Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c46b31a595c9e3cacc33ae9ff0d04745cee24796af58038220f67a5fa33c36
+oid sha256:e6753d3df8dfde0128bba6803bc18a080b76948952f20d94e4b277d3dd52b988
 size 359190616

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2582a72cfe28b6154411dfdf8976e7882bbd5caf3fa407d4a12c3bf9a2eeaeb6
+oid sha256:f287f42962dbaffca0ab078583289297fa2017f47f973ae831779a8ce8ba446d
 size 718509882

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ecdb2aab127fdd4a50e882dca2103373b1eb980735e992800a6e69e40807b5c
+oid sha256:9eddd062c87af5cdb7eb6cacd39e60170f32e8ccbf9998f5ee427cf57e54f0d8
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c92f011cd3caa037f9d6a8e340e59b8a7fe10331eb357c4ea4d3f3cdba14fb
+oid sha256:cf07e257697ce1cc88d0a81710c44ebed4ed1f45a8a2905a95f4c93940bc6e95
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.967008960660055,
   "best_model_checkpoint": "/kaggle/working/mmoe_vit_results/checkpoint-24012",
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 28014,
+  "global_step": 32016,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -707,6 +707,106 @@
       "eval_style_recall": 0.6907946008292029,
       "eval_style_weighted_f1": 0.6607505081198878,
       "step": 28014
+    },
+    {
+      "epoch": 7.12143928035982,
+      "grad_norm": 43.210941314697266,
+      "learning_rate": 1.4574898785425101e-05,
+      "loss": 3.7497,
+      "step": 28500
+    },
+    {
+      "epoch": 7.246376811594203,
+      "grad_norm": 34.3553352355957,
+      "learning_rate": 1.3942307692307693e-05,
+      "loss": 3.8133,
+      "step": 29000
+    },
+    {
+      "epoch": 7.371314342828586,
+      "grad_norm": 38.11077880859375,
+      "learning_rate": 1.3309716599190283e-05,
+      "loss": 3.8536,
+      "step": 29500
+    },
+    {
+      "epoch": 7.496251874062969,
+      "grad_norm": 34.092018127441406,
+      "learning_rate": 1.2677125506072876e-05,
+      "loss": 3.8057,
+      "step": 30000
+    },
+    {
+      "epoch": 7.6211894052973514,
+      "grad_norm": 31.957683563232422,
+      "learning_rate": 1.2044534412955466e-05,
+      "loss": 3.813,
+      "step": 30500
+    },
+    {
+      "epoch": 7.746126936531734,
+      "grad_norm": 34.03321075439453,
+      "learning_rate": 1.1411943319838058e-05,
+      "loss": 3.7924,
+      "step": 31000
+    },
+    {
+      "epoch": 7.871064467766117,
+      "grad_norm": 38.06154251098633,
+      "learning_rate": 1.077935222672065e-05,
+      "loss": 3.8135,
+      "step": 31500
+    },
+    {
+      "epoch": 7.9960019990005,
+      "grad_norm": 45.78370666503906,
+      "learning_rate": 1.014676113360324e-05,
+      "loss": 3.7866,
+      "step": 32000
+    },
+    {
+      "epoch": 8.0,
+      "eval_category_macro_f1": 0.8146478162196177,
+      "eval_category_precision": 0.9667355952687459,
+      "eval_category_recall": 0.9672059602855451,
+      "eval_category_weighted_f1": 0.9666613335359282,
+      "eval_color_macro_f1": 0.494972223269362,
+      "eval_color_precision": 0.8179178024945392,
+      "eval_color_recall": 0.8253686212163721,
+      "eval_color_weighted_f1": 0.8171143847468179,
+      "eval_gender_macro_f1": 0.726822473815732,
+      "eval_gender_precision": 0.9595388610516349,
+      "eval_gender_recall": 0.9593503538140217,
+      "eval_gender_weighted_f1": 0.9590467785701566,
+      "eval_loss": 6.086089134216309,
+      "eval_material_macro_f1": 0.4653083418810649,
+      "eval_material_precision": 0.6660165608707495,
+      "eval_material_recall": 0.6859316063468313,
+      "eval_material_weighted_f1": 0.6641222350586232,
+      "eval_neck_macro_f1": 0.3385488552152788,
+      "eval_neck_precision": 0.8103884255493873,
+      "eval_neck_recall": 0.8168272078306681,
+      "eval_neck_weighted_f1": 0.8100463958001771,
+      "eval_pattern_macro_f1": 0.29354348124717355,
+      "eval_pattern_precision": 0.6421689432624941,
+      "eval_pattern_recall": 0.6699398360298014,
+      "eval_pattern_weighted_f1": 0.6249061713173589,
+      "eval_product_type_macro_f1": 0.750138460482341,
+      "eval_product_type_precision": 0.7549316716640776,
+      "eval_product_type_recall": 0.7525795691885657,
+      "eval_product_type_weighted_f1": 0.7506829441074545,
+      "eval_runtime": 301.8256,
+      "eval_samples_per_second": 106.283,
+      "eval_sleeve_macro_f1": 0.4663248985167306,
+      "eval_sleeve_precision": 0.8591320313081251,
+      "eval_sleeve_recall": 0.86252688674834,
+      "eval_sleeve_weighted_f1": 0.8568151400744953,
+      "eval_steps_per_second": 1.663,
+      "eval_style_macro_f1": 0.3329861421512565,
+      "eval_style_precision": 0.6707667240667725,
+      "eval_style_recall": 0.6972162473892578,
+      "eval_style_weighted_f1": 0.6732692090638879,
+      "step": 32016
     }
   ],
   "logging_steps": 500,
@@ -721,7 +821,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {