Hugging Face's logo

pmangesh
/
FML_project

Safetensors
Model card Files
xet
 Community
pmangesh commited on
Commit
064ae0e
·
verified ·
1 Parent(s): 2b71709

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. joint_gt_sft_seed1/results_stage1_joint/gsm8k.jsonl +0 -0
  2. joint_gt_sft_seed1/results_stage1_joint/humaneval.jsonl +0 -0
  3. joint_gt_sft_seed1/results_stage1_joint/humaneval_eval_results.json +0 -0
  4. joint_gt_sft_seed1/results_stage1_joint/math500.jsonl +0 -0
  5. joint_gt_sft_seed1/results_stage1_joint/mbpp.jsonl +0 -0
  6. joint_gt_sft_seed1/results_stage1_joint/mbpp_eval_results.json +0 -0
  7. joint_gt_sft_seed1/results_stage1_joint/summary.json +1 -0
  8. joint_gt_sft_seed1/run_info.json +3 -1
joint_gt_sft_seed1/results_stage1_joint/gsm8k.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
joint_gt_sft_seed1/results_stage1_joint/humaneval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
joint_gt_sft_seed1/results_stage1_joint/humaneval_eval_results.json ADDED
The diff for this file is too large to render. See raw diff
 
joint_gt_sft_seed1/results_stage1_joint/math500.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
joint_gt_sft_seed1/results_stage1_joint/mbpp.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
joint_gt_sft_seed1/results_stage1_joint/mbpp_eval_results.json ADDED
The diff for this file is too large to render. See raw diff
 
joint_gt_sft_seed1/results_stage1_joint/summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "joint_gt_sft_seed1/stage1_joint", "gsm8k": 0.579226686884003, "mbpp": 0.6534391534391535, "mbpp_plus": 0.5687830687830688, "humaneval": 0.5670731707317073, "humaneval_plus": 0.5060975609756098, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164, "math500": 0.268, "n_math500": 500}
joint_gt_sft_seed1/run_info.json CHANGED
@@ -29,5 +29,7 @@
29
  "peak_gb_student": 36.57978296279907,
30
  "peak_gb_teachers": 29.54020071029663,
31
  "exp": 2,
32
- "student": "Qwen/Qwen2.5-1.5B-Instruct"
 
 
33
  }
 
29
  "peak_gb_student": 36.57978296279907,
30
  "peak_gb_teachers": 29.54020071029663,
31
  "exp": 2,
32
+ "student": "Qwen/Qwen2.5-1.5B-Instruct",
33
+ "bench_h": 0.5001309351788626,
34
+ "gpu_bench": "NVIDIA RTX A6000"
35
  }