-49_chimera13/events.out.tfevents.1724122557.chimera13.2043887.1 +3 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3.1
3
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Meta-Llama-3.1-8B-Instruct-function-calling-json-mode-VisitorRequests_Lora
10
+ results: []
11
+ library_name: peft
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Meta-Llama-3.1-8B-Instruct-function-calling-json-mode-VisitorRequests_Lora
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6890
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0003
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 8
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: constant
48
+ - num_epochs: 2
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 2.2123 | 0.0630 | 1 | 2.0355 |
55
+ | 2.031 | 0.1260 | 2 | 1.8189 |
56
+ | 1.8617 | 0.1890 | 3 | 1.2382 |
57
+ | 1.2165 | 0.2520 | 4 | 1.2213 |
58
+ | 1.2384 | 0.3150 | 5 | 1.3884 |
59
+ | 1.2876 | 0.3780 | 6 | 1.3734 |
60
+ | 1.3752 | 0.4409 | 7 | 1.0046 |
61
+ | 0.9925 | 0.5039 | 8 | 1.1719 |
62
+ | 1.1438 | 0.5669 | 9 | 0.9010 |
63
+ | 0.9124 | 0.6299 | 10 | 0.8452 |
64
+ | 0.8283 | 0.6929 | 11 | 0.7755 |
65
+ | 0.762 | 0.7559 | 12 | 0.7758 |
66
+ | 0.7601 | 0.8189 | 13 | 0.8326 |
67
+ | 0.7841 | 0.8819 | 14 | 0.7731 |
68
+ | 0.697 | 0.9449 | 15 | 0.7534 |
69
+ | 0.7392 | 1.0079 | 16 | 0.7244 |
70
+ | 0.6977 | 1.0709 | 17 | 0.7054 |
71
+ | 0.6216 | 1.1339 | 18 | 0.6978 |
72
+ | 0.9607 | 1.1969 | 19 | 0.7370 |
73
+ | 0.693 | 1.2598 | 20 | 0.8337 |
74
+ | 0.8311 | 1.3228 | 21 | 0.9197 |
75
+ | 0.8475 | 1.3858 | 22 | 0.8201 |
76
+ | 0.7663 | 1.4488 | 23 | 0.7467 |
77
+ | 0.6859 | 1.5118 | 24 | 0.7316 |
78
+ | 0.6419 | 1.5748 | 25 | 0.7193 |
79
+ | 0.6363 | 1.6378 | 26 | 0.7011 |
80
+ | 0.6569 | 1.7008 | 27 | 0.7019 |
81
+ | 0.6467 | 1.7638 | 28 | 0.6921 |
82
+ | 0.6779 | 1.8268 | 29 | 0.6918 |
83
+ | 0.6638 | 1.8898 | 30 | 0.6890 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - PEFT 0.5.0
89
+ - Transformers 4.44.0
90
+ - Pytorch 2.1.0+cu118
91
+ - Datasets 2.16.0
92
+ - Tokenizers 0.19.1
runs/Aug19_22-39-49_chimera13/events.out.tfevents.1724122557.chimera13.2043887.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96662cab19191c2a57e4209f6499304e050f601b42674e6863ababa3497bce6
3
+ size 354