Hugging Face's logo

strickvl
/
isafpr-mistral-lora-templatefree

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
isafpr-mistral-lora-templatefree / README.md
strickvl's picture
strickvl
End of training
b0fabfa verified
preview code
|
raw
history blame
4.14 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
  - name: isafpr-mistral-lora-templatefree
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

data_seed: 42
seed: 42

datasets:
  - path: data/templatefree_isaf_press_releases_ft_train.jsonl
    type: input_output
dataset_prepared_path:
val_set_size: 0.1
output_dir: ./outputs/mistral/lora-out-templatefree
hub_model_id: strickvl/isafpr-mistral-lora-templatefree


sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: isaf_pr_ft
wandb_entity: strickvl
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
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:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"

isafpr-mistral-lora-templatefree

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0297

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: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • 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: 10
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
1.4053 0.0276 1 1.4080
0.1866 0.2483 9 0.1346
0.0544 0.4966 18 0.0551
0.0516 0.7448 27 0.0442
0.0387 0.9931 36 0.0400
0.0354 1.2138 45 0.0367
0.0396 1.4621 54 0.0352
0.0282 1.7103 63 0.0341
0.0335 1.9586 72 0.0333
0.0257 2.1793 81 0.0317
0.0206 2.4276 90 0.0313
0.0259 2.6759 99 0.0312
0.024 2.9241 108 0.0301
0.0219 3.1517 117 0.0300
0.0221 3.4 126 0.0298
0.0225 3.6483 135 0.0297
0.0208 3.8966 144 0.0297

Framework versions

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