Merge pull request #189 from OpenAccess-AI-Collective/fixes-20230711

various fixes

configs/accelerate/default_config.yaml

@@ -1,15 +0,0 @@
-compute_environment: LOCAL_MACHINE
-distributed_type: 'NO'
-downcast_bf16: 'no'
-gpu_ids: all
-machine_rank: 0
-main_training_function: main
-mixed_precision: bf16
-num_machines: 1
-num_processes: 1
-rdzv_backend: static
-same_network: true
-tpu_env: []
-tpu_use_cluster: false
-tpu_use_sudo: false
-use_cpu: false

configs/llama_13B_alpaca.yml

@@ -1,39 +0,0 @@
-base_model: huggyllama/llama-13b
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: true
-datasets:
-  - path: anon8231489123/ShareGPT_Vicuna_unfiltered
-    data_files: ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json
-    type: sharegpt
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.002
-adapter:
-lora_model_dir:
-sequence_len: 2048
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - q_proj
-  - v_proj
-lora_fan_in_fan_out: false
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./llama-13b-sharegpt
-gradient_accumulation_steps: 1
-micro_batch_size: 2
-warmup_steps: 1000
-save_steps:
-eval_steps:
-num_epochs: 5
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-early_stopping_patience: 5
-resume_from_checkpoint:
-local_rank:

configs/llama_65B_alpaca.yml

@@ -1,44 +0,0 @@
-base_model: huggyllama/llama-65b
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: true
-datasets:
-  - path: data/alpaca_data_gpt4.jsonl
-    type: alpaca
-  - path: anon8231489123/ShareGPT_Vicuna_unfiltered
-    data_files: ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json
-    type: sharegpt
-  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
-    type: gpteacher
-  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
-    type: gpteacher
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - q_proj
-  - v_proj
-lora_fan_in_fan_out: false
-wandb_project: llama-65b-lora
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./lora-llama-alpaca
-gradient_accumulation_steps: 1
-micro_batch_size: 16
-warmup_steps: 1000
-save_steps:
-num_epochs: 5
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:

configs/llama_7B_4bit.yml

@@ -1,45 +0,0 @@
-base_model: decapoda-research/llama-7b-hf-int4
-base_model_config: decapoda-research/llama-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: true
-datasets:
-  - path: tatsu-lab/alpaca  # original alpaca dataset
-    type: alpaca
-dataset_prepared_path: data/last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len: 1024
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - q_proj
-  - v_proj
-#  - k_proj
-#  - o_proj
-lora_fan_in_fan_out: false
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./lora-test
-gradient_accumulation_steps: 1
-micro_batch_size: 2
-num_epochs: 3
-warmup_steps: 100
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-gradient_checkpointing: false
-early_stopping_patience: 3
-resume_from_checkpoint:
-auto_resume_from_checkpoints: true
-local_rank:
-load_4bit: true
-xformers_attention: true
-flash_attention:

configs/quickstart.yml

@@ -1,45 +0,0 @@
-base_model: decapoda-research/llama-7b-hf-int4
-base_model_config: decapoda-research/llama-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: true
-datasets:
-  - path: tatsu-lab/alpaca  # original alpaca dataset
-    type: alpaca
-dataset_prepared_path: data/last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 1024
-max_packed_sequence_len: 1024
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - q_proj
-  - v_proj
-#  - k_proj
-#  - o_proj
-lora_fan_in_fan_out: false
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./lora-test
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 3
-warmup_steps: 100
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-gradient_checkpointing: false
-early_stopping_patience: 3
-resume_from_checkpoint:
-auto_resume_from_checkpoints: true
-local_rank:
-gptq: true
-xformers_attention: true
-flash_attention:

