End of training

README.md

@@ -1,199 +1,50 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- image-segmentation
+- instance-segmentation
+- vision
+- generated_from_trainer
+model-index:
+- name: table-transformer-page-segmentation-floorplan
+  results: []
 ---
 
-# Model Card for Model ID
+<!-- 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. -->
 
-<!-- Provide a quick summary of what the model is/does. -->
+# table-transformer-page-segmentation-floorplan
 
+This model was trained from scratch on an unknown dataset.
 
+## Model description
 
-## Model Details
+More information needed
 
-### Model Description
+## Intended uses & limitations
 
-<!-- Provide a longer summary of what this model is. -->
+More information needed
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## Training and evaluation data
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+More information needed
 
-### Model Sources [optional]
+## Training procedure
 
-<!-- Provide the basic links for the model. -->
+### Training hyperparameters
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 50.0
 
-## Uses
+### Framework versions
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "/home/azureuser/cloudfiles/code/Users/nick.degroot/page-segmentation/runs/20250307-table-transformer-is-floorplan/checkpoint-7428",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "TableTransformerForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet18",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "ce_loss_coefficient": 1,
+  "class_cost": 1,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.4,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "layer_non_floorplan",
+    "1": "layer_floorplan"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "layer_floorplan": 1,
+    "layer_non_floorplan": 0
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "table-transformer",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 15,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a682bc0f0fb2b5cf9b07eec1294fe526bc6eeeba51307a3d77a57348dd920cb5
+size 115317108

runs/Mar08_00-10-39_nick-train/events.out.tfevents.1741392684.nick-train.9917.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9eb407c8951ffb5f5dc95ae54e619cf6ca5f451f0d7813cc45368bdd85f3ce
+size 6433

runs/Mar08_00-19-05_nick-train/events.out.tfevents.1741393160.nick-train.10390.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0636133fdd3dc1899421e412cc0bdc61a6ea1d4391e52e5e876d4fd65f2d8a4
+size 22837

runs/Mar10_17-19-56_nick-train/events.out.tfevents.1741627521.nick-train.4611.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148ff285d1285cf9dddd779497ef593ad6fdc83f7557f39a2e3cd701497e73d3
+size 21681

runs/Mar10_20-57-17_nick-train/events.out.tfevents.1741640263.nick-train.8610.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c80f59d7a6c75eafd336e09bfc48456c1f225f4be54d619a4f0229e07124fe0
+size 6401

runs/Mar10_20-59-40_nick-train/events.out.tfevents.1741640428.nick-train.8770.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc5b6980317de76a319262f51b0cde6846f84aa14c53b20837db3b0e2258b14
+size 6437

runs/Mar10_21-01-41_nick-train/events.out.tfevents.1741640553.nick-train.8931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd41761957a1395e8f378065666ed3c68bf32efd3e2fcc84de77a76d29ba159
+size 6437

runs/Mar10_21-04-06_nick-train/events.out.tfevents.1741640692.nick-train.9090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ff09ec972db8abed2ac596e84ccba4f3a1a4150699b72b68a2d7bd22518dac
+size 12784

runs/Mar10_21-08-31_nick-train/events.out.tfevents.1741641023.nick-train.9295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a48e1a436c2933ca02b44a4e314eb629f09abb9eb4294eefc94eba2e357f16
+size 1197

test_results.json

@@ -0,0 +1,23 @@
+{
+    "test_loss": 1.0017343759536743,
+    "test_map": 0.5854,
+    "test_map_50": 0.7887,
+    "test_map_75": 0.671,
+    "test_map_large": 0.5858,
+    "test_map_layer_floorplan": 0.6009,
+    "test_map_layer_non_floorplan": 0.5699,
+    "test_map_medium": 0.0,
+    "test_map_small": 0.0,
+    "test_mar_1": 0.5276,
+    "test_mar_10": 0.7597,
+    "test_mar_100": 0.7648,
+    "test_mar_100_layer_floorplan": 0.768,
+    "test_mar_100_layer_non_floorplan": 0.7616,
+    "test_mar_large": 0.7652,
+    "test_mar_medium": 0.0,
+    "test_mar_small": 0.0,
+    "test_model_preparation_time": 0.0051,
+    "test_runtime": 99.1744,
+    "test_samples_per_second": 22.173,
+    "test_steps_per_second": 1.391
+}

