metadata

license: apache-2.0
library_name: peft
tags:
  - axolotl
  - generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
  - name: mistral-tenglish-april5_2
    results: []

See axolotl config

axolotl version: 0.4.0

base_model: mistralai/Mistral-7B-v0.1
base_model_config: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
 
load_in_8bit: true
load_in_4bit: false

bf16: true
fp16: false
tf32: false

bfloat16: true

datasets:
  - path: indiehackers/telugu_romanized_2048_mistral
    type: completion
    field: text

#dataset_prepared_path: ./dataset_tt23

hub_model_id: indiehackers/mistral-tenglish-april5_2
hf_use_auth_token: true 
val_set_size: 0.0

sequence_len: 2048
pad_to_sequence_len: true
sample_packing: true
# eval_sample_packing: false

adapter: lora
lora_r: 128
lora_alpha: 256
lora_dropout: 0.05
lora_target_linear: true

wandb_project: mistral-tenglish
wandb_entity: team-nik
#wandb_log_model: end

output_dir: ./mistral-tenglish-out

# Training hyperparameters
gradient_accumulation_steps: 2
micro_batch_size: 7
warmup_steps: 50
learning_rate: 0.00002
logging_steps: 1
evals_per_epoch: 
save_strategy: steps
save_steps: 100
save_total_limit: 10
num_epochs: 1
#max_steps: 162945
# eval_table_size:
# eval_max_new_tokens: 128

train_on_inputs: false
group_by_length: false

gradient_checkpointing: true
early_stopping_patience:

lr_scheduler: linear

optimizer: adamw_bnb_8bit

weight_decay: 0.01

xformers_attention:
flash_attention: true
resume_from_checkpoint:
auto_resume_from_checkpoints: true

local_rank:

fsdp:
fsdp_config:

deepspeed:

debug:

strict: false

# load_best_model_at_end: True
max_grad_norm: 0.3

mistral-tenglish-april5_2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.

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: 2e-05
train_batch_size: 7
eval_batch_size: 7
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 56
total_eval_batch_size: 28
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 1

Training results

Framework versions

PEFT 0.10.0
Transformers 4.40.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.18.0
Tokenizers 0.15.0