Hugging Face's logo

llama-duo
/
gemma2b-summarize-claude3sonnet-128k

PEFT
TensorBoard
Safetensors
gemma
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
chansung commited on
Commit
0f4d9a5
•
1 Parent(s): d4697f6

Model save

Browse files
Files changed (6) hide show
  1. README.md +16 -22
  2. adapter_model.safetensors +1 -1
  3. all_results.json +6 -11
  4. runs/Jun10_19-04-55_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718013909.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.13878.0 +2 -2
  5. train_results.json +6 -6
  6. trainer_state.json +0 -0
README.md CHANGED
@@ -2,13 +2,12 @@
2
  license: gemma
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  base_model: google/gemma-2b
10
  datasets:
11
- - llama-duo/synth_summarize_dataset_dedup
12
  model-index:
13
  - name: gemma2b-summarize-claude3sonnet-128k
14
  results: []
@@ -19,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # gemma2b-summarize-claude3sonnet-128k
21
 
22
- This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the llama-duo/synth_summarize_dataset_dedup dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 2.5270
25
 
26
  ## Model description
27
 
@@ -52,33 +51,28 @@ The following hyperparameters were used during training:
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: cosine
54
  - lr_scheduler_warmup_ratio: 0.1
55
- - num_epochs: 15
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss |
60
  |:-------------:|:-----:|:----:|:---------------:|
61
- | 1.097 | 1.0 | 402 | 2.4839 |
62
- | 1.0176 | 2.0 | 804 | 2.4534 |
63
- | 0.9746 | 3.0 | 1206 | 2.4625 |
64
- | 0.9525 | 4.0 | 1608 | 2.4586 |
65
- | 0.9361 | 5.0 | 2010 | 2.4669 |
66
- | 0.9077 | 6.0 | 2412 | 2.4844 |
67
- | 0.896 | 7.0 | 2814 | 2.4947 |
68
- | 0.8858 | 8.0 | 3216 | 2.5056 |
69
- | 0.8811 | 9.0 | 3618 | 2.5128 |
70
- | 0.8634 | 10.0 | 4020 | 2.5166 |
71
- | 0.8758 | 11.0 | 4422 | 2.5237 |
72
- | 0.8644 | 12.0 | 4824 | 2.5264 |
73
- | 0.8641 | 13.0 | 5226 | 2.5268 |
74
- | 0.8607 | 14.0 | 5628 | 2.5271 |
75
- | 0.8609 | 15.0 | 6030 | 2.5270 |
76
 
77
 
78
  ### Framework versions
79
 
80
- - PEFT 0.10.0
81
- - Transformers 4.40.0
82
  - Pytorch 2.2.2+cu121
83
  - Datasets 2.19.1
84
  - Tokenizers 0.19.1
 
2
  license: gemma
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: google/gemma-2b
9
  datasets:
10
+ - generator
11
  model-index:
12
  - name: gemma2b-summarize-claude3sonnet-128k
13
  results: []
 
18
 
19
  # gemma2b-summarize-claude3sonnet-128k
20
 
21
+ This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 2.6928
24
 
25
  ## Model description
26
 
 
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: cosine
53
  - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 10
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss |
59
  |:-------------:|:-----:|:----:|:---------------:|
60
+ | 1.0192 | 1.0 | 402 | 2.4514 |
61
+ | 0.9424 | 2.0 | 804 | 2.4604 |
62
+ | 0.8955 | 3.0 | 1206 | 2.5064 |
63
+ | 0.8659 | 4.0 | 1608 | 2.5306 |
64
+ | 0.8359 | 5.0 | 2010 | 2.5706 |
65
+ | 0.7986 | 6.0 | 2412 | 2.6196 |
66
+ | 0.7778 | 7.0 | 2814 | 2.6583 |
67
+ | 0.7562 | 8.0 | 3216 | 2.6846 |
68
+ | 0.7563 | 9.0 | 3618 | 2.6927 |
69
+ | 0.7461 | 10.0 | 4020 | 2.6928 |
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
73
 
74
+ - PEFT 0.11.1
75
+ - Transformers 4.41.2
76
  - Pytorch 2.2.2+cu121
77
  - Datasets 2.19.1
78
  - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a10936cba622657c61f8f1925c16495d39e3996341d75997cfd9c5d0e56f4aa
3
  size 78480320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385fda0f1efd859eb391182ef31bfe8dfc967ee95263e7d8aecc886aff4a01f2
3
  size 78480320
all_results.json CHANGED
@@ -1,14 +1,9 @@
1
  {
2
- "epoch": 15.0,
3
- "eval_loss": 2.5269672870635986,
4
- "eval_runtime": 0.5011,
5
- "eval_samples": 25,
6
- "eval_samples_per_second": 19.954,
7
- "eval_steps_per_second": 1.995,
8
- "total_flos": 3.5418612320488653e+18,
9
- "train_loss": 0.9510796088682083,
10
- "train_runtime": 20707.2957,
11
  "train_samples": 126989,
12
- "train_samples_per_second": 13.97,
13
- "train_steps_per_second": 0.291
14
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "total_flos": 2.396116594708185e+18,
4
+ "train_loss": 0.875829508648583,
5
+ "train_runtime": 25148.6449,
 
 
 
 
 
6
  "train_samples": 126989,
7
+ "train_samples_per_second": 7.668,
8
+ "train_steps_per_second": 0.16
9
  }
runs/Jun10_19-04-55_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718013909.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.13878.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca37e92d5565ae9e4f0df24056b8832ea9c852a5d328f09bccab3f39ef11bed6
3
- size 176979
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95467affcbeb77ae206036caad6420b46727bccb610ffabb294a845d0c6b3f96
3
+ size 178448
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 15.0,
3
- "total_flos": 3.5418612320488653e+18,
4
- "train_loss": 0.9510796088682083,
5
- "train_runtime": 20707.2957,
6
  "train_samples": 126989,
7
- "train_samples_per_second": 13.97,
8
- "train_steps_per_second": 0.291
9
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "total_flos": 2.396116594708185e+18,
4
+ "train_loss": 0.875829508648583,
5
+ "train_runtime": 25148.6449,
6
  "train_samples": 126989,
7
+ "train_samples_per_second": 7.668,
8
+ "train_steps_per_second": 0.16
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff