Training in progress, epoch 1

config.json

@@ -0,0 +1,96 @@
+{
+  "architectures": [
+    "Pix2StructForConditionalGeneration"
+  ],
+  "decoder_start_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "is_vqa": true,
+  "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": "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,
+    "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

@@ -0,0 +1,38 @@
+{
+  "_from_model_config": false,
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "decoder_start_token_id": 0,
+  "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,
+  "is_vqa": true,
+  "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,
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5901813f540d1135bfc0b5c5315a5acb2a7d6a9a94958d9fa4c16cf3f663553d
+size 1130333048

runs/Mar14_23-53-02_77b291cf41b2/events.out.tfevents.1773532382.77b291cf41b2.903.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53121787ea952993127fb993230b9d9fce792ed453b7b2e2d4605bfd073fb221
+size 8206

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322207a7e24e485920a18a55467921f09607d5fe20761065d5dce3794e54c722
+size 5393