End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -1,4 +1,14 @@
 {
+    "epoch": 13.16,
+    "eval_accuracy": 0.8535829122645843,
+    "eval_f1": 0.9075504610017443,
+    "eval_loss": 0.8330431580543518,
+    "eval_precision": 0.9046199701937406,
+    "eval_recall": 0.9105,
+    "eval_runtime": 2.2353,
+    "eval_samples": 54,
+    "eval_samples_per_second": 24.158,
+    "eval_steps_per_second": 1.789,
     "predict_accuracy": 0.8218373936014088,
     "predict_f1": 0.9038133181559477,
     "predict_loss": 0.6888472437858582,
@@ -6,5 +16,10 @@
     "predict_recall": 0.9126436781609195,
     "predict_runtime": 2.0596,
     "predict_samples_per_second": 8.74,
-    "predict_steps_per_second": 0.971
+    "predict_steps_per_second": 0.971,
+    "train_loss": 0.256378173828125,
+    "train_runtime": 215.2806,
+    "train_samples": 150,
+    "train_samples_per_second": 9.29,
+    "train_steps_per_second": 2.323
 }

config.json

@@ -7,52 +7,57 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "coordinate_size": 128,
+  "device": "cuda",
+  "discrete_vae_type": "dall-e",
+  "discrete_vae_weight_path": "",
   "eos_token_id": 2,
+  "finetuning_task": "ner",
   "has_relative_attention_bias": true,
   "has_spatial_attention_bias": true,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "O",
-    "1": "B-HEADER",
-    "2": "I-HEADER",
-    "3": "B-QUESTION",
-    "4": "I-QUESTION",
-    "5": "B-ANSWER",
-    "6": "I-ANSWER"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
   },
   "initializer_range": 0.02,
   "input_size": 224,
   "intermediate_size": 3072,
   "label2id": {
-    "B-ANSWER": 5,
-    "B-HEADER": 1,
-    "B-QUESTION": 3,
-    "I-ANSWER": 6,
-    "I-HEADER": 2,
-    "I-QUESTION": 4,
-    "O": 0
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
   },
   "layer_norm_eps": 1e-05,
   "max_2d_position_embeddings": 1024,
   "max_position_embeddings": 514,
   "max_rel_2d_pos": 256,
   "max_rel_pos": 128,
+  "mim": false,
   "model_type": "layoutlmv3",
   "num_attention_heads": 12,
-  "num_channels": 3,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "patch_size": 16,
+  "position_embedding_type": "absolute",
   "rel_2d_pos_bins": 64,
   "rel_pos_bins": 32,
   "second_input_size": 112,
   "shape_size": 128,
-  "text_embed": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
+  "transformers_version": "4.12.5",
   "type_vocab_size": 1,
+  "use_cache": true,
   "visual_embed": true,
-  "vocab_size": 50265
+  "vocab_size": 50265,
+  "wpa_task": false
 }

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 13.16,
+    "eval_accuracy": 0.8535829122645843,
+    "eval_f1": 0.9075504610017443,
+    "eval_loss": 0.8330431580543518,
+    "eval_precision": 0.9046199701937406,
+    "eval_recall": 0.9105,
+    "eval_runtime": 2.2353,
+    "eval_samples": 54,
+    "eval_samples_per_second": 24.158,
+    "eval_steps_per_second": 1.789
+}

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a199f09773c9ccd3c9ed282276252abdd4fb21595348d9a4616fad33649056d
+size 501420883

runs/Aug24_17-06-00_bernini/1724512220.8391128/events.out.tfevents.1724512220.bernini.30511.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da857c91ba0f95212eb2f5941c0edb09aec289239a86860b62ca0a310bbb4f4
+size 4689

runs/Aug24_17-06-00_bernini/events.out.tfevents.1724512220.bernini.30511.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db850f850e6bdc9006830635a2ec09bf1e84faec1d01a1f92c9621ebfef20b35
+size 9322

runs/Aug24_17-06-00_bernini/events.out.tfevents.1724512439.bernini.30511.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c5ce7ee0f3e9eb76983011c3502f891d63bfb39cf7822811bf69dd7e3195fd
+size 512

