See axolotl config
axolotl version: 0.4.0
base_model: mistral-community/Mistral-7B-v0.2
trust_remote_code: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: dataset/medical_meadow_large.json
type: alpaca
ds_type: json
chat_template: chatml
dataset_prepared_path:
val_set_size: 0.01
output_dir: ./out
sequence_len: 1024
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
use_wandb: true
wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name: Mistroll-v0.1
wandb_log_model:
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
low_cpu_mem_usage: true
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 4
save_total_limit: 2
debug:
deepspeed:
weight_decay: 0.0
special_tokens:
out
This model is a fine-tuned version of mistral-community/Mistral-7B-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1296
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.7713 | 0.0 | 1 | 1.6075 |
1.4023 | 0.25 | 1246 | 1.2095 |
1.2564 | 0.5 | 2492 | 1.1769 |
1.6691 | 0.75 | 3738 | 1.1296 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 2
Model tree for MatthieuO/Mistroll-v0.1
Base model
mistral-community/Mistral-7B-v0.2
Adapter
this model