Hugging Face's logo

rbelanec
/
train_codealpacapy_456_1765305198

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
2d46e3c
路
verified 路
1 Parent(s): af68081

Model save

Browse files
Files changed (2) hide show
  1. README.md +81 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: train_codealpacapy_456_1765305198
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # train_codealpacapy_456_1765305198
17
+
18
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.5947
21
+ - Num Input Tokens Seen: 24973864
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: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 456
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: 0.1
47
+ - num_epochs: 20
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:-----------------:|
53
+ | 0.4909 | 1.0 | 1908 | 0.4533 | 1246832 |
54
+ | 0.5107 | 2.0 | 3816 | 0.4463 | 2497936 |
55
+ | 0.4271 | 3.0 | 5724 | 0.4399 | 3743760 |
56
+ | 0.3778 | 4.0 | 7632 | 0.4473 | 4991472 |
57
+ | 0.9067 | 5.0 | 9540 | 0.4627 | 6239608 |
58
+ | 0.2917 | 6.0 | 11448 | 0.4996 | 7485248 |
59
+ | 0.4214 | 7.0 | 13356 | 0.5415 | 8733024 |
60
+ | 0.3429 | 8.0 | 15264 | 0.5936 | 9983720 |
61
+ | 0.1361 | 9.0 | 17172 | 0.6715 | 11229792 |
62
+ | 0.1287 | 10.0 | 19080 | 0.7588 | 12476552 |
63
+ | 0.0863 | 11.0 | 20988 | 0.8549 | 13725560 |
64
+ | 0.0963 | 12.0 | 22896 | 0.9736 | 14977976 |
65
+ | 0.0586 | 13.0 | 24804 | 1.0952 | 16225896 |
66
+ | 0.0351 | 14.0 | 26712 | 1.2337 | 17477224 |
67
+ | 0.013 | 15.0 | 28620 | 1.3411 | 18726216 |
68
+ | 0.0066 | 16.0 | 30528 | 1.4384 | 19973408 |
69
+ | 0.0078 | 17.0 | 32436 | 1.5158 | 21226656 |
70
+ | 0.0046 | 18.0 | 34344 | 1.5550 | 22472696 |
71
+ | 0.0027 | 19.0 | 36252 | 1.5828 | 23722376 |
72
+ | 0.0136 | 20.0 | 38160 | 1.5947 | 24973864 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - PEFT 0.15.2
78
+ - Transformers 4.51.3
79
+ - Pytorch 2.8.0+cu128
80
+ - Datasets 3.6.0
81
+ - Tokenizers 0.21.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74bab9cbb4e5a395adf55896536973786bf7b8f97ffc5ea43feef12b6faacef6
3
  size 58745928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab361daac7dfd647422063b585307f3f251c1964759760acbb91b13d1cbb091
3
  size 58745928