base_model: ./prince-canuma_Ministral-8B-Instruct-2410-HF
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Story-writing-Alt-Data-sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Misc-Phase-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Synth-RP-Phase-sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Claude-instruct-Merged-Sharegpt
    type: sharegpt
    conversation: chatml
  - path: NewEden/Intelligence-Phase-Sharegpt
    type: sharegpt
    conversation: chatml
chat_template: chatml

output_dir: ./ministral_outputs

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

sequence_len: 16384
  #sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true


wandb_project: Ministral-Tor
wandb_entity:
wandb_watch:
wandb_name: run-1
wandb_log_model:


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

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5

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

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

warmup_steps: 30
eval_table_size:
saves_per_epoch: 1
weight_decay: 0.1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
  #deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
  #deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<pad>"

ministral_outputs

This model was trained from scratch on the None dataset.

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 30
num_epochs: 2

Training results

Framework versions

Transformers 4.45.2
Pytorch 2.3.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1

Edens-Gate/ministral-tor-r1-e2212

ministral_outputs

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Edens-Gate/
ministral-tor-r1-e2212