Training in progress, step 3000

checkpoint-2100/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:512527b7eee38db411ede8d4a5208a6de7ea4cf290d62c72ab4bebf8c05949c3
-size 1476527911

checkpoint-2100/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3baf3eb940f9c08d86eacafabb898ebe3902336c36d8fa207a86fe12023b6e48
-size 14503

checkpoint-2100/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:68ab0d467c1a39d8e6af3831a4424f6b07abf2138b9e8e3583edebceab5bd2f1
-size 559

checkpoint-2100/trainer_state.json

@@ -1,124 +0,0 @@
-{
-  "best_metric": 0.6593356503902912,
-  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-2100",
-  "epoch": 0.8724553385957624,
-  "global_step": 2100,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.12,
-      "eval_accuracy": 0.8412902144953226,
-      "eval_f1": 0.13109765966400155,
-      "eval_loss": 0.5185014605522156,
-      "eval_precision": 0.14371894960965223,
-      "eval_recall": 0.1205141938939475,
-      "eval_runtime": 363.2958,
-      "eval_samples_per_second": 5.648,
-      "eval_steps_per_second": 0.355,
-      "step": 300
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 1.372060857538036e-05,
-      "loss": 0.9231,
-      "step": 500
-    },
-    {
-      "epoch": 0.25,
-      "eval_accuracy": 0.8751371332529899,
-      "eval_f1": 0.5030902012034086,
-      "eval_loss": 0.4107707738876343,
-      "eval_precision": 0.4636655625815517,
-      "eval_recall": 0.5498422900672499,
-      "eval_runtime": 366.1838,
-      "eval_samples_per_second": 5.604,
-      "eval_steps_per_second": 0.352,
-      "step": 600
-    },
-    {
-      "epoch": 0.37,
-      "eval_accuracy": 0.8887072454995973,
-      "eval_f1": 0.520614670919107,
-      "eval_loss": 0.3911038935184479,
-      "eval_precision": 0.5076044552496184,
-      "eval_recall": 0.5343093495209189,
-      "eval_runtime": 358.5079,
-      "eval_samples_per_second": 5.724,
-      "eval_steps_per_second": 0.36,
-      "step": 900
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 1.9159741458910434e-05,
-      "loss": 0.369,
-      "step": 1000
-    },
-    {
-      "epoch": 0.5,
-      "eval_accuracy": 0.8723944681931917,
-      "eval_f1": 0.5365372697053354,
-      "eval_loss": 0.41175082325935364,
-      "eval_precision": 0.5093875367745386,
-      "eval_recall": 0.5667440338034875,
-      "eval_runtime": 370.2231,
-      "eval_samples_per_second": 5.543,
-      "eval_steps_per_second": 0.348,
-      "step": 1200
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 1.7620806401969838e-05,
-      "loss": 0.2737,
-      "step": 1500
-    },
-    {
-      "epoch": 0.62,
-      "eval_accuracy": 0.8960354303687331,
-      "eval_f1": 0.6032919847328244,
-      "eval_loss": 0.33280590176582336,
-      "eval_precision": 0.6045538755752107,
-      "eval_recall": 0.6020353508302089,
-      "eval_runtime": 369.9685,
-      "eval_samples_per_second": 5.546,
-      "eval_steps_per_second": 0.349,
-      "step": 1500
-    },
-    {
-      "epoch": 0.75,
-      "eval_accuracy": 0.9185901350526106,
-      "eval_f1": 0.640386343216532,
-      "eval_loss": 0.2983764410018921,
-      "eval_precision": 0.6061765800244512,
-      "eval_recall": 0.6786883294649765,
-      "eval_runtime": 366.7561,
-      "eval_samples_per_second": 5.595,
-      "eval_steps_per_second": 0.352,
-      "step": 1800
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 1.6084949215143123e-05,
-      "loss": 0.2542,
-      "step": 2000
-    },
-    {
-      "epoch": 0.87,
-      "eval_accuracy": 0.9162879176822183,
-      "eval_f1": 0.6593356503902912,
-      "eval_loss": 0.3114674985408783,
-      "eval_precision": 0.6323842832941691,
-      "eval_recall": 0.6886865440695114,
-      "eval_runtime": 356.8285,
-      "eval_samples_per_second": 5.751,
-      "eval_steps_per_second": 0.362,
-      "step": 2100
-    }
-  ],
-  "max_steps": 7221,
-  "num_train_epochs": 3,
-  "total_flos": 6802348015411200.0,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-2400/config.json

