Hugging Face's logo

tttx
/
ttt-problem10-32b-021025-sl25000

PEFT
Safetensors
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Community
aadityap commited on
Commit
83cf367
·
verified ·
1 Parent(s): fdaa848

Model save

Browse files
Files changed (3) hide show
  1. README.md +1 -6
  2. all_results.json +6 -6
  3. train_results.json +6 -6
README.md CHANGED
@@ -3,14 +3,9 @@ library_name: peft
3
  license: mit
4
  base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
5
  tags:
6
- - alignment-handbook
7
  - trl
8
  - sft
9
  - generated_from_trainer
10
- datasets:
11
- - tttx/star-run-step1-master
12
- - tttx/ttt-problem-10-continue-step1-master
13
- - tttx/ttt-problem-10-continue-step2-master
14
  model-index:
15
  - name: ttt-problem10-32b-021025-sl25000
16
  results: []
@@ -21,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  # ttt-problem10-32b-021025-sl25000
23
 
24
- This model is a fine-tuned version of [tttx/sft-32b-020925-19k-5ep](https://huggingface.co/tttx/sft-32b-020925-19k-5ep) on the tttx/star-run-step1-master, the tttx/ttt-problem-10-continue-step1-master and the tttx/ttt-problem-10-continue-step2-master datasets.
25
 
26
  ## Model description
27
 
 
3
  license: mit
4
  base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
5
  tags:
 
6
  - trl
7
  - sft
8
  - generated_from_trainer
 
 
 
 
9
  model-index:
10
  - name: ttt-problem10-32b-021025-sl25000
11
  results: []
 
16
 
17
  # ttt-problem10-32b-021025-sl25000
18
 
19
+ This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on an unknown dataset.
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 2.0,
3
- "total_flos": 1704342039035904.0,
4
- "train_loss": 0.08834147482282585,
5
- "train_runtime": 2715.1649,
6
- "train_samples": 715,
7
- "train_samples_per_second": 0.527,
8
- "train_steps_per_second": 0.033
9
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "total_flos": 490074470875136.0,
4
+ "train_loss": 0.058849748490112166,
5
+ "train_runtime": 478.1215,
6
+ "train_samples": 216,
7
+ "train_samples_per_second": 0.904,
8
+ "train_steps_per_second": 0.059
9
  }
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 2.0,
3
- "total_flos": 1704342039035904.0,
4
- "train_loss": 0.08834147482282585,
5
- "train_runtime": 2715.1649,
6
- "train_samples": 715,
7
- "train_samples_per_second": 0.527,
8
- "train_steps_per_second": 0.033
9
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "total_flos": 490074470875136.0,
4
+ "train_loss": 0.058849748490112166,
5
+ "train_runtime": 478.1215,
6
+ "train_samples": 216,
7
+ "train_samples_per_second": 0.904,
8
+ "train_steps_per_second": 0.059
9
  }