yuzhounie commited on
Commit
bc4eac1
·
verified ·
1 Parent(s): 00505fe

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Con_Qwen2.5-7B-Instruct_sft
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: final_model
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # final_model
17
 
18
- This model is a fine-tuned version of [secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Con_Qwen2.5-7B-Instruct_sft](https://huggingface.co/secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Con_Qwen2.5-7B-Instruct_sft) on the None dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Con_Qwen2.5-7B-Instruct_sft
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: final_model
 
16
 
17
  # final_model
18
 
19
+ This model is a fine-tuned version of [secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Con_Qwen2.5-7B-Instruct_sft](https://huggingface.co/secmlr/DS-Noisy_DS-Clean_DS-OSS_QWQ-OSS_QWQ-Clean_QWQ-Noisy_Con_Qwen2.5-7B-Instruct_sft) on the ruizhe_simplier_reasoning_ds_clean_32k, the ruizhe_simplier_reasoning_ds_noisy_32k, the ruizhe_simplier_reasoning_ds_ossfuzz_32k, the ruizhe_simplier_reasoning_qwq_clean_32k, the ruizhe_simplier_reasoning_qwq_noisy_small_32k and the ruizhe_simplier_reasoning_qwq_ossfuzz_32k datasets.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998837479655894,
3
+ "total_flos": 3.265949006466908e+17,
4
+ "train_loss": 0.4850710421606371,
5
+ "train_runtime": 18100.1171,
6
+ "train_samples_per_second": 2.851,
7
+ "train_steps_per_second": 0.119
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998837479655894,
3
+ "total_flos": 3.265949006466908e+17,
4
+ "train_loss": 0.4850710421606371,
5
+ "train_runtime": 18100.1171,
6
+ "train_samples_per_second": 2.851,
7
+ "train_steps_per_second": 0.119
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_loss.png ADDED