configs/vicuna_13B_4bit_reflect.yml

@@ -1,45 +0,0 @@
-base_model: anon8231489123/vicuna-13b-GPTQ-4bit-128g
-base_model_config: anon8231489123/vicuna-13b-GPTQ-4bit-128g
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-load_in_8bit: false
-load_4bit: true
-gptq_groupsize: 128
-gptq_model_v1: false
-datasets:
-# https://github.com/vaguenebula/AlpacaDataReflect/blob/main/alpaca_reflect_pruned.json
-  - path: data/alpaca_reflect_pruned.jsonl
-    type: reflection
-dataset_prepared_path: data/last_run_prepared
-val_set_size: 0.04
-adapter: lora
-lora_model_dir:
-sequence_len: 2048
-max_packed_sequence_len: 2048
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-  - q_proj
-  - v_proj
-#  - k_proj
-#  - o_proj
-lora_fan_in_fan_out: false
-wandb_project:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./lora-reflect
-gradient_accumulation_steps: 1
-micro_batch_size: 2
-num_epochs: 3
-learning_rate: 0.00003
-train_on_inputs: false
-group_by_length: false
-bf16: true
-tf32: true
-gradient_checkpointing: false
-early_stopping_patience: 3
-resume_from_checkpoint:
-local_rank:
-flash_attention: true

examples/pythia/lora.yml

@@ -1,36 +1,29 @@
 base_model: EleutherAI/pythia-1.4b-deduped
-model_type: GPTNeoXForCausalLM
-tokenizer_type: AutoTokenizer
+base_model_config: EleutherAI/pythia-1.4b-deduped
 load_in_8bit: true
 datasets:
-  - path: data/alpaca_data_gpt4.jsonl
+  - path: teknium/GPT4-LLM-Cleaned
     type: alpaca
-  - path: data/vicuna_cleaned.jsonl
-    type: sharegpt
-  - path: data/gpt4-instruct-similarity-0.6-dataset.jsonl
-    type: gpteacher
-  - path: data/roleplay-similarity_0.6-instruct-dataset.jsonl
-    type: gpteacher
 dataset_prepared_path: last_run_prepared
 val_set_size: 0.05
 adapter: lora
 lora_model_dir:
-sequence_len: 2048
-lora_r: 8
+sequence_len: 512
+lora_r: 16
 lora_alpha: 32
 lora_dropout: 0.05
 lora_target_modules:
   - query_key_value
-#  - xxx
+lora_target_linear:
 lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
-wandb_project: pythia-1.4b-lora
+wandb_project:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
-output_dir: ./lora-alpaca
+output_dir: ./lora-alpaca-pythia
 gradient_accumulation_steps: 1
 micro_batch_size: 4
-num_epochs: 5
+num_epochs: 3
 learning_rate: 0.00001
 train_on_inputs: false
 group_by_length: false
@@ -39,3 +32,6 @@ tf32: True
 early_stopping_patience:
 resume_from_checkpoint:
 local_rank:
+weight_decay: 0.1
+eval_steps: 20
+logging_steps: 1

src/axolotl/utils/models.py

@@ -305,7 +305,9 @@ def load_model(
         or (cfg.adapter == "qlora" and cfg.load_in_4bit)
     ):
         logging.info("converting PEFT model w/ prepare_model_for_kbit_training")
-        model = prepare_model_for_kbit_training(model)
+        model = prepare_model_for_kbit_training(
+            model, use_gradient_checkpointing=cfg.gradient_checkpointing
+        )
 
     model, lora_config = load_adapter(model, cfg, adapter)
 

src/axolotl/utils/validation.py

@@ -57,6 +57,11 @@ def validate_config(cfg):
     if (cfg.base_model and "falcon" in cfg.base_model.lower()) and cfg.fsdp:
         raise ValueError("FSDP is not supported for falcon models")
 
+    if (
+        cfg.base_model and "mpt" in cfg.base_model.lower()
+    ) and cfg.gradient_checkpointing:
+        raise ValueError("gradient_checkpointing is not supported for MPT models")
+
     # TODO
     # MPT 7b
     # https://github.com/facebookresearch/bitsandbytes/issues/25

tests/test_validation.py

@@ -198,3 +198,17 @@ class ValidationTest(unittest.TestCase):
         )
 
         validate_config(cfg)
+
+    def test_mpt_gradient_checkpointing(self):
+        regex_exp = r".*gradient_checkpointing is not supported for MPT models*"
+
+        # Check for lower-case
+        cfg = DictDefault(
+            {
+                "base_model": "mosaicml/mpt-7b",
+                "gradient_checkpointing": True,
+            }
+        )
+
+        with pytest.raises(ValueError, match=regex_exp):
+            validate_config(cfg)