adapter: lora
base_model: NousResearch/Yarn-Mistral-7b-64k
bf16: auto
datasets:
- data_files:
  - 56d8176ecf3014df_train_data.json
  ds_type: json
  format: custom
  path: 56d8176ecf3014df_train_data.json
  type:
    field: null
    field_input: null
    field_instruction: text
    field_output: code
    field_system: null
    format: null
    no_input_format: null
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_sample_packing: false
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: FatCat87/taopanda-3_5cbd8b3f-9553-4538-beb8-e2b7bc77d242
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 2
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: ./outputs/out/taopanda-3_5cbd8b3f-9553-4538-beb8-e2b7bc77d242
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: 1
seed: 19681
sequence_len: 4096
special_tokens:
  pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: fatcat87-taopanda
wandb_log_model: null
wandb_mode: online
wandb_name: taopanda-3_5cbd8b3f-9553-4538-beb8-e2b7bc77d242
wandb_project: subnet56
wandb_runid: taopanda-3_5cbd8b3f-9553-4538-beb8-e2b7bc77d242
wandb_watch: null
warmup_ratio: 0.05
weight_decay: 0.0
xformers_attention: null

Visualize in Weights & Biases

taopanda-3_5cbd8b3f-9553-4538-beb8-e2b7bc77d242

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: 0.5568

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: 19681
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 2
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.4151	0.0460	1	0.6549
0.8678	0.2759	6	0.6351
0.6408	0.5517	12	0.6029
0.6546	0.8276	18	0.5754
0.574	1.0575	24	0.5621
0.5518	1.3333	30	0.5595
0.5446	1.6092	36	0.5576
0.6227	1.8851	42	0.5568

Framework versions

PEFT 0.11.1
Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1