Training in progress, epoch 1

README.md

@@ -1,3 +1,72 @@
----
-license: mit
----
+---
+library_name: transformers
+license: apache-2.0
+base_model: TomasFAV/Pix2StructCzechInvoice
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: Pix2StructCzechInvoiceV1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Pix2StructCzechInvoiceV1
+
+This model is a fine-tuned version of [TomasFAV/Pix2StructCzechInvoice](https://huggingface.co/TomasFAV/Pix2StructCzechInvoice) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4679
+- F1: 0.6432
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1978        | 1.0   | 75   | 0.3757          | 0.5804 |
+| 0.1031        | 2.0   | 150  | 0.3578          | 0.6399 |
+| 0.0725        | 3.0   | 225  | 0.3504          | 0.6318 |
+| 0.0512        | 4.0   | 300  | 0.3929          | 0.6396 |
+| 0.0500        | 5.0   | 375  | 0.4072          | 0.6394 |
+| 0.0462        | 6.0   | 450  | 0.4655          | 0.4377 |
+| 0.0502        | 7.0   | 525  | 0.6320          | 0.3384 |
+| 0.0528        | 8.0   | 600  | 0.4835          | 0.5018 |
+| 0.0393        | 9.0   | 675  | 0.4679          | 0.6432 |
+| 0.0392        | 10.0  | 750  | 0.5330          | 0.4931 |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

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:b7c397026a886c650591eebd8b14f3c8176e86e6151245883696a8a8772bfdbb
+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:a5deb0ca1f22b1c6f4aa4dcf486483e33fde84d1348f5ec24d1589b68d81d1fd
+size 25741

runs/Mar14_23-53-02_77b291cf41b2/events.out.tfevents.1773534537.77b291cf41b2.903.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37aa2724b2be2089dd9468656452b1fabb68b7da7c33e70ff22e67cf08b5a5d4
+size 405

runs/Mar15_00-30-03_77b291cf41b2/events.out.tfevents.1773534603.77b291cf41b2.11106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e202322a62fefd2d5afdfa69bb2fc38549ed2345ece3cbd957ef65ae286c4bad
+size 9034

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6e133d9d7cbd69f0474fc0ae2c121e589f9dc8bbee7515ed5e526c180572a7
+size 5393