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

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./Mistral_FFT

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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: 100
evals_per_epoch: 4
eval_table_size:
eval_sample_packing: False
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:

Mistral_FFT

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: 1.2369

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: 3
total_train_batch_size: 3
total_eval_batch_size: 3
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.9016	0.03	1	1.1080
0.8288	0.25	8	0.8722
1.0797	0.5	16	0.9858
1.036	0.75	24	1.1281
1.4318	1.0	32	1.2369

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.2+cu118
Datasets 2.17.0
Tokenizers 0.15.0

joseagmz/Mistral_FFT

Mistral_FFT

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

joseagmz/
Mistral_FFT