Downloads · 30 days
11
3% of all-time downloads
AlekseyKorshuk/ultrachat-phi-2-dpo-chatml
ultrachat-phi-2-dpo-chatml is a text generation model from AlekseyKorshuk. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
11
3% of all-time downloads
All-time downloads
422
Public
Parameters
2.8B
22.2 GB on disk
Likes
1
Public
Click a slice to open those files.
.bin5.6 GB · 50%
From the Hugging Face model README
axolotl version: 0.4.0
base_model: AlekseyKorshuk/ultrachat-phi-2-sft-chatml
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true
hub_model_id: AlekseyKorshuk/ultrachat-phi-2-dpo-chatml
hub_strategy: every_save
load_in_8bit: false
load_in_4bit: false
strict: false
rl: dpo
datasets:
- path: argilla/ultrafeedback-binarized-preferences
split: train
type: chatml.argilla
dataset_prepared_path:
#val_set_size: 0.001
output_dir: ./output
sequence_len: 2048
#sample_packing: false # currently unsupported
pad_to_sequence_len:
lora_r:
lora_alpha:
lora_dropout:
lora_target_modules:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project: ui-thesis
wandb_entity:
wandb_watch:
wandb_name: ultrachat-phi-2-dpo-chatml
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 8
num_epochs: 3
optimizer: paged_adamw_8bit
adam_beta1: 0.9
adam_beta2: 0.95
max_grad_norm: 1.0
adam_epsilon: 0.00001
lr_scheduler: cosine
cosine_min_lr_ratio: 0.1
learning_rate: 5.0e-7
warmup_steps: 32
#warmup_ratio: 0.1
weight_decay: 0.01
dpo_beta: 0.01
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
#evals_per_epoch: 5
#eval_table_size: 8 # Approximate number of predictions sent to wandb depending on batch size. Enabled above 0. Default is 0
#eval_table_max_new_tokens: 768 # Total number of tokens generated for predictions sent to wandb. Default is 128
chat_template: chatml
#saves_per_epoch: 1
save_steps: 500
save_total_limit: 1
seed: 42
debug:
deepspeed:
fsdp:
fsdp_config:
resize_token_embeddings_to_32x: true
</details><br>
This model is a fine-tuned version of AlekseyKorshuk/ultrachat-phi-2-sft-chatml on the None dataset.
More information needed
More information needed
More information needed
The following hyperparameters were used during training: