|
--- |
|
tags: |
|
- generated_from_trainer |
|
base_model: Locutusque/TinyMistral-248M-v2 |
|
model-index: |
|
- name: TinyMistral-v2-Test1/ |
|
results: [] |
|
datasets: |
|
- JeanKaddour/minipile |
|
- epfl-llm/guidelines |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.3.0` |
|
```yaml |
|
base_model: Locutusque/TinyMistral-248M-v2 |
|
model_type: MistralForCausalLM |
|
is_mistral_derived_model: true |
|
|
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
dataset_processes: 20 |
|
|
|
datasets: |
|
- path: epfl-llm/guidelines |
|
type: completion |
|
field: clean_text |
|
- path: JeanKaddour/minipile |
|
type: completion |
|
field: text |
|
|
|
dataset_prepared_path: TinyMistral-FFT-data |
|
val_set_size: 0.001 |
|
output_dir: ./TinyMistral-FFT |
|
|
|
sequence_len: 2048 |
|
sample_packing: false |
|
pad_to_sequence_len: true |
|
|
|
adapter: |
|
lora_model_dir: |
|
lora_r: |
|
lora_alpha: |
|
lora_dropout: |
|
lora_target_linear: |
|
lora_fan_in_fan_out: |
|
|
|
# wandb configuration |
|
wandb_project: TinyMistral-FFT |
|
wandb_watch: |
|
wandb_run_id: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 8 |
|
micro_batch_size: 1 |
|
num_epochs: 1 |
|
optimizer: paged_adamw_32bit |
|
lr_scheduler: constant |
|
cosine_min_lr_ratio: |
|
|
|
learning_rate: 0.00005 |
|
|
|
train_on_inputs: true |
|
group_by_length: false |
|
bf16: false |
|
fp16: false |
|
tf32: true |
|
|
|
gradient_checkpointing: false |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
auto_resume_from_checkpoints: false |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: false |
|
flash_attn_cross_entropy: false |
|
flash_attn_rms_norm: true |
|
flash_attn_fuse_qkv: false |
|
flash_attn_fuse_mlp: true |
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 100 |
|
# eval_steps: 10 |
|
eval_table_size: |
|
saves_per_epoch: 50 |
|
debug: |
|
deepspeed: #deepspeed/zero2.json # multi-gpu only |
|
weight_decay: 0 |
|
|
|
# tokens: |
|
|
|
|
|
special_tokens: |
|
bos_token: "<|bos|>" |
|
eos_token: "<|endoftext|>" |
|
unk_token: "<unk>" |
|
``` |
|
|
|
</details><br> |
|
|
|
# TinyMistral-StructureEvaluator |
|
|
|
This model was further trained on the epfl-llm/guidelines and JeanKaddour/minipile datasets. |
|
|
|
## 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-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- training_steps: 39460 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
