Mistral-7B-v0.1-q-sparse-fineweb-edu-10000steps-4M-bs

<!-- 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: 0.5.2

base_model: mistralai/Mistral-7B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false
resize_token_embeddings_to_32x: false

flash_attention: true
xformers_attention:

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: skymizer/Mistral-7B-v0.1-base-tokenized-fineweb-edu-45B-4096
    train_on_split: train
    type: completion

test_datasets:
  - path: skymizer/Mistral-7B-v0.1-base-tokenized-fineweb-edu-test-4K
    split: test
    type: completion

is_preprocess: true
skip_prepare_dataset: true

dataset_prepared_path:

hf_use_auth_token: true
output_dir: /mnt/home/model-team/models/Mistral-7B-v0.1-q-sparse-fineweb-edu-10000steps-4M-bs
resume_from_checkpoint:
auto_resume_from_checkpoints: true

sequence_len: 4096
sample_packing: true
sample_packing_group_size: 100000
sample_packing_bin_size: 200
pad_to_sequence_len: true

eval_sample_packing: false
# eval_causal_lm_metrics: ["perplexity"]

wandb_project: "sparse-tuning-cpt"
wandb_entity:
wandb_watch:
wandb_name: "Mistral-7B-v0.1-q-sparse-fineweb-edu-10000steps-4M-bs"
wandb_log_model:

# global batch size = 2 * 8 * 8 GPUs * 8 Nodes * 4096 = 4M
gradient_accumulation_steps: 8
micro_batch_size: 2
eval_batch_size: 1
max_steps: 10000
optimizer: adamw_torch
learning_rate: 0.00005
lr_scheduler: cosine
cosine_min_lr_ratio: 0.2 
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.95
adam_eps: 0.000001
max_grad_norm: 2.0

train_on_inputs: false
group_by_length: false
bf16: true
fp16:
tf32: false

hub_model_id: "skymizer/Mistral-7B-v0.1-q-sparse-fineweb-edu-10000steps-4M-bs"

save_strategy: "steps"
save_steps: 500

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
local_rank:
logging_steps: 1

warmup_steps: 375
eval_steps: 500
eval_table_size:
debug:
deepspeed: /root/train/axolotl/deepspeed_configs/zero3_bf16.json
fsdp:
fsdp_config:
seed: 42

</details><br>

Mistral-7B-v0.1-q-sparse-fineweb-edu-10000steps-4M-bs

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9685

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 64
• gradient_accumulation_steps: 8
• total_train_batch_size: 1024
• total_eval_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 375
• training_steps: 10000

Training results

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3