See axolotl config

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: false
strict: false

chat_template: chatml
datasets:
  - path: data/merged_all.json
    ds_type: json
    type: alpaca
    conversation: chatml

  - path: data/capybara_sharegpt.json
    ds_type: json
    type: sharegpt
    conversation: chatml

  - path: data/synthia-v1.3_sharegpt_12500.json
    ds_type: json
    type: sharegpt
    conversation: chatml  

dataset_prepared_path: last_run_prepared
val_set_size: 0.005
output_dir: ./Einstein-v3-model

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project: huggingface
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
hub_model_id: Weyaxi/Einstein-v3-7B

save_safetensors: true

gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4  
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 2
debug:

deepspeed: zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "<|im_end|>"
  unk_token: "<unk>"
tokens:
  - "<|im_start|>"

Einstein-v3-7B

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: 0.5059

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• total_eval_batch_size: 8
• 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
1.038	0.0	1	1.1250
0.5254	0.25	107	0.5754
0.5144	0.5	214	0.5360
0.483	0.75	321	0.5118
0.4674	1.0	428	0.5059

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.2+cu118
• Datasets 2.16.1
• Tokenizers 0.15.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	64.09
AI2 Reasoning Challenge (25-Shot)	62.29
HellaSwag (10-Shot)	83.01
MMLU (5-Shot)	63.32
TruthfulQA (0-shot)	51.18
Winogrande (5-shot)	79.95
GSM8k (5-shot)	44.81