Crystalcareai/WeakAuraGenerator

See axolotl config

axolotl version: 0.3.0

base_model: NurtureAI/OpenHermes-2.5-Mistral-7B-16k
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: Crystalcareai/WATOP600
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 16000
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_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

# Added line to resolve the error
lora_modules_to_save: ['embed_tokens', 'lm_head']

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1.5
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
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_table_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>"

qlora-out

This model is a fine-tuned version of NurtureAI/OpenHermes-2.5-Mistral-7B-16k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5566

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 1.5

Training results

Training Loss	Epoch	Step	Validation Loss
1.0027	0.03	1	0.9286
0.8464	0.27	9	0.7312
0.5254	0.54	18	0.6451
0.712	0.81	27	0.5988
0.5733	1.01	36	0.5616
0.3739	1.28	45	0.5566

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.1+cu117
• Datasets 2.16.1
• Tokenizers 0.15.0

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: False
• load_in_4bit: True
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: nf4
• bnb_4bit_use_double_quant: True
• bnb_4bit_compute_dtype: bfloat16

Framework versions

• PEFT 0.6.0