trainer_state.json

@@ -0,0 +1,755 @@
+{
+  "best_metric": 0.5854,
+  "best_model_checkpoint": "/home/azureuser/cloudfiles/code/Users/nick.degroot/page-segmentation/runs/20250307-table-transformer-is-floorplan/checkpoint-14237",
+  "epoch": 23.0,
+  "eval_steps": 500,
+  "global_step": 14237,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.473027229309082,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9573,
+      "step": 619
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.048191785812378,
+      "eval_map": 0.4914,
+      "eval_map_50": 0.7176,
+      "eval_map_75": 0.5594,
+      "eval_map_large": 0.4916,
+      "eval_map_layer_floorplan": 0.4995,
+      "eval_map_layer_non_floorplan": 0.4832,
+      "eval_map_medium": 0.0,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.4913,
+      "eval_mar_10": 0.7178,
+      "eval_mar_100": 0.7221,
+      "eval_mar_100_layer_floorplan": 0.7331,
+      "eval_mar_100_layer_non_floorplan": 0.7112,
+      "eval_mar_large": 0.7225,
+      "eval_mar_medium": 0.0,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 96.7259,
+      "eval_samples_per_second": 22.734,
+      "eval_steps_per_second": 1.427,
+      "step": 619
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.47475528717041,
+      "learning_rate": 4.8e-05,
+      "loss": 0.9177,
+      "step": 1238
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0183632373809814,
+      "eval_map": 0.5167,
+      "eval_map_50": 0.7402,
+      "eval_map_75": 0.5901,
+      "eval_map_large": 0.517,
+      "eval_map_layer_floorplan": 0.524,
+      "eval_map_layer_non_floorplan": 0.5093,
+      "eval_map_medium": 0.0,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5002,
+      "eval_mar_10": 0.7294,
+      "eval_mar_100": 0.7339,
+      "eval_mar_100_layer_floorplan": 0.74,
+      "eval_mar_100_layer_non_floorplan": 0.7278,
+      "eval_mar_large": 0.7343,
+      "eval_mar_medium": 0.0,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 98.7563,
+      "eval_samples_per_second": 22.267,
+      "eval_steps_per_second": 1.397,
+      "step": 1238
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 20.04204750061035,
+      "learning_rate": 4.7e-05,
+      "loss": 0.8733,
+      "step": 1857
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.004949927330017,
+      "eval_map": 0.513,
+      "eval_map_50": 0.7336,
+      "eval_map_75": 0.592,
+      "eval_map_large": 0.5133,
+      "eval_map_layer_floorplan": 0.5146,
+      "eval_map_layer_non_floorplan": 0.5115,
+      "eval_map_medium": 0.101,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5033,
+      "eval_mar_10": 0.7314,
+      "eval_mar_100": 0.7355,
+      "eval_mar_100_layer_floorplan": 0.7343,
+      "eval_mar_100_layer_non_floorplan": 0.7367,
+      "eval_mar_large": 0.7359,
+      "eval_mar_medium": 0.1,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 99.4564,
+      "eval_samples_per_second": 22.11,
+      "eval_steps_per_second": 1.388,
+      "step": 1857
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 13.674722671508789,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.8412,
+      "step": 2476
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9946977496147156,
+      "eval_map": 0.5209,
+      "eval_map_50": 0.7417,
+      "eval_map_75": 0.6007,
+      "eval_map_large": 0.5212,
+      "eval_map_layer_floorplan": 0.5212,
+      "eval_map_layer_non_floorplan": 0.5207,
+      "eval_map_medium": 0.0,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5025,
+      "eval_mar_10": 0.7295,
+      "eval_mar_100": 0.7341,
+      "eval_mar_100_layer_floorplan": 0.7329,
+      "eval_mar_100_layer_non_floorplan": 0.7352,
+      "eval_mar_large": 0.7345,
+      "eval_mar_medium": 0.0,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 99.2293,
+      "eval_samples_per_second": 22.161,
+      "eval_steps_per_second": 1.391,
+      "step": 2476
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 16.09870719909668,
+      "learning_rate": 4.5e-05,
+      "loss": 0.8108,
+      "step": 3095
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.0007381439208984,
+      "eval_map": 0.5323,
+      "eval_map_50": 0.76,
+      "eval_map_75": 0.6165,
+      "eval_map_large": 0.5326,
+      "eval_map_layer_floorplan": 0.5335,
