Hugging Face's logo

advy
/
tinyllama-mentalchat16k

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
advy commited on
Commit
3f046e3
·
verified ·
1 Parent(s): 0195c09

Model save

Browse files
Files changed (2) hide show
  1. README.md +87 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: tinyllama-mentalchat16k
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
+ # tinyllama-mentalchat16k
16
+
17
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.8010
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: 0.0002
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 8
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.03
47
+ - num_epochs: 4
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.9602 | 0.1496 | 100 | 0.9461 |
55
+ | 0.9058 | 0.2992 | 200 | 0.8929 |
56
+ | 0.8474 | 0.4488 | 300 | 0.8695 |
57
+ | 0.8474 | 0.5984 | 400 | 0.8520 |
58
+ | 0.8393 | 0.7479 | 500 | 0.8393 |
59
+ | 0.8246 | 0.8975 | 600 | 0.8247 |
60
+ | 0.7652 | 1.0471 | 700 | 0.8210 |
61
+ | 0.7436 | 1.1967 | 800 | 0.8142 |
62
+ | 0.7248 | 1.3463 | 900 | 0.8076 |
63
+ | 0.7341 | 1.4959 | 1000 | 0.8008 |
64
+ | 0.7295 | 1.6455 | 1100 | 0.7940 |
65
+ | 0.7073 | 1.7951 | 1200 | 0.7896 |
66
+ | 0.7209 | 1.9447 | 1300 | 0.7836 |
67
+ | 0.6142 | 2.0942 | 1400 | 0.7935 |
68
+ | 0.6168 | 2.2438 | 1500 | 0.7946 |
69
+ | 0.6068 | 2.3934 | 1600 | 0.7908 |
70
+ | 0.6264 | 2.5430 | 1700 | 0.7899 |
71
+ | 0.6187 | 2.6926 | 1800 | 0.7833 |
72
+ | 0.6049 | 2.8422 | 1900 | 0.7842 |
73
+ | 0.6007 | 2.9918 | 2000 | 0.7816 |
74
+ | 0.5308 | 3.1414 | 2100 | 0.8032 |
75
+ | 0.5341 | 3.2909 | 2200 | 0.8018 |
76
+ | 0.5376 | 3.4405 | 2300 | 0.8013 |
77
+ | 0.5365 | 3.5901 | 2400 | 0.8018 |
78
+ | 0.5358 | 3.7397 | 2500 | 0.8010 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - PEFT 0.13.2
84
+ - Transformers 4.46.3
85
+ - Pytorch 2.4.1+cu118
86
+ - Datasets 3.1.0
87
+ - Tokenizers 0.20.3
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efee5f15a6ab6ae2aac41a5b72e2348f297a8d9be317eefa6b81d4bf46f9b2d2
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328feef4a1b98054c9ab300d362e6c5a63f586c069f4564e4ac7d4f77bc3ff46
3
  size 50503544