Hugging Face's logo

frankmorales2020
/
Meta-Llama-3-8B_AviationQA-cosine

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
frankmorales2020 commited on
Commit
0a65a61
•
1 Parent(s): 3773140

Model save

Browse files
Files changed (3) hide show
  1. README.md +59 -5
  2. adapter_model.safetensors +1 -1
  3. logs/events.out.tfevents.1718902739.5cd879085d61.217.0 +2 -2
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- license: llama3
 
 
3
  library_name: peft
 
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: meta-llama/Meta-Llama-3-8B
9
- datasets:
10
- - generator
11
  model-index:
12
  - name: Meta-Llama-3-8B_AviationQA-cosine
13
  results: []
@@ -19,6 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
19
  # Meta-Llama-3-8B_AviationQA-cosine
20
 
21
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
 
 
22
 
23
  ## Model description
24
 
@@ -46,10 +48,62 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: cosine
48
  - lr_scheduler_warmup_ratio: 0.03
49
- - num_epochs: 30
50
 
51
  ### Training results
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
 
1
  ---
2
+ base_model: meta-llama/Meta-Llama-3-8B
3
+ datasets:
4
+ - generator
5
  library_name: peft
6
+ license: llama3
7
  tags:
8
  - trl
9
  - sft
10
  - generated_from_trainer
 
 
 
11
  model-index:
12
  - name: Meta-Llama-3-8B_AviationQA-cosine
13
  results: []
 
19
  # Meta-Llama-3-8B_AviationQA-cosine
20
 
21
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.6061
24
 
25
  ## Model description
26
 
 
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: cosine
50
  - lr_scheduler_warmup_ratio: 0.03
51
+ - num_epochs: 3
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.7872 | 0.0590 | 50 | 0.7652 |
58
+ | 0.7373 | 0.1181 | 100 | 0.7328 |
59
+ | 0.7242 | 0.1771 | 150 | 0.7182 |
60
+ | 0.7143 | 0.2361 | 200 | 0.7107 |
61
+ | 0.73 | 0.2952 | 250 | 0.7046 |
62
+ | 0.7159 | 0.3542 | 300 | 0.6973 |
63
+ | 0.7211 | 0.4132 | 350 | 0.6921 |
64
+ | 0.7096 | 0.4723 | 400 | 0.6873 |
65
+ | 0.6845 | 0.5313 | 450 | 0.6824 |
66
+ | 0.7251 | 0.5903 | 500 | 0.6783 |
67
+ | 0.6685 | 0.6494 | 550 | 0.6720 |
68
+ | 0.697 | 0.7084 | 600 | 0.6667 |
69
+ | 0.7006 | 0.7674 | 650 | 0.6639 |
70
+ | 0.6952 | 0.8264 | 700 | 0.6618 |
71
+ | 0.6649 | 0.8855 | 750 | 0.6596 |
72
+ | 0.6877 | 0.9445 | 800 | 0.6553 |
73
+ | 0.6673 | 1.0035 | 850 | 0.6531 |
74
+ | 0.6611 | 1.0626 | 900 | 0.6487 |
75
+ | 0.6971 | 1.1216 | 950 | 0.6452 |
76
+ | 0.6652 | 1.1806 | 1000 | 0.6423 |
77
+ | 0.645 | 1.2397 | 1050 | 0.6397 |
78
+ | 0.6494 | 1.2987 | 1100 | 0.6388 |
79
+ | 0.6623 | 1.3577 | 1150 | 0.6359 |
80
+ | 0.6552 | 1.4168 | 1200 | 0.6334 |
81
+ | 0.6465 | 1.4758 | 1250 | 0.6297 |
82
+ | 0.6495 | 1.5348 | 1300 | 0.6285 |
83
+ | 0.6521 | 1.5939 | 1350 | 0.6272 |
84
+ | 0.6505 | 1.6529 | 1400 | 0.6261 |
85
+ | 0.6773 | 1.7119 | 1450 | 0.6238 |
86
+ | 0.6487 | 1.7710 | 1500 | 0.6225 |
87
+ | 0.639 | 1.8300 | 1550 | 0.6208 |
88
+ | 0.6465 | 1.8890 | 1600 | 0.6194 |
89
+ | 0.6528 | 1.9481 | 1650 | 0.6182 |
90
+ | 0.6265 | 2.0071 | 1700 | 0.6164 |
91
+ | 0.6161 | 2.0661 | 1750 | 0.6137 |
92
+ | 0.6236 | 2.1251 | 1800 | 0.6118 |
93
+ | 0.6371 | 2.1842 | 1850 | 0.6111 |
94
+ | 0.6294 | 2.2432 | 1900 | 0.6093 |
95
+ | 0.6257 | 2.3022 | 1950 | 0.6087 |
96
+ | 0.6204 | 2.3613 | 2000 | 0.6081 |
97
+ | 0.6133 | 2.4203 | 2050 | 0.6073 |
98
+ | 0.6108 | 2.4793 | 2100 | 0.6068 |
99
+ | 0.622 | 2.5384 | 2150 | 0.6066 |
100
+ | 0.6233 | 2.5974 | 2200 | 0.6064 |
101
+ | 0.6183 | 2.6564 | 2250 | 0.6063 |
102
+ | 0.6237 | 2.7155 | 2300 | 0.6062 |
103
+ | 0.6388 | 2.7745 | 2350 | 0.6062 |
104
+ | 0.6236 | 2.8335 | 2400 | 0.6062 |
105
+ | 0.6236 | 2.8926 | 2450 | 0.6062 |
106
+ | 0.6205 | 2.9516 | 2500 | 0.6061 |
107
 
108
 
109
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:479e4ef3b9de4c8d26b40352845a9daed2a6bcad0bd949fdc40db3df674317c4
3
  size 1342239008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bef23a6decfe6bd4d683a8ce1bc8fb322b979b6cbaa6c0ff97fb7fdbcd78b295
3
  size 1342239008
logs/events.out.tfevents.1718902739.5cd879085d61.217.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41cfe62eb5269f36a0610942a92e982f1b095fa63b296aa3cea97436d76c04c6
3
- size 71748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fab62e77e050645d35d5705c9746fbcfa7870d1df143dc1c8d164c23e5d3e32
3
+ size 72946