+      "eval_map_layer_non_floorplan": 0.5311,
+      "eval_map_medium": 0.0,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.4993,
+      "eval_mar_10": 0.7173,
+      "eval_mar_100": 0.7217,
+      "eval_mar_100_layer_floorplan": 0.7096,
+      "eval_mar_100_layer_non_floorplan": 0.7339,
+      "eval_mar_large": 0.7221,
+      "eval_mar_medium": 0.0,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 102.6206,
+      "eval_samples_per_second": 21.428,
+      "eval_steps_per_second": 1.345,
+      "step": 3095
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 12.526081085205078,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.7762,
+      "step": 3714
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.002115249633789,
+      "eval_map": 0.5456,
+      "eval_map_50": 0.7755,
+      "eval_map_75": 0.6331,
+      "eval_map_large": 0.5459,
+      "eval_map_layer_floorplan": 0.5596,
+      "eval_map_layer_non_floorplan": 0.5315,
+      "eval_map_medium": 0.0,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5189,
+      "eval_mar_10": 0.7423,
+      "eval_mar_100": 0.7473,
+      "eval_mar_100_layer_floorplan": 0.7634,
+      "eval_mar_100_layer_non_floorplan": 0.7312,
+      "eval_mar_large": 0.7477,
+      "eval_mar_medium": 0.0,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 198.1173,
+      "eval_samples_per_second": 11.099,
+      "eval_steps_per_second": 0.697,
+      "step": 3714
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 14.044904708862305,
+      "learning_rate": 4.3e-05,
+      "loss": 0.7409,
+      "step": 4333
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.980305552482605,
+      "eval_map": 0.5279,
+      "eval_map_50": 0.742,
+      "eval_map_75": 0.6106,
+      "eval_map_large": 0.5283,
+      "eval_map_layer_floorplan": 0.519,
+      "eval_map_layer_non_floorplan": 0.5369,
+      "eval_map_medium": 0.0,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.499,
+      "eval_mar_10": 0.713,
+      "eval_mar_100": 0.7182,
+      "eval_mar_100_layer_floorplan": 0.6898,
+      "eval_mar_100_layer_non_floorplan": 0.7465,
+      "eval_mar_large": 0.7186,
+      "eval_mar_medium": 0.0,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 209.8003,
+      "eval_samples_per_second": 10.481,
+      "eval_steps_per_second": 0.658,
+      "step": 4333
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 9.8011474609375,
+      "learning_rate": 4.2e-05,
+      "loss": 0.7191,
+      "step": 4952
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.9737862348556519,
+      "eval_map": 0.5495,
+      "eval_map_50": 0.7693,
+      "eval_map_75": 0.6357,
+      "eval_map_large": 0.5497,
+      "eval_map_layer_floorplan": 0.5569,
+      "eval_map_layer_non_floorplan": 0.542,
+      "eval_map_medium": 0.101,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5066,
+      "eval_mar_10": 0.7273,
+      "eval_mar_100": 0.7321,
+      "eval_mar_100_layer_floorplan": 0.7217,
+      "eval_mar_100_layer_non_floorplan": 0.7424,
+      "eval_mar_large": 0.7324,
+      "eval_mar_medium": 0.1,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 144.0008,
+      "eval_samples_per_second": 15.271,
+      "eval_steps_per_second": 0.958,
+      "step": 4952
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 17.39337730407715,
+      "learning_rate": 4.1e-05,
+      "loss": 0.6875,
+      "step": 5571
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9566386938095093,
+      "eval_map": 0.5568,
+      "eval_map_50": 0.7737,
+      "eval_map_75": 0.6427,
+      "eval_map_large": 0.5571,
+      "eval_map_layer_floorplan": 0.5738,
+      "eval_map_layer_non_floorplan": 0.5398,
+      "eval_map_medium": 0.101,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5216,
+      "eval_mar_10": 0.7445,
+      "eval_mar_100": 0.7495,
+      "eval_mar_100_layer_floorplan": 0.7502,
+      "eval_mar_100_layer_non_floorplan": 0.7488,
+      "eval_mar_large": 0.7499,
+      "eval_mar_medium": 0.1,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 196.7202,
+      "eval_samples_per_second": 11.178,
+      "eval_steps_per_second": 0.702,
+      "step": 5571
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 23.622432708740234,
+      "learning_rate": 4e-05,
+      "loss": 0.6574,
+      "step": 6190
