adapter: lora
base_model: NousResearch/Yarn-Mistral-7b-64k
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - bbea9bfbc6b704d4_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/bbea9bfbc6b704d4_train_data.json
  type:
    field_instruction: Patient
    field_output: Doctor
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: romainnn/67134654-9ad4-4eba-9805-386c9c8cc0e0
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 840
micro_batch_size: 4
mlflow_experiment_name: /tmp/bbea9bfbc6b704d4_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 2048
special_tokens:
  pad_token: </s>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.01948436574492627
wandb_entity: null
wandb_mode: online
wandb_name: fc61cee8-2b4c-428c-9f57-cf984121e779
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: fc61cee8-2b4c-428c-9f57-cf984121e779
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

67134654-9ad4-4eba-9805-386c9c8cc0e0

This model is a fine-tuned version of NousResearch/Yarn-Mistral-7b-64k on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.7090

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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: 840

Training results

Training Loss	Epoch	Step	Validation Loss
20.2151	0.0001	1	2.4834
15.5342	0.0127	100	1.9175
13.8705	0.0254	200	1.8468
14.0375	0.0382	300	1.8074
12.4894	0.0509	400	1.7711
14.6932	0.0636	500	1.7441
14.322	0.0763	600	1.7251
16.4402	0.0890	700	1.7132
13.6008	0.1017	800	1.7090

Framework versions

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