sujith013 commited on
Commit
ecf2769
1 Parent(s): e7a4038

End of training

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ta
4
+ license: llama2
5
+ library_name: peft
6
+ tags:
7
+ - trl
8
+ - sft
9
+ - Tamil-ASR, ASR-fine-tuning, Tamil-llama
10
+ - generated_from_trainer
11
+ base_model: abhinand/tamil-llama-7b-instruct-v0.1
12
+ model-index:
13
+ - name: tamil-llama-7b-instruct-quantized-ASR-output-fine-tuning
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # tamil-llama-7b-instruct-quantized-ASR-output-fine-tuning
21
+
22
+ This model is a fine-tuned version of [abhinand/tamil-llama-7b-instruct-v0.1](https://huggingface.co/abhinand/tamil-llama-7b-instruct-v0.1) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 5.3527
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 0.0002
44
+ - train_batch_size: 1
45
+ - eval_batch_size: 1
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 4
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: constant
51
+ - lr_scheduler_warmup_ratio: 0.03
52
+ - training_steps: 1500
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 2.4659 | 2.58 | 500 | 4.2383 |
59
+ | 1.9248 | 5.17 | 1000 | 4.6944 |
60
+ | 1.4112 | 7.75 | 1500 | 5.3527 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - PEFT 0.8.2
66
+ - Transformers 4.37.0
67
+ - Pytorch 2.1.2
68
+ - Datasets 2.16.1
69
+ - Tokenizers 0.15.1