Training in progress, epoch 1

config.json

@@ -23,15 +23,15 @@
     "init_std": 0.02,
     "is_decoder": true,
     "is_encoder_decoder": false,
-    "max_length": 1024,
+    "max_length": 512,
     "max_position_embeddings": 1536,
     "model_type": "mbart",
     "num_hidden_layers": 12,
     "scale_embedding": true,
     "use_cache": true,
-    "vocab_size": 57536
+    "vocab_size": 57533
   },
-  "decoder_start_token_id": 41040,
+  "decoder_start_token_id": 0,
   "dtype": "float32",
   "encoder": {
     "attention_probs_dropout_prob": 0.0,
@@ -48,8 +48,8 @@
     "hidden_dropout_prob": 0.0,
     "hidden_size": 1024,
     "image_size": [
-      2338,
-      1654
+      960,
+      720
     ],
     "initializer_range": 0.02,
     "layer_norm_eps": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b670810663d5938e2888c857726c46211a0cc0bf7de7b41ec876f0dcd883b6
-size 809115800
+oid sha256:3bdcfd42248f0774096cb9a08576cdd4acd86eb132013efa7898b16a0170d836
+size 809103512

runs/Dec23_21-26-37_99571680d95d/events.out.tfevents.1766525202.99571680d95d.6856.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb8ec3f577eacc3bad766133836b35ea9856004b23855ba1dfccbed84c35b2e
+size 7386

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1776202e94067ae588d54473eb7b058202c1b54f74ecb7c4e1332c567747e4
+oid sha256:56cdaacf2cf85a6d1fe083b3a5dea16ca923551427a6da55861c3d13106637d6
 size 6033