timarni/base_test_set_9
07
<!-- 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"/> <details><summary>See axolotl config</summary>
axolotl version: 0.9.2
base_model: Qwen/Qwen3-0.6B-Base
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name
plugins:
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
strict: false
chat_template: qwen3
datasets:
- path: timarni/MNLP_M2_mcqa_dataset
type: alpaca
split: train
shuffle_merged_datasets: true
val_set_size: 0.1
output_dir: ./outputs/base_test_set
dataset_prepared_path: last_run_prepared
sequence_len: 4096 #2048
sample_packing: true # was true -> need to check if it actually learns on the samples or not (better understand te hyperparam and event. install axolotl to debug)
eval_sample_packing: false
pad_to_sequence_len: true
# train_on_inputs: true # NEW
# group_by_length: false NEW?
# To be sure that no LORA is done
adapter: null
lora: false
merge_lora: false
wandb_project: mnlp_project
wandb_entity: tim-arni
wandb_watch:
wandb_name: base_test_set
wandb_log_model:
gradient_accumulation_steps: 16 # 2
micro_batch_size: 2 # 1
num_epochs: 25
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00005 # 0.00005
# cosine_min_lr_ratio: 0.1
warmup_ratio: 0.05
weight_decay: 0.01
bf16: auto
tf32: true
gradient_checkpointing: offload
gradient_checkpointing_kwargs:
use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
gradient_clipping: 1.0 # or max_grad_norm?
flash_attention: true
evals_per_epoch: 4
saves_per_epoch: 2
save_total_limit: 25
special_tokens:
</details><br>
outputs/basetestset
This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base on the timarni/MNLPM2mcqa_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.2652
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: 5e-05
- trainbatchsize: 2
- evalbatchsize: 2
- seed: 42
- gradientaccumulationsteps: 16
- totaltrainbatch_size: 32
- optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: cosine
- lrschedulerwarmup_steps: 2
- num_epochs: 25.0
Training results
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.5.1
- Tokenizers 0.21.1