See axolotl config
axolotl version: 0.4.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: ./data/tool_used_training.jsonl
type: sharegpt
- path: ./data/tool_not_used_training.jsonl
type: sharegpt
- path: ./data/no_tools_training.jsonl
type: sharegpt
dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ../../text-generation-webui/loras/mistral-instruct-better-formatting-v1
adapter: qlora
lora_model_dir:
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
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: function-call
wandb_name: mixtral-instruct-qlora-v1
wandb_log_model: end
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.001
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
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: 20
eval_steps: 0.1
save_steps: 0.1
eval_table_size:
eval_max_new_tokens: 256
# saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
text-generation-webui/loras/mistral-instruct-better-formatting-v1
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3566
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: 0.001
- 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=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.9252 | 0.0 | 1 | 0.9944 |
0.3953 | 0.1 | 27 | 0.3981 |
0.3662 | 0.21 | 54 | 0.3824 |
0.3383 | 0.31 | 81 | 0.3778 |
0.3484 | 0.41 | 108 | 0.3730 |
0.4098 | 0.52 | 135 | 0.3686 |
0.3728 | 0.62 | 162 | 0.3642 |
0.3274 | 0.72 | 189 | 0.3602 |
0.3579 | 0.83 | 216 | 0.3576 |
0.3293 | 0.93 | 243 | 0.3566 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.0
- Downloads last month
- 1
Unable to determine this model’s pipeline type. Check the
docs
.