---
library_name: transformers
license: llama3.1
base_model: meta-llama/Llama-3.1-8B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: Llama3.1-8B-relu-stage-2-dolma-v1_7-50B-4096
  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: `0.5.2`
```yaml
base_model: meta-llama/Llama-3.1-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: false
resize_token_embeddings_to_32x: false

flash_attention: true
xformers_attention:

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: skymizer/Llama3.1-base-tokenized-dolma-v1_7-50B
    train_on_split: train
    type: completion

test_datasets:
  - path: skymizer/Llama3.1-tokenized-dolma-v1_7-test
    split: test
    type: completion

is_preprocess: true
skip_prepare_dataset: true

dataset_prepared_path: /mnt/home/model-team/datasets/pretokenized/Llama3.1-8B-base-tokenized-dolma-v1_7_50B-4096 

hf_use_auth_token: true
output_dir: /mnt/home/model-team/models/Llama3.1-8B-relu-stage-2-dolma-50B-4096
resume_from_checkpoint:
auto_resume_from_checkpoints: true

sequence_len: 4096
sample_packing: true
sample_packing_group_size: 100000
sample_packing_bin_size: 200
pad_to_sequence_len: true

eval_sample_packing: false
# eval_causal_lm_metrics: ["perplexity"]

wandb_project: "sparse-tuning-cpt"
wandb_entity:
wandb_watch:
wandb_name: "Llama3.1-8B-relu-stage-1-dolma-50B-4096"
wandb_log_model:

# global batch size = 2 * 8 * 8 GPUs * 8 Nodes * 4096 = 4M
gradient_accumulation_steps: 8
micro_batch_size: 2
  # eval_batch_size: 2
num_epochs: 1
optimizer: adamw_torch
learning_rate: 0.000015
lr_scheduler: cosine
cosine_min_lr_ratio: 1.0 
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.95
adam_eps: 0.000001
max_grad_norm: 1.0

train_on_inputs: false
group_by_length: false
bf16: true
fp16:
tf32: false

hub_model_id: "skymizer/Llama3.1-8B-relu-stage-2-dolma-v1_7-50B-4096"

save_strategy: "steps"
save_steps: 500

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1

warmup_steps: 1
eval_steps: 500
eval_table_size:
debug:
deepspeed: /root/train/axolotl/deepspeed_configs/zero3_bf16.json
fsdp:
fsdp_config:
seed: 42

special_tokens:
  pad_token: "<|end_of_text|>"

```

</details><br>

# Llama3.1-8B-relu-stage-2-dolma-v1_7-50B-4096

This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co./meta-llama/Llama-3.1-8B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4342

## 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: 64
- gradient_accumulation_steps: 8
- total_train_batch_size: 1024
- total_eval_batch_size: 128
- 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
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 14.2348       | 0.0001 | 1     | 14.2931         |
| 2.9296        | 0.0414 | 500   | 3.0717          |
| 2.6209        | 0.0829 | 1000  | 2.7409          |
| 2.4945        | 0.1243 | 1500  | 2.6571          |
| 2.5314        | 0.1657 | 2000  | 2.6148          |
| 2.4494        | 0.2072 | 2500  | 2.5855          |
| 2.4257        | 0.2486 | 3000  | 2.5569          |
| 2.4346        | 0.2901 | 3500  | 2.5402          |
| 2.4243        | 0.3315 | 4000  | 2.5284          |
| 2.3699        | 0.3729 | 4500  | 2.5134          |
| 2.4072        | 0.4144 | 5000  | 2.5064          |
| 2.4064        | 0.4558 | 5500  | 2.4953          |
| 2.3683        | 0.4972 | 6000  | 2.4950          |
| 2.3811        | 0.5387 | 6500  | 2.4804          |
| 2.3494        | 0.5801 | 7000  | 2.4734          |
| 2.3444        | 0.6215 | 7500  | 2.4663          |
| 2.3578        | 0.6630 | 8000  | 2.4626          |
| 2.344         | 0.7044 | 8500  | 2.4557          |
| 2.3284        | 0.7458 | 9000  | 2.4529          |
| 2.3086        | 0.7873 | 9500  | 2.4488          |
| 2.321         | 0.8287 | 10000 | 2.4443          |
| 2.3339        | 0.8702 | 10500 | 2.4409          |
| 2.3236        | 0.9116 | 11000 | 2.4391          |
| 2.3404        | 0.9530 | 11500 | 2.4387          |
| 2.3103        | 0.9945 | 12000 | 2.4342          |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3