Training in progress, epoch 1

config.json

@@ -85,7 +85,7 @@
   },
   "decoder_start_token_id": 0,
   "encoder": {
-    "_name_or_path": "google/vit-large-patch16-384",
+    "_name_or_path": "google/vit-base-patch16-384",
     "add_cross_attention": false,
     "architectures": [
       "ViTForImageClassification"
@@ -109,7 +109,7 @@
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
-    "hidden_size": 1024,
+    "hidden_size": 768,
     "id2label": {
       "0": "tench, Tinca tinca",
       "1": "goldfish, Carassius auratus",
@@ -1114,7 +1114,7 @@
     },
     "image_size": 384,
     "initializer_range": 0.02,
-    "intermediate_size": 4096,
+    "intermediate_size": 3072,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -2124,11 +2124,11 @@
     "min_length": 0,
     "model_type": "vit",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 16,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
-    "num_hidden_layers": 24,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39446144a75ed83b4a159da1cb72154dbe6f663a3f612b2d5e43db6e34ab8300
-size 1834458276
+oid sha256:2371b80236ca2f8b5d62586264a192fae13de09de32ff400f45f0cf1e45325d4
+size 959047772

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f69f2b9078d3ef7f7df637b1b4336f3111b1afb1a0ef3a59f96164d47ad590
+oid sha256:1a0f96a1663ea83cf24651aa3e0a3b789a732732fa915133e48bb93d0fa04d8e
 size 4411