Enable bf16 in train.py but disable it by default in script

zhanwenchen · Nov 16, 2023 · b2a2fef · b2a2fef
1 parent a20e972
commit b2a2fef
Show file tree

Hide file tree

Showing 2 changed files with 96 additions and 1 deletion.
diff --git a/install_azure.sh b/install_azure.sh
@@ -220,7 +220,7 @@ PYTHONPATH="./:$PYTHONPATH" torchrun --nproc_per_node=${NPROC_PER_NODE} --master
           --video_folder data/clip_features_train \
           --tune_mm_mlp_adapter True \
           --mm_use_vid_start_end \
-          --bf16 True \
+          --bf16 False \
           --output_dir ./Video-ChatGPT_7B-1.1_Checkpoints \
           --num_train_epochs 3 \
           --per_device_train_batch_size 8 \

diff --git a/tomloc_checkpoints_1/checkpoint-400/tokenizer_config.json b/tomloc_checkpoints_1/checkpoint-400/tokenizer_config.json
@@ -0,0 +1,95 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<im_patch>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "<im_start>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "<im_end>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "<vid_patch>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<vid_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<vid_end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<vid_patch>",
+    "<vid_start>",
+    "<vid_end>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}