Hugging Face's logo

mingye94
/
rm_llama3_8B_helpsteer2

Safetensors
llama
trl
reward-trainer
Generated from Trainer
Model card Files Community
mingye94 commited on
Commit
2dbb74b
·
verified ·
1 Parent(s): e1ab458

End of training

Browse files
Files changed (7) hide show
  1. README.md +22 -15
  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. tokenizer.json +2 -16
  7. training_args.bin +1 -1
README.md CHANGED
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6229
23
- - Accuracy: 0.6628
24
 
25
  ## Model description
26
 
@@ -46,24 +46,31 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 10
49
- - num_epochs: 2
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 0.8065 | 0.1572 | 50 | 0.7081 | 0.5684 |
56
- | 0.7286 | 0.3145 | 100 | 0.7295 | 0.5780 |
57
- | 0.6961 | 0.4717 | 150 | 0.6795 | 0.5761 |
58
- | 0.6768 | 0.6289 | 200 | 0.6843 | 0.5800 |
59
- | 0.6646 | 0.7862 | 250 | 0.6486 | 0.6204 |
60
- | 0.6684 | 0.9434 | 300 | 0.6573 | 0.6127 |
61
- | 0.605 | 1.1006 | 350 | 0.6337 | 0.6744 |
62
- | 0.5492 | 1.2579 | 400 | 0.6335 | 0.6705 |
63
- | 0.5426 | 1.4151 | 450 | 0.6267 | 0.6859 |
64
- | 0.5521 | 1.5723 | 500 | 0.6206 | 0.6898 |
65
- | 0.561 | 1.7296 | 550 | 0.6247 | 0.6782 |
66
- | 0.5445 | 1.8868 | 600 | 0.6229 | 0.6628 |
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.1203
23
+ - Accuracy: 0.6339
24
 
25
  ## Model description
26
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 10
49
+ - num_epochs: 3
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
+ | 0.8471 | 0.1572 | 50 | 0.7326 | 0.5819 |
56
+ | 0.7455 | 0.3145 | 100 | 0.6821 | 0.5549 |
57
+ | 0.7059 | 0.4717 | 150 | 0.6642 | 0.6050 |
58
+ | 0.6926 | 0.6289 | 200 | 0.6707 | 0.5915 |
59
+ | 0.6683 | 0.7862 | 250 | 0.6506 | 0.6320 |
60
+ | 0.6727 | 0.9434 | 300 | 0.6456 | 0.6224 |
61
+ | 0.629 | 1.1006 | 350 | 0.6218 | 0.6551 |
62
+ | 0.5446 | 1.2579 | 400 | 0.6604 | 0.6281 |
63
+ | 0.5377 | 1.4151 | 450 | 0.6345 | 0.6455 |
64
+ | 0.5555 | 1.5723 | 500 | 0.6145 | 0.6320 |
65
+ | 0.5645 | 1.7296 | 550 | 0.6178 | 0.6474 |
66
+ | 0.5392 | 1.8868 | 600 | 0.6323 | 0.6532 |
67
+ | 0.4505 | 2.0440 | 650 | 0.7539 | 0.6455 |
68
+ | 0.1406 | 2.2013 | 700 | 1.0884 | 0.6339 |
69
+ | 0.1487 | 2.3585 | 750 | 1.1136 | 0.6339 |
70
+ | 0.1493 | 2.5157 | 800 | 1.1202 | 0.6358 |
71
+ | 0.1259 | 2.6730 | 850 | 1.1253 | 0.6320 |
72
+ | 0.1382 | 2.8302 | 900 | 1.1189 | 0.6320 |
73
+ | 0.1448 | 2.9874 | 950 | 1.1203 | 0.6339 |
74
 
75
 
76
  ### Framework versions
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e20bba8ca292537852eebf8d44a1d35f4438e6147f58173db5693fe70fbf519
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09870c98a049847736c67cf38bc5fadc75c5b800865efe54a60e2a980794ae44
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b7457d0ea2af65bc04c1c0d50e95c52187c83c15521473ec8fa687a7174a024
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df744eb764c1e15304de8efbf0e9244d19f34fd72a4f0a1f02fccf22fca1084
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:d1095fd5a9bb5cae1e31e07e5d192bedda1841435a60e386074356c268144d87
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf791b5e13aa9704a74254949d2270be13787ff0a7e2c25f1d77ea16d03247a
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:b3afdb82665fffac7502ac1b3b0741b0f9a923b8b0f79c7b73fadbd5c6fd6391
3
  size 117473824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db9e311f61523884d6fb889ebf727e0739e31df7fef59a55d6064482b3408c60
3
  size 117473824
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 1024
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 128001,
16
- "pad_type_id": 0,
17
- "pad_token": "<|end_of_text|>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 128000,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 128000,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f04b0dc5d4f25b702d8dfd5ecdd080cc18f60089bc4fb84876bf1a569c068e74
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2560e6e96b39bdc52e63b65a2521afe6fa98f993a7cc6318e1c6c0cbce4f96
3
  size 5304