See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: NousResearch/Yarn-Llama-2-7b-128k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1e4dac8291eb0dd5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1e4dac8291eb0dd5_train_data.json
  type:
    field_input: Patient
    field_instruction: Description
    field_output: Doctor
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 256
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: false
hub_model_id: eddysang/eb83a1bc-e639-4f1a-889c-e4f9ad78e192
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 3
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
lr_scheduler: cosine
max_grad_norm: 2
max_steps: 100
micro_batch_size: 2
mlflow_experiment_name: /tmp/1e4dac8291eb0dd5_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1.0e-05
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 4
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: yaudayah0
wandb_mode: online
wandb_name: faa8963c-9500-4409-b4dc-23c50cbd5a98
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: faa8963c-9500-4409-b4dc-23c50cbd5a98
warmup_steps: 20
weight_decay: 0.02
xformers_attention: false

eb83a1bc-e639-4f1a-889c-e4f9ad78e192

This model is a fine-tuned version of NousResearch/Yarn-Llama-2-7b-128k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9334

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: 32
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-05
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	2.4194
74.5329	0.0024	9	2.2487
68.8249	0.0047	18	2.1339
67.7895	0.0071	27	2.0770
68.4813	0.0094	36	2.0368
62.9029	0.0118	45	2.0083
64.6338	0.0142	54	1.9837
65.246	0.0165	63	1.9635
62.0766	0.0189	72	1.9492
65.6011	0.0213	81	1.9402
62.156	0.0236	90	1.9347
63.4709	0.0260	99	1.9334

Framework versions

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