EdBerg/outputs3

README.md

@@ -1,60 +1,57 @@
 ---
-library_name: peft
-license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
+library_name: transformers
+model_name: outputs3
 tags:
+- generated_from_trainer
 - trl
 - sft
-- generated_from_trainer
-model-index:
-- name: outputs3
-  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. -->
-
-# outputs3
-
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
-
-## Model description
+# Model Card for outputs3
 
-More information needed
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-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="EdBerg/outputs3", 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/harpermia882/huggingface/runs/esh8k20f)
+
+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
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 4
-- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2
-- training_steps: 1000
-- mixed_precision_training: Native AMP
+### Framework versions
 
-### Training results
+- TRL: 0.12.0
+- Transformers: 4.46.1
+- Pytorch: 2.5.0+cu121
+- Datasets: 3.1.0
+- Tokenizers: 0.20.1
 
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.13.3.dev0
-- Transformers 4.46.1
-- Pytorch 2.5.0+cu121
-- Datasets 3.1.0
-- Tokenizers 0.20.1
+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

@@ -21,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
     "up_proj",
-    "k_proj",
     "o_proj",
-    "down_proj",
     "gate_proj",
-    "q_proj",
-    "v_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a55e62b27376ceea218a94e198e1e7f7b8ff9136f369d75d7df6abdeabf862
+oid sha256:dcb6cc8fab1412818ed23836cbf8bf0fe57a169b073c4afd2b80fd4a6c02d5c9
 size 83945296

runs/Nov01_16-07-05_d293895f1d52/events.out.tfevents.1730477226.d293895f1d52.1614.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0988bd3b219c45f28d452706dd1b58708f86297412bac1aed23c11be653abf46
+size 6093

runs/Nov01_16-11-45_d293895f1d52/events.out.tfevents.1730477507.d293895f1d52.24554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abbf1326a255e395e0fe1710801741b1f016b0a1991d5d10ab7df8e26f6a3fa
+size 216734

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd5bab83d45198adb5e115ea1e4bd95aa6c48a5b971632f1982f26d2fda10bea
+oid sha256:2e173a2c6b55f5433ebe510f0078ba17d3b378890d84b98cc90198022c1d33e6
 size 5496