|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: sail/Sailor-7B |
|
model-index: |
|
- name: Sailor-7B-toba |
|
results: [] |
|
--- |
|
|
|
<!-- 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: `0.4.0` |
|
```yaml |
|
base_model: sail/Sailor-7B |
|
model_type: AutoModelForCausalLM |
|
tokenizer_type: AutoTokenizer |
|
is_mistral_derived_model: false |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
datasets: |
|
#we used a small dataset to teach the model function calling abilities |
|
- path: ./echonettobatrain.jsonl |
|
ds_type: json |
|
type: sharegpt |
|
|
|
dataset_prepared_path: last_run_function_call |
|
#0.05 |
|
val_set_size: 0.02 |
|
output_dir: ./Sailor-7B-toba |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
sequence_len: 8192 |
|
sample_packing: false |
|
eval_sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
# important, to get the same trainable parameters then for a qlora training with lora_r=32 and lora_alpha=16 you need to adjust the lora_r depending on the amount of filtered layers you want to use. With top_n=4 you would go for lora_r= 256 |
|
|
|
lora_r: 64 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_linear: false |
|
lora_fan_in_fan_out: |
|
lora_target_modules: |
|
- layers.0.self_attn.v_proj |
|
- layers.1.self_attn.v_proj |
|
- layers.2.self_attn.v_proj |
|
- layers.3.self_attn.v_proj |
|
- layers.4.self_attn.v_proj |
|
- layers.5.self_attn.v_proj |
|
- layers.6.self_attn.v_proj |
|
- layers.7.self_attn.v_proj |
|
- layers.8.self_attn.v_proj |
|
- layers.9.self_attn.v_proj |
|
- layers.10.self_attn.v_proj |
|
- layers.11.self_attn.v_proj |
|
- layers.12.self_attn.v_proj |
|
- layers.13.self_attn.v_proj |
|
- layers.14.self_attn.v_proj |
|
- layers.15.self_attn.v_proj |
|
- layers.16.self_attn.v_proj |
|
- layers.17.self_attn.v_proj |
|
- layers.18.self_attn.v_proj |
|
- layers.19.self_attn.v_proj |
|
- layers.20.self_attn.v_proj |
|
- layers.21.self_attn.v_proj |
|
- layers.22.self_attn.v_proj |
|
- layers.23.self_attn.v_proj |
|
- layers.24.self_attn.v_proj |
|
- layers.25.self_attn.v_proj |
|
- layers.26.self_attn.v_proj |
|
- layers.27.self_attn.v_proj |
|
- layers.28.self_attn.v_proj |
|
- layers.29.self_attn.v_proj |
|
- layers.30.self_attn.v_proj |
|
- layers.31.self_attn.v_proj |
|
- layers.0.self_attn.k_proj |
|
- layers.1.self_attn.k_proj |
|
- layers.2.self_attn.k_proj |
|
- layers.3.self_attn.k_proj |
|
- layers.4.self_attn.k_proj |
|
- layers.5.self_attn.k_proj |
|
- layers.6.self_attn.k_proj |
|
- layers.7.self_attn.k_proj |
|
- layers.8.self_attn.k_proj |
|
- layers.9.self_attn.k_proj |
|
- layers.10.self_attn.k_proj |
|
- layers.11.self_attn.k_proj |
|
- layers.12.self_attn.k_proj |
|
- layers.13.self_attn.k_proj |
|
- layers.14.self_attn.k_proj |
|
- layers.15.self_attn.k_proj |
|
- layers.16.self_attn.k_proj |
|
- layers.17.self_attn.k_proj |
|
- layers.18.self_attn.k_proj |
|
- layers.19.self_attn.k_proj |
|
- layers.20.self_attn.k_proj |
|
- layers.21.self_attn.k_proj |
|
- layers.22.self_attn.k_proj |
|
- layers.23.self_attn.k_proj |
|
- layers.24.self_attn.k_proj |
|
- layers.25.self_attn.k_proj |
|
- layers.26.self_attn.k_proj |
|
- layers.27.self_attn.k_proj |
|
- layers.28.self_attn.k_proj |
|
- layers.29.self_attn.k_proj |
|
- layers.30.self_attn.k_proj |
|
- layers.31.self_attn.k_proj |
|
- layers.0.self_attn.o_proj |
|
- layers.1.self_attn.o_proj |
|
- layers.2.self_attn.o_proj |
|
- layers.3.self_attn.o_proj |
|
- layers.4.self_attn.o_proj |
|
- layers.5.self_attn.o_proj |
|
- layers.6.self_attn.o_proj |
|
- layers.7.self_attn.o_proj |
|
- layers.8.self_attn.o_proj |
|
- layers.9.self_attn.o_proj |
|
- layers.10.self_attn.o_proj |
|
- layers.11.self_attn.o_proj |
|
- layers.12.self_attn.o_proj |
|
- layers.13.self_attn.o_proj |
|
- layers.14.self_attn.o_proj |
|
- layers.15.self_attn.o_proj |
|
- layers.16.self_attn.o_proj |
|
- layers.17.self_attn.o_proj |
|
- layers.18.self_attn.o_proj |
|
- layers.19.self_attn.o_proj |
|
- layers.20.self_attn.o_proj |
|
- layers.21.self_attn.o_proj |
|
- layers.22.self_attn.o_proj |
|
- layers.23.self_attn.o_proj |
|
- layers.24.self_attn.o_proj |
|
- layers.25.self_attn.o_proj |
|
- layers.26.self_attn.o_proj |
