Training in progress, epoch 1

config.json

@@ -1,6 +1,6 @@
 {
-  "_commit_hash": "a959cf33c20e09215873e338299c900f57047c61",
-  "_name_or_path": "naver-clova-ix/donut-base",
+  "_commit_hash": null,
+  "_name_or_path": "my-model",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -9,7 +9,6 @@
     "activation_dropout": 0.0,
     "activation_function": "gelu",
     "add_cross_attention": true,
-    "add_final_layer_norm": true,
     "architectures": null,
     "attention_dropout": 0.0,
     "bad_words_ids": null,
@@ -22,8 +21,8 @@
     "decoder_attention_heads": 16,
     "decoder_ffn_dim": 4096,
     "decoder_layerdrop": 0.0,
-    "decoder_layers": 4,
-    "decoder_start_token_id": null,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 2,
     "diversity_penalty": 0.0,
     "do_sample": false,
     "dropout": 0.1,
@@ -40,20 +39,22 @@
     "forced_eos_token_id": 2,
     "id2label": {
       "0": "LABEL_0",
-      "1": "LABEL_1"
+      "1": "LABEL_1",
+      "2": "LABEL_2"
     },
     "init_std": 0.02,
     "is_decoder": true,
-    "is_encoder_decoder": false,
+    "is_encoder_decoder": true,
     "label2id": {
       "LABEL_0": 0,
-      "LABEL_1": 1
+      "LABEL_1": 1,
+      "LABEL_2": 2
     },
     "length_penalty": 1.0,
     "max_length": 512,
-    "max_position_embeddings": 1536,
+    "max_position_embeddings": 1024,
     "min_length": 0,
-    "model_type": "mbart",
+    "model_type": "bart",
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
@@ -70,7 +71,7 @@
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "scale_embedding": true,
+    "scale_embedding": false,
     "sep_token_id": null,
     "suppress_tokens": null,
     "task_specific_params": null,
@@ -87,7 +88,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 57537
+    "vocab_size": 57531
   },
   "decoder_start_token_id": 0,
   "encoder": {
@@ -104,15 +105,16 @@
     "depths": [
       2,
       2,
-      14,
+      6,
       2
     ],
     "diversity_penalty": 0.0,
     "do_sample": false,
     "drop_path_rate": 0.1,
     "early_stopping": false,
-    "embed_dim": 128,
+    "embed_dim": 96,
     "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 32,
     "eos_token_id": null,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
@@ -120,7 +122,7 @@
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
-    "hidden_size": 1024,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
@@ -141,19 +143,20 @@
     "max_length": 20,
     "min_length": 0,
     "mlp_ratio": 4.0,
-    "model_type": "donut-swin",
+    "model_type": "swin",
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
     "num_heads": [
-      4,
-      8,
-      16,
-      32
+      3,
+      6,
+      12,
+      24
     ],
     "num_layers": 4,
     "num_return_sequences": 1,
+    "out_features": null,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
@@ -169,6 +172,13 @@
     "return_dict": true,
     "return_dict_in_generate": false,
     "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
     "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
@@ -184,7 +194,7 @@
     "typical_p": 1.0,
     "use_absolute_embeddings": false,
     "use_bfloat16": false,
-    "window_size": 10
+    "window_size": 7
   },
   "is_encoder_decoder": true,
   "model_type": "vision-encoder-decoder",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28371c96c2cab1325beccd7fc9399470744a69401e48132934c43ba0754fe5d5
-size 809224571
+oid sha256:97d177e779ce583dced643e828989e74f48543e43cbf7ef0478e38d07e688e50
+size 1159744119

runs/Oct13_01-25-31_DESKTOP-P4C2GQ0/1697128089.3916984/events.out.tfevents.1697128089.DESKTOP-P4C2GQ0.10744.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0ba9712b34e7de9660002d192c76a05c112d8759b3879d6d58417858355a86
+size 5916

runs/Oct13_01-25-31_DESKTOP-P4C2GQ0/events.out.tfevents.1697128089.DESKTOP-P4C2GQ0.10744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29599b1e66798d81d4d97f7972bfdc8d178aff073812c60d77319814e0554e60
+size 8427

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bef1682a67c4ab58f0c94196b1753c267bf7c2d2b973ccf18662f2461d27953
+oid sha256:07f593c5ebd0f2acbe50f60ed97f0ddac8f32157f049871c3a5f78ac37daa151
 size 3695