PygTesting/sum_qlora_1epoch

See axolotl config

axolotl version: 0.4.1

base_model: mistralai/Mistral-Nemo-Base-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

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

adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

datasets:
  - path: /home/austin/disk1/summaries_fixed.jsonl
    type: sharegpt
dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ./qlora_outputs_1ep

sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project: summarization-qlora
wandb_entity:
wandb_watch:
wandb_name: actual_run1
wandb_log_model:
 
 #unsloth_cross_entropy_loss: true

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention: false
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 25
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: ./deepspeed_configs/zero2.json
weight_decay: 0.0
fsdp:
  #  - full_shard
  #  - auto_wrap
fsdp_config:
  #  fsdp_limit_all_gathers: true
  #  fsdp_activation_checkpointing: true
  #  fsdp_sync_module_states: true
  #  fsdp_offload_params: false
  #  fsdp_use_orig_params: false
  #  fsdp_cpu_ram_efficient_loading: false
  #  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer
  #  fsdp_state_dict_type: FULL_STATE_DICT
  #  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
special_tokens:
  pad_token: </s>

qlora_outputs_1ep

This model is a fine-tuned version of mistralai/Mistral-Nemo-Base-2407 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1865

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: 4
• total_train_batch_size: 4
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 25
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.0177	0.0014	1	1.6514
1.623	0.2507	177	1.2010
1.4373	0.5014	354	1.1926
1.6839	0.7521	531	1.1865

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1