@@ -1,161 +0,0 @@
-{
-  "_name_or_path": "microsoft/layoutxlm-base",
-  "architectures": [
-    "LayoutLMv2ForTokenClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "convert_sync_batchnorm": true,
-  "coordinate_size": 128,
-  "detectron2_config_args": {
-    "MODEL.ANCHOR_GENERATOR.SIZES": [
-      [
-        32
-      ],
-      [
-        64
-      ],
-      [
-        128
-      ],
-      [
-        256
-      ],
-      [
-        512
-      ]
-    ],
-    "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
-    "MODEL.FPN.IN_FEATURES": [
-      "res2",
-      "res3",
-      "res4",
-      "res5"
-    ],
-    "MODEL.MASK_ON": true,
-    "MODEL.PIXEL_STD": [
-      57.375,
-      57.12,
-      58.395
-    ],
-    "MODEL.POST_NMS_TOPK_TEST": 1000,
-    "MODEL.RESNETS.ASPECT_RATIOS": [
-      [
-        0.5,
-        1.0,
-        2.0
-      ]
-    ],
-    "MODEL.RESNETS.DEPTH": 101,
-    "MODEL.RESNETS.NUM_GROUPS": 32,
-    "MODEL.RESNETS.OUT_FEATURES": [
-      "res2",
-      "res3",
-      "res4",
-      "res5"
-    ],
-    "MODEL.RESNETS.SIZES": [
-      [
-        32
-      ],
-      [
-        64
-      ],
-      [
-        128
-      ],
-      [
-        256
-      ],
-      [
-        512
-      ]
-    ],
-    "MODEL.RESNETS.STRIDE_IN_1X1": false,
-    "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
-    "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
-    "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
-    "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
-    "MODEL.ROI_HEADS.IN_FEATURES": [
-      "p2",
-      "p3",
-      "p4",
-      "p5"
-    ],
-    "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
-    "MODEL.ROI_HEADS.NUM_CLASSES": 5,
-    "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
-    "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
-    "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
-    "MODEL.RPN.IN_FEATURES": [
-      "p2",
-      "p3",
-      "p4",
-      "p5",
-      "p6"
-    ],
-    "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
-    "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
-    "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
-  },
-  "eos_token_id": 2,
-  "fast_qkv": false,
-  "gradient_checkpointing": false,
-  "has_relative_attention_bias": false,
-  "has_spatial_attention_bias": false,
-  "has_visual_segment_embedding": true,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "Caption",
-    "1": "Footnote",
-    "2": "Formula",
-    "3": "List-item",
-    "4": "Page-footer",
-    "5": "Page-header",
-    "6": "Picture",
-    "7": "Section-header",
-    "8": "Table",
-    "9": "Text",
-    "10": "Title"
-  },
-  "image_feature_pool_shape": [
-    7,
-    7,
-    256
-  ],
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Caption": 0,
-    "Footnote": 1,
-    "Formula": 2,
-    "List-item": 3,
-    "Page-footer": 4,
-    "Page-header": 5,
-    "Picture": 6,
-    "Section-header": 7,
-    "Table": 8,
-    "Text": 9,
-    "Title": 10
-  },
-  "layer_norm_eps": 1e-05,
-  "max_2d_position_embeddings": 1024,
-  "max_position_embeddings": 514,
-  "max_rel_2d_pos": 256,
-  "max_rel_pos": 128,
-  "model_type": "layoutlmv2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "rel_2d_pos_bins": 64,
-  "rel_pos_bins": 32,
-  "shape_size": 128,
-  "tokenizer_class": "LayoutXLMTokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "type_vocab_size": 1,
-  "vocab_size": 250002
-}

checkpoint-2400/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7bc5cf25e6f54483af844ac4723f8d5c06d820152e78be52a676f593d2f448c6
-size 2927175013

checkpoint-2400/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2761f9550874a09b5d22ac60b3f5fa4fbd17bc7de27a59ffbbf18ac882e0f645
-size 623

checkpoint-2400/sentencepiece.bpe.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
-size 5069051

checkpoint-2400/special_tokens_map.json

@@ -1,15 +0,0 @@
-{
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
-}

checkpoint-2400/tokenizer_config.json

@@ -1,41 +0,0 @@
-{
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "cls_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "microsoft/layoutxlm-base",
-  "only_label_first_subword": true,
-  "pad_token": "<pad>",
-  "pad_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "pad_token_label": -100,
-  "sep_token": "</s>",
-  "sep_token_box": [
-    1000,
-    1000,
-    1000,
-    1000
-  ],
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": null,
-  "tokenizer_class": "LayoutXLMTokenizer",
-  "unk_token": "<unk>"
-}

checkpoint-2400/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2feceede1dfbfaea489fd19d51c164bec6d3d91511b6afa493c5456b912b5f10
-size 3631

