Training in progress, step 4000

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/leonardo666-tsinghua-university/huggingface/runs/1pmwwho5) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/leonardo666-tsinghua-university/huggingface/runs/3vln44gm) 
 
 
 This model was trained with SFT.

config.json

@@ -38,7 +38,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.53.3",
-  "use_cache": false,
   "vision_config": {
     "attention_dropout": 0.0,
     "hidden_act": "quick_gelu",

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c81611a342bc2be8d5abcbabddf7ab3e79e20c7e1b723b868055e296bdcf92
+oid sha256:e73ae3711999b615243cc9183fa77be2999a17a8d1eab669952e709c02e42801
 size 4992930688

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4041e679d005bcd57436aef34c2830d5db5603208f09cef6db3fdc303c2474a
+oid sha256:a879ea3d08e88d86883f3378bf1fb8f6fce74e80b09bf8b0e1e0bb8fce07f7d6
 size 4957878552

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ba9908beb0b22267e1f3de260fb875a1f9ef10c1228faeceff3e38015430cf
+oid sha256:09a2fe3cea0d4d3542a79322c21fecbc2e09ab8b3e8bf48e5a81588e4ad662f1
 size 4176137496

preprocessor_config.json

@@ -0,0 +1,34 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "shortest_edge": 336
+  }
+}

processor_config.json

@@ -0,0 +1,7 @@
+{
+  "image_token": "<image>",
+  "num_additional_image_tokens": 1,
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c8a0b05e5c02ef11b8fa912c50f9ce281980fe7bd41027aece23679dbb04a4
+oid sha256:15fafaf8cb9904875114f70cc31ae2c5cd5064f2d06433ca6f4da75fec366e7e
 size 7096