rasdani commited on
Commit
40e5cfe
1 Parent(s): 807331f

Model save

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2-Math-1.5B-Instruct
5
+ tags:
6
+ - trl
7
+ - dpo
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: qwen2-math-1_5b-step-dpo
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # qwen2-math-1_5b-step-dpo
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen2-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-Math-1.5B-Instruct) on an unknown dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-07
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 64
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 8.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.44.2
59
+ - Pytorch 2.3.1.post300
60
+ - Datasets 2.21.0
61
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.964444444444444,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.19260043763954723,
5
+ "train_runtime": 3828.823,
6
+ "train_samples": 10795,
7
+ "train_samples_per_second": 22.555,
8
+ "train_steps_per_second": 0.351
9
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.0,
10
+ "transformers_version": "4.44.2"
11
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.964444444444444,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.19260043763954723,
5
+ "train_runtime": 3828.823,
6
+ "train_samples": 10795,
7
+ "train_samples_per_second": 22.555,
8
+ "train_steps_per_second": 0.351
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff