End of training

README.md

@@ -1,70 +1,54 @@
 ---
-license: mit
+license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
-  - trl
-  - sft
+- trl
+- sft
+- generated_from_trainer
 model-index:
-  - name: mayo
-    results: []
-datasets:
-  - nroggendorff/mayo
-language:
-  - en
+- name: mayo
+  results: []
 ---
 
-# Mayonnaise LLM
+<!-- 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. -->
 
-Mayo is a language model fine-tuned on the [Mayo dataset](https://huggingface.co/datasets/nroggendorff/mayo) using Supervised Fine-Tuning (SFT) and Teacher Reinforced Learning (TRL) techniques. It is based on the [TinyLlama/TinyLlama-1.1B-Chat-v1.0 model](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
+# mayo
 
-## Features
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
 
-- Utilizes SFT and TRL techniques for improved performance
-- Supports English language
+## Model description
 
-## Usage
+More information needed
 
-To use the Mayo LLM, you can load the model using the Hugging Face Transformers library:
+## Intended uses & limitations
 
-```python
-from transformers import pipeline
+More information needed
 
-pipe = pipeline("text-generation", model="nroggendorff/mayo")
+## Training and evaluation data
 
-question = "What color is the sky?"
-conv = [{"role": "system", "content": "You are a very bored real human named Noa Roggendorff."}, {"role": "user", "content": question}]
+More information needed
 
-response = pipe(conv, max_new_tokens=2048)[0]['generated_text'][-1]['content']
-print(response)
-```
+## Training procedure
 
-To use the model with quantization:
+### Training hyperparameters
 
-```python
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
-import torch
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 4600
 
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
+### Training results
 
-model_id = "nroggendorff/mayo"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)
 
-prompt = "<|user|>What color is the sky?</s>"
-inputs = tokenizer(prompt, return_tensors="pt")
+### Framework versions
 
-outputs = model.generate(**inputs, max_new_tokens=10)
-
-generated_text = tokenizer.batch_decode(outputs)[0]
-print(generated_text)
-```
-
-## License
-
-This project is licensed under the MIT License.
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f62e9f0760df0a57e2adc0649781d69bf57cbf44e9df7b1f707d1ba1ecd4d0d9
+oid sha256:99c18cf11cb2cac3b2dbd3e0d1aaba0c1bd9924552105735b10103e4eedda17e
 size 4400216536

runs/May31_21-14-36_c548f4a40faf/events.out.tfevents.1717190090.c548f4a40faf.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4413f4c79a99e8f2c6845027eb2b0ddd1843c02402d928da180cf01983a761a6
+size 6893

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b099e321dc66efe84c22bcb19968019ade0421834e952fa5298ad6b7ed352319
+oid sha256:18e0f4ea6da1a0e1c578e01e53436a44a6edf5684ba13ddccc1fcd1a9b21d9ca
 size 4920