Hugging Face's logo

nlee-208
/
limo_S-dsr1b_T-qwq_100

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
Metrics Community
nlee-208 commited on
Commit
8c37b3e
·
verified ·
1 Parent(s): ffd3695

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_21-47-25_al-clops-debugging-pipeline-4nn6w-ac6d-0/events.out.tfevents.1755121657.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/xy6a6e5k)
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/5v45jg0w)
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": 0.3476698352740361,
4
- "train_runtime": 3370.7423,
5
  "train_samples": 817,
6
- "train_samples_per_second": 3.151,
7
  "train_steps_per_second": 0.1
8
  }
 
1
  {
2
  "total_flos": 192705258979328.0,
3
+ "train_loss": 0.34760819860464015,
4
+ "train_runtime": 3369.3955,
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 sha256:76c46c0d42e828d2bf23891ab3486bfd0820576f71bf5c160c2ab689162ab81b
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841494b3e356a5e876134b6247ecc8b599f9393e453d3ca70404fdf1966e813d
3
  size 3554214752
runs/Aug13_21-47-25_al-clops-debugging-pipeline-4nn6w-ac6d-0/events.out.tfevents.1755121657.al-clops-debugging-pipeline-4nn6w-ac6d-0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c37b38bc5f04a5d98159c70e30b8a0646eb0177ab8d3cdb853ac7fa6a6f04a3b
3
+ size 50487
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 192705258979328.0,
3
- "train_loss": 0.3476698352740361,
4
- "train_runtime": 3370.7423,
5
  "train_samples": 817,
6
- "train_samples_per_second": 3.151,
7
  "train_steps_per_second": 0.1
8
  }
 
1
  {
2
  "total_flos": 192705258979328.0,
3
+ "train_loss": 0.34760819860464015,
4
+ "train_runtime": 3369.3955,
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:ff519721bc58711ad03dbc5fa2d3de65f7fe106983d11e8ef6463fe7f0b0e7f6
3
  size 7505
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc43e6aa1b1f0a1888b53e2b762df17def16388aa2a369d322f676368ab1a4a
3
  size 7505