Modelpublic

dyang415/mixtral-fc-w-resp-new-format-4e-no-negative

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes10downloads

Model Card

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.4.0

yaml

base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false
chat_template: inst

datasets:
  - path: ./data/with_function_response/function_not_used_training.jsonl
    type: sharegpt
    conversation: mistral
  # - path: ./data/with_function_response/no_function_training.jsonl
  #   type: sharegpt
  #   conversation: mistral
  - path: ./data/with_function_response/function_used_training.jsonl
    type: sharegpt
    conversation: mistral

dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ../mixtral-fc-w-resp-new-format-4e-no-negative

model_config:
  output_router_logits: true

adapter: qlora
lora_model_dir:

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj


wandb_project: function-call
wandb_name: mixtral-instruct-lora-no-negative
wandb_log_model: end
hub_model_id: dyang415/mixtral-fc-w-resp-new-format-4e-no-negative


gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: paged_adamw_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
logging_steps: 1
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:
weight_decay: 0.0
fsdp:
fsdp_config:

</details><br>

mixtral-fc-w-resp-new-format-4e-no-negative

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

—quantmethod: QuantizationMethod.BITSAND_BYTES
—loadin8bit: False
—loadin4bit: True
—llmint8threshold: 6.0
—llmint8skip_modules: None
—llmint8enablefp32cpu_offload: False
—llmint8hasfp16weight: False
—bnb4bitquant_type: nf4
—bnb4bitusedoublequant: True
—bnb4bitcompute_dtype: bfloat16

Training hyperparameters

The following hyperparameters were used during training:

—learning_rate: 0.0002
—trainbatchsize: 2
—evalbatchsize: 2
—seed: 42
—distributed_type: multi-GPU
—num_devices: 2
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 16
—totalevalbatch_size: 4
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 10
—num_epochs: 4

Framework versions

—PEFT 0.7.0
—Transformers 4.37.0
—Pytorch 2.0.1+cu117
—Datasets 2.17.1
—Tokenizers 0.15.0