Hugging Face's logo

nlee-208
/
limo_S-dsr1b_T-qwq_75

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files Metrics Community
nlee-208 commited on
Commit
c001cc3
·
verified ·
1 Parent(s): 67de608

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. all_results.json +3 -3
  3. config.json +1 -1
  4. model.safetensors +1 -1
  5. runs/Aug13_20-49-10_al-clops-debugging-pipeline-4nn6w-ac6d-0/events.out.tfevents.1755118162.al-clops-debugging-pipeline-4nn6w-ac6d-0 +3 -0
  6. train_results.json +3 -3
  7. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nlee28/cross1/runs/4kqfh6nn)
31
 
32
 
33
  This model was trained with SFT.
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nlee28/cross1/runs/apptse8h)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 192705258979328.0,
3
- "train_loss": 0.3476923556017452,
4
- "train_runtime": 3371.3009,
5
  "train_samples": 817,
6
- "train_samples_per_second": 3.15,
7
  "train_steps_per_second": 0.1
8
  }
 
1
  {
2
  "total_flos": 192705258979328.0,
3
+ "train_loss": 0.347608188023934,
4
+ "train_runtime": 3369.3082,
5
  "train_samples": 817,
6
+ "train_samples_per_second": 3.152,
7
  "train_steps_per_second": 0.1
8
  }
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.4",
25
- "use_cache": true,
26
  "use_mrope": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
 
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.4",
25
+ "use_cache": false,
26
  "use_mrope": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36f76b1cf8a2910481e527b30df6fe626cca42bf2a61ff230e56c7ed4f35187b
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56eba86d1d98c5282ce714338313abe934f114840671abbeb00b22726d551e8f
3
  size 3554214752
runs/Aug13_20-49-10_al-clops-debugging-pipeline-4nn6w-ac6d-0/events.out.tfevents.1755118162.al-clops-debugging-pipeline-4nn6w-ac6d-0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ca4f6148d9395110d0e62383ae38b65718aea63929806e1a4308a76ecb2257
3
+ size 50483
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 192705258979328.0,
3
- "train_loss": 0.3476923556017452,
4
- "train_runtime": 3371.3009,
5
  "train_samples": 817,
6
- "train_samples_per_second": 3.15,
7
  "train_steps_per_second": 0.1
8
  }
 
1
  {
2
  "total_flos": 192705258979328.0,
3
+ "train_loss": 0.347608188023934,
4
+ "train_runtime": 3369.3082,
5
  "train_samples": 817,
6
+ "train_samples_per_second": 3.152,
7
  "train_steps_per_second": 0.1
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc2b3598ae496793b6d3014af1cb4c0f2d17fb489d7653bdb542d14ffc0e2931
3
  size 7505
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:263e5cbb67a22ea096e4db771b39bbfa8c67ba7855f22e6b8b04f8fd4da216ad
3
  size 7505