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.9592899084091187,
+      "eval_map": 0.566,
+      "eval_map_50": 0.7816,
+      "eval_map_75": 0.6534,
+      "eval_map_large": 0.5663,
+      "eval_map_layer_floorplan": 0.5839,
+      "eval_map_layer_non_floorplan": 0.5481,
+      "eval_map_medium": 0.101,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5291,
+      "eval_mar_10": 0.7545,
+      "eval_mar_100": 0.7593,
+      "eval_mar_100_layer_floorplan": 0.771,
+      "eval_mar_100_layer_non_floorplan": 0.7477,
+      "eval_mar_large": 0.7597,
+      "eval_mar_medium": 0.1,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 202.0923,
+      "eval_samples_per_second": 10.881,
+      "eval_steps_per_second": 0.683,
+      "step": 6190
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 13.85277271270752,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.6332,
+      "step": 6809
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.9667688012123108,
+      "eval_map": 0.5658,
+      "eval_map_50": 0.7827,
+      "eval_map_75": 0.6532,
+      "eval_map_large": 0.566,
+      "eval_map_layer_floorplan": 0.5933,
+      "eval_map_layer_non_floorplan": 0.5382,
+      "eval_map_medium": 0.0505,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5277,
+      "eval_mar_10": 0.7522,
+      "eval_mar_100": 0.7575,
+      "eval_mar_100_layer_floorplan": 0.7712,
+      "eval_mar_100_layer_non_floorplan": 0.7439,
+      "eval_mar_large": 0.7579,
+      "eval_mar_medium": 0.05,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 160.7511,
+      "eval_samples_per_second": 13.68,
+      "eval_steps_per_second": 0.858,
+      "step": 6809
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 9.858610153198242,
+      "learning_rate": 3.8e-05,
+      "loss": 0.607,
+      "step": 7428
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.9639933109283447,
+      "eval_map": 0.5617,
+      "eval_map_50": 0.7748,
+      "eval_map_75": 0.6539,
+      "eval_map_large": 0.562,
+      "eval_map_layer_floorplan": 0.5682,
+      "eval_map_layer_non_floorplan": 0.5553,
+      "eval_map_medium": 0.1515,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5244,
+      "eval_mar_10": 0.7477,
+      "eval_mar_100": 0.7535,
+      "eval_mar_100_layer_floorplan": 0.7554,
+      "eval_mar_100_layer_non_floorplan": 0.7517,
+      "eval_mar_large": 0.7539,
+      "eval_mar_medium": 0.15,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 291.5919,
+      "eval_samples_per_second": 7.541,
+      "eval_steps_per_second": 0.473,
+      "step": 7428
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 12.362223625183105,
+      "learning_rate": 3.7e-05,
+      "loss": 0.5848,
+      "step": 8047
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.9631391167640686,
+      "eval_map": 0.5616,
+      "eval_map_50": 0.7762,
+      "eval_map_75": 0.6555,
+      "eval_map_large": 0.5619,
+      "eval_map_layer_floorplan": 0.5612,
+      "eval_map_layer_non_floorplan": 0.562,
+      "eval_map_medium": 0.202,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5228,
+      "eval_mar_10": 0.7442,
+      "eval_mar_100": 0.7493,
+      "eval_mar_100_layer_floorplan": 0.7451,
+      "eval_mar_100_layer_non_floorplan": 0.7534,
+      "eval_mar_large": 0.7496,
+      "eval_mar_medium": 0.2,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 96.8323,
+      "eval_samples_per_second": 22.709,
+      "eval_steps_per_second": 1.425,
+      "step": 8047
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 13.06834888458252,
+      "learning_rate": 3.6e-05,
+      "loss": 0.5699,
+      "step": 8666
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.9597959518432617,
+      "eval_map": 0.5661,
+      "eval_map_50": 0.7729,
+      "eval_map_75": 0.6515,
+      "eval_map_large": 0.5663,
+      "eval_map_layer_floorplan": 0.5704,
+      "eval_map_layer_non_floorplan": 0.5618,
+      "eval_map_medium": 0.303,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5281,
+      "eval_mar_10": 0.7506,
+      "eval_mar_100": 0.7559,
+      "eval_mar_100_layer_floorplan": 0.7567,
+      "eval_mar_100_layer_non_floorplan": 0.755,
+      "eval_mar_large": 0.7562,
+      "eval_mar_medium": 0.3,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 95.7299,
