See axolotl config
axolotl version: 0.4.0
base_model: Lambent/cosmoem-8x1B
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: vicgalle/alpaca-gpt4
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./cosmoe-lora-out
unfrozen_parameters:
model_config:
output_router_logits: true
adapter: lora
lora_model_dir:
lora_r: 64
lora_alpha: 16
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
lora_r: 64
lora_alpha: 16
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: CosMoEAlpacaLight-1b-v0.1
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
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
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
cosmoe-lora-out
This model is a fine-tuned version of Lambent/cosmoem-8x1B on the vicgalle/alpaca-gpt4 dataset.
Model description
Model broke somewhat in training.
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- 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
Framework versions
- PEFT 0.8.2
- Transformers 4.39.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.0
- Downloads last month
- 2
Model tree for Lambent/CosMoEAlpacaLight-8x1b
Base model
Lambent/cosmoem-8x1B
Adapter
this model