Hugging Face's logo

raulgdp
/
Llama-3.2-3B-Instruct-JEP

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
raulgdp commited on
Commit
ea0fdf4
·
verified ·
1 Parent(s): 9bb6ed1

End of training

Browse files
Files changed (2) hide show
  1. README.md +126 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.2
4
+ base_model: meta-llama/Llama-3.2-3B-Instruct
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Llama-3.2-3B-Instruct-JEP
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-3.2-3B-Instruct-JEP
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.1199
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: 2e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 4
44
+ - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.4921 | 0.1535 | 100 | 1.4430 |
54
+ | 1.2984 | 0.3070 | 200 | 1.3138 |
55
+ | 1.2315 | 0.4605 | 300 | 1.2702 |
56
+ | 1.2217 | 0.6140 | 400 | 1.2429 |
57
+ | 1.263 | 0.7675 | 500 | 1.2280 |
58
+ | 1.1829 | 0.9210 | 600 | 1.2155 |
59
+ | 1.1802 | 1.0737 | 700 | 1.2063 |
60
+ | 1.2061 | 1.2272 | 800 | 1.1995 |
61
+ | 1.1387 | 1.3807 | 900 | 1.1922 |
62
+ | 1.1639 | 1.5342 | 1000 | 1.1858 |
63
+ | 1.1446 | 1.6876 | 1100 | 1.1828 |
64
+ | 1.1536 | 1.8411 | 1200 | 1.1768 |
65
+ | 1.1929 | 1.9946 | 1300 | 1.1715 |
66
+ | 1.1902 | 2.1474 | 1400 | 1.1703 |
67
+ | 1.165 | 2.3008 | 1500 | 1.1661 |
68
+ | 1.146 | 2.4543 | 1600 | 1.1634 |
69
+ | 1.1346 | 2.6078 | 1700 | 1.1604 |
70
+ | 1.1227 | 2.7613 | 1800 | 1.1571 |
71
+ | 1.1103 | 2.9148 | 1900 | 1.1537 |
72
+ | 1.0672 | 3.0675 | 2000 | 1.1522 |
73
+ | 1.1103 | 3.2210 | 2100 | 1.1514 |
74
+ | 1.1034 | 3.3745 | 2200 | 1.1489 |
75
+ | 1.1958 | 3.5280 | 2300 | 1.1459 |
76
+ | 1.1257 | 3.6815 | 2400 | 1.1447 |
77
+ | 1.0882 | 3.8350 | 2500 | 1.1435 |
78
+ | 1.1452 | 3.9885 | 2600 | 1.1427 |
79
+ | 1.1185 | 4.1412 | 2700 | 1.1423 |
80
+ | 1.0371 | 4.2947 | 2800 | 1.1410 |
81
+ | 1.1447 | 4.4482 | 2900 | 1.1386 |
82
+ | 1.0647 | 4.6017 | 3000 | 1.1368 |
83
+ | 1.0847 | 4.7552 | 3100 | 1.1355 |
84
+ | 1.0754 | 4.9087 | 3200 | 1.1337 |
85
+ | 1.0596 | 5.0614 | 3300 | 1.1335 |
86
+ | 1.127 | 5.2149 | 3400 | 1.1337 |
87
+ | 1.0244 | 5.3684 | 3500 | 1.1325 |
88
+ | 1.1621 | 5.5219 | 3600 | 1.1310 |
89
+ | 1.102 | 5.6754 | 3700 | 1.1305 |
90
+ | 1.1348 | 5.8289 | 3800 | 1.1289 |
91
+ | 1.0641 | 5.9823 | 3900 | 1.1280 |
92
+ | 1.0889 | 6.1351 | 4000 | 1.1276 |
93
+ | 1.0684 | 6.2886 | 4100 | 1.1274 |
94
+ | 1.0523 | 6.4421 | 4200 | 1.1264 |
95
+ | 1.0437 | 6.5955 | 4300 | 1.1265 |
96
+ | 1.0645 | 6.7490 | 4400 | 1.1256 |
97
+ | 1.0412 | 6.9025 | 4500 | 1.1248 |
98
+ | 1.0904 | 7.0553 | 4600 | 1.1248 |
99
+ | 1.0982 | 7.2087 | 4700 | 1.1249 |
100
+ | 1.0802 | 7.3622 | 4800 | 1.1246 |
101
+ | 1.0236 | 7.5157 | 4900 | 1.1236 |
102
+ | 1.0447 | 7.6692 | 5000 | 1.1224 |
103
+ | 1.0408 | 7.8227 | 5100 | 1.1219 |
104
+ | 1.1236 | 7.9762 | 5200 | 1.1215 |
105
+ | 1.0381 | 8.1289 | 5300 | 1.1216 |
106
+ | 1.0971 | 8.2824 | 5400 | 1.1212 |
107
+ | 1.0529 | 8.4359 | 5500 | 1.1211 |
108
+ | 0.966 | 8.5894 | 5600 | 1.1214 |
109
+ | 1.0575 | 8.7429 | 5700 | 1.1205 |
110
+ | 1.0836 | 8.8964 | 5800 | 1.1201 |
111
+ | 0.997 | 9.0491 | 5900 | 1.1207 |
112
+ | 1.0106 | 9.2026 | 6000 | 1.1204 |
113
+ | 1.0164 | 9.3561 | 6100 | 1.1203 |
114
+ | 1.0576 | 9.5096 | 6200 | 1.1203 |
115
+ | 1.0619 | 9.6631 | 6300 | 1.1199 |
116
+ | 1.0607 | 9.8166 | 6400 | 1.1201 |
117
+ | 0.9816 | 9.9701 | 6500 | 1.1199 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - PEFT 0.15.2
123
+ - Transformers 4.51.3
124
+ - Pytorch 2.6.0+cu126
125
+ - Datasets 3.5.0
126
+ - Tokenizers 0.21.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04e59486780d68ac18a0ce9b4a857261ca06aa4582910bd1b31bc9a2a16ba5d3
3
  size 18379784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186504f91edf5de0a0d20784df7844b734544bbd5a0b8f43beee2e2c9e84a520
3
  size 18379784