+      "eval_samples_per_second": 22.971,
+      "eval_steps_per_second": 1.442,
+      "step": 8666
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 14.259442329406738,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5423,
+      "step": 9285
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.9839197993278503,
+      "eval_map": 0.5705,
+      "eval_map_50": 0.7785,
+      "eval_map_75": 0.657,
+      "eval_map_large": 0.5708,
+      "eval_map_layer_floorplan": 0.5797,
+      "eval_map_layer_non_floorplan": 0.5612,
+      "eval_map_medium": 0.101,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5305,
+      "eval_mar_10": 0.7529,
+      "eval_mar_100": 0.7584,
+      "eval_mar_100_layer_floorplan": 0.7634,
+      "eval_mar_100_layer_non_floorplan": 0.7534,
+      "eval_mar_large": 0.7588,
+      "eval_mar_medium": 0.1,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 97.4975,
+      "eval_samples_per_second": 22.554,
+      "eval_steps_per_second": 1.415,
+      "step": 9285
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 18.98026466369629,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.5249,
+      "step": 9904
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.9859117865562439,
+      "eval_map": 0.5662,
+      "eval_map_50": 0.7755,
+      "eval_map_75": 0.6497,
+      "eval_map_large": 0.5663,
+      "eval_map_layer_floorplan": 0.5673,
+      "eval_map_layer_non_floorplan": 0.565,
+      "eval_map_medium": 0.404,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5144,
+      "eval_mar_10": 0.7364,
+      "eval_mar_100": 0.7422,
+      "eval_mar_100_layer_floorplan": 0.726,
+      "eval_mar_100_layer_non_floorplan": 0.7583,
+      "eval_mar_large": 0.7424,
+      "eval_mar_medium": 0.4,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 98.0807,
+      "eval_samples_per_second": 22.42,
+      "eval_steps_per_second": 1.407,
+      "step": 9904
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 10.991700172424316,
+      "learning_rate": 3.3e-05,
+      "loss": 0.5071,
+      "step": 10523
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.9921765923500061,
+      "eval_map": 0.5737,
+      "eval_map_50": 0.7827,
+      "eval_map_75": 0.6516,
+      "eval_map_large": 0.5739,
+      "eval_map_layer_floorplan": 0.5805,
+      "eval_map_layer_non_floorplan": 0.567,
+      "eval_map_medium": 0.303,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5194,
+      "eval_mar_10": 0.7465,
+      "eval_mar_100": 0.7525,
+      "eval_mar_100_layer_floorplan": 0.7471,
+      "eval_mar_100_layer_non_floorplan": 0.7579,
+      "eval_mar_large": 0.7528,
+      "eval_mar_medium": 0.3,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 114.1971,
+      "eval_samples_per_second": 19.256,
+      "eval_steps_per_second": 1.208,
+      "step": 10523
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 11.373696327209473,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.4895,
+      "step": 11142
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 0.9796280860900879,
+      "eval_map": 0.5763,
+      "eval_map_50": 0.7822,
+      "eval_map_75": 0.6614,
+      "eval_map_large": 0.5767,
+      "eval_map_layer_floorplan": 0.5869,
+      "eval_map_layer_non_floorplan": 0.5658,
+      "eval_map_medium": 0.101,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5269,
+      "eval_mar_10": 0.7526,
+      "eval_mar_100": 0.7583,
+      "eval_mar_100_layer_floorplan": 0.7582,
+      "eval_mar_100_layer_non_floorplan": 0.7584,
+      "eval_mar_large": 0.7587,
+      "eval_mar_medium": 0.1,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 164.2202,
+      "eval_samples_per_second": 13.391,
+      "eval_steps_per_second": 0.84,
+      "step": 11142
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 15.639002799987793,
+      "learning_rate": 3.1e-05,
+      "loss": 0.4784,
+      "step": 11761
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.9923657774925232,
+      "eval_map": 0.5794,
+      "eval_map_50": 0.7862,
+      "eval_map_75": 0.6607,
+      "eval_map_large": 0.5797,
+      "eval_map_layer_floorplan": 0.5907,
+      "eval_map_layer_non_floorplan": 0.5682,
+      "eval_map_medium": 0.2525,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5286,
