pepoo20 commited on
Commit
1e2fae2
·
verified ·
1 Parent(s): 7095b78

Upload Orca_End/README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. Orca_End/README.md +71 -0
Orca_End/README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- ---
2
+ base_model: /home/ray/default/save/SFT_merge
3
+ library_name: peft
4
+ license: other
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Orca_End
11
+ results: []
12
+ --- -->
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Orca_End
18
+
19
+ This model is a fine-tuned version of [/home/ray/default/save/SFT_merge](https://huggingface.co//home/ray/default/save/SFT_merge) on the WordProblems_SFT_LLama_End dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1417
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: 2
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 16
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_steps: 1000
49
+ - num_epochs: 2.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.2267 | 0.2341 | 500 | 0.2229 |
56
+ | 0.177 | 0.4682 | 1000 | 0.1735 |
57
+ | 0.1592 | 0.7022 | 1500 | 0.1591 |
58
+ | 0.1572 | 0.9363 | 2000 | 0.1515 |
59
+ | 0.142 | 1.1704 | 2500 | 0.1472 |
60
+ | 0.1376 | 1.4045 | 3000 | 0.1441 |
61
+ | 0.1569 | 1.6386 | 3500 | 0.1425 |
62
+ | 0.1413 | 1.8727 | 4000 | 0.1417 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - PEFT 0.12.0
68
+ - Transformers 4.44.2
69
+ - Pytorch 2.3.0+cu121
70
+ - Datasets 2.17.1
71
+ - Tokenizers 0.19.1