|
|
--- |
|
|
library_name: peft |
|
|
license: gemma |
|
|
base_model: google/gemma-2-2b-it |
|
|
tags: |
|
|
- axolotl |
|
|
- base_model:adapter:google/gemma-2-2b-it |
|
|
- lora |
|
|
- transformers |
|
|
datasets: |
|
|
- AiAF/conversations |
|
|
pipeline_tag: text-generation |
|
|
model-index: |
|
|
- name: rp-2b |
|
|
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: `0.13.0.dev0` |
|
|
```yaml |
|
|
# 1. Base Model & Tokenizer |
|
|
base_model: google/gemma-2-2b-it |
|
|
model_type: AutoModelForCausalLM # Corrected from 'type_of_model' for axolotl |
|
|
tokenizer_type: AutoTokenizer |
|
|
hub_model_id: AiAF/rp-2b # New model ID for this finetune |
|
|
hub_strategy: checkpoint |
|
|
|
|
|
# 2. LoRA / QLoRA Configuration |
|
|
load_in_4bit: true |
|
|
adapter: qlora |
|
|
lora_r: 64 |
|
|
lora_alpha: 128 |
|
|
lora_dropout: 0.05 |
|
|
lora_target_linear: true |
|
|
|
|
|
# 3. Dataset Configuration (TRAIN = streamed) |
|
|
streaming: true |
|
|
streaming_multipack_buffer_size: 10000 |
|
|
sample_packing: true |
|
|
datasets: |
|
|
- path: AiAF/conversations |
|
|
data_files: conversations_V3.jsonl |
|
|
# revision: |
|
|
type: chat_template |
|
|
split: train |
|
|
field_messages: conversations |
|
|
message_property_mappings: |
|
|
role: from |
|
|
content: value |
|
|
chat_template: jinja |
|
|
chat_template_jinja: | |
|
|
{{ bos_token }} |
|
|
{% for m in messages %} |
|
|
{% set role = 'model' if m['role']=='assistant' else 'user' %} |
|
|
{{ '<start_of_turn>' + role + '\n' + m['content'] | trim + '<end_of_turn>\n' }} |
|
|
{% endfor %} |
|
|
{% if add_generation_prompt %} |
|
|
{{ '<start_of_turn>model\n' }} |
|
|
{% endif %} |
|
|
|
|
|
# chat_template_jinja: | |
|
|
# {{ bos_token }} |
|
|
# {% set last = None %} |
|
|
# {% for m in messages %} |
|
|
# {% set raw_role = 'model' if m['role']=='assistant' else m['role'] %} |
|
|
# {% set role = 'user' if raw_role=='system' else raw_role %} |
|
|
# {% if role == last and role == 'user' %} |
|
|
# {{ m['content'] | trim }} |
|
|
# {% else %} |
|
|
# {{ '<start_of_turn>' + role + '\n' + m['content'] | trim + '<end_of_turn>\n' }} |
|
|
# {% endif %} |
|
|
# {% set last = role %} |
|
|
# {% endfor %} |
|
|
# {% if add_generation_prompt %} |
|
|
# {{ '<start_of_turn>model\n' }} |
|
|
# {% endif %} |
|
|
roles_to_train: ["assistant"] |
|
|
train_on_eos: "turn" |
|
|
# Use a fixed (non-streamed) eval file with the same schema/Jinja |
|
|
test_datasets: |
|
|
- path: . |
|
|
name: json |
|
|
type: chat_template |
|
|
data_files: eval-datasets/shuf-1000_conversations_V2.jsonl # small, representative eval slice |
|
|
split: train |
|
|
field_messages: conversations |
|
|
message_property_mappings: |
|
|
role: from |
|
|
content: value |
|
|
chat_template: jinja |
|
|
chat_template_jinja: | |
|
|
{{ bos_token }} |
|
|
{% for m in messages %} |
|
|
{% set role = 'model' if m['role']=='assistant' else 'user' %} |
|
|
{{ '<start_of_turn>' + role + '\n' + m['content'] | trim + '<end_of_turn>\n' }} |
|
|
{% endfor %} |
|
|
{% if add_generation_prompt %} |
|
|
{{ '<start_of_turn>model\n' }} |
|
|
{% endif %} |
|
|
# chat_template_jinja: | |
|
|
# {{ bos_token }} |
|
|
# {% set last = None %} |
|
|
# {% for m in messages %} |
|
|
# {% set raw_role = 'model' if m['role']=='assistant' else m['role'] %} |
|
|
# {% set role = 'user' if raw_role=='system' else raw_role %} |
|
|
# {% if role == last and role == 'user' %} |
|
|
# {{ m['content'] | trim }} |
|
|
# {% else %} |
|
|
# {{ '<start_of_turn>' + role + '\n' + m['content'] | trim + '<end_of_turn>\n' }} |
|
|
# {% endif %} |
|
|
# {% set last = role %} |
|
|
# {% endfor %} |
|
|
# {% if add_generation_prompt %} |
|
|
# {{ '<start_of_turn>model\n' }} |
|
|
# {% endif %} |
|
|
roles_to_train: ["assistant"] |
|
|
|
|
|
# 4. Training Parameters |
|
|
sequence_len: 2048 |
|
|
