README.md

metadata

license: apache-2.0
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT
model-index:
  - name: Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca
    results: []

See axolotl config

axolotl version: 0.4.0

base_model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT
model_type: MixtralForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true

# hub_model_id: MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Function-Calling
hub_model_id: MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca
hf_use_auth_token: true

load_in_4bit: true
strict: false

# datasets:
#   - path: Arist12/EABF-ShareGPT-Long-3.5k
#     type: sharegpt
#     conversation: chatml
# datasets:
#   - path: hypervariance/function-calling-sharegpt
#     type: sharegpt
#     conversation: chatml
datasets:
  - path: tatsu-lab/alpaca
    type: alpaca
    
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-out

# save_safetensors: true

adapter: qlora
lora_model_dir: 

sequence_len: 1024
sample_packing: true
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
  - q_proj
#  - k_proj
  - v_proj
#  - o_proj
#  - w1
#  - w2
#  - w3

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
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:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca

This model is a fine-tuned version of NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0276

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: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.3912	0.01	1	1.3714
1.0321	0.25	45	1.0427
1.0312	0.51	90	1.0327
0.9917	0.76	135	1.0276

Framework versions

• PEFT 0.8.2
• Transformers 4.38.0.dev0
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.0