Hugging Face's logo

Ramikan-BR
/
tinyllama_PY-CODER-bnb-4bit-lora_model-4k

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
tinyllamacoder-py
coder-py
coder
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
Ramikan-BR commited on
Commit
ce792c2
•
1 Parent(s): 96986db

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -5
README.md CHANGED
@@ -21,11 +21,36 @@ Accumulation steps = 16 \ / Total batch size = 32 | Total steps = 30 "-____-"
21
  Number of trainable parameters = 100,925,440 [30/30 26:26, Epoch 0/1] Step
22
  Training Loss
23
 
24
- 1 1.737000 2 1.738000 3 1.384700 4 1.086400 5 1.009600 6 0.921000 7 0.830400 8
25
- 0.808900 9 0.774500 10 0.759900 11 0.736100 12 0.721200 13 0.733200 14 0.701000
26
- 15 0.711700 16 0.701400 17 0.689500 18 0.678800 19 0.675200 20 0.680500 21
27
- 0.685800 22 0.681200 23 0.672000 24 0.679900 25 0.675500 26 0.666600 27 0.687900
28
- 28 0.653600 29 0.672500 30 0.660900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
 
30
  ---
31
  null
 
21
  Number of trainable parameters = 100,925,440 [30/30 26:26, Epoch 0/1] Step
22
  Training Loss
23
 
24
+ 1 1.737000
25
+ 2 1.738000
26
+ 3 1.384700
27
+ 4 1.086400
28
+ 5 1.009600
29
+ 6 0.921000
30
+ 7 0.830400
31
+ 8 0.808900
32
+ 9 0.774500
33
+ 10 0.759900
34
+ 11 0.736100
35
+ 12 0.721200
36
+ 13 0.733200
37
+ 14 0.701000
38
+ 15 0.711700
39
+ 16 0.701400
40
+ 17 0.689500
41
+ 18 0.678800
42
+ 19 0.675200
43
+ 20 0.680500
44
+ 21 0.685800
45
+ 22 0.681200
46
+ 23 0.672000
47
+ 24 0.679900
48
+ 25 0.675500
49
+ 26 0.666600
50
+ 27 0.687900
51
+ 28 0.653600
52
+ 29 0.672500
53
+ 30 0.660900
54
 
55
  ---
56
  null