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 sha256:2fcc041839408c1fcf6ef609b90cd247cc465f192b7bfe7c8796213a33d8b717
+oid sha256:9d551e3674b71fc419d1a422e7b6ff5a7f296e367024511e640146b84ee40bda
 size 598445936

runs/Feb24_12-44-13_vapratux/events.out.tfevents.1740397454.vapratux.103021.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09608ec1085cf3d95e5cc6770f7197d4238b1d12cd864ba21e19460d0faacdef
+size 6974

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c94a56dc387466af442e2b301d92a670c28f6a20e3340f9f151d9cdc4ebc4c
-size 5368
+oid sha256:2970cf00dba7b437cb55dca603400159f95b665d280d2361cc91762036839264
+size 5432