Hugging Face's logo

Jennny
/
llama3_8b_helpsteer_helpful_rm

Text Classification
Transformers
Safetensors
llama
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
Jennny commited on
Commit
df93693
·
verified ·
1 Parent(s): 9358f6a

llama3_8b_helpsteer_helpful_rm

Browse files
Files changed (6) hide show
  1. README.md +24 -6
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. training_args.bin +1 -1
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: transformers
3
  base_model: Jennny/llama3_8b_sft_helpsteer
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: llama3_8b_helpsteer_helpful_rm
8
  results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
14
  # llama3_8b_helpsteer_helpful_rm
15
 
16
  This model is a fine-tuned version of [Jennny/llama3_8b_sft_helpsteer](https://huggingface.co/Jennny/llama3_8b_sft_helpsteer) on an unknown dataset.
 
 
 
17
 
18
  ## Model description
19
 
@@ -33,21 +38,34 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 1e-05
36
- - train_batch_size: 4
37
- - eval_batch_size: 4
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
  - num_devices: 8
41
- - gradient_accumulation_steps: 16
42
- - total_train_batch_size: 512
43
- - total_eval_batch_size: 32
44
  - optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.03
47
- - num_epochs: 1
48
 
49
  ### Training results
50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
 
53
  ### Framework versions
 
3
  base_model: Jennny/llama3_8b_sft_helpsteer
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
  model-index:
9
  - name: llama3_8b_helpsteer_helpful_rm
10
  results: []
 
16
  # llama3_8b_helpsteer_helpful_rm
17
 
18
  This model is a fine-tuned version of [Jennny/llama3_8b_sft_helpsteer](https://huggingface.co/Jennny/llama3_8b_sft_helpsteer) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.0740
21
+ - Accuracy: 0.6381
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
  - seed: 42
44
  - distributed_type: multi-GPU
45
  - num_devices: 8
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 128
48
+ - total_eval_batch_size: 16
49
  - optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: cosine
51
  - lr_scheduler_warmup_ratio: 0.03
52
+ - num_epochs: 2
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
58
+ | 0.2319 | 0.1770 | 10 | 0.7814 | 0.5603 |
59
+ | 0.1672 | 0.3540 | 20 | 0.8783 | 0.6059 |
60
+ | 0.2095 | 0.5310 | 30 | 0.7078 | 0.6327 |
61
+ | 0.1445 | 0.7080 | 40 | 0.7842 | 0.6354 |
62
+ | 0.2071 | 0.8850 | 50 | 0.6209 | 0.6568 |
63
+ | 0.0539 | 1.0531 | 60 | 0.7969 | 0.6193 |
64
+ | 0.0391 | 1.2301 | 70 | 1.0878 | 0.6327 |
65
+ | 0.0172 | 1.4071 | 80 | 1.1465 | 0.6327 |
66
+ | 0.0193 | 1.5841 | 90 | 1.1174 | 0.6408 |
67
+ | 0.0277 | 1.7611 | 100 | 1.0800 | 0.6381 |
68
+ | 0.0184 | 1.9381 | 110 | 1.0740 | 0.6381 |
69
 
70
 
71
  ### Framework versions
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e05fc4a880d9fa55cd8397a5bd6c08b8116faa3732a8e6ce19d944ef652b9bf0
3
  size 4976706864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4474b673b0defc67ecba2724215710f18ace4f8643b37b785562a180d6ae03
3
  size 4976706864
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56213c54be4d1e0fb680d86de26eb84058bd78ecd906c739c432b979b15117ed
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1908a060c06c25995789b812dc882d0bbabe9549356f1b1c15ce9c0e1748f92
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ae227243918d077700ed52ad60388808d54c8031211ce4330d1fa569c8f6955
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651e5667f1d2ae372c20905a8898cac91c6fe4767cf69151deab7b6d9623a8f0
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be04856a0bcc449bc7c9f9a24af38ca4759ba93e6bd637ded71882c0f19aa568
3
  size 117473824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8155ce517c3cccd5655a2f2d370938acfaba7a009a934076a4234ffb5e6b3603
3
  size 117473824
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d58e80b374bd592a5f44942e430cdc3aa92cda8dca5db1064794dc30431e9c1f
3
  size 7160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031402932ab88770bff95765ed96463fb1416567bf8c27c3de5dfb565b476f4a
3
  size 7160