---
library_name: transformers
base_model: Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML
tags:
- generated_from_trainer
model-index:
- name: l3.1-8b-dans-instruct
  results: []
---

<!-- 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. -->

[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.4.1`
```yaml
base_model: Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code:

# wandb configuration
wandb_project: l3.1-8b-dans-instruct
wandb_watch:
wandb_run_id:
wandb_log_model: 

# where to save the finished model to
output_dir: ./l3.1-8b-dans-instruct

# dataset settings (local or huggingface repo)
datasets:
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: sharegpt
    conversation: chatml
  - path: AquaV/Energetic-Materials-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: AquaV/Chemical-Biological-Safety-Applications-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: PocketDoc/Dans-Mathmaxx
    type: sharegpt
    conversation: chatml
  - path: PocketDoc/Dans-Benchmaxx
    type: sharegpt
    conversation: chatml
  - path: PocketDoc/Dans-Codemaxx
    type: sharegpt
    conversation: chatml
  - path: PocketDoc/Dans-Taskmaxx
    type: sharegpt
    conversation: chatml
  - path: PocketDoc/Dans-ASCIIMaxx-Wordart
    type: sharegpt
    conversation: chatml
  - path: PocketDoc/Dans-Prosemaxx
    type: sharegpt
    conversation: chatml
  - path: PocketDoc/Dans-Toolmaxx
    type: sharegpt
    conversation: chatml

chat_template: chatml

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

dataset_prepared_path: ./l3.1-8b-dans-instruct-data
val_set_size: 0.03

lora_model_dir: 

sequence_len: 8192

# use efficient multi-packing with block diagonal attention and per sequence position_ids. Recommend set to 'true'
sample_packing: true
eval_sample_packing: true

# you can set these packing optimizations AFTER starting a training at least once.
# The trainer will provide recommended values for these values.

pad_to_sequence_len: true

#rope_scaling:
  #type:  # linear | dynamic
  #factor:  # float (2 for 2x)

adapter: # blank for full finetune
lora_r: 64
lora_alpha: 64
lora_dropout: 0.2
lora_target_linear: True
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj
lora_modules_to_save:
  - embed_tokens
  - lm_head
lora_fan_in_fan_out:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0000015
cosine_min_lr_ratio: 

train_on_inputs: false
group_by_length: true
bf16: true
fp16: false
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
auto_resume_from_checkpoints: false
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 15
eval_steps: 25
# save_steps: 100
saves_per_epoch: 3
debug: false
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:


special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|im_end|>
```

</details><br>

# l3.1-8b-dans-instruct

This model is a fine-tuned version of [Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML](https://huggingface.co/Dans-DiscountModels/Meta-Llama-3.1-8B-ChatML) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7432

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1.5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 15
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.0783        | 0.0077 | 1    | 1.0298          |
| 0.8528        | 0.1931 | 25   | 0.8603          |
| 0.7776        | 0.3862 | 50   | 0.7925          |
| 0.7089        | 0.5793 | 75   | 0.7697          |
| 0.6868        | 0.7724 | 100  | 0.7584          |
| 0.7158        | 0.9655 | 125  | 0.7524          |
| 0.6938        | 1.1566 | 150  | 0.7488          |
| 0.733         | 1.3499 | 175  | 0.7464          |
| 0.7956        | 1.5433 | 200  | 0.7450          |
| 0.6886        | 1.7366 | 225  | 0.7442          |
| 0.9065        | 1.9299 | 250  | 0.7437          |
| 0.7851        | 2.1210 | 275  | 0.7434          |
| 0.7256        | 2.3142 | 300  | 0.7433          |
| 0.7832        | 2.5074 | 325  | 0.7432          |
| 0.7317        | 2.7006 | 350  | 0.7432          |
| 0.7112        | 2.8937 | 375  | 0.7432          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1