Training in progress, epoch 1

config.json

@@ -12,48 +12,85 @@
   "model_type": "pix2struct",
   "pad_token_id": 0,
   "text_config": {
+    "add_cross_attention": false,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
     "d_ff": 2048,
     "d_kv": 64,
+    "decoder_start_token_id": 0,
     "dense_act_fn": "gelu_new",
     "dropout_rate": 0.1,
     "dtype": "float32",
     "encoder_hidden_size": 768,
+    "eos_token_id": 1,
+    "finetuning_task": null,
     "hidden_size": 768,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
+    "is_decoder": true,
     "is_encoder_decoder": true,
     "layer_norm_epsilon": 1e-06,
     "model_type": "pix2struct_text_model",
     "num_heads": 12,
     "num_layers": 12,
+    "pad_token_id": 0,
+    "prefix": null,
+    "pruned_heads": {},
     "relative_attention_max_distance": 128,
     "relative_attention_num_buckets": 32,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false,
     "use_cache": false,
     "vocab_size": 50432
   },
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.6",
+  "transformers_version": "5.0.0",
+  "use_cache": false,
   "vision_config": {
+    "add_cross_attention": false,
     "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
     "d_ff": 2048,
     "d_kv": 64,
+    "decoder_start_token_id": null,
     "dense_act_fn": "gelu_new",
     "dropout_rate": 0.0,
     "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
     "hidden_size": 768,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
+    "is_decoder": false,
     "layer_norm_bias": false,
     "layer_norm_eps": 1e-06,
     "model_type": "pix2struct_vision_model",
     "num_attention_heads": 12,
     "num_channels": 3,
     "num_hidden_layers": 12,
+    "pad_token_id": null,
     "patch_embed_hidden_size": 768,
     "patch_size": 16,
+    "prefix": null,
     "projection_dim": 768,
+    "pruned_heads": {},
     "relative_attention_max_distance": 128,
     "relative_attention_num_buckets": 32,
-    "seq_len": 4096
+    "sep_token_id": null,
+    "seq_len": 4096,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false
   }
 }

generation_config.json

@@ -1,10 +1,37 @@
 {
-  "_from_model_config": true,
+  "_from_model_config": false,
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
   "decoder_start_token_id": 0,
-  "eos_token_id": [
-    1
-  ],
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 1,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
   "pad_token_id": 0,
-  "transformers_version": "4.57.6",
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.0.0",
+  "typical_p": 1.0,
   "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3940f7c9aedc1462944844240007f93a9408d44e91b2ad6976f1a90fdd2e7824
+oid sha256:3d1baccf6a548300f308e5cf73aa1f66e08d22b16b0f08df9ce350b54a27c80e
 size 1130333048

runs/Mar14_20-34-13_5ae8aa8c2e3d/events.out.tfevents.1773520453.5ae8aa8c2e3d.3669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c000dbf3befb9e059818c223eafef55afbf1124e9c29a8fb1002dfb083e815a9
+size 12726

runs/Mar14_20-43-28_5ae8aa8c2e3d/events.out.tfevents.1773521008.5ae8aa8c2e3d.3669.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70532a26f82a1c971b13f0da71451057b6fcf5c4fd1116399cb75ac4f870e77c
+size 13043

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3acef359c1c419af021199467e761a7dd71aef22ce5c5878809a5b738e9b8ca4
-size 6033
+oid sha256:6b096720e0ea837863085e7628764c14d82809b7fd00afeb91e0ea441d55be28
+size 5393