axolotl version: 0.3.0
base_model: out/
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: cognitivecomputations/leet10k-alpaca
type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
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: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
out
This model was trained from scratch on the /leet10k-alpaca dataset. It achieves the following results on the evaluation set:
- Loss: 0.5907
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_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 |
|---|---|---|---|
| 0.7842 | 0.01 | 1 | 0.8053 |
| 0.5057 | 0.26 | 35 | 0.5694 |
| 0.3987 | 0.51 | 70 | 0.5752 |
| 0.2964 | 0.77 | 105 | 0.5907 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 56.57 |
| AI2 Reasoning Challenge (25-Shot) | 61.01 |
| HellaSwag (10-Shot) | 84.12 |
| MMLU (5-Shot) | 64.05 |
| TruthfulQA (0-shot) | 42.21 |
| Winogrande (5-shot) | 79.87 |
| GSM8k (5-shot) | 8.19 |