End of training

checkpoint-1700/config.json

@@ -1,56 +0,0 @@
-{
-  "_name_or_path": "nielsr/lilt-xlm-roberta-base",
-  "architectures": [
-    "LiltForTokenClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "channel_shrink_ratio": 4,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "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"
-  },
-  "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,
-  "model_type": "lilt",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
-}

checkpoint-1700/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:729004fcf99456996b5021ebe5a947784fe395af38a311463a6c8394258a65e1
-size 2265828101

checkpoint-1700/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:071823a09cad0d0ee1a84e696398cf09288e9b6d735bcc30cdd2d342f3f51d7b
-size 1134425553

checkpoint-1700/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:601d09199bbd913a7215c8cba0939124457c2a49e668a60ddf927eb5c0634883
-size 14575

checkpoint-1700/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3bd9cd8c155d5657070f8ed265a80ce72d9d2060869298c24c5bdd0b74109812
-size 557

checkpoint-1700/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52c3445de958aa8136571bb30deff20a540a52b3340cc380d53bac08e004773d
-size 627

checkpoint-1700/special_tokens_map.json

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

checkpoint-1700/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
-size 17082660

checkpoint-1700/tokenizer_config.json

@@ -1,20 +0,0 @@
-{
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 512,
-  "name_or_path": "nielsr/lilt-xlm-roberta-base",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
-}

