| architecture: |
| backbone_dtype: int4 |
| force_embedding_gradients: false |
| gradient_checkpointing: true |
| intermediate_dropout: 0.0 |
| pretrained: true |
| pretrained_weights: '' |
| augmentation: |
| random_parent_probability: 0.0 |
| skip_parent_probability: 0.0 |
| token_mask_probability: 0.0 |
| dataset: |
| add_eos_token_to_answer: true |
| add_eos_token_to_prompt: true |
| add_eos_token_to_system: true |
| answer_column: output |
| chatbot_author: PAIX.Cloud |
| chatbot_name: Astrid |
| data_sample: 1.0 |
| data_sample_choice: |
| - Train |
| - Validation |
| limit_chained_samples: false |
| mask_prompt_labels: true |
| parent_id_column: None |
| personalize: true |
| prompt_column: |
| - instruction |
| system_column: None |
| text_answer_separator: <|answer|> |
| text_prompt_start: <|prompt|> |
| text_system_start: <|system|> |
| train_dataframe: /workspace/data/user/oasst/train_full.pq |
| validation_dataframe: None |
| validation_size: 0.01 |
| validation_strategy: automatic |
| environment: |
| compile_model: false |
| find_unused_parameters: false |
| gpus: |
| - '0' |
| huggingface_branch: main |
| mixed_precision: true |
| number_of_workers: 8 |
| seed: -1 |
| trust_remote_code: true |
| use_fsdp: false |
| experiment_name: Astrid-7b-Instruct |
| llm_backbone: mistralai/Mistral-7B-Instruct-v0.1 |
| logging: |
| logger: Neptune |
| neptune_project: daviess/paix |
| output_directory: /workspace/output/user/Astrid-7b-Instruct/ |
| prediction: |
| batch_size_inference: 0 |
| do_sample: false |
| max_length_inference: 256 |
| metric: GPT |
| metric_gpt_model: gpt-3.5-turbo-0301 |
| min_length_inference: 2 |
| num_beams: 1 |
| num_history: 4 |
| repetition_penalty: 1.2 |
| stop_tokens: '' |
| temperature: 0.3 |
| top_k: 0 |
| top_p: 1.0 |
| problem_type: text_causal_language_modeling |
| tokenizer: |
| add_prefix_space: false |
| add_prompt_answer_tokens: false |
| max_length: 512 |
| max_length_answer: 256 |
| max_length_prompt: 256 |
| padding_quantile: 1.0 |
| use_fast: true |
| training: |
| batch_size: 2 |
| differential_learning_rate: 1.0e-05 |
| differential_learning_rate_layers: [] |
| drop_last_batch: true |
| epochs: 1 |
| evaluate_before_training: false |
| evaluation_epochs: 1.0 |
| grad_accumulation: 1 |
| gradient_clip: 0.0 |
| learning_rate: 0.0001 |
| lora: true |
| lora_alpha: 16 |
| lora_dropout: 0.05 |
| lora_r: 4 |
| lora_target_modules: '' |
| loss_function: TokenAveragedCrossEntropy |
| optimizer: AdamW |
| save_best_checkpoint: false |
| schedule: Cosine |
| train_validation_data: false |
| warmup_epochs: 0.0 |
| weight_decay: 0.0 |
|
|
