Training in progress, epoch 10

config.json

@@ -21,8 +21,8 @@
   "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
-    "0": "FLUID_REASONING",
-    "1": "COMPREHENSION_KNOWLEDGE",
+    "0": "COMPREHENSION_KNOWLEDGE",
+    "1": "FLUID_REASONING",
     "2": "QUANTITATIVE_KNOWLEDGE",
     "3": "VISUAL_REASONING"
   },
@@ -30,8 +30,8 @@
   "initializer_range": 0.02,
   "intermediate_size": 1152,
   "label2id": {
-    "COMPREHENSION_KNOWLEDGE": "1",
-    "FLUID_REASONING": "0",
+    "COMPREHENSION_KNOWLEDGE": "0",
+    "FLUID_REASONING": "1",
     "QUANTITATIVE_KNOWLEDGE": "2",
     "VISUAL_REASONING": "3"
   },
@@ -49,12 +49,11 @@
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "reference_compile": false,
-  "repad_logits_with_grad": false,
+  "reference_compile": true,
   "sep_token_id": 50282,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.0",
+  "transformers_version": "4.48.0.dev0",
   "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298ac3f8eab8953eab34e49c0456d09b0953aed1990a918fdfe1e2ac4fcb3008
+oid sha256:29e852ac37809e83f07dc77bbf455d39061e88497aac86e34ff978ae886d4030
 size 598445936

runs/Feb24_11-48-40_vapratux/events.out.tfevents.1740394121.vapratux.103021.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784ff9e79c0034445c915bbdc4c7d206604b26c9a426ab368c7a6a8344fe3a18
-size 12674
+oid sha256:85a61126788450fcb94722fa32d088b3a17242be8cb7f3335faef65cb501c366
+size 15207

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c02dfc7b956c7a4c519ba888f79aec6174bdeb90be13637f2740c1ffa344c26d
-size 5368
+oid sha256:66a029c761f4cea86c21790fd0329193d5bc22dfd906e17d70a44bf85d133be9
+size 5432