Update README.md

README.md

@@ -9,6 +9,9 @@ tags:
 - unsloth
 - mistral
 - trl
+- rp
+- experimental
+- long-context
 ---
 
 # Uploaded  model
@@ -17,6 +20,77 @@ tags:
 - **License:** apache-2.0
 - **Finetuned from model :** unsloth/Mistral-Nemo-Instruct-2407
 
+This is the 4th (and likely final) experimental fine-tune of Nemo. I made these to teach myself the basics of fine-tuning, with notes extensively borrowed from https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9
+
+It is an RP finetune using 8,160 human-generated conversations of varying lengths from a variety of sources, trained in ChatML format. 
+
+The big differences from Celeste is a different LoRA scaling factor. Celeste uses 8; I did several tests with this data before concluding I got lower training loss with 2.
+
+Training took around 4 hours on a single Colab A100 (but I didn't do an eval loop). Neat that I could get it all to fit into 40GB of vRAM thanks to Unsloth.
+
+It was trained with the following settings:
+
+```
+==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1
+   \\   /|    Num examples = 8,160 | Num Epochs = 2
+O^O/ \_/ \    Batch size per device = 2 | Gradient Accumulation steps = 4
+\        /    Total batch size = 8 | Total steps = 2,040
+ "-____-"     Number of trainable parameters = 912,261,120
+
+[2040/2040 3:35:30, Epoch 2/2] 
+
+model = FastLanguageModel.get_peft_model(
+    model,
+    r = 256,
+    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
+                      "gate_proj", "up_proj", "down_proj",],
+    lora_alpha = 32,  #   32 / sqrt(256) gives a scaling factor of 2
+    lora_dropout = 0, # Supports any, but = 0 is optimized
+    bias = "none",    # Supports any, but = "none" is optimized
+    # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
+    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
+    random_state = 3407,
+    use_rslora = True,  # setting the adapter scaling factor to lora_alpha/math.sqrt(r) instead of lora_alpha/r
+    loftq_config = None, # And LoftQ
+)
+
+lr_scheduler_kwargs = {
+    'min_lr': 0.0000024  # Adjust this value as needed
+}
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = train_ds,
+    compute_metrics = compute_metrics,
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    dataset_num_proc = 2,
+    packing = False, # Can make training 5x faster for short sequences.
+    args = TrainingArguments(
+        per_device_train_batch_size = 2,
+        per_device_eval_batch_size = 2, # defaults to 8!
+        gradient_accumulation_steps = 4,
+        warmup_steps = 5,
+        num_train_epochs = 2,
+        learning_rate = 8e-5,
+        fp16 = not is_bfloat16_supported(),
+        bf16 = is_bfloat16_supported(),
+        fp16_full_eval = True, # stops eval from trying to use fp32
+        eval_strategy = "no", # 'no', 'steps', 'epoch'. Don't use this without an eval dataset etc
+        eval_steps = 1, # is eval_strat is set to 'steps', do every N steps.
+        logging_steps = 1, # so eval and logging happen on the same schedule
+        optim = "adamw_8bit", 
+        weight_decay = 0.01,
+        lr_scheduler_type = "cosine_with_min_lr", # linear, cosine, cosine_with_min_lr, default linear
+        lr_scheduler_kwargs = lr_scheduler_kwargs, # needed for cosine_with_min_lr
+        seed = 3407,
+        output_dir = "outputs",
+    ),
+)
+
+```
+
 This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)