See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: heegyu/WizardVicuna-open-llama-3b-v2
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- chat_template: chatml
  data_files:
  - e41fb6a21c7e2cd8_train_data.json
  ds_type: json
  field_messages: conversations
  message_field_content: value
  message_field_role: from
  message_property_mappings:
    content: value
    role: from
  path: /workspace/input_data/
  roles:
    assistant:
    - gpt
    user:
    - human
  type: chat_template
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: false
hub_model_id: cwaud/f2634928-d956-4450-bc4e-dc25bde4ac82
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 10
micro_batch_size: 2
mlflow_experiment_name: /tmp/e41fb6a21c7e2cd8_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: /root/.cache/huggingface/hub/trained_repo
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 512
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: offline
wandb_name: 75fcf414-63f5-4dfa-acab-a8f037a25cf7
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 75fcf414-63f5-4dfa-acab-a8f037a25cf7
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

f2634928-d956-4450-bc4e-dc25bde4ac82

This model is a fine-tuned version of heegyu/WizardVicuna-open-llama-3b-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1576

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss
1.9736	0.0000	1	2.3274
2.2583	0.0001	3	2.3239
1.6485	0.0002	6	2.2780
2.3931	0.0003	9	2.1576

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1