Training in progress, step 4500

checkpoint-3600/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a82055984a94f79cb2264f837f26cd9f6fbaa7ac73815c752b60cb679ec95b99
-size 1476527911

checkpoint-3600/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:97dafb41e6b2d845433cabc0385f79521a1748f40cacf377834e385edebbe88e
-size 14503

checkpoint-3600/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:17a078295ee7cf9ec1efda07a06dbe386525103781fda3952c273e1b99345434
-size 559

checkpoint-3600/trainer_state.json

@@ -1,202 +0,0 @@
-{
-  "best_metric": 0.7083662914511712,
-  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-3600",
-  "epoch": 1.4956377233070213,
-  "global_step": 3600,
-  "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
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.919752052270062,
-      "eval_f1": 0.6536656236030397,
-      "eval_loss": 0.2877778708934784,
-      "eval_precision": 0.6160408657643899,
-      "eval_recall": 0.6961852050229126,
-      "eval_runtime": 352.6194,
-      "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
-    },
-    {
-      "epoch": 1.37,
-      "eval_accuracy": 0.9256291916839153,
-      "eval_f1": 0.6821629855293222,
-      "eval_loss": 0.2762657403945923,
-      "eval_precision": 0.6987891648982649,
-      "eval_recall": 0.6663095875736476,
-      "eval_runtime": 342.8929,
-      "eval_samples_per_second": 5.984,
-      "eval_steps_per_second": 0.376,
-      "step": 3300
-    },
-    {
-      "epoch": 1.45,
-      "learning_rate": 1.1471221914435212e-05,
-      "loss": 0.1428,
-      "step": 3500
-    },
-    {
-      "epoch": 1.5,
-      "eval_accuracy": 0.9287285383081404,
-      "eval_f1": 0.7083662914511712,
-      "eval_loss": 0.306523859500885,
-      "eval_precision": 0.7245907761249767,
-      "eval_recall": 0.6928524668214009,
-      "eval_runtime": 342.9768,
-      "eval_samples_per_second": 5.983,
-      "eval_steps_per_second": 0.376,
-      "step": 3600
-    }
-  ],
-  "max_steps": 7221,
-  "num_train_epochs": 3,
-  "total_flos": 1.1658333714746112e+16,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-3600/training_args.bin

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

checkpoint-3900/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-3900/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4ffcb52090745a514e47d2115bf03f6123be6df5ff3176e6112ae8135dcaf90b
-size 2927175013

checkpoint-3900/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3cae92a5b5517addc09624239460dbe9f9a2b4d77f17c1e22aca26ae891722e7
-size 623

checkpoint-3900/sentencepiece.bpe.model

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

checkpoint-3900/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-3900/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-3600 → checkpoint-4500}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4ddfc874682c8d52bbd39a46240d0be526b4053b95453565889a63053ea284
+oid sha256:3d7204a2172f425b4ff67641f159d21def875a44b33dc67e3af8f91eb077baff
 size 2927175013

{checkpoint-3900 → checkpoint-4500}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8f79bb76452baec7f223f35785ef55cc656bdab1a4c05c27a1c18a29a55813
+oid sha256:f59c12a6b69e0c623eae641e7587cc350259130678357d3a08d5c5589e187adc
 size 1476527911

{checkpoint-3900 → checkpoint-4500}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b56915cfbf79f70b1899a7c98726b2bd8281acc4751dc1900715caedbce7d67
+oid sha256:ed8161ead50e3f2c857650a0cca5df64a4c9835be5692e8439c0646751a6fde6
 size 14503

{checkpoint-3900 → checkpoint-4500}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2d843e7732b0509142909fa49a572adf418b30a232919bf6d460cf8efda9a6
+oid sha256:0d77897d9f3f73ebc6f3967c5ba80cbdfbb4ed8c1145ffa5026c17d5b93c623b
 size 559

{checkpoint-3600 → checkpoint-4500}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c8b647f417577617986ed9f7fe3d062a43e941b7695ee886d49a03bb28882f3
+oid sha256:934192368a69a4b2a29705df388bd8eaaf0ff6a8d77e5e3b9d03b9746d0c19e3
 size 623

{checkpoint-3900 → checkpoint-4500}/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.7083662914511712,
-  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-3600",
-  "epoch": 1.620274200249273,
-  "global_step": 3900,
+  "best_metric": 0.7223092684102689,
+  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-4200",
+  "epoch": 1.8695471541337765,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,11 +204,47 @@
       "eval_samples_per_second": 6.031,
       "eval_steps_per_second": 0.379,
       "step": 3900
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 9.932286857494614e-06,
+      "loss": 0.1025,
+      "step": 4000
+    },
+    {
+      "epoch": 1.74,
+      "eval_accuracy": 0.9346597203832706,
+      "eval_f1": 0.7223092684102689,
+      "eval_loss": 0.2989632189273834,
+      "eval_precision": 0.7315227342081172,
+      "eval_recall": 0.7133250014878295,
+      "eval_runtime": 368.8508,
+      "eval_samples_per_second": 5.563,
+      "eval_steps_per_second": 0.35,
+      "step": 4200
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 8.393351800554018e-06,
+      "loss": 0.1225,
+      "step": 4500
+    },
+    {
+      "epoch": 1.87,
+      "eval_accuracy": 0.9360324039797016,
+      "eval_f1": 0.7047921954799842,
+      "eval_loss": 0.2729274332523346,
+      "eval_precision": 0.7248993457473578,
+      "eval_recall": 0.6857703981431887,
+      "eval_runtime": 366.3118,
+      "eval_samples_per_second": 5.602,
+      "eval_steps_per_second": 0.352,
+      "step": 4500
     }
   ],
   "max_steps": 7221,
   "num_train_epochs": 3,
-  "total_flos": 1.2630097716947712e+16,
+  "total_flos": 1.4573625721350912e+16,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-3900 → checkpoint-4500}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2feceede1dfbfaea489fd19d51c164bec6d3d91511b6afa493c5456b912b5f10
+oid sha256:3d554a246c9d1500a68bf4e37a596c2e5946f5469add6feef1ac70c782486238
 size 3631

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef1e47fcc8c0e356669655002ff75334efc1ef812af4b3615899bbb6b71004f
+oid sha256:f59c12a6b69e0c623eae641e7587cc350259130678357d3a08d5c5589e187adc
 size 1476527911

runs/Mar02_19-25-20_fe43f16895b4/events.out.tfevents.1677786852.fe43f16895b4.165.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab7aa3f6bec6b145a9ccb9efd8bb411aaa4b8aab693160659b0b72ae488552f
-size 7236
+oid sha256:8e36df32b41727ab4cfc4d34ae74bfef0fb1fa79ca5aea4caf4ce3b12989a5a5
+size 7865