Mistral-7B-wikipedia_ru_pruned-0.1_merged

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.4.0

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: true
strict: false

datasets:
  - path: ./datasets/ruwiki-pruned
    type: completion
    field: text
dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ./models/output

adapter: qlora
lora_model_dir:

sequence_len: 1024
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:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 11
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:
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch:
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

</details><br>

Mistral-7B-wikipedia_ru_pruned-0.1_merged

This model is a merge of WlappaAI/Mistral-7B-v0.1-wikipedia_ru_pruned-0.1 together with mistralai/Mistral-7B-v0.1. It's trained on modified danasone/wikipedia_ru dataset. It achieves the following results on the evaluation set:

• Loss: 1.1876

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 11
• eval_batch_size: 11
• seed: 42
• 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

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0.dev0
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.0