140 lines
3.8 KiB
Markdown
140 lines
3.8 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
base_model: Qwen/Qwen3-8B
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
datasets:
|
||
|
|
- laion/CoderForge-Preview-v3-316
|
||
|
|
model-index:
|
||
|
|
- name: e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B
|
||
|
|
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: `0.16.0.dev0`
|
||
|
|
```yaml
|
||
|
|
# CoderForge v3 axolotl config template.
|
||
|
|
# Consumes the pre-tokenized laion/CoderForge-Preview-v3-<SIZE> datasets.
|
||
|
|
# Axolotl auto-detects pre-tokenized via input_ids + attention_mask + labels
|
||
|
|
# (_is_dataset_already_tokenized) and skips chat_template rendering entirely.
|
||
|
|
# Fill 316 via sed-substitution.
|
||
|
|
|
||
|
|
base_model: Qwen/Qwen3-8B
|
||
|
|
deepspeed: /e/scratch/jureap59/feuer1/code/axolotl/deepspeed_configs/zero3_bf16.json
|
||
|
|
|
||
|
|
load_in_8bit: false
|
||
|
|
load_in_4bit: false
|
||
|
|
|
||
|
|
# plugins disabled 2026-04-22: CCE + bf16 + flash-attn on aarch64/torch2.9 caused
|
||
|
|
# gradient explosion (grad_norm 9.8e+11) and loss -> 0 within first 3-7 steps.
|
||
|
|
# plugins:
|
||
|
|
# - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
||
|
|
|
||
|
|
# chat_template still set so tokenizer can be loaded, even though axolotl
|
||
|
|
# bypasses template rendering for pre-tokenized data.
|
||
|
|
chat_template: chatml
|
||
|
|
datasets:
|
||
|
|
- path: laion/CoderForge-Preview-v3-316
|
||
|
|
# No `type:` specified — axolotl's _is_dataset_already_tokenized() fires
|
||
|
|
# early and returns the dataset as-is.
|
||
|
|
ds_type: parquet
|
||
|
|
|
||
|
|
dataset_prepared_path: /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/cf-v3-316
|
||
|
|
output_dir: /e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B
|
||
|
|
# hub_model_id: laion/CoderForge-Preview-v3-316-axolotl__Qwen3-8B
|
||
|
|
# hub_strategy: end
|
||
|
|
|
||
|
|
# Upstream pre-tokenized sequences can exceed 80k tokens; matches Sera v3 truncation.
|
||
|
|
sequence_len: 32768
|
||
|
|
|
||
|
|
wandb_project:
|
||
|
|
wandb_entity:
|
||
|
|
wandb_watch:
|
||
|
|
wandb_name: cf-v3-316-axolotl__Qwen3-8B
|
||
|
|
wandb_log_model:
|
||
|
|
|
||
|
|
# Matches upstream SERA config's optimization hparams for apples-to-apples.
|
||
|
|
gradient_accumulation_steps: 8
|
||
|
|
micro_batch_size: 1
|
||
|
|
num_epochs: 3
|
||
|
|
optimizer: adamw_torch
|
||
|
|
lr_scheduler: cosine
|
||
|
|
learning_rate: 1e-5
|
||
|
|
adam_beta1: 0.9
|
||
|
|
adam_beta2: 0.95
|
||
|
|
|
||
|
|
bf16: auto
|
||
|
|
tf32: false
|
||
|
|
|
||
|
|
gradient_checkpointing: true
|
||
|
|
activation_offloading: true
|
||
|
|
resume_from_checkpoint:
|
||
|
|
logging_steps: 1
|
||
|
|
flash_attention: true
|
||
|
|
|
||
|
|
loss_watchdog_threshold: 5.0
|
||
|
|
loss_watchdog_patience: 3
|
||
|
|
|
||
|
|
warmup_ratio: 0.1875
|
||
|
|
evals_per_epoch: 0
|
||
|
|
save_strategy: epoch
|
||
|
|
|
||
|
|
weight_decay: 0.01
|
||
|
|
max_grad_norm: 1.0
|
||
|
|
special_tokens:
|
||
|
|
|
||
|
|
```
|
||
|
|
|
||
|
|
</details><br>
|
||
|
|
|
||
|
|
# e/data1/datasets/playground/ot-baf/checkpoints/cf-v3-316-axolotl__Qwen3-8B
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the laion/CoderForge-Preview-v3-316 dataset.
|
||
|
|
|
||
|
|
## 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: 4
|
||
|
|
- gradient_accumulation_steps: 8
|
||
|
|
- total_train_batch_size: 32
|
||
|
|
- total_eval_batch_size: 4
|
||
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||
|
|
- lr_scheduler_type: cosine
|
||
|
|
- lr_scheduler_warmup_steps: 2
|
||
|
|
- training_steps: 9
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 5.5.0
|
||
|
|
- Pytorch 2.9.1+cu130
|
||
|
|
- Datasets 4.5.0
|
||
|
|
- Tokenizers 0.22.2
|