Einstein Models
Collection
Einstein series
•
10 items
•
Updated
•
3
axolotl version: 0.4.0
base_model: Qwen/Qwen1.5-32B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
chat_template: chatml
datasets:
- path: data/merged_all.json
ds_type: json
type: alpaca
conversation: chatml
- path: data/capybara_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/synthia-v1.3_sharegpt_12500.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/slimorca_dedup_filtered_95k_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0 # because we won't eval, out of memory :(
output_dir: ./Einstein-v4-Qwen-1.5-32B-model
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
adapter: qlora
lora_model_dir:
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_modules_to_save:
- "embed_tokens"
- "lm_head"
wandb_project: Einstein
wandb_entity:
wandb_watch:
wandb_name: Einstein-v4-Qwen-1.5-32B-qlora-2-epoch
wandb_log_model:
hub_model_id: Weyaxi/Einstein-v4-Qwen-1.5-32B
save_safetensors: true
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
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
warmup_steps: 10
evals_per_epoch: 0 # because we won't eval, out of memory :(
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 2
debug:
deepspeed: zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "<|im_end|>"
unk_token: "<unk>"
tokens:
- "<|im_start|>"
This model is a fine-tuned version of Qwen/Qwen1.5-32B on the None dataset.
More information needed
More information needed
More information needed
The following hyperparameters were used during training: