Training in progress, step 10

README.md

@@ -34,11 +34,11 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
 
 ### Framework versions
 
-- TRL: 0.20.0.dev0
-- Transformers: 4.53.2
-- Pytorch: 2.6.0+cu124
+- TRL: 0.25.1
+- Transformers: 4.57.1
+- Pytorch: 2.8.0+cu126
 - Datasets: 4.0.0
-- Tokenizers: 0.21.2
+- Tokenizers: 0.22.1
 
 ## Citations
 

adapter_config.json

@@ -28,14 +28,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
-    "up_proj",
     "o_proj",
-    "gate_proj",
     "v_proj",
-    "k_proj",
+    "up_proj",
+    "gate_proj",
     "down_proj"
   ],
+  "target_parameters": null,
   "task_type": null,
   "trainable_token_indices": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87073d4aac4526586d76df6604f51e587a99ce529c75e685aa4ba2c6b419efbb
+oid sha256:d8a27351b48ab1278516815c8d1ed7a6a7194014e5f926bf4952c7ea0a97cb93
 size 79626296

preprocessor_config.json

@@ -7,6 +7,7 @@
   "do_center_crop": null,
   "do_convert_rgb": true,
   "do_normalize": true,
+  "do_pad": null,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
@@ -24,6 +25,7 @@
   "max_pixels": 12845056,
   "merge_size": 2,
   "min_pixels": 3136,
+  "pad_size": null,
   "patch_size": 14,
   "processor_class": "Qwen2_5_VLProcessor",
   "resample": 3,

runs/Nov15_14-02-10_964bdf5cc237/events.out.tfevents.1763215642.964bdf5cc237.2899.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cc6af4b8f13ba6997b5ccd325f12891066d9af265b91c8d70524bd48d02223
+size 10813

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7afd18de1b858dc2c065b71e4d10becec68847a0dca96d545d54938f64d6cae7
-size 6392
+oid sha256:92c1e42727b1dae9458ff24d1cdd4c38ff6aed6ef3f23e84ffa40522e40d50fe
+size 6929

video_preprocessor_config.json

@@ -6,7 +6,6 @@
   "do_center_crop": null,
   "do_convert_rgb": true,
   "do_normalize": true,
-  "do_pad": null,
   "do_rescale": true,
   "do_resize": true,
   "do_sample_frames": false,
@@ -28,15 +27,16 @@
   "min_frames": 4,
   "min_pixels": 3136,
   "num_frames": null,
+  "pad_size": null,
   "patch_size": 14,
   "processor_class": "Qwen2_5_VLProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
   "size": {
     "longest_edge": 12845056,
     "shortest_edge": 3136
   },
-  "size_divisor": null,
   "temporal_patch_size": 2,
   "video_metadata": null,
   "video_processor_type": "Qwen2VLVideoProcessor"