AXOLOTL_NOTES.md

---
library_name: transformers
tags:
- generated_from_trainer
datasets:
- /home/athuser/modelC_train/sft_modelC.jsonl
model-index:
- name: models/modelC_out/70B_fft_e1
  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: `0.12.2`
```yaml
# Model C anchor run: Llama-3.1-70B FFT on the assembled keeper set.
# Derived from /models/axolot/llama3_70b_fsdp.yaml (the out_FFT_E precedent);
# dataset swapped to Model C keepers in completion format (full-doc LM loss,
# both speakers, 15% header dropout baked into the jsonl by export_sft.py).
base_model: /models/Llama-3.1-70B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
datasets:
  - path: /home/athuser/modelC_train/sft_modelC.jsonl
    type: completion
    field: text
dataset_prepared_path: /home/athuser/modelC_train/last_run_prepared
val_set_size: 0.02
output_dir: /models/modelC_out/70B_fft_e1
sequence_len: 4096
sample_packing: true
tf32: true
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch_fused
lr_scheduler: constant_with_warmup
learning_rate: 2.0e-05
bf16: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
warmup_ratio: 0.03
evals_per_epoch: 4
saves_per_epoch: 1
save_only_model: true
weight_decay: 0.0
ddp_backend: nccl
fsdp_version: 2
fsdp_config:
  offload_params: false
  cpu_ram_efficient_loading: true
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: LlamaDecoderLayer
  state_dict_type: FULL_STATE_DICT
  reshard_after_forward: true
  activation_checkpointing: true
special_tokens:
  pad_token: <|end_of_text|>

```

</details><br>

# models/modelC_out/70B_fft_e1

This model was trained from scratch on the /home/athuser/modelC_train/sft_modelC.jsonl dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4970
- Memory/max Mem Active(gib): 89.15
- Memory/max Mem Allocated(gib): 89.15
- Memory/device Mem Reserved(gib): 94.15

## 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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 3
- training_steps: 113

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Mem Active(gib) | Mem Allocated(gib) | Mem Reserved(gib) |
|:-------------:|:------:|:----:|:---------------:|:---------------:|:------------------:|:-----------------:|
| No log        | 0      | 0    | 1.7114          | 27.73           | 27.73              | 31.33             |
| 1.53          | 0.2549 | 29   | 1.5095          | 89.15           | 89.15              | 94.15             |
| 1.49          | 0.5099 | 58   | 1.5013          | 89.15           | 89.15              | 94.15             |
| 1.4778        | 0.7648 | 87   | 1.4970          | 89.15           | 89.15              | 94.15             |


### Framework versions

- Transformers 4.55.2
- Pytorch 2.7.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.2