Training in progress, epoch 1

config.json

@@ -31,7 +31,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.1",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a93d511a98455c9d5009dcd7ea903d76fcb4303705b60a2d3a9362d1f716da4d
+oid sha256:0226e13e09ba5b6f9fde2d8c2d39ee779221531533c73f44c1e1a493d9fe6d17
 size 4418050848

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
-size 11420371
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

tokenizer_config.json

@@ -138,7 +138,6 @@
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
-  "processor_class": "Qwen2VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5400234002a39681ded90e6b855bb91540f369831054877899b9164742860350
-size 7096
+oid sha256:d98d616a3c3618345915671a1aca9cfbe746b75e826905c403d6f0739ab42f05
+size 7224