Modelpublic

MaziyarPanahi/Mistral-7B-Alpaca-52k-v0.2

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

2likes

Model Card

<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: 0.4.0

yaml

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


hub_model_id: MaziyarPanahi/Mistral-7B-Alpaca-52k-v0.2
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: tatsu-lab/alpaca
    type: alpaca
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./MaziyarPanahi/Mistral-7B-Alpaca-52k-v0.2

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project:
wandb_entity:
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: 0.000005

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

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>"
  unk_token: "<unk>"

</details><br>

Mistral-7B-Alpaca-52k-v0.2

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: 0.9730

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
—trainbatchsize: 2
—evalbatchsize: 2
—seed: 42
—distributed_type: multi-GPU
—num_devices: 4
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 32
—totalevalbatch_size: 8
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 10
—num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.3017	0.04	1	1.4067
1.1285	0.25	6	1.0677
1.0586	0.5	12	0.9915
1.0515	0.75	18	0.9769
1.0608	1.0	24	0.9700
1.0003	1.23	30	0.9689
0.9761	1.48	36	0.9679
0.9783	1.73	42	0.9659
0.9631	1.98	48	0.9663
0.9273	2.21	54	0.9724
0.9093	2.46	60	0.9720
0.9038	2.71	66	0.9729
0.903	2.96	72	0.9724
0.9231	3.19	78	0.9725
0.9017	3.44	84	0.9729
0.9279	3.69	90	0.9730
0.9069	3.94	96	0.9730

Framework versions

—Transformers 4.38.0.dev0
—Pytorch 2.2.0+cu121
—Datasets 2.17.0
—Tokenizers 0.15.0