You can deploy this model and start earning money today!

Edens-Gate/
Ohashi-NeMo-12B-Lora

Name: Ohashi-NeMo-12B-Lora
Availability: InStock

peft

safetensors

mistral

generated_from_trainer

Views

No views yet

See axolotl config

axolotl version: 0.5.0

yaml

base_model: mistralai_Mistral-Nemo-Instruct-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

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

datasets:
  - path: NewEden/OpenCAI-ShareGPT
    type: chat_template
#    chat_template: mistralv3tekken
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: NewEden/vanilla-backrooms-claude-sharegpt
    type: chat_template
#    chat_template: mistralv3tekken
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn    
  - path: anthracite-org/kalo_opus_misc_240827
    type: chat_template
#    chat_template: mistralv3tekken
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn    
  - path: anthracite-org/kalo_misc_part2
    type: chat_template
#    chat_template: mistralv3tekken
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: NewEden/Roleplay-Logs-V2
    type: chat_template
#    chat_template: mistralv3tekken
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
dataset_prepared_path: dataset_prepared
val_set_size: 0.0
output_dir: 12b-out-r2

sequence_len: 16384
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:
  #lora_fan_in_fan_out: true
peft_use_rslora: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj


wandb_project: 12b-control
wandb_entity:
wandb_watch:
wandb_name: 12b-control-r2
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 4
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00001

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

gradient_checkpointing: unsloth
  #gradient_checkpointing_kwargs:
  #  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
evals_per_epoch: 
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.03
fsdp:
fsdp_config:
special_tokens:
  pad_token: <pad>

12b-out-r2

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: 2
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 40
num_epochs: 4

Training results

Framework versions

PEFT 0.13.2
Transformers 4.46.1
Pytorch 2.3.1+cu121
Datasets 3.0.1
Tokenizers 0.20.3

Edens-Gate/Ohashi-NeMo-12B-Lora

12b-out-r2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Edens-Gate/
Ohashi-NeMo-12B-Lora