See axolotl config

axolotl version: 0.4.1

adapter: qlora
base_model: sethuiyer/Medichat-Llama3-8B
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - a1b281c6d31a7336_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/a1b281c6d31a7336_train_data.json
  type:
    field_instruction: passage
    field_output: question
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
#evals_per_epoch: 1
eval_steps: 25
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: error577/bfddfda6-fae6-439b-854e-7c3911715acf
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
dataloader_num_workers: 6
early_stopping_patience: 3
early_stopping_threshold: 0.001
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 200
micro_batch_size: 1
mlflow_experiment_name: /tmp/a1b281c6d31a7336_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 4
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
#saves_per_epoch: 1
save_steps: 25
sequence_len: 512
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: online
wandb_name: 12e67bb2-1212-4109-94de-02222dc25293
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 12e67bb2-1212-4109-94de-02222dc25293
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

bfddfda6-fae6-439b-854e-7c3911715acf

This model is a fine-tuned version of sethuiyer/Medichat-Llama3-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3868

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
• gradient_accumulation_steps: 8
• 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: 200

Training results

Training Loss	Epoch	Step	Validation Loss
3.3026	0.0107	1	2.7749
1.4955	0.2681	25	1.5085
1.2204	0.5362	50	1.4510
1.6689	0.8043	75	1.4629
0.904	1.0724	100	1.3672
0.6045	1.3405	125	1.4109
0.8388	1.6086	150	1.3938
0.8251	1.8767	175	1.3868

Framework versions

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