{checkpoint-2100 → checkpoint-3000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c0bb408290c1719c92adebd86e479bda90d7356ab026bfca29c04fb6798d80
+oid sha256:a93af659234c9e1a022052410bda9a739f784f37a05d1c54584f762a0000b9f8
 size 2927175013

{checkpoint-2400 → checkpoint-3000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5349abbd0cd546f7174ad1bf0ac6a175ee84d7b26fca045eb511ca06874070ec
+oid sha256:1d80d8298c4e2201951a41e219cb2c8b8cb4efc1850e1eb60b5c92f5608b00df
 size 1476527911

{checkpoint-2400 → checkpoint-3000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dbd74498150865897c8707f706169619e0048ffc4cfcf3784bc37db5c5ba1d0
+oid sha256:f544250a818c1665c43e95860b8487209d04ef4b697b8ec32dc9e388b4207be0
 size 14503

{checkpoint-2400 → checkpoint-3000}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13fdedd4ddff2b7dc325bc721753954b34837bb20becda9984f7a1c2286e23d9
+oid sha256:bb2928f2ac1957fe641f8ee2df09d382b1d5bdacf6330686461541713cea7182
 size 559

{checkpoint-2100 → checkpoint-3000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649a4d7aa565309b2ed1fc445715be13ceadcc6746d1ea08d8e0302d75672746
+oid sha256:23152bdad547fcdb9b6f40181a3c047a0a6802dc3e674f97236c9943977c2bb2
 size 623

{checkpoint-2400 → checkpoint-3000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.6593356503902912,
-  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-2100",
-  "epoch": 0.9970918155380141,
-  "global_step": 2400,
+  "best_metric": 0.6871282417320962,
+  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-3000",
+  "epoch": 1.2463647694225177,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -126,11 +126,47 @@
       "eval_samples_per_second": 5.819,
       "eval_steps_per_second": 0.366,
       "step": 2400
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.4546014158202526e-05,
+      "loss": 0.1938,
+      "step": 2500
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.9165257053918363,
+      "eval_f1": 0.6752131725962951,
+      "eval_loss": 0.34137091040611267,
+      "eval_precision": 0.6672865694194223,
+      "eval_recall": 0.6833303576742248,
+      "eval_runtime": 349.7664,
+      "eval_samples_per_second": 5.867,
+      "eval_steps_per_second": 0.369,
+      "step": 2700
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3007079101261929e-05,
+      "loss": 0.1581,
+      "step": 3000
+    },
+    {
+      "epoch": 1.25,
+      "eval_accuracy": 0.9193251152459752,
+      "eval_f1": 0.6871282417320962,
+      "eval_loss": 0.3610578179359436,
+      "eval_precision": 0.6867605968729564,
+      "eval_recall": 0.6874962804261144,
+      "eval_runtime": 346.075,
+      "eval_samples_per_second": 5.929,
+      "eval_steps_per_second": 0.373,
+      "step": 3000
     }
   ],
   "max_steps": 7221,
   "num_train_epochs": 3,
-  "total_flos": 7774112017612800.0,
+  "total_flos": 9714805710342912.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57247f2699ca2dd71ace441b0284d871b4db7c5940547a1dc2f196f95b4e4005
+oid sha256:1d80d8298c4e2201951a41e219cb2c8b8cb4efc1850e1eb60b5c92f5608b00df
 size 1476527911

runs/Mar02_14-30-16_3eedd57194cc/events.out.tfevents.1677769428.3eedd57194cc.131.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5500a154c83762b109d5ffb571bbfece6909310ca00afe91eaca986654289f
-size 10067
+oid sha256:39a077ef4fc5300dd502438fb13f83ae56ba0fa0d39319b06a341a69fa289dbd
+size 10696