deepseek_70b

<!-- 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: 0.8.0.dev0

base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: ugaoo/transformed_short_answer_dataset_prompt
    type: alpaca
val_set_size: 0
output_dir: ./out/transformed_short_answer_dataset_prompt_deepseek70bllama

sequence_len: 4000
sample_packing: true
pad_to_sequence_len: true

adapter: qlora
lora_r: 256
lora_alpha: 512
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - up_proj
  - down_proj
  - gate_proj
lora_modules_to_save:
  - embed_tokens
  - lm_head
 
wandb_project: cosmosearch
wandb_entity:
wandb_watch: 
wandb_name: transformed_short_answer_dataset_prompt_deepseek70bllama
wandb_log_model:

gradient_accumulation_steps: 3
micro_batch_size: 4
num_epochs: 6
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 5e-6

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 6
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
save_total_limit: 6
special_tokens:
   pad_token: <｜end▁of▁sentence｜>

</details><br>

out/transformed_short_answer_dataset_prompt_deepseek70bllama

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Llama-70B on the ugaoo/transformed_short_answer_dataset_prompt 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: 5e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 3
• total_train_batch_size: 48
• total_eval_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 6.0

Training results

Framework versions

• PEFT 0.14.0
• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.1