don't compile deepspeed or bitsandbytes from source (#837)

2023-11-08 19:49:55 -05:00
parent 641e6f7e51
commit f544ab2bed
25 changed files with 29 additions and 65 deletions
--- a/examples/cerebras/btlm-ft.yml
+++ b/examples/cerebras/btlm-ft.yml
@@ -14,7 +14,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path: last_prepared_run
-val_set_size: 0.01
+val_set_size: 0.05

 adapter:
 lora_model_dir:
--- a/examples/cerebras/qlora.yml
+++ b/examples/cerebras/qlora.yml
@@ -7,7 +7,7 @@ datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 adapter: qlora
 lora_model_dir:
 sequence_len: 2048
--- a/examples/code-llama/13b/lora.yml
+++ b/examples/code-llama/13b/lora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./lora-out

 sequence_len: 4096
--- a/examples/code-llama/13b/qlora.yml
+++ b/examples/code-llama/13b/qlora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./qlora-out

 adapter: qlora
--- a/examples/code-llama/34b/lora.yml
+++ b/examples/code-llama/34b/lora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./lora-out

 sequence_len: 4096
--- a/examples/code-llama/34b/qlora.yml
+++ b/examples/code-llama/34b/qlora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./qlora-out

 adapter: qlora
--- a/examples/code-llama/7b/lora.yml
+++ b/examples/code-llama/7b/lora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./lora-out

 sequence_len: 4096
--- a/examples/code-llama/7b/qlora.yml
+++ b/examples/code-llama/7b/qlora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./qlora-out

 adapter: qlora
--- a/examples/falcon/config-7b-lora.yml
+++ b/examples/falcon/config-7b-lora.yml
@@ -12,7 +12,7 @@ datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca:chat
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 adapter: lora
 lora_model_dir:
 sequence_len: 2048
--- a/examples/falcon/config-7b-qlora.yml
+++ b/examples/falcon/config-7b-qlora.yml
@@ -18,7 +18,7 @@ datasets:
      - Chain-of-Thought/formatted_cot_data/gsm8k_train.json
    type: "alpaca:chat"
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 # enable QLoRA
 adapter: qlora
 lora_model_dir:
--- a/examples/falcon/config-7b.yml
+++ b/examples/falcon/config-7b.yml
@@ -12,7 +12,7 @@ datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca:chat
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 adapter:
 lora_model_dir:
 sequence_len: 2048
--- a/examples/gptj/qlora.yml
+++ b/examples/gptj/qlora.yml
@@ -7,7 +7,7 @@ datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 adapter: qlora
 lora_model_dir:
 sequence_len: 2048
--- a/examples/llama-2/fft_optimized.yml
+++ b/examples/llama-2/fft_optimized.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./out

 sequence_len: 4096
--- a/examples/llama-2/gptq-lora.yml
+++ b/examples/llama-2/gptq-lora.yml
@@ -15,7 +15,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 adapter: lora
 lora_model_dir:
 sequence_len: 4096
--- a/examples/llama-2/lora.yml
+++ b/examples/llama-2/lora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./lora-out

 sequence_len: 4096
--- a/examples/llama-2/qlora.yml
+++ b/examples/llama-2/qlora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./qlora-out

 adapter: qlora
--- a/examples/llama-2/relora.yml
+++ b/examples/llama-2/relora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./relora-out

 adapter: qlora
--- a/examples/llama-2/tiny-llama.yml
+++ b/examples/llama-2/tiny-llama.yml
@@ -12,7 +12,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./lora-out

 sequence_len: 4096
--- a/examples/mistral/config.yml
+++ b/examples/mistral/config.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./out

 sequence_len: 8192
--- a/examples/mistral/qlora.yml
+++ b/examples/mistral/qlora.yml
@@ -11,7 +11,7 @@ datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
 dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
+val_set_size: 0.05
 output_dir: ./qlora-out

 adapter: qlora
--- a/examples/openllama-3b/qlora.yml
+++ b/examples/openllama-3b/qlora.yml
@@ -9,7 +9,7 @@ datasets:
  - path: teknium/GPT4-LLM-Cleaned
    type: alpaca
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 adapter: qlora
 lora_model_dir:
 sequence_len: 1024
--- a/examples/xgen-7b/xgen-7b-8k-qlora.yml
+++ b/examples/xgen-7b/xgen-7b-8k-qlora.yml
@@ -16,7 +16,7 @@ datasets:
      - openassistant_best_replies_train.jsonl
    type: "completion"
 dataset_prepared_path:
-val_set_size: 0.01
+val_set_size: 0.05
 # enable QLoRA
 adapter: qlora
 lora_model_dir: