Mistral-7B-Base-SFT-Tulu2

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.4.1

base_model: mistralai/Mistral-7B-v0.3
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: allenai/tulu-v2-sft-mixture
    type: sharegpt.load_ultrachat
    conversation: llama3

chat_template: llama3

dataset_prepared_path: ./datasets/tulu-v2-sft-2.0
output_dir: ./outputs/m7b-tulu-v2-sft

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: lm-evals
wandb_entity:
wandb_watch:
wandb_name: Mistral-7B-tulu-v2
wandb_log_model:
hub_model_id: penfever/Mistral-7B-tulu-v2

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

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

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

warmup_steps: 100
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: <|begin_of_text|>
  eos_token: <|end_of_text|>
  pad_token: <|end_of_text|>
tokens:
  - "<|start_header_id|>"
  - "<|end_header_id|>"
  - "<|eot_id|>"

</details><br>

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

Mistral-7B-tulu-v2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 2

Training results

Framework versions

• Transformers 4.43.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1