+      "eval_mar_10": 0.7549,
+      "eval_mar_100": 0.7611,
+      "eval_mar_100_layer_floorplan": 0.76,
+      "eval_mar_100_layer_non_floorplan": 0.7623,
+      "eval_mar_large": 0.7614,
+      "eval_mar_medium": 0.25,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 148.8739,
+      "eval_samples_per_second": 14.771,
+      "eval_steps_per_second": 0.927,
+      "step": 11761
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 11.518092155456543,
+      "learning_rate": 3e-05,
+      "loss": 0.4621,
+      "step": 12380
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.9944785833358765,
+      "eval_map": 0.5815,
+      "eval_map_50": 0.7851,
+      "eval_map_75": 0.6678,
+      "eval_map_large": 0.5816,
+      "eval_map_layer_floorplan": 0.5936,
+      "eval_map_layer_non_floorplan": 0.5694,
+      "eval_map_medium": 0.404,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.53,
+      "eval_mar_10": 0.7575,
+      "eval_mar_100": 0.7625,
+      "eval_mar_100_layer_floorplan": 0.7674,
+      "eval_mar_100_layer_non_floorplan": 0.7576,
+      "eval_mar_large": 0.7628,
+      "eval_mar_medium": 0.4,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 150.1731,
+      "eval_samples_per_second": 14.643,
+      "eval_steps_per_second": 0.919,
+      "step": 12380
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 11.369315147399902,
+      "learning_rate": 2.9e-05,
+      "loss": 0.4484,
+      "step": 12999
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.0060081481933594,
+      "eval_map": 0.5747,
+      "eval_map_50": 0.7778,
+      "eval_map_75": 0.6543,
+      "eval_map_large": 0.575,
+      "eval_map_layer_floorplan": 0.5877,
+      "eval_map_layer_non_floorplan": 0.5617,
+      "eval_map_medium": 0.202,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5261,
+      "eval_mar_10": 0.7515,
+      "eval_mar_100": 0.7567,
+      "eval_mar_100_layer_floorplan": 0.7567,
+      "eval_mar_100_layer_non_floorplan": 0.7567,
+      "eval_mar_large": 0.7571,
+      "eval_mar_medium": 0.2,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 129.9803,
+      "eval_samples_per_second": 16.918,
+      "eval_steps_per_second": 1.062,
+      "step": 12999
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 14.859123229980469,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.4358,
+      "step": 13618
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 0.9802154898643494,
+      "eval_map": 0.5826,
+      "eval_map_50": 0.7803,
+      "eval_map_75": 0.6678,
+      "eval_map_large": 0.5829,
+      "eval_map_layer_floorplan": 0.5968,
+      "eval_map_layer_non_floorplan": 0.5683,
+      "eval_map_medium": 0.0505,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5264,
+      "eval_mar_10": 0.7593,
+      "eval_mar_100": 0.7652,
+      "eval_mar_100_layer_floorplan": 0.7666,
+      "eval_mar_100_layer_non_floorplan": 0.7638,
+      "eval_mar_large": 0.7656,
+      "eval_mar_medium": 0.05,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 127.1201,
+      "eval_samples_per_second": 17.299,
+      "eval_steps_per_second": 1.086,
+      "step": 13618
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 12.832348823547363,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.4236,
+      "step": 14237
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.0017343759536743,
+      "eval_map": 0.5854,
+      "eval_map_50": 0.7887,
+      "eval_map_75": 0.671,
+      "eval_map_large": 0.5858,
+      "eval_map_layer_floorplan": 0.6009,
+      "eval_map_layer_non_floorplan": 0.5699,
+      "eval_map_medium": 0.0,
+      "eval_map_small": 0.0,
+      "eval_mar_1": 0.5276,
+      "eval_mar_10": 0.7597,
+      "eval_mar_100": 0.7648,
+      "eval_mar_100_layer_floorplan": 0.768,
+      "eval_mar_100_layer_non_floorplan": 0.7616,
+      "eval_mar_large": 0.7652,
+      "eval_mar_medium": 0.0,
+      "eval_mar_small": 0.0,
+      "eval_runtime": 219.2113,
+      "eval_samples_per_second": 10.031,
+      "eval_steps_per_second": 0.63,
+      "step": 14237
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 30950,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4729502081028093e+20,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59973ae866477c99cd8f7e62f6ff7d4406962f0b9d9546ec63649b9841bbb302
+size 5688