|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: allenai/Olmo-3-1025-7B |
|
|
tags: |
|
|
- axolotl |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- dataset-tfs-mk-IMP-SOS-processed-olmo3-think.jsonl |
|
|
model-index: |
|
|
- name: O37BB |
|
|
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 |
|
|
# --- Base Model & Tokenizer Configuration --- |
|
|
base_model: allenai/Olmo-3-1025-7B |
|
|
trust_remote_code: true |
|
|
hub_model_id: Auditt/O37BB # Push the model to the Hugging Face Hub |
|
|
chat_template_jinja: /workspace/data/model-output/chat_template.jinja # Uses the template defined in tokenizer_config.json |
|
|
|
|
|
# --- Dataset Configuration --- |
|
|
# Assuming a standard conversation format (ShareGPT/ChatML style) |
|
|
datasets: |
|
|
- path: dataset-tfs-mk-IMP-SOS-processed-olmo3-think.jsonl |
|
|
type: chat_template |
|
|
field_messages: messages # The top-level key containing the list |
|
|
message_field_role: role # The key inside the list for 'user'/'assistant' |
|
|
message_field_content: content # The key inside the list for the actual text |
|
|
|
|
|
# 4. MAP YOUR ROLES |
|
|
# The keys (left) are what Axolotl expects. |
|
|
# The values (right) are what exist in your raw JSONL file. |
|
|
roles: |
|
|
user: ["user"] |
|
|
assistant: ["assistant"] |
|
|
system: ["system"] |
|
|
|
|
|
# 5. SUPERVISION |
|
|
# This ensures loss is calculated ONLY on the "assistant" turns. |
|
|
roles_to_train: ["assistant"] |
|
|
|
|
|
val_set_size: 0.1 # 10% Validation, 90% Training |
|
|
dataset_prepared_path: last_run_prepared |
|
|
|
|
|
# --- Training Strategy --- |
|
|
sequence_len: 60000 # Max sequence length |
|
|
sample_packing: true # Efficiently packs samples to fill sequence_len |
|
|
pad_to_sequence_len: true |
|
|
|
|
|
# Supervision Settings |
|
|
train_on_inputs: false # False = Mask User prompts (Supervise Assistant only) |
|
|
group_by_length: false # Usually false when sample_packing is true |
|
|
|
|
|
# --- Hyperparameters & Training Loop --- |
|
|
num_epochs: 2 |
|
|
micro_batch_size: 1 # Keep small due to 60k context |
|
|
gradient_accumulation_steps: 4 # Adjust based on desired global batch size |
|
|
learning_rate: 0.00001 |
|
|
optimizer: adamw_torch |
|
|
|
|
|
# --- Distributed Training & Memory --- |
|
|
context_parallel_size: 2 # Splits the 60k sequence across 2 GPUs |
|
|
gradient_checkpointing: true # Essential for 60k context |
|
|
flash_attention: true # Essential for speed/memory at this length |
|
|
|
|
|
# --- Logging & Evaluation --- |
|
|
logging_steps: 1 # Log training loss every step |
|
|
evals_per_epoch: 1 # Run eval 1 times per epoch (roughly) |
|
|
#eval_strategy: epoch |
|
|
#save_strategy: epoch # Save checkpoint at end of epoch |
|
|
#wandb_project: olmo3-finetune # Optional: Weights & Biases logging |
|
|
#wandb_entity: your-entity # Optional |
|
|
output_dir: /workspace/data/model-output-base |
|
|
|
|
|
# --- Precision --- |
|
|
bf16: true # Bfloat16 is recommended for OLMo |
|
|
fp16: false |
|
|
tf32: true |
|
|
|
|
|
tokens: # Add these to the tokenizer |
|
|
- "π²" |
|
|
- "πΎ" |
|
|
- "γ" |
|
|
- "π" |
|
|
- "β" |
|
|
- "π " |
|
|
- "π" |
|
|
- "πΈ" |
|
|
- "β§" |
|
|
- "β₯" |
|
|
- "π" |
|
|
- "π" |
|
|
- "β" |
|
|
- "π" |
|
|
- "β" |
|
|
- "π£" |
|
|
- "π" |
|
|
- "π" |
|
|
- "π" |
|
|
- "Ο" |
|
|
- "π" |
|
|
- "γ" |
|
|
- "π" |
|
|
- "π»" |
|
|
- "π" |
|
|
- "π³" |
|
|
- "β " |
|
|
- "π·" |
|
|
- "β€" |
|
|
- "π" |
|
|
- "π±" |
|
|
- "π" |
|
|
- "β¦" |
|
|
- "π" |
|
|
- "β" |
|
|
- "π" |
|
|
- "π°" |
|
|
- "Ξ΅" |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# O37BB |
|
|
|
|
|
This model is a fine-tuned version of [allenai/Olmo-3-1025-7B](https://huggingface.co/allenai/Olmo-3-1025-7B) on the dataset-tfs-mk-IMP-SOS-processed-olmo3-think.jsonl dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0019 |
|
|
- Memory/max Active (gib): 85.95 |
|
|
- Memory/max Allocated (gib): 82.72 |
|
|
- Memory/device Reserved (gib): 93.36 |
|
|
|
|
|
## 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: 1e-05 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 2 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 8 |
|
|
- total_eval_batch_size: 2 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 10 |
|
|
- training_steps: 348 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Active (gib) | Allocated (gib) | Reserved (gib) | |
|
|
|:-------------:|:------:|:----:|:---------------:|:------------:|:---------------:|:--------------:| |
|
|
| No log | 0 | 0 | 1.0680 | 58.72 | 55.5 | 65.44 | |
|
|
| 0.0647 | 0.9943 | 174 | 0.0021 | 85.95 | 82.72 | 106.04 | |
|
|
| 0.0296 | 1.9943 | 348 | 0.0019 | 85.95 | 82.72 | 93.36 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.57.0 |
|
|
- Pytorch 2.7.1+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.1 |
|
|
|
