---
library_name: transformers
license: apache-2.0
base_model: GreenerPastures/Bald-Beaver-8B
tags:
- axolotl
- generated_from_trainer
datasets:
- NewEden/Joe-Games
model-index:
- name: Games8B
  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: `0.10.0.dev0`
```yaml
base_model: GreenerPastures/Bald-Beaver-8B

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: qwen3
datasets:
  - path: NewEden/Joe-Games
    type: completion

val_set_size: 0.05
output_dir: ./outputs/out
dataset_prepared_path: last_run_prepared
shuffle_merged_datasets: true

hub_model_id: hardlyworking/Games8B
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

sequence_len: 32768
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

wandb_project: Qwen8B
wandb_entity:
wandb_watch:
wandb_name: Qwen8B
wandb_log_model:

evals_per_epoch: 8
eval_table_size:
eval_max_new_tokens: 128

max_grad_norm: 1.0
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 1e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: offload
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
s2_attention:

deepspeed:

warmup_ratio: 0.05
saves_per_epoch: 1
debug:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
   pad_token:
```

</details><br>

# Games8B

This model is a fine-tuned version of [GreenerPastures/Bald-Beaver-8B](https://huggingface.co/GreenerPastures/Bald-Beaver-8B) on the NewEden/Joe-Games dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9796

## 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
- total_train_batch_size: 4
- total_eval_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: 13
- num_epochs: 2.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.6433        | 0.0074 | 1    | 2.0240          |
| 1.5696        | 0.125  | 17   | 2.0077          |
| 2.5862        | 0.25   | 34   | 1.9995          |
| 1.9231        | 0.375  | 51   | 1.9944          |
| 1.9655        | 0.5    | 68   | 1.9908          |
| 1.6909        | 0.625  | 85   | 1.9880          |
| 1.8634        | 0.75   | 102  | 1.9857          |
| 1.6684        | 0.875  | 119  | 1.9832          |
| 1.8727        | 1.0    | 136  | 1.9816          |
| 1.542         | 1.125  | 153  | 1.9806          |
| 2.5733        | 1.25   | 170  | 1.9801          |
| 1.8934        | 1.375  | 187  | 1.9797          |
| 1.9386        | 1.5    | 204  | 1.9796          |
| 1.6764        | 1.625  | 221  | 1.9796          |
| 1.8524        | 1.75   | 238  | 1.9796          |
| 1.661         | 1.875  | 255  | 1.9795          |
| 1.8697        | 2.0    | 272  | 1.9796          |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1