jkilpatrick/tension

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,83 +1,57 @@
 ---
 base_model: NousResearch/Meta-Llama-3.1-8B-Instruct
-datasets:
-- generator
-library_name: peft
-license: llama3.1
+library_name: transformers
+model_name: llama381binstruct_summarize_short
 tags:
+- generated_from_trainer
 - trl
 - sft
-- generated_from_trainer
-model-index:
-- name: llama381binstruct_summarize_short
-  results: []
+licence: license
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# llama381binstruct_summarize_short
-
-This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.8489
-
-## Model description
+# Model Card for llama381binstruct_summarize_short
 
-More information needed
+This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Intended uses & limitations
+## Quick start
 
-More information needed
+```python
+from transformers import pipeline
 
-## Training and evaluation data
-
-More information needed
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="JKilpatrick/llama381binstruct_summarize_short", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
 ## Training procedure
 
-### Training hyperparameters
+[<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/jacob-kilpatrick/huggingface/runs/106enyqe)
+
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 30
-- training_steps: 500
+### Framework versions
 
-### Training results
+- TRL: 0.12.0
+- Transformers: 4.46.2
+- Pytorch: 2.5.0+cu121
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.7667        | 1.25  | 25   | 1.7939          |
-| 0.7156        | 2.5   | 50   | 1.8135          |
-| 0.3944        | 3.75  | 75   | 1.8429          |
-| 0.2053        | 5.0   | 100  | 2.0996          |
-| 0.1153        | 6.25  | 125  | 2.3466          |
-| 0.0316        | 7.5   | 150  | 2.6045          |
-| 0.0224        | 8.75  | 175  | 2.5789          |
-| 0.0198        | 10.0  | 200  | 2.5765          |
-| 0.0112        | 11.25 | 225  | 2.7507          |
-| 0.0053        | 12.5  | 250  | 2.6317          |
-| 0.0047        | 13.75 | 275  | 2.6792          |
-| 0.0039        | 15.0  | 300  | 2.7628          |
-| 0.0041        | 16.25 | 325  | 2.7830          |
-| 0.0013        | 17.5  | 350  | 2.7905          |
-| 0.0014        | 18.75 | 375  | 2.8053          |
-| 0.0017        | 20.0  | 400  | 2.8236          |
-| 0.0017        | 21.25 | 425  | 2.8352          |
-| 0.0012        | 22.5  | 450  | 2.8429          |
-| 0.0011        | 23.75 | 475  | 2.8473          |
-| 0.0013        | 25.0  | 500  | 2.8489          |
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.12.0
-- Transformers 4.44.2
-- Pytorch 2.4.0+cu121
-- Datasets 3.0.0
-- Tokenizers 0.19.1
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
-    "down_proj",
-    "gate_proj",
     "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
     "up_proj",
-    "k_proj"
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c5edb2da8f4a8894b04221c3df3aedf21c977cce09fe275cab73d0d66e52d9
+oid sha256:38143cefb99da77cd7a201eb2c7bbda8828ee3533b17c65f43041d5e5182ae16
 size 167832240

runs/Nov06_22-54-32_40eb697e7e59/events.out.tfevents.1730933682.40eb697e7e59.1849.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3b533ea7355e20f12327becef71bfd459b135ddadb22bd888d4dba594d82d2
+size 20268

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b842afafa533b7afae3f6b3b0816483711425f85b28846fcb891388bf6fbe1ee
-size 5496
+oid sha256:ee77a671a9673d65d90f492135a0bffc87228720cce1637269443d6213264ec4
+size 5624