Training in progress, step 1500

{checkpoint-600 → checkpoint-1500}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9c0946b2396c93f3f67e4439c626fd81274184f644540a03939332322a3e5a
+oid sha256:13dac546a729ed5b85ca8744dc152fdfd91141dc4421e199372bf3655f64262f
 size 2927175013

{checkpoint-900 → checkpoint-1500}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44c5f5b5f8062c79577f422f54e463f03cb3b7b67189019eebcdb26e09b668d
+oid sha256:af145d070e5615c14f0ec1187a25e662502074cab47062cebeb7ffb3c71a534b
 size 1476527911

{checkpoint-900 → checkpoint-1500}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd8dd810bd9bec3bb12c0df4d7793b907710f87c8c7e6e8565ed95a7ee888ad8
+oid sha256:2d3a8137afaaabfeeca8f8f44239daaa6efb5b2d590bd25c6f40f5f30763c03a
 size 14503

{checkpoint-900 → checkpoint-1500}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e058e61ed5c50e9f9a93d8a8b8ace71ae0475455378aaed9bfedf1e0a4403f77
+oid sha256:949ee770948d63b3ef5a33cc0d78017797a81b4ce1aabe2875a57db2d9896235
 size 559

{checkpoint-600 → checkpoint-1500}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcff1bd24dac66498acbac31bf86b0d89f6f110939c77232fe7f16db22426b34
+oid sha256:0ab027bfd64dddf1fb94bfa5e11110ecf2f9f0749b31370778d6463624c06524
 size 623

{checkpoint-900 → checkpoint-1500}/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.520614670919107,
-  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-900",
-  "epoch": 0.3739094308267553,
-  "global_step": 900,
+  "best_metric": 0.6032919847328244,
+  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-1500",
+  "epoch": 0.6231823847112589,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -48,11 +48,47 @@
       "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
     }
   ],
   "max_steps": 7221,
   "num_train_epochs": 3,
-  "total_flos": 2915292006604800.0,
+  "total_flos": 4858820011008000.0,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-900 → checkpoint-1500}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1abf369559179e8514a3a374fd35ebd67ed07d23a983236704f1d39b8e94622b
+oid sha256:2feceede1dfbfaea489fd19d51c164bec6d3d91511b6afa493c5456b912b5f10
 size 3631

checkpoint-600/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:70427062db314d44e2e0895211a998b57e8983fe7d7fcc888308d49659a391cf
-size 1476527911

checkpoint-600/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2179282d868703ce3a69b8087f5525b45e3a622a27fae1f27532fda1268616af
-size 14503

checkpoint-600/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:921c1f43fccb20a95f58d76fbbb336cc1a11c030809c500114ab060a3e6c9e13
-size 559

checkpoint-600/trainer_state.json

@@ -1,46 +0,0 @@
-{
-  "best_metric": 0.5030902012034086,
-  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-600",
-  "epoch": 0.24927295388450352,
-  "global_step": 600,
-  "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
-    }
-  ],
-  "max_steps": 7221,
-  "num_train_epochs": 3,
-  "total_flos": 1943528004403200.0,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-600/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1abf369559179e8514a3a374fd35ebd67ed07d23a983236704f1d39b8e94622b
-size 3631

checkpoint-900/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-900/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a67db9df12435295414167cc1b9e78a0d2679b7262e374e179473c7b875bd7e
-size 2927175013

checkpoint-900/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8423042d8431504e61d3300f9474afc3454b4e4a6ed4dfc504ba5cbf6bdeb8c6
-size 623

checkpoint-900/sentencepiece.bpe.model

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

checkpoint-900/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-900/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>"
-}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f2de50ebb22f439bb718ceae2526771b7b002d20a2d2082ea22f7c99095a32
+oid sha256:af145d070e5615c14f0ec1187a25e662502074cab47062cebeb7ffb3c71a534b
 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:ec43212c08d502fc1e4cbef9aaa609dde8cb91eb3c0a5436386fd0d08111b47a
-size 7236
+oid sha256:a9a5d22b3f2c79d513379eeb52c44a2a83dc2f6cb7a581abd84e0a0da088cfdb
+size 7865