aaditya/gemma_out

See axolotl config

axolotl version: 0.4.0

base_model: google/gemma-7b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
 
load_in_8bit: false
load_in_4bit: true
strict: false
 
datasets:
  - path: combined_file.json
    ds_type: json
    type: alpaca
val_set_size: 0.1
output_dir: ./out
 
adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
  - q_proj
  - v_proj
  - v_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj
 
sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false
 
wandb_project: gemma_results
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
 
 
gradient_accumulation_steps: 3
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 5e-5
 
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_ratio: 0.1
evals_per_epoch: 1
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

out

This model is a fine-tuned version of google/gemma-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0418

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-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 3
• total_train_batch_size: 6
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 2092
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.1309	1.0	20924	1.0418

Framework versions

• PEFT 0.8.2
• Transformers 4.39.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.17.1
• Tokenizers 0.15.0