base_model: GeneZC/MiniChat-2-3B
base_model_config: GeneZC/MiniChat-2-3B
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: THUDM/AgentInstruct
    type: sharegpt
    conversation: llama-2
    split: os
  - path: THUDM/AgentInstruct
    type: sharegpt
    conversation: llama-2
    split: db
  - path: THUDM/AgentInstruct
    type: sharegpt
    conversation: llama-2
    split: alfworld
  - path: THUDM/AgentInstruct
    type: sharegpt
    conversation: llama-2
    split: webshop
  - path: THUDM/AgentInstruct
    type: sharegpt
    conversation: llama-2
    split: kg
  - path: THUDM/AgentInstruct
    type: sharegpt
    conversation: llama-2
    split: mind2web

dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-out

hub_model_id: gultar/Automata-Minichat-3b

wandb_project: "Mistral-Agent"
wandb_log_model: "checkpoint"

chat_template: inst

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

Automata-Minichat-3b

This model is a fine-tuned version of GeneZC/MiniChat-2-3B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3139

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: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.9648	0.01	1	0.9762
0.5564	0.26	19	0.5018
0.2629	0.52	38	0.3400
0.2789	0.78	57	0.3139

Framework versions

PEFT 0.8.2.dev0
Transformers 4.37.0
Pytorch 2.0.1+cu118
Datasets 2.16.1
Tokenizers 0.15.0