---
library_name: peft
license: other
base_model: unsloth/Mistral-Small-Instruct-2409
tags:
- axolotl
- generated_from_trainer
datasets:
- ToastyPigeon/some-rp
model-index:
- name: ms-rp-test-ws
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: `0.6.0`
```yaml
# git clone https://github.com/axolotl-ai-cloud/axolotl
# cd axolotl
# git checkout 844331005c1ef45430ff26b9f42f757dce6ee66a
# pip3 install packaging ninja huggingface_hub[cli]
# pip3 install -e '.[flash-attn,deepspeed]'
# huggingface-cli login --token $hf_key && wandb login $wandb_key
# python -m axolotl.cli.preprocess nemo-rp-test-2.yml
# accelerate launch -m axolotl.cli.train nemo-rp-test-2.yml
# python -m axolotl.cli.merge_lora nemo-rp-test.yml
# huggingface-cli upload Columbidae/nemo-rp-test train-workspace/merged . --exclude "*.md"
# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && pip3 install packaging ninja huggingface_hub[cli] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key
# Model
base_model: unsloth/Mistral-Small-Instruct-2409
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
bf16: true
fp16:
tf32: false
flash_attention: true
special_tokens:
# Output
output_dir: ./train-workspace
hub_model_id: ToastyPigeon/ms-rp-test-ws
hub_strategy: "all_checkpoints"
resume_from_checkpoint:
saves_per_epoch: 5
# Data
sequence_len: 16384 # fits
min_sample_len: 128
dataset_prepared_path: last_run_prepared
datasets:
- path: ToastyPigeon/some-rp
type: chat_template
field_messages: conversations
message_field_role: from
message_field_content: value
train_on_inputs: true
warmup_steps: 20
shuffle_merged_datasets: true
sample_packing: true
pad_to_sequence_len: true
chat_template: jinja
chat_template_jinja: "{%- if messages[0][\"role\"] == \"fake\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if message[\"role\"] == \"user\" or message[\"role\"] == \"system\"%}\n {%- if tools is not none and (message == user_messages[-1]) %}\n {{- \"[AVAILABLE_TOOLS][\" }}\n {%- for tool in tools %}\n {%- set tool = tool.function %}\n {{- '{\"type\": \"function\", \"function\": {' }}\n {%- for key, val in tool.items() if key != \"return\" %}\n {%- if val is string %}\n {{- '\"' + key + '\": \"' + val + '\"' }}\n {%- else %}\n {{- '\"' + key + '\": ' + val|tojson }}\n {%- endif %}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \"}}\" }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" }}\n {%- endif %}\n {%- endfor %}\n {{- \"[/AVAILABLE_TOOLS]\" }}\n {%- endif %}\n {%- if loop.last and system_message is defined %}\n {{- \"[INST] \" + system_message + \"\\n\\n\" + message[\"content\"] + \"[/INST] \" }}\n {%- else %}\n {{- \"[INST] \" + message[\"content\"] + \"[/INST] \" }}\n {%- endif %}\n {%- elif (message.tool_calls is defined and message.tool_calls is not none) %}\n {{- \"[TOOL_CALLS][\" }}\n {%- for tool_call in message.tool_calls %}\n {%- set out = tool_call.function|tojson %}\n {{- out[:-1] }}\n {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- ', \"id\": \"' + tool_call.id + '\"}' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" + eos_token }}\n {%- endif %}\n {%- endfor %}\n {%- elif message[\"role\"] == \"assistant\" %}\n {{- message[\"content\"] + eos_token}}\n {%- elif message[\"role\"] == \"tool_results\" or message[\"role\"] == \"tool\" %}\n {%- if message.content is defined and message.content.content is defined %}\n {%- set content = message.content.content %}\n {%- else %}\n {%- set content = message.content %}\n {%- endif %}\n {{- '[TOOL_RESULTS]{\"content\": ' + content|string + \", \" }}\n {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- '\"call_id\": \"' + message.tool_call_id + '\"}[/TOOL_RESULTS]' }}\n {%- else %}\n {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n {%- endif %}\n{%- endfor %}\n"
# Batching
num_epochs: 1
gradient_accumulation_steps: 1
micro_batch_size: 1
eval_batch_size: 1
# Evaluation
val_set_size: 50
evals_per_epoch: 10
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
save_safetensors: true
# WandB
wandb_project: Nemo-Rp-Test
#wandb_entity:
gradient_checkpointing: 'unsloth'
gradient_checkpointing_kwargs:
use_reentrant: false
unsloth_cross_entropy_loss: true
#unsloth_lora_mlp: true
#unsloth_lora_qkv: true
#unsloth_lora_o: true
# LoRA
adapter: qlora
lora_model_dir:
lora_r: 32
lora_alpha: 64
lora_dropout: 0.25
lora_target_linear:
lora_fan_in_fan_out:
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
lora_modules_to_save:
# Optimizer
optimizer: paged_ademamix_8bit # adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-5
cosine_min_lr_ratio: 0.1
weight_decay: 0.01
max_grad_norm: 1.0
# Misc
#train_on_inputs: false
group_by_length: false
early_stopping_patience:
local_rank:
logging_steps: 1
xformers_attention:
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
fsdp:
fsdp_config:
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true
gc_steps: 10
seed: 69
```
</details><br>
# ms-rp-test-ws
This model is a fine-tuned version of [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) on the ToastyPigeon/some-rp dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0036
## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 69
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Use OptimizerNames.PAGED_ADEMAMIX_8BIT and the args are:
No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.1185 | 0.0034 | 1 | 2.0953 |
| 2.055 | 0.1014 | 30 | 2.0229 |
| 2.1407 | 0.2027 | 60 | 2.0158 |
| 2.0997 | 0.3041 | 90 | 2.0111 |
| 2.1113 | 0.4054 | 120 | 2.0099 |
| 2.1695 | 0.5068 | 150 | 2.0076 |
| 2.0782 | 0.6081 | 180 | 2.0063 |
| 2.0972 | 0.7095 | 210 | 2.0054 |
| 2.1761 | 0.8108 | 240 | 2.0043 |
| 2.1288 | 0.9122 | 270 | 2.0036 |
### Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0