isafpr-phi3-lora

<!-- 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/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: 0.4.1

base_model: microsoft/Phi-3-mini-4k-instruct
trust_remote_code: true
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
chat_template: phi_3

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: data/isaf_press_releases_ft.jsonl
    conversation: alpaca
    type: sharegpt

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/phi3/lora-out
hub_model_id: strickvl/isafpr-phi3-lora

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: isaf_pr_ft
wandb_entity: strickvl

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_torch
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 5.0e-6

train_on_inputs: false
group_by_length: false
bf16: auto

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: True
early_stopping_patience: 3
logging_steps: 1
flash_attention: true

eval_steps: 1000
save_steps: 5000
eval_table_size: 2
eval_batch_size: 2
eval_sample_packing: false
eval_max_new_tokens: 32
eval_causal_lm_metrics: ["perplexity"]
do_causal_lm_eval: true

warmup_ratio: 0.2
debug: true
weight_decay: 0.1
resize_token_embeddings_to_32x: true

</details><br>

isafpr-phi3-lora

This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.2970

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: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 4
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 53
• num_epochs: 1

Training results

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1