secretmodel-indevelopment

<!-- 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: 0.13.1

base_model: MuXodious/GLM-4.7-Flash-impotent-heresy # Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

#load_in_4bit: true

pretraining_dataset:
  - path: Guilherme34/Dataset-for-updating-llm-to-be-aware-of-the-situation
    type: pretrain
    text_column: text
dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./outputs/qlora-out
save_steps: 45
adapter: lora
lora_model_dir:

sequence_len: 1024
sample_packing: true
eval_sample_packing: true


lora_r: 24
lora_alpha: 48
lora_dropout: 0.05
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
#num_epochs: 2
max_steps: 496
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.0002

bf16: true
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_ratio: 0.1
evals_per_epoch: 1
#saves_per_epoch: 1
weight_decay: 0.0

weight_decay: 0.0
fsdp:
  - full_shard
  - auto_wrap
fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: Glm4MoeLiteDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
special_tokens:
  pad_token: <|endoftext|>

</details><br>

outputs/qlora-out

This model is a fine-tuned version of MuXodious/GLM-4.7-Flash-impotent-heresy on an unknown 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: 0.0002
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 2
• total_eval_batch_size: 2
• 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: cosine
• training_steps: 496

Training results

Framework versions

• PEFT 0.18.1
• Transformers 5.0.0rc3
• Pytorch 2.10.0+cu130
• Datasets 4.5.0
• Tokenizers 0.22.2