---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-32B
tags:
- generated_from_trainer
datasets:
- datasets/Sugarquill10k_Clean.jsonl
- datasets/Mixed-Novels-Completions.jsonl
- datasets/Mixed-Novels-Completions-2.jsonl
- datasets/recursal-scp-8k-filtered-4k.jsonl
- datasets/disco-chat.json
model-index:
- name: marigold-exp-pretrain
  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: `0.8.0.dev0`
```yaml
base_model: Qwen/Qwen2.5-32B
model_type: AutoModelForCausalLM

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: chatml
datasets:
  # Continued pretrain: novels, short stories
  - path: datasets/Sugarquill10k_Clean.jsonl
    type: completion
  - path: datasets/Mixed-Novels-Completions.jsonl
    type: completion
  - path: datasets/Mixed-Novels-Completions-2.jsonl
    type: completion
  - path: datasets/recursal-scp-8k-filtered-4k.jsonl
    type: completion
  - path: datasets/disco-chat.json
    type: completion

shuffle_merged_datasets: true

special_tokens:
  eos_token: "<|im_end|>"

dataset_prepared_path: pretrain_run_prepared
val_set_size: 0.02
output_dir: ./marigold-exp-pretrain

sequence_len: 10240
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

micro_batch_size: 2
gradient_accumulation_steps: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: rex
learning_rate: 1.5e-5
warmup_ratio: 0.05
cosine_min_lr_ratio: 0.1

weight_decay: 0.01
max_grad_norm: 2

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

gradient_checkpointing: unsloth
gradient_checkpointing_kwargs:
  use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 256

saves_per_epoch: 4
save_total_limit: 12

debug:

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

deepspeed: deepspeed_configs/zero3_bf16.json

wandb_project: Qwen2.5-32B-Marigold-v2-exp
wandb_entity:
wandb_name: Marigold-v2-exp-pretrain
```

</details><br>

# marigold-exp-pretrain

This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the datasets/Sugarquill10k_Clean.jsonl, the datasets/Mixed-Novels-Completions.jsonl, the datasets/Mixed-Novels-Completions-2.jsonl, the datasets/recursal-scp-8k-filtered-4k.jsonl and the datasets/disco-chat.json datasets.
It achieves the following results on the evaluation set:
- Loss: 2.2462

## 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: 1.5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Use paged_adamw_8bit 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: 15
- num_epochs: 2.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.2936        | 0.0065 | 1    | 2.3129          |
| 2.2657        | 0.2532 | 39   | 2.2685          |
| 2.1967        | 0.5065 | 78   | 2.2528          |
| 2.1965        | 0.7597 | 117  | 2.2450          |
| 2.0824        | 1.0130 | 156  | 2.2430          |
| 2.0373        | 1.2662 | 195  | 2.2516          |
| 2.055         | 1.5195 | 234  | 2.2480          |
| 2.1127        | 1.7727 | 273  | 2.2462          |


### Framework versions

- Transformers 4.50.0
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1