Training in progress, epoch 0

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "MCG-NJU/videomae-large-finetuned-kinetics",
   "architectures": [
     "VideoMAEForVideoClassification"
   ],
@@ -8,6 +7,7 @@
   "decoder_intermediate_size": 2048,
   "decoder_num_attention_heads": 8,
   "decoder_num_hidden_layers": 12,
+  "dtype": "float32",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 1024,
@@ -32,8 +32,7 @@
   "patch_size": 16,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.56.2",
   "tubelet_size": 2,
   "use_mean_pooling": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae0b95f39ca6d96f7e5f822068d1ecbc07f8926e81e7796973b65e484397d60
+oid sha256:dc0e0b042d9fa58518f5974bc74c504429578e433101804ad182e9b11b4fc59d
 size 1215496208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9305effe35248e9e07c7d824f77fc1c5c7ba75429b7c3f9b3f7f8d2509eff41f
-size 4856
+oid sha256:a6566c70b974e90b1774e5d3e4d57d3be36bdf95f5e5d38d770ca097321dbb38
+size 5368