doganmustafa commited on
Commit
14bd1fa
1 Parent(s): 42521f6

End of training

Browse files
Files changed (1) hide show
  1. README.md +79 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-1B
3
+ library_name: peft
4
+ license: llama3.2
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Llama-3.2-1B
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # Llama-3.2-1B
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2404
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 30
45
+ - training_steps: 2000
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.4565 | 0.05 | 100 | 0.4042 |
52
+ | 0.355 | 0.1 | 200 | 0.3224 |
53
+ | 0.3004 | 0.15 | 300 | 0.3054 |
54
+ | 0.2844 | 0.2 | 400 | 0.2904 |
55
+ | 0.2331 | 0.25 | 500 | 0.2829 |
56
+ | 0.241 | 0.3 | 600 | 0.2737 |
57
+ | 0.3013 | 0.35 | 700 | 0.2682 |
58
+ | 0.2619 | 0.4 | 800 | 0.2626 |
59
+ | 0.2367 | 0.45 | 900 | 0.2588 |
60
+ | 0.2152 | 0.5 | 1000 | 0.2563 |
61
+ | 0.2464 | 0.55 | 1100 | 0.2521 |
62
+ | 0.2443 | 0.6 | 1200 | 0.2491 |
63
+ | 0.2639 | 0.65 | 1300 | 0.2467 |
64
+ | 0.2602 | 0.7 | 1400 | 0.2447 |
65
+ | 0.291 | 0.75 | 1500 | 0.2434 |
66
+ | 0.2524 | 0.8 | 1600 | 0.2419 |
67
+ | 0.272 | 0.85 | 1700 | 0.2410 |
68
+ | 0.2273 | 0.9 | 1800 | 0.2406 |
69
+ | 0.2584 | 0.95 | 1900 | 0.2405 |
70
+ | 0.237 | 1.0 | 2000 | 0.2404 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - PEFT 0.13.0
76
+ - Transformers 4.44.2
77
+ - Pytorch 2.4.1+cu121
78
+ - Datasets 3.0.1
79
+ - Tokenizers 0.19.1