adapter: qlora
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
bf16: true
chat_template: inst
dataset_prepared_path: last_run_prepared
datasets:
- conversation: mistral
  path: ./data/with_function_response/more_functions/function_not_used_training_small.jsonl
  type: sharegpt
- conversation: mistral
  path: ./data/with_function_response/more_functions/function_used_training_small.jsonl
  type: sharegpt
- conversation: mistral
  path: ./data/with_function_response/parallel_call/parallel_data_training.jsonl
  type: sharegpt
debug: null
eval_max_new_tokens: 256
eval_steps: 0.05
eval_table_size: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: liuylhf/empower-functions-more-tools-staging
learning_rate: 0.0002
load_in_4bit: true
load_in_8bit: false
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_model_dir: null
lora_r: 32
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
loss_watchdog_patience: 3
loss_watchdog_threshold: 5.0
lr_scheduler: cosine
micro_batch_size: 2
model_config:
  output_router_logits: true
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: paged_adamw_8bit
output_dir: 2af0968cad514d6e9d5fb8448230e1c6/model
pad_to_sequence_len: true
sample_packing: true
save_steps: 0.1
sequence_len: 4096
strict: false
tf32: false
tokenizer_type: LlamaTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.025
wandb_log_model: end
wandb_name: mixtral-instruct-lora-no-negative
wandb_project: function-call
warmup_steps: 10
weight_decay: 0.0

empower-functions-more-tools-staging

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0904

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
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.8305	0.0	1	1.9892
0.1336	0.1	27	0.1444
0.1006	0.2	54	0.1193
0.102	0.3	81	0.1120
0.0798	0.41	108	0.1068
0.0976	0.51	135	0.1051
0.1145	0.61	162	0.1021
0.0984	0.71	189	0.1008
0.0817	0.81	216	0.1006
0.0841	0.91	243	0.0971
0.0983	1.02	270	0.0967
0.0948	1.09	297	0.0956
0.093	1.2	324	0.0944
0.0991	1.3	351	0.0938
0.072	1.4	378	0.0927
0.0831	1.5	405	0.0920
0.0768	1.6	432	0.0912
0.0915	1.7	459	0.0905
0.082	1.81	486	0.0906
0.0702	1.91	513	0.0904

Framework versions

PEFT 0.9.0
Transformers 4.38.2
Pytorch 2.2.0+cu121
Datasets 2.18.0
Tokenizers 0.15.0

liuylhf/empower-functions-more-tools-v2

empower-functions-more-tools-staging

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

liuylhf/
empower-functions-more-tools-v2