Training in progress, epoch 1

config.json

@@ -21,19 +21,19 @@
   "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
-    "0": "VISUAL_REASONING",
-    "1": "COMPREHENSION_KNOWLEDGE",
+    "0": "COMPREHENSION_KNOWLEDGE",
+    "1": "FLUID_REASONING",
     "2": "QUANTITATIVE_KNOWLEDGE",
-    "3": "FLUID_REASONING"
+    "3": "VISUAL_REASONING"
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
   "intermediate_size": 1152,
   "label2id": {
-    "COMPREHENSION_KNOWLEDGE": "1",
-    "FLUID_REASONING": "3",
+    "COMPREHENSION_KNOWLEDGE": "0",
+    "FLUID_REASONING": "1",
     "QUANTITATIVE_KNOWLEDGE": "2",
-    "VISUAL_REASONING": "0"
+    "VISUAL_REASONING": "3"
   },
   "layer_norm_eps": 1e-05,
   "local_attention": 128,
@@ -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:d659f25d6c2233bc79d3746c4d616d5d636a9c58a8ecf115edbfedf7457792d2
+oid sha256:a6dfeffcc6d38c83f72e05413edf68437679feaa78a07886f8eaff7235051530
 size 598445936

runs/Feb24_13-12-51_vapratux/events.out.tfevents.1740399172.vapratux.103021.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9536da663460c3561804cee6715cd945554b2c3eb620b097ce464fb2f009d6
+size 6974

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f4c8aa4de30c419a1af56f5c76821b6d8b84b44e130ad09618e9221ce513d9
-size 5368
+oid sha256:609998671f3b3e2b3d310560c91dfcfd94601c79aa12946d99d9d80a0d331b92
+size 5432