Edit model card

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

mlflow_tracking_uri: http://127.0.0.1:2340
mlflow_experiment_name: Default

base_model: intervitens/internlm2-limarp-chat-20b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: ResplendentAI/Alpaca_NSFW_Shuffled
    type: alpaca
  - path: diffnamehard/toxic-dpo-v0.1-NoWarning-alpaca
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/qlora-out

adapter: lora
lora_model_dir:

sequence_len: 8192
sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

outputs/qlora-out

This model is a fine-tuned version of intervitens/internlm2-limarp-chat-20b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9868

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: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 7
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 56
  • total_eval_batch_size: 14
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
1.465 0.0476 1 1.4508
1.3472 0.2857 6 1.4126
1.1997 0.5714 12 1.1998
1.0735 0.8571 18 1.1192
1.077 1.1429 24 1.0703
1.0478 1.4286 30 1.0410
0.9997 1.7143 36 1.0259
0.9696 2.0 42 1.0091
0.8861 2.2857 48 1.0042
0.8961 2.5714 54 0.9928
0.8615 2.8571 60 0.9889
0.8603 3.1429 66 0.9860
0.7825 3.4286 72 0.9877
0.9228 3.7143 78 0.9860
0.8684 4.0 84 0.9868

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.3.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
1
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for Fischerboot/InternLM2-ToxicRP-QLORA-8Bit

Collection including Fischerboot/InternLM2-ToxicRP-QLORA-8Bit