Hugging Face's logo

deman539
/
llama381binstruct_summarize_short

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
deman539 commited on
Commit
2f732c0
·
verified ·
1 Parent(s): 736ce1a

deman539/llama381binstruct_summarize_short_merged

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. README.md +26 -26
  3. adapter_config.json +4 -4
  4. adapter_model.safetensors +1 -1
  5. runs/Sep29_14-19-26_5a3674a12739/events.out.tfevents.1727619607.5a3674a12739.6297.0 +3 -0
  6. tokenizer.json +0 -0
  7. training_args.bin +1 -1
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 2.7944
24
 
25
  ## Model description
26
 
@@ -52,32 +52,32 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 1.782 | 1.25 | 25 | 1.8304 |
56
- | 0.7787 | 2.5 | 50 | 1.7098 |
57
- | 0.3977 | 3.75 | 75 | 1.8415 |
58
- | 0.1875 | 5.0 | 100 | 1.9322 |
59
- | 0.0907 | 6.25 | 125 | 2.1723 |
60
- | 0.0304 | 7.5 | 150 | 2.4278 |
61
- | 0.0195 | 8.75 | 175 | 2.4924 |
62
- | 0.02 | 10.0 | 200 | 2.4250 |
63
- | 0.0194 | 11.25 | 225 | 2.5124 |
64
- | 0.0069 | 12.5 | 250 | 2.5796 |
65
- | 0.0048 | 13.75 | 275 | 2.5765 |
66
- | 0.0055 | 15.0 | 300 | 2.6462 |
67
- | 0.0038 | 16.25 | 325 | 2.6535 |
68
- | 0.0023 | 17.5 | 350 | 2.6849 |
69
- | 0.0026 | 18.75 | 375 | 2.7281 |
70
- | 0.0021 | 20.0 | 400 | 2.7575 |
71
- | 0.0018 | 21.25 | 425 | 2.7753 |
72
- | 0.0016 | 22.5 | 450 | 2.7865 |
73
- | 0.0016 | 23.75 | 475 | 2.7929 |
74
- | 0.0017 | 25.0 | 500 | 2.7944 |
75
 
76
 
77
  ### Framework versions
78
 
79
- - PEFT 0.12.0
80
- - Transformers 4.44.2
81
- - Pytorch 2.4.0+cu121
82
- - Datasets 3.0.0
83
- - Tokenizers 0.19.1
 
20
 
21
  This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.9597
24
 
25
  ## Model description
26
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 1.5955 | 2.5 | 25 | 1.1871 |
56
+ | 0.4382 | 5.0 | 50 | 1.3249 |
57
+ | 0.1055 | 7.5 | 75 | 1.6587 |
58
+ | 0.0314 | 10.0 | 100 | 1.7388 |
59
+ | 0.018 | 12.5 | 125 | 1.7894 |
60
+ | 0.0062 | 15.0 | 150 | 1.8581 |
61
+ | 0.0167 | 17.5 | 175 | 1.8562 |
62
+ | 0.0034 | 20.0 | 200 | 1.8495 |
63
+ | 0.0038 | 22.5 | 225 | 1.8778 |
64
+ | 0.0016 | 25.0 | 250 | 1.8412 |
65
+ | 0.0012 | 27.5 | 275 | 1.8858 |
66
+ | 0.0011 | 30.0 | 300 | 1.9118 |
67
+ | 0.001 | 32.5 | 325 | 1.9290 |
68
+ | 0.0009 | 35.0 | 350 | 1.9401 |
69
+ | 0.0008 | 37.5 | 375 | 1.9467 |
70
+ | 0.0008 | 40.0 | 400 | 1.9519 |
71
+ | 0.0008 | 42.5 | 425 | 1.9556 |
72
+ | 0.0007 | 45.0 | 450 | 1.9579 |
73
+ | 0.0007 | 47.5 | 475 | 1.9597 |
74
+ | 0.0006 | 50.0 | 500 | 1.9597 |
75
 
76
 
77
  ### Framework versions
78
 
79
+ - PEFT 0.13.0
80
+ - Transformers 4.45.1
81
+ - Pytorch 2.4.1+cu121
82
+ - Datasets 3.0.1
83
+ - Tokenizers 0.20.0
adapter_config.json CHANGED
@@ -21,12 +21,12 @@
21
  "revision": null,
22
  "target_modules": [
23
  "down_proj",
24
- "k_proj",
25
- "up_proj",
26
- "gate_proj",
27
  "o_proj",
 
28
  "q_proj",
29
- "v_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "down_proj",
24
+ "v_proj",
 
 
25
  "o_proj",
26
+ "k_proj",
27
  "q_proj",
28
+ "up_proj",
29
+ "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16df53eea17cad29723b7a007ff3bd5715fbcda0335fd36d95d205d62ee6d29e
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d063aacc9c484f7333d23589be7f14ee4755f05aa69aba5ac4de6a9e0a06c31b
3
  size 167832240
runs/Sep29_14-19-26_5a3674a12739/events.out.tfevents.1727619607.5a3674a12739.6297.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9a6133399da59c770cb5ebd2a4d0417414a662f496cc100781da67f8fb122b
3
+ size 22377
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:544f5ecd7307de5490611396486f54fcb31ba4f87e50adeea034b751e65da865
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b63821b0257e5fea24fca4b9f38844a8fb3733dacb9d1ec7c179152c2aa71d1
3
  size 5496