|
- layers.27.self_attn.o_proj |
|
- layers.28.self_attn.o_proj |
|
- layers.29.self_attn.o_proj |
|
- layers.30.self_attn.o_proj |
|
- layers.31.self_attn.o_proj |
|
- layers.0.self_attn.q_proj |
|
- layers.1.self_attn.q_proj |
|
- layers.2.self_attn.q_proj |
|
- layers.3.self_attn.q_proj |
|
- layers.4.self_attn.q_proj |
|
- layers.5.self_attn.q_proj |
|
- layers.6.self_attn.q_proj |
|
- layers.7.self_attn.q_proj |
|
- layers.8.self_attn.q_proj |
|
- layers.9.self_attn.q_proj |
|
- layers.10.self_attn.q_proj |
|
- layers.11.self_attn.q_proj |
|
- layers.12.self_attn.q_proj |
|
- layers.13.self_attn.q_proj |
|
- layers.14.self_attn.q_proj |
|
- layers.15.self_attn.q_proj |
|
- layers.16.self_attn.q_proj |
|
- layers.17.self_attn.q_proj |
|
- layers.18.self_attn.q_proj |
|
- layers.19.self_attn.q_proj |
|
- layers.20.self_attn.q_proj |
|
- layers.21.self_attn.q_proj |
|
- layers.22.self_attn.q_proj |
|
- layers.23.self_attn.q_proj |
|
- layers.24.self_attn.q_proj |
|
- layers.25.self_attn.q_proj |
|
- layers.26.self_attn.q_proj |
|
- layers.27.self_attn.q_proj |
|
- layers.28.self_attn.q_proj |
|
- layers.29.self_attn.q_proj |
|
- layers.30.self_attn.q_proj |
|
- layers.31.self_attn.q_proj |
|
- layers.0.mlp.down_proj |
|
- layers.1.mlp.down_proj |
|
- layers.2.mlp.down_proj |
|
- layers.3.mlp.down_proj |
|
- layers.4.mlp.down_proj |
|
- layers.5.mlp.down_proj |
|
- layers.6.mlp.down_proj |
|
- layers.7.mlp.down_proj |
|
- layers.8.mlp.down_proj |
|
- layers.9.mlp.down_proj |
|
- layers.10.mlp.down_proj |
|
- layers.11.mlp.down_proj |
|
- layers.12.mlp.down_proj |
|
- layers.13.mlp.down_proj |
|
- layers.14.mlp.down_proj |
|
- layers.15.mlp.down_proj |
|
- layers.16.mlp.down_proj |
|
- layers.17.mlp.down_proj |
|
- layers.18.mlp.down_proj |
|
- layers.19.mlp.down_proj |
|
- layers.20.mlp.down_proj |
|
- layers.21.mlp.down_proj |
|
- layers.22.mlp.down_proj |
|
- layers.23.mlp.down_proj |
|
- layers.24.mlp.down_proj |
|
- layers.25.mlp.down_proj |
|
- layers.26.mlp.down_proj |
|
- layers.27.mlp.down_proj |
|
- layers.28.mlp.down_proj |
|
- layers.29.mlp.down_proj |
|
- layers.30.mlp.down_proj |
|
- layers.31.mlp.down_proj |
|
- layers.0.mlp.up_proj |
|
- layers.1.mlp.up_proj |
|
- layers.2.mlp.up_proj |
|
- layers.3.mlp.up_proj |
|
- layers.4.mlp.up_proj |
|
- layers.5.mlp.up_proj |
|
- layers.6.mlp.up_proj |
|
- layers.7.mlp.up_proj |
|
- layers.8.mlp.up_proj |
|
- layers.9.mlp.up_proj |
|
- layers.10.mlp.up_proj |
|
- layers.11.mlp.up_proj |
|
- layers.12.mlp.up_proj |
|
- layers.13.mlp.up_proj |
|
- layers.14.mlp.up_proj |
|
- layers.15.mlp.up_proj |
|
- layers.16.mlp.up_proj |
|
- layers.17.mlp.up_proj |
|
- layers.18.mlp.up_proj |
|
- layers.19.mlp.up_proj |
|
- layers.20.mlp.up_proj |
|
- layers.21.mlp.up_proj |
|
- layers.22.mlp.up_proj |
|
- layers.23.mlp.up_proj |
|
- layers.24.mlp.up_proj |
|
- layers.25.mlp.up_proj |
|
- layers.26.mlp.up_proj |
|
- layers.27.mlp.up_proj |
|
- layers.28.mlp.up_proj |
|
- layers.29.mlp.up_proj |
|
- layers.30.mlp.up_proj |
|
- layers.31.mlp.up_proj |
|
# important: you need to unfreeze the lm.head |
|
- lm.head |
|
|
|
wandb_project: axolotl-sailor7b-toba |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_run_id: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 2 |
|
num_epochs: 3 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.00025 |
|
|
|
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: 100 |
|
eval_steps: 0.2 |
|
eval_table_size: |
|
eval_table_max_new_tokens: 128 |
|
save_steps: |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
``` |
|
|
|
</details><br> |
|
|
|
# Sailor-7B-toba |
|
|
|
This model is a fine-tuned version of [sail/Sailor-7B](https://huggingface.co/sail/Sailor-7B) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3876 |
|
|
|
## 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: 0.00025 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.0998 | 0.0 | 1 | 5.1501 | |
|
| 1.3477 | 0.6 | 622 | 1.6304 | |
|
| 1.268 | 1.2 | 1244 | 1.4755 | |
|
| 0.8714 | 1.8 | 1866 | 1.2799 | |
|
| 0.4408 | 2.4 | 2488 | 1.3876 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.1.dev0 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.0 |
