Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/trocr-large-printed",
+  "_name_or_path": "microsoft/trocr-large-stage1",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -15,7 +15,7 @@
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
     "classifier_dropout": 0.0,
-    "cross_attention_hidden_size": 1024,
+    "cross_attention_hidden_size": null,
     "d_model": 1024,
     "decoder_attention_heads": 16,
     "decoder_ffn_dim": 4096,
@@ -26,6 +26,7 @@
     "do_sample": false,
     "dropout": 0.1,
     "early_stopping": false,
+    "encoder_hidden_size": 1024,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 2,
     "exponential_decay_length_penalty": null,
@@ -172,6 +173,6 @@
   "pad_token_id": 1,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.36.0",
+  "transformers_version": "4.37.2",
   "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab93b8850e4aa64f1a8799ae7c343d93facb9060b8b43479d1737408e4210c46
+oid sha256:bee196663a8d7d2735603e71e8c2d6d058984dd011a8b87454d4ce4ac6483f70
 size 2436757100

runs/Feb12_20-07-43_104-171-203-98/events.out.tfevents.1707768464.104-171-203-98.2525.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9afcb2743806e6428a5eaa86e724b178e8e560f033be123a553d1a2814a6b24
+size 9306

runs/Feb12_20-11-05_104-171-203-98/events.out.tfevents.1707768665.104-171-203-98.10676.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aaee1b1b63a49f7de9269c360525fb1f1b99e567513df3d468ae9af9b91d3d1
+size 56403

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1817677f4eb80a970d83e3fd86a70c037f25d13b69d9cecb0a57f597c874cf3f
-size 4411
+oid sha256:77d2f2aac669541bf81947f1f8f4dc60450ab9f1696170ab8d2eb969c2f769af
+size 4475