Hugging Face's logo

Harshini2004
/
englishTeluguModel

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files
xet
Community
Harshini2004 commited on
Commit
5bbe654
·
verified ·
1 Parent(s): aa6c240

Model save

Browse files
Files changed (2) hide show
  1. README.md +88 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/tinyllama-chat-bnb-4bit
5
+ tags:
6
+ - unsloth
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: englishTeluguModel
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
+ # englishTeluguModel
17
+
18
+ This model is a fine-tuned version of [unsloth/tinyllama-chat-bnb-4bit](https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 4.8606
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 8
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 2
48
+ - num_epochs: 10
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 3.1943 | 0.4 | 2 | 5.0423 |
56
+ | 3.5 | 0.8 | 4 | 5.0423 |
57
+ | 4.6154 | 1.2 | 6 | 5.0423 |
58
+ | 3.1785 | 1.6 | 8 | 5.0423 |
59
+ | 4.2688 | 2.0 | 10 | 5.0344 |
60
+ | 3.2921 | 2.4 | 12 | 5.0084 |
61
+ | 3.3623 | 2.8 | 14 | 5.0084 |
62
+ | 3.35 | 3.2 | 16 | 4.9870 |
63
+ | 2.9667 | 3.6 | 18 | 4.9529 |
64
+ | 1.6306 | 4.0 | 20 | 4.9077 |
65
+ | 2.4324 | 4.4 | 22 | 4.8973 |
66
+ | 3.3228 | 4.8 | 24 | 4.8848 |
67
+ | 3.1761 | 5.2 | 26 | 4.8712 |
68
+ | 2.3414 | 5.6 | 28 | 4.8483 |
69
+ | 3.8609 | 6.0 | 30 | 4.8307 |
70
+ | 2.0469 | 6.4 | 32 | 4.8273 |
71
+ | 1.8496 | 6.8 | 34 | 4.8161 |
72
+ | 3.4417 | 7.2 | 36 | 4.8191 |
73
+ | 1.3278 | 7.6 | 38 | 4.8450 |
74
+ | 2.2355 | 8.0 | 40 | 4.8493 |
75
+ | 1.0422 | 8.4 | 42 | 4.8465 |
76
+ | 2.1946 | 8.8 | 44 | 4.8404 |
77
+ | 1.6153 | 9.2 | 46 | 4.8502 |
78
+ | 1.0659 | 9.6 | 48 | 4.8601 |
79
+ | 1.7748 | 10.0 | 50 | 4.8606 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - PEFT 0.14.0
85
+ - Transformers 4.48.3
86
+ - Pytorch 2.6.0+cu124
87
+ - Datasets 3.3.1
88
+ - Tokenizers 0.21.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63fa8b2c83a609272e7af0f797bd7873945646aaba55b69b8045c49835e3d399
3
  size 18045856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b7c8524e59b076dc59939d5fc256ada4f0c8db88e235cf2c53e4997aff3343
3
  size 18045856