MS3.2-24B-Magnum-Diamond-LoRA

6
24.0B
license:apache-2.0
by
Doctor-Shotgun
Other
OTHER
24B params
New
6 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
54GB+ RAM
Mobile
Laptop
Server
Quick Summary

Magnum "Diamond" in reference to the intense heat and pressure (generated through matrix multiplications) needed to turn the coal-esque material of dry, assista...

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
23GB+ RAM

Code Examples

optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
optionally might have model_type or tokenizer_typeyaml
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
#base_model_ignore_patterns: "consolidated.safetensors"
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: NewEden/magnum-v5-sft-prototype-ms3.2-lora
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/magnum-v5-sft-proto-mistral-v7-tekken-rev1-32k
    ds_type: parquet
    type:
shuffle_merged_datasets: true
dataset_prepared_path: ./magnum-24b-data
val_set_size: 0.0
output_dir: ./magnum-24b-lora-out

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: 24b-magnum-lora
wandb_entity:
wandb_watch:
wandb_name: 24b-magnum-lora-mistral-3.2
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 2e-5
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.