metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- generated_from_trainer
model-index:
- name: out
results: []
See axolotl config
axolotl version: 0.4.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: KolaGang/privacy_sumsum
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
output_dir: ./out
lisa_n_layers: 4
lisa_step_interval: 20
lisa_layers_attribute: model.layers
wandb_project: mistral_law
wandb_entity:
wandb_watch:
wandb_name: mistral_law
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 10
num_epochs: 1
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
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: 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:
out
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: 0.9301
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
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 160
- total_eval_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.4237 | 0.02 | 1 | 2.8640 |
0.9506 | 0.26 | 13 | 1.5696 |
0.5752 | 0.53 | 26 | 1.0073 |
0.5111 | 0.79 | 39 | 0.9301 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.1
- Datasets 2.18.0
- Tokenizers 0.15.0