Training in progress, epoch 1

config.json

@@ -21,19 +21,19 @@
   "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
-    "0": "VISUAL_REASONING",
+    "0": "FLUID_REASONING",
     "1": "COMPREHENSION_KNOWLEDGE",
-    "2": "FLUID_REASONING",
-    "3": "QUANTITATIVE_KNOWLEDGE"
+    "2": "QUANTITATIVE_KNOWLEDGE",
+    "3": "VISUAL_REASONING"
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
   "intermediate_size": 1152,
   "label2id": {
     "COMPREHENSION_KNOWLEDGE": "1",
-    "FLUID_REASONING": "2",
-    "QUANTITATIVE_KNOWLEDGE": "3",
-    "VISUAL_REASONING": "0"
+    "FLUID_REASONING": "0",
+    "QUANTITATIVE_KNOWLEDGE": "2",
+    "VISUAL_REASONING": "3"
   },
   "layer_norm_eps": 1e-05,
   "local_attention": 128,
@@ -49,11 +49,12 @@
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "reference_compile": true,
+  "reference_compile": false,
+  "repad_logits_with_grad": false,
   "sep_token_id": 50282,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.0.dev0",
+  "transformers_version": "4.48.0",
   "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870fd765bef3c19a4fb7524e02d1efa25899a80826dd63947b72b5293b825eeb
+oid sha256:76de2558bb10d464053dda8de12d79740022429bf616ccb85e9ce7e06ced86f3
 size 598445936

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7971f83d6a80236f6e66e53d117223d5ba34c2c25c2a75023074e6baedd2423
-size 5432
+oid sha256:887454f3e0f4dfdb7eaac06af34fb8017c6aba600862b128a63ffff4ba7720e3
+size 5368