|
--- |
|
library_name: peft |
|
license: apache-2.0 |
|
base_model: berkeley-nest/Starling-LM-7B-alpha |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
model-index: |
|
- name: 8bbdc04b-65eb-4624-b7e7-667fcf55e4c0 |
|
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.1` |
|
```yaml |
|
adapter: lora |
|
base_model: berkeley-nest/Starling-LM-7B-alpha |
|
bf16: auto |
|
chat_template: llama3 |
|
dataset_prepared_path: null |
|
datasets: |
|
- data_files: |
|
- 6048e49854cb2d5a_train_data.json |
|
ds_type: json |
|
format: custom |
|
path: /workspace/input_data/6048e49854cb2d5a_train_data.json |
|
type: |
|
field_instruction: question |
|
field_output: risposta_1 |
|
format: '{instruction}' |
|
no_input_format: '{instruction}' |
|
system_format: '{system}' |
|
system_prompt: '' |
|
debug: null |
|
deepspeed: null |
|
device_map: auto |
|
do_eval: true |
|
early_stopping_patience: 3 |
|
eval_batch_size: 4 |
|
eval_max_new_tokens: 128 |
|
eval_steps: 150 |
|
eval_table_size: null |
|
evals_per_epoch: null |
|
flash_attention: true |
|
fp16: false |
|
fsdp: null |
|
fsdp_config: null |
|
gradient_accumulation_steps: 4 |
|
gradient_checkpointing: true |
|
group_by_length: true |
|
hub_model_id: brixeus/8bbdc04b-65eb-4624-b7e7-667fcf55e4c0 |
|
hub_repo: null |
|
hub_strategy: end |
|
hub_token: null |
|
learning_rate: 0.0002 |
|
load_in_4bit: false |
|
load_in_8bit: false |
|
local_rank: 0 |
|
logging_steps: 10 |
|
lora_alpha: 32 |
|
lora_dropout: 0.05 |
|
lora_fan_in_fan_out: null |
|
lora_model_dir: null |
|
lora_r: 16 |
|
lora_target_linear: true |
|
lr_scheduler: constant |
|
max_grad_norm: 1.0 |
|
max_memory: |
|
0: 75GB |
|
max_steps: 1350 |
|
micro_batch_size: 4 |
|
mlflow_experiment_name: /tmp/6048e49854cb2d5a_train_data.json |
|
model_type: AutoModelForCausalLM |
|
num_epochs: 10 |
|
optim_args: |
|
adam_beta1: 0.9 |
|
adam_beta2: 0.999 |
|
adam_epsilon: 1e-08 |
|
optimizer: adamw_bnb_8bit |
|
output_dir: miner_id_24 |
|
pad_to_sequence_len: true |
|
resume_from_checkpoint: null |
|
s2_attention: null |
|
sample_packing: false |
|
save_steps: 150 |
|
saves_per_epoch: null |
|
sequence_len: 512 |
|
strict: false |
|
tf32: true |
|
tokenizer_type: AutoTokenizer |
|
train_on_inputs: false |
|
trust_remote_code: true |
|
val_set_size: 0.05 |
|
wandb_entity: acopia-grant |
|
wandb_mode: online |
|
wandb_name: 62f85a5e-425f-4d9f-b1fc-8243f1d183bc |
|
wandb_project: Gradients-On-60 |
|
wandb_run: your_name |
|
wandb_runid: 62f85a5e-425f-4d9f-b1fc-8243f1d183bc |
|
warmup_steps: 50 |
|
weight_decay: 0.0 |
|
xformers_attention: null |
|
|
|
``` |
|
|
|
</details><br> |
|
|
|
# 8bbdc04b-65eb-4624-b7e7-667fcf55e4c0 |
|
|
|
This model is a fine-tuned version of [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7578 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_steps: 50 |
|
- training_steps: 1350 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| No log | 0.0009 | 1 | 0.8906 | |
|
| 3.3553 | 0.1346 | 150 | 0.7584 | |
|
| 3.0848 | 0.2692 | 300 | 0.7462 | |
|
| 3.2953 | 0.4038 | 450 | 0.7363 | |
|
| 3.152 | 0.5384 | 600 | 0.7344 | |
|
| 3.2696 | 0.6729 | 750 | 0.7295 | |
|
| 3.342 | 0.8075 | 900 | 0.7277 | |
|
| 3.1095 | 0.9421 | 1050 | 0.7241 | |
|
| 1.9505 | 1.0767 | 1200 | 0.7440 | |
|
| 1.9207 | 1.2113 | 1350 | 0.7578 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.46.0 |
|
- Pytorch 2.5.0+cu124 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.1 |
