mdean77/llama381binstruct_summarize_short_challenge

.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 +1,58 @@
 ---
 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: 2.2429
+# Model Card for llama381binstruct_summarize_short
 
-## Model description
+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).
 
-More information needed
+## Quick start
 
-## Intended uses & limitations
+```python
+from transformers import pipeline
 
-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="Mdean77/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 and evaluation data
+## Training procedure
 
-More information needed
+[<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/miketraindoc-university-of-utah/huggingface/runs/letgphjl) 
 
-## Training procedure
 
-### Training hyperparameters
+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: 0.16.0
+- Transformers: 4.50.1
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
 
-| Training Loss | Epoch   | Step | Validation Loss |
-|:-------------:|:-------:|:----:|:---------------:|
-| 1.653         | 1.3158  | 25   | 1.3192          |
-| 0.7031        | 2.6316  | 50   | 1.3904          |
-| 0.3683        | 3.9474  | 75   | 1.5407          |
-| 0.1658        | 5.2632  | 100  | 1.9100          |
-| 0.0716        | 6.5789  | 125  | 1.9351          |
-| 0.036         | 7.8947  | 150  | 1.9408          |
-| 0.0372        | 9.2105  | 175  | 1.9649          |
-| 0.01          | 10.5263 | 200  | 2.1079          |
-| 0.009         | 11.8421 | 225  | 2.1175          |
-| 0.0144        | 13.1579 | 250  | 2.0791          |
-| 0.0064        | 14.4737 | 275  | 2.0624          |
-| 0.0048        | 15.7895 | 300  | 2.1707          |
-| 0.0039        | 17.1053 | 325  | 2.0981          |
-| 0.0026        | 18.4211 | 350  | 2.1469          |
-| 0.0021        | 19.7368 | 375  | 2.1868          |
-| 0.0021        | 21.0526 | 400  | 2.2096          |
-| 0.0018        | 22.3684 | 425  | 2.2259          |
-| 0.0017        | 23.6842 | 450  | 2.2357          |
-| 0.0016        | 25.0    | 475  | 2.2411          |
-| 0.0019        | 26.3158 | 500  | 2.2429          |
+## 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

@@ -3,6 +3,9 @@
   "auto_mapping": null,
   "base_model_name_or_path": "NousResearch/Meta-Llama-3.1-8B-Instruct",
   "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +14,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,15 +24,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "k_proj",
     "gate_proj",
-    "v_proj",
-    "up_proj",
     "down_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj"
+    "up_proj",
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
-size 40
+oid sha256:d70a33f6a812494c6b4b8f0d2f85cb82f04521181abd32a67c1dd3b06355f201
+size 167832240

runs/Mar26_16-54-03_61f7f7d06b80/events.out.tfevents.1743008130.61f7f7d06b80.1273.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79413744c47653aae369b4649572223de50177cf98c0c3cd03367f325d963f87
+size 29690

tokenizer_config.json

@@ -2053,11 +2053,12 @@
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
   "pad_token": "<|eot_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizer"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6daebb1eaa753f4a52e454faf9b635a703b31c05e8c966c3fd4586a3d1801d1
-size 5496
+oid sha256:317a50ee638041f79d369f632af1b6919038101379555ba6b0b86cc6378dc319
+size 5688