CoolFace
Modelpublic

mfirth/l3t_agi_maybe_not_garbage

sourceHugging Facellama3.2updated 2y agoView on Hugging Face
0likes9downloads
Model Card

<!-- 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: 0.5.3.dev44+g5bef1906

yaml
base_model: meta-llama/Llama-3.2-3B-Instruct

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

datasets:
  - path: shuffled_output.json
    type: input_output
dataset_prepared_path: last_run_prepared
dataset_exact_deduplication: false

sequence_length: 131072
pad_to_sequence_len: true
    
output_dir: ./models/llama_wm_v3

wandb_project: agent-v0
wandb_name: llama-3b_wm_v3

train_on_inputs: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
optimizer: adamw_torch
learning_rate: 2e-5
xformers_attention:
flash_attention: true

logging_steps: 5

warmup_steps: 10
saves_per_epoch: 1
weight_decay: 0.0

deepspeed: axolotl/deepspeed_configs/zero3_bf16_cpuoffload_all.json

special_tokens:
  pad_token: <|end_of_text|>

</details><br>

models/llamawmv3

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the shuffled_output.json dataset.

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
  • —trainbatchsize: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —distributed_type: multi-GPU
  • —num_devices: 8
  • —gradientaccumulationsteps: 4
  • —totaltrainbatch_size: 128
  • —totalevalbatch_size: 32
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 10
  • —num_epochs: 1

Training results

Framework versions

  • —Transformers 4.47.0
  • —Pytorch 2.5.1+cu124
  • —Datasets 3.1.0
  • —Tokenizers 0.21.0