# === Model Configuration ===
base_model: mistralai/Mistral-Nemo-Base-2407
load_in_8bit: false
load_in_4bit: true

# === HF Configuration === 
hub_model_id: ToastyPigeon/nemo-kink-lora
hub_strategy: "checkpoint"

# === Training Setup ===
num_epochs: 1
micro_batch_size: 2
gradient_accumulation_steps: 2
sequence_len: 8192
#sequence_parallel_degree: 2
#heads_k_stride: 1
sample_packing: true
pad_to_sequence_len: true
#max_steps: 10
# === Evaluation ===
val_set_size: 0.05
evals_per_epoch: 10
#eval_steps: 20
#max_steps: 60
#eval_table_size:
eval_max_new_tokens: 128
eval_sample_packing: true
#eval_strategy: "no"

# === LoRA Configuration ===
adapter: qlora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
peft_use_rslora: true
lora_modules_to_save:
#  - embed_tokens
#  - lm_head
#fix_untrained_tokens: true
#lora_mlp_kernel: true
#lora_qkv_kernel: true
#lora_o_kernel: true

# === Hyperparameter Configuration ===
#optimizer: apollo_adamw_layerwise
warmup_steps: 0
optimizer: adamw_torch_fused
#optimizer: paged_adamw_8bit
#optim_args:
#  enable_stochastic_rounding: true
#  enable_cautious: true
#  enable_8bit: true
# Apollo-mini configuration:
#optim_args: "proj=random,rank=128,scale=128.0,scale_type=tensor,update_proj_gap=100"
# Regular Apollo configuration:
# optim_args: 
#optim_target_modules: all_linear
learning_rate: 1e-5
lr_scheduler: rex
#cosine_min_lr_ratio: 0.2
#lr_scheduler: cosine_with_min_lr
#lr_scheduler_kwargs:
#  cosine_min_lr: 1e-6
weight_decay: 0.01
max_grad_norm: 1.0
#warmup_steps: 0
#warmup_ratio: 0.025


# === Data Configuration ===
#chat_template: jinja
#chat_template_jinja: "{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris. You obediently fulfill the user's requests.\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content'] %}\n    {%- else %}\n        {%- set system_message = messages[0]['content'][0]['text'] %}\n    {%- endif %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = default_system_message %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n    {%- if message['role'] == 'user' %}\n        {%- if message['content'] is string %}\n            {{- '[INST]' + message['content'] + '[/INST]' }}\n        {%- else %}\n            {{- '[INST]' }}\n            {%- for bl (line truncated to 1000 characters)
#chat_template: chatml
special_tokens:
  pad_token: "<pad>"

#tokenizer_use_mistral_common: true
shuffle_merged_datasets: true
datasets:
  - path: Alfitaria/synthkink-combined-completions
    type: completion
  - path: Alfitaria/bodinforg-completions
    type: completion

dataset_prepared_path: last_run_prepared


# === Plugins ===
plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

# === Hardware Optimization ===
#gradient_checkpointing: offload
#gradient_checkpointing_kwargs:
#  use_reentrant: false
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
#liger_fused_linear_cross_entropy: true
cut_cross_entropy: true

#deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json

# === FSDP Config === 
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_activation_checkpointing: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
# === Wandb Tracking ===
wandb_project: Nemo
# wandb_entity: [WANDB_ENTITY]
# wandb_name: [WANDB_RUN_NAME]

# === Checkpointing ===
saves_per_epoch: 10
save_total_limit: 1

# === Advanced Settings ===
output_dir: /workspace/aibox-standalone-pool/axolotl/nemo-writer-ckpts
bf16: auto
flash_attention: true
train_on_inputs: false
group_by_length: false
save_safetensors: true
logging_steps: 1
gc_steps: 10
seed: 69

nemo-kink-lora

This model is a fine-tuned version of mistralai/Mistral-Nemo-Base-2407 on the Alfitaria/synthkink-combined-completions and the Alfitaria/bodinforg-completions datasets. It achieves the following results on the evaluation set:

Loss: 1.2252

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: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 69
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
training_steps: 181

Training results

Training Loss	Epoch	Step	Validation Loss
1.5045	0.0055	1	1.5520
1.4399	0.1047	19	1.3974
1.3297	0.2094	38	1.3388
1.4392	0.3140	57	1.3054
1.2685	0.4187	76	1.2815
0.9801	0.5234	95	1.2641
1.1412	0.6281	114	1.2507
1.1564	0.7328	133	1.2393
1.1739	0.8375	152	1.2313
1.2154	0.9421	171	1.2252

Framework versions

PEFT 0.15.2
Transformers 4.51.3
Pytorch 2.7.0+cu128
Datasets 3.5.1
Tokenizers 0.21.1

ToastyPigeon/nemo-kimi-lora

nemo-kink-lora

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ToastyPigeon/
nemo-kimi-lora