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 sha256:06aaf9ea2063a3fd091f1801b65e0640b2ebc34de7e6df85fc812275ca69e7d2
+oid sha256:ada526f4a85bb6690b25881c52381b04cf0e5639efb67d4d0fb85cb9af383c46
 size 598445936

runs/Feb24_12-16-13_vapratux/events.out.tfevents.1740395774.vapratux.103021.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63da44283916557b6dab3de591d0544ee3f2144217114f3fc5947f6155c92c13
+size 6974

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928ff56558e99192524ff1c39a39bee41655b46afd107405d40cb604564da5b6
-size 5368
+oid sha256:2b575cc4055fd74b99c462a89dd77496ca692d618ca8035fc86dc50bb16b21e7
+size 5432