See axolotl config
axolotl version: 0.4.0
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
- path: jspr/bts-long-gpt-4-32k-0314-prompt
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out
# using lora for lower cost
adapter: lora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- v_proj
sequence_len: 4096
sample_packing: false # makes it faster but uses more memory
pad_to_sequence_len: false
model_config:
rope_scaling:
type: linear
factor: 8.0
hub_model_id: jspr/bts_mistral_7b_v3_32k
hub_strategy: end
hub_private_repo: true
wandb_project: bts
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
# only 2 epochs because of small dataset
gradient_accumulation_steps: 3
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
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: 16
eval_sample_packing: false
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
bts_mistral_7b_v3_32k
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: 1.8543
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
- gradient_accumulation_steps: 3
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.0334 | 0.12 | 1 | 1.8829 |
1.8664 | 0.25 | 2 | 1.8844 |
1.813 | 0.5 | 4 | 1.8803 |
1.8574 | 0.75 | 6 | 1.8751 |
1.878 | 1.0 | 8 | 1.8680 |
1.841 | 1.25 | 10 | 1.8599 |
1.7903 | 1.5 | 12 | 1.8559 |
1.808 | 1.75 | 14 | 1.8543 |
1.9314 | 2.0 | 16 | 1.8543 |
Framework versions
- PEFT 0.9.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.17.1
- Tokenizers 0.15.0
- Downloads last month
- 0
Model tree for jspr/bts_mistral_7b_v3_32k_LoRA
Base model
mistralai/Mistral-7B-v0.1