sample_packing: true |
|
|
eval_sample_packing: true |
|
|
# val_set_size: 0.05 # remove for streaming |
|
|
# num_epochs: 10 # replace epochs with max_steps |
|
|
max_steps: 1000 # set your target steps |
|
|
dataset_prepared_path: last_run_prepared |
|
|
|
|
|
# 5. Saving and Evaluation Strategy (use steps with streaming) |
|
|
evaluation_strategy: steps |
|
|
save_strategy: steps |
|
|
eval_steps: 50 |
|
|
save_steps: 50 |
|
|
save_total_limit: 100 |
|
|
|
|
|
resume_from_checkpoint: |
|
|
|
|
|
# 6. Output & Logging |
|
|
output_dir: ./outputs/sft/gemma-2-2b-it-rp-sft-qlora |
|
|
|
|
|
wandb_project: "rp-sft" |
|
|
wandb_name: "gemma-2-2b-it-rp-sft-qlora" |
|
|
wandb_log_model: "false" |
|
|
wandb_run_id: "gemma-2-2b-it-rp-sft-qlora" |
|
|
|
|
|
# 7. Batching & Optimizer |
|
|
gradient_accumulation_steps: 4 |
|
|
micro_batch_size: 2 |
|
|
optimizer: adamw_bnb_8bit |
|
|
lr_scheduler: cosine |
|
|
learning_rate: 0.0002 |
|
|
weight_decay: 0.0 |
|
|
|
|
|
# 8. Hardware & Performance |
|
|
bf16: true |
|
|
#fp16: true |
|
|
tf32: true |
|
|
|
|
|
flash_attention: true |
|
|
gradient_checkpointing: true |
|
|
logging_steps: 1 |
|
|
|
|
|
# 9. Special Tokens |
|
|
eot_tokens: ["<end_of_turn>"] |
|
|
special_tokens: |
|
|
bos_token: "<bos>" |
|
|
eos_token: "<eos>" |
|
|
pad_token: "<pad>" |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# rp-2b |
|
|
|
|
|
This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the AiAF/conversations dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.2455 |
|
|
- Memory/max Active (gib): 7.78 |
|
|
- Memory/max Allocated (gib): 7.78 |
|
|
- Memory/device Reserved (gib): 17.79 |
|
|
|
|
|
## 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: 1 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 4 |
|
|
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 30 |
|
|
- training_steps: 1000 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Active (gib) | Allocated (gib) | Reserved (gib) | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------------:|:---------------:|:--------------:| |
|
|
| No log | 0 | 0 | 3.1654 | 7.61 | 7.61 | 8.66 | |
|
|
| 2.7377 | 0.05 | 50 | 2.5978 | 7.78 | 7.78 | 17.75 | |
|
|
| 2.3997 | 0.1 | 100 | 2.5592 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.6275 | 0.15 | 150 | 2.5410 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.8182 | 0.2 | 200 | 2.5224 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.4428 | 0.25 | 250 | 2.4962 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.6206 | 0.3 | 300 | 2.4672 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.4492 | 0.35 | 350 | 2.4435 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.2787 | 0.4 | 400 | 2.4185 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.541 | 0.45 | 450 | 2.3998 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.5542 | 0.5 | 500 | 2.3640 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.6825 | 0.55 | 550 | 2.3484 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.6304 | 0.6 | 600 | 2.3278 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.4854 | 0.65 | 650 | 2.3104 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.3788 | 0.7 | 700 | 2.2877 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.2126 | 0.75 | 750 | 2.2748 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.4695 | 0.8 | 800 | 2.2662 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.5086 | 0.85 | 850 | 2.2553 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.404 | 0.9 | 900 | 2.2489 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.4012 | 0.95 | 950 | 2.2460 | 7.78 | 7.78 | 17.79 | |
|
|
| 2.2586 | 1.0 | 1000 | 2.2455 | 7.78 | 7.78 | 17.79 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.17.1 |
|
|
- Transformers 4.57.0 |
|
|
- Pytorch 2.7.1+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.1 |
