Hugging Face's logo

imdatta0
/
llama_2_7b_Magiccoder_evol_10k_qlora_ortho

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
f53e2fa
•
1 Parent(s): 7b4d29e

End of training

Browse files
Files changed (1) hide show
  1. README.md +100 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - unsloth
6
+ - generated_from_trainer
7
+ base_model: unsloth/llama-2-7b-bnb-4bit
8
+ model-index:
9
+ - name: llama_2_7b_Magiccoder_evol_10k_qlora_ortho
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
+ # llama_2_7b_Magiccoder_evol_10k_qlora_ortho
17
+
18
+ This model is a fine-tuned version of [unsloth/llama-2-7b-bnb-4bit](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.1526
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: 0.0001
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 8
44
+ - total_train_batch_size: 64
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_steps: 0.02
48
+ - num_epochs: 1
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.3112 | 0.0262 | 4 | 1.3071 |
55
+ | 1.2618 | 0.0523 | 8 | 1.2507 |
56
+ | 1.1942 | 0.0785 | 12 | 1.2344 |
57
+ | 1.1464 | 0.1047 | 16 | 1.2197 |
58
+ | 1.1847 | 0.1308 | 20 | 1.2100 |
59
+ | 1.1386 | 0.1570 | 24 | 1.2049 |
60
+ | 1.1422 | 0.1832 | 28 | 1.1980 |
61
+ | 1.1842 | 0.2093 | 32 | 1.1905 |
62
+ | 1.1147 | 0.2355 | 36 | 1.1862 |
63
+ | 1.1942 | 0.2617 | 40 | 1.1814 |
64
+ | 1.1704 | 0.2878 | 44 | 1.1771 |
65
+ | 1.2081 | 0.3140 | 48 | 1.1754 |
66
+ | 1.1866 | 0.3401 | 52 | 1.1731 |
67
+ | 1.1538 | 0.3663 | 56 | 1.1722 |
68
+ | 1.2015 | 0.3925 | 60 | 1.1690 |
69
+ | 1.1997 | 0.4186 | 64 | 1.1671 |
70
+ | 1.146 | 0.4448 | 68 | 1.1648 |
71
+ | 1.1609 | 0.4710 | 72 | 1.1629 |
72
+ | 1.1125 | 0.4971 | 76 | 1.1641 |
73
+ | 1.1983 | 0.5233 | 80 | 1.1624 |
74
+ | 1.215 | 0.5495 | 84 | 1.1605 |
75
+ | 1.1462 | 0.5756 | 88 | 1.1595 |
76
+ | 1.0991 | 0.6018 | 92 | 1.1581 |
77
+ | 1.0994 | 0.6280 | 96 | 1.1569 |
78
+ | 1.1604 | 0.6541 | 100 | 1.1556 |
79
+ | 1.1534 | 0.6803 | 104 | 1.1551 |
80
+ | 1.1376 | 0.7065 | 108 | 1.1550 |
81
+ | 1.1722 | 0.7326 | 112 | 1.1545 |
82
+ | 1.1151 | 0.7588 | 116 | 1.1540 |
83
+ | 1.1393 | 0.7850 | 120 | 1.1531 |
84
+ | 1.1587 | 0.8111 | 124 | 1.1525 |
85
+ | 1.1199 | 0.8373 | 128 | 1.1526 |
86
+ | 1.0548 | 0.8635 | 132 | 1.1527 |
87
+ | 1.1717 | 0.8896 | 136 | 1.1526 |
88
+ | 1.0785 | 0.9158 | 140 | 1.1526 |
89
+ | 1.1314 | 0.9419 | 144 | 1.1527 |
90
+ | 1.1544 | 0.9681 | 148 | 1.1526 |
91
+ | 1.1402 | 0.9943 | 152 | 1.1526 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - PEFT 0.7.1
97
+ - Transformers 4.40.2
98
+ - Pytorch 2.3.0+cu121
99
+ - Datasets 2.19.1
100
+ - Tokenizers 0.19.1