special_tokens_map.json

@@ -1,51 +1 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -1,80 +1 @@
-{
-  "add_prefix_space": true,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "apply_ocr": false,
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "cls_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "only_label_first_subword": true,
-  "pad_token": "<pad>",
-  "pad_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "pad_token_label": -100,
-  "processor_class": "LayoutLMv3Processor",
-  "sep_token": "</s>",
-  "sep_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "tokenizer_class": "LayoutLMv3Tokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>",
-  "use_fast": true
-}
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/layoutlmv3-base", "tokenizer_class": "LayoutLMv3Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 13.16,
+    "train_loss": 0.256378173828125,
+    "train_runtime": 215.2806,
+    "train_samples": 150,
+    "train_samples_per_second": 9.29,
+    "train_steps_per_second": 2.323
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.157894736842104,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.32,
+      "eval_accuracy": 0.8087965089572806,
+      "eval_f1": 0.8503675598766895,
+      "eval_loss": 0.616326630115509,
+      "eval_precision": 0.8087505638249888,
+      "eval_recall": 0.8965,
+      "eval_runtime": 2.4397,
+      "eval_samples_per_second": 22.134,
+      "eval_steps_per_second": 1.64,
+      "step": 50
+    },
+    {
+      "epoch": 2.63,
+      "eval_accuracy": 0.8133899862195683,
+      "eval_f1": 0.8346153846153846,
+      "eval_loss": 0.541599690914154,
+      "eval_precision": 0.8037037037037037,
+      "eval_recall": 0.868,
+      "eval_runtime": 2.2528,
+      "eval_samples_per_second": 23.97,
+      "eval_steps_per_second": 1.776,
+      "step": 100
+    },
+    {
+      "epoch": 3.95,
+      "eval_accuracy": 0.8385392742305926,
+      "eval_f1": 0.8659844054580897,
+      "eval_loss": 0.5571682453155518,
+      "eval_precision": 0.8445817490494296,
+      "eval_recall": 0.8885,
+      "eval_runtime": 2.2592,
+      "eval_samples_per_second": 23.902,
+      "eval_steps_per_second": 1.771,
+      "step": 150
+    },
+    {
+      "epoch": 5.26,
+      "eval_accuracy": 0.8123564538355535,
+      "eval_f1": 0.850608998260005,
+      "eval_loss": 0.7317042350769043,
+      "eval_precision": 0.8457736035590707,
+      "eval_recall": 0.8555,
+      "eval_runtime": 2.2554,
+      "eval_samples_per_second": 23.943,
+      "eval_steps_per_second": 1.774,
+      "step": 200
+    },
+    {
+      "epoch": 6.58,
+      "eval_accuracy": 0.8385392742305926,
+      "eval_f1": 0.8906055320209318,
+      "eval_loss": 0.7219748497009277,
+      "eval_precision": 0.8877297565822156,
+      "eval_recall": 0.8935,
+      "eval_runtime": 2.2283,
+      "eval_samples_per_second": 24.234,
+      "eval_steps_per_second": 1.795,
+      "step": 250
+    },
+    {
+      "epoch": 7.89,
+      "eval_accuracy": 0.8435920992191088,
+      "eval_f1": 0.8914595126753629,
+      "eval_loss": 0.8069794774055481,
+      "eval_precision": 0.8778477944740669,
+      "eval_recall": 0.9055,
+      "eval_runtime": 2.2476,
+      "eval_samples_per_second": 24.025,
+      "eval_steps_per_second": 1.78,
+      "step": 300
+    },
+    {
+      "epoch": 9.21,
+      "eval_accuracy": 0.8477262287551677,
+      "eval_f1": 0.9048562933597621,
+      "eval_loss": 0.7895194888114929,
+      "eval_precision": 0.8968565815324165,
+      "eval_recall": 0.913,
+      "eval_runtime": 2.3704,
+      "eval_samples_per_second": 22.781,
+      "eval_steps_per_second": 1.687,
+      "step": 350
+    },
+    {
+      "epoch": 10.53,
+      "eval_accuracy": 0.8411805236564079,
+      "eval_f1": 0.8912280701754386,
+      "eval_loss": 0.8168221712112427,
+      "eval_precision": 0.893467336683417,
+      "eval_recall": 0.889,
+      "eval_runtime": 2.4315,
+      "eval_samples_per_second": 22.208,
+      "eval_steps_per_second": 1.645,
+      "step": 400
+    },
+    {
+      "epoch": 11.84,
+      "eval_accuracy": 0.8520900321543409,
+      "eval_f1": 0.9061264822134387,
+      "eval_loss": 0.8232607841491699,
+      "eval_precision": 0.8955078125,
+      "eval_recall": 0.917,
+      "eval_runtime": 2.2665,
+      "eval_samples_per_second": 23.825,
+      "eval_steps_per_second": 1.765,
+      "step": 450
+    },
+    {
+      "epoch": 13.16,
+      "learning_rate": 0.0,
+      "loss": 0.2564,
+      "step": 500
+    },
+    {
+      "epoch": 13.16,
+      "eval_accuracy": 0.8535829122645843,
+      "eval_f1": 0.9075504610017443,
+      "eval_loss": 0.8330431580543518,
+      "eval_precision": 0.9046199701937406,
+      "eval_recall": 0.9105,
+      "eval_runtime": 2.224,
+      "eval_samples_per_second": 24.281,
+      "eval_steps_per_second": 1.799,
+      "step": 500
+    },
+    {
+      "epoch": 13.16,
+      "step": 500,
+      "total_flos": 520356947539968.0,
+      "train_loss": 0.256378173828125,
+      "train_runtime": 215.2806,
+      "train_samples_per_second": 9.29,
+      "train_steps_per_second": 2.323
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 14,
+  "total_flos": 520356947539968.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a00e9e2eb4d526ef08352565518f227fb0a5281651fc78cd4ba3cb25fb2f28
-size 5240
+oid sha256:3ff27db448ecc4f0766af29a31b5c5ce5b719f6114c6d3e3be5126e0327583fa
+size 2991