lewtun HF staff commited on
Commit
8b5b2ce
1 Parent(s): bf35de4

Model save

Browse files
Files changed (2) hide show
  1. README.md +53 -0
  2. generation_config.json +9 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - trl
4
+ - online-dpo
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: qwen2-0.5B-lr-3e-6
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # qwen2-0.5B-lr-3e-6
15
+
16
+ This model was trained from scratch on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 3e-06
36
+ - train_batch_size: 2
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - distributed_type: multi-GPU
40
+ - num_devices: 8
41
+ - gradient_accumulation_steps: 32
42
+ - total_train_batch_size: 512
43
+ - total_eval_batch_size: 64
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3.0
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.44.0
51
+ - Pytorch 2.1.2+cu121
52
+ - Datasets 2.18.0
53
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "repetition_penalty": 1.1,
5
+ "temperature": 0.7,
6
+ "top_k": 20,
7
+ "top_p": 0.8,
8
+ "transformers_version": "4.44.0"
9
+ }