axolotl version: 0.4.0
base_model: ConvexAI/Metabird-7B
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: Intel/orca_dpo_pairs
type:
system_prompt: ""
field_system: system
field_instruction: question
field_output: rejected
field_output: chosen
format: "[INST] {instruction} [/INST]"
no_input_format: "[INST] {instruction} [/INST]"
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
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>"
out
This model is a fine-tuned version of ConvexAI/Metabird-7B on the Intel/orca_dpo_pairs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6861
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: 5e-06
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8728 | 0.01 | 1 | 0.8624 |
| 0.8527 | 0.26 | 19 | 0.6827 |
| 0.7749 | 0.51 | 38 | 0.6716 |
| 0.7289 | 0.77 | 57 | 0.6641 |
| 0.7166 | 1.02 | 76 | 0.6603 |
| 0.5306 | 1.25 | 95 | 0.6858 |
| 0.474 | 1.51 | 114 | 0.6858 |
| 0.4748 | 1.76 | 133 | 0.6861 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0