checkpoint-1700/trainer_state.json

@@ -1,238 +0,0 @@
-{
-  "best_metric": 0.885723696687195,
-  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
-  "epoch": 0.906183368869936,
-  "global_step": 1700,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.05,
-      "eval_accuracy": 0.6585185702735884,
-      "eval_f1": 0.6585185702735884,
-      "eval_loss": 0.9875321388244629,
-      "eval_precision": 0.6585185702735884,
-      "eval_recall": 0.6585185702735884,
-      "eval_runtime": 47.6616,
-      "eval_samples_per_second": 33.717,
-      "eval_steps_per_second": 2.119,
-      "step": 100
-    },
-    {
-      "epoch": 0.11,
-      "eval_accuracy": 0.7551279108067913,
-      "eval_f1": 0.7551279108067913,
-      "eval_loss": 0.7886354327201843,
-      "eval_precision": 0.7551279108067913,
-      "eval_recall": 0.7551279108067913,
-      "eval_runtime": 48.4163,
-      "eval_samples_per_second": 33.191,
-      "eval_steps_per_second": 2.086,
-      "step": 200
-    },
-    {
-      "epoch": 0.16,
-      "eval_accuracy": 0.8248275724395381,
-      "eval_f1": 0.8248275724395382,
-      "eval_loss": 0.5894176363945007,
-      "eval_precision": 0.8248275724395381,
-      "eval_recall": 0.8248275724395381,
-      "eval_runtime": 47.5388,
-      "eval_samples_per_second": 33.804,
-      "eval_steps_per_second": 2.125,
-      "step": 300
-    },
-    {
-      "epoch": 0.21,
-      "eval_accuracy": 0.839579985427251,
-      "eval_f1": 0.8395799854272509,
-      "eval_loss": 0.479428768157959,
-      "eval_precision": 0.839579985427251,
-      "eval_recall": 0.839579985427251,
-      "eval_runtime": 45.3857,
-      "eval_samples_per_second": 35.408,
-      "eval_steps_per_second": 2.225,
-      "step": 400
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 1.4712153518123668e-05,
-      "loss": 0.7446,
-      "step": 500
-    },
-    {
-      "epoch": 0.27,
-      "eval_accuracy": 0.870342459600547,
-      "eval_f1": 0.8703424596005469,
-      "eval_loss": 0.39928165078163147,
-      "eval_precision": 0.870342459600547,
-      "eval_recall": 0.870342459600547,
-      "eval_runtime": 46.3389,
-      "eval_samples_per_second": 34.679,
-      "eval_steps_per_second": 2.18,
-      "step": 500
-    },
-    {
-      "epoch": 0.32,
-      "eval_accuracy": 0.885723696687195,
-      "eval_f1": 0.885723696687195,
-      "eval_loss": 0.36305829882621765,
-      "eval_precision": 0.885723696687195,
-      "eval_recall": 0.885723696687195,
-      "eval_runtime": 46.9181,
-      "eval_samples_per_second": 34.251,
-      "eval_steps_per_second": 2.153,
-      "step": 600
-    },
-    {
-      "epoch": 0.37,
-      "eval_accuracy": 0.8629662531066905,
-      "eval_f1": 0.8629662531066905,
-      "eval_loss": 0.4096183180809021,
-      "eval_precision": 0.8629662531066905,
-      "eval_recall": 0.8629662531066905,
-      "eval_runtime": 45.8414,
-      "eval_samples_per_second": 35.056,
-      "eval_steps_per_second": 2.203,
-      "step": 700
-    },
-    {
-      "epoch": 0.43,
-      "eval_accuracy": 0.8528252168445007,
-      "eval_f1": 0.8528252168445007,
-      "eval_loss": 0.44917240738868713,
-      "eval_precision": 0.8528252168445007,
-      "eval_recall": 0.8528252168445007,
-      "eval_runtime": 45.6102,
-      "eval_samples_per_second": 35.233,
-      "eval_steps_per_second": 2.214,
-      "step": 800
-    },
-    {
-      "epoch": 0.48,
-      "eval_accuracy": 0.8833980456546259,
-      "eval_f1": 0.8833980456546259,
-      "eval_loss": 0.38389313220977783,
-      "eval_precision": 0.8833980456546259,
-      "eval_recall": 0.8833980456546259,
-      "eval_runtime": 47.6493,
-      "eval_samples_per_second": 33.726,
-      "eval_steps_per_second": 2.12,
-      "step": 900
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 9.381663113006397e-06,
-      "loss": 0.4464,
-      "step": 1000
-    },
-    {
-      "epoch": 0.53,
-      "eval_accuracy": 0.8498407977082855,
-      "eval_f1": 0.8498407977082856,
-      "eval_loss": 0.4365050792694092,
-      "eval_precision": 0.8498407977082855,
-      "eval_recall": 0.8498407977082855,
-      "eval_runtime": 47.0078,
-      "eval_samples_per_second": 34.186,
-      "eval_steps_per_second": 2.149,
-      "step": 1000
-    },
-    {
-      "epoch": 0.59,
-      "eval_accuracy": 0.8811622266361904,
-      "eval_f1": 0.8811622266361904,
-      "eval_loss": 0.36158204078674316,
-      "eval_precision": 0.8811622266361904,
-      "eval_recall": 0.8811622266361904,
-      "eval_runtime": 44.8724,
-      "eval_samples_per_second": 35.813,
-      "eval_steps_per_second": 2.251,
-      "step": 1100
-    },
-    {
-      "epoch": 0.64,
-      "eval_accuracy": 0.8795751943864972,
-      "eval_f1": 0.8795751943864972,
-      "eval_loss": 0.3948919177055359,
-      "eval_precision": 0.8795751943864972,
-      "eval_recall": 0.8795751943864972,
-      "eval_runtime": 45.1224,
-      "eval_samples_per_second": 35.614,
-      "eval_steps_per_second": 2.238,
-      "step": 1200
-    },
-    {
-      "epoch": 0.69,
-      "eval_accuracy": 0.8612794075079601,
-      "eval_f1": 0.8612794075079601,
-      "eval_loss": 0.41840043663978577,
-      "eval_precision": 0.8612794075079601,
-      "eval_recall": 0.8612794075079601,
-      "eval_runtime": 39.7377,
-      "eval_samples_per_second": 40.44,
-      "eval_steps_per_second": 2.542,
-      "step": 1300
-    },
-    {
-      "epoch": 0.75,
-      "eval_accuracy": 0.874334993562039,
-      "eval_f1": 0.874334993562039,
-      "eval_loss": 0.4129931926727295,
-      "eval_precision": 0.874334993562039,
-      "eval_recall": 0.874334993562039,
-      "eval_runtime": 44.8477,
-      "eval_samples_per_second": 35.832,
-      "eval_steps_per_second": 2.252,
-      "step": 1400
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 4.051172707889126e-06,
-      "loss": 0.3672,
-      "step": 1500
-    },
-    {
-      "epoch": 0.8,
-      "eval_accuracy": 0.8288799944104525,
-      "eval_f1": 0.8288799944104525,
-      "eval_loss": 0.45351940393447876,
-      "eval_precision": 0.8288799944104525,
-      "eval_recall": 0.8288799944104525,
-      "eval_runtime": 45.3573,
-      "eval_samples_per_second": 35.43,
-      "eval_steps_per_second": 2.227,
-      "step": 1500
-    },
-    {
-      "epoch": 0.85,
-      "eval_accuracy": 0.8712607424116902,
-      "eval_f1": 0.8712607424116902,
-      "eval_loss": 0.36811864376068115,
-      "eval_precision": 0.8712607424116902,
-      "eval_recall": 0.8712607424116902,
-      "eval_runtime": 44.3035,
-      "eval_samples_per_second": 36.273,
-      "eval_steps_per_second": 2.28,
-      "step": 1600
-    },
-    {
-      "epoch": 0.91,
-      "eval_accuracy": 0.885723696687195,
-      "eval_f1": 0.885723696687195,
-      "eval_loss": 0.34459415078163147,
-      "eval_precision": 0.885723696687195,
-      "eval_recall": 0.885723696687195,
-      "eval_runtime": 44.6077,
-      "eval_samples_per_second": 36.025,
-      "eval_steps_per_second": 2.264,
-      "step": 1700
-    }
-  ],
-  "max_steps": 1876,
-  "num_train_epochs": 1,
-  "total_flos": 3783142448332800.0,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1700/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:575d482dfbe4b5795db81627b295d36a31851f66bb801524d15bc53043f733c4
-size 3707

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ce50e2c3bc965514eb957251870b9e018aa89a1eb3c0b2d421e00f4020f51b
+oid sha256:5d412db68cafdb004b544f6d25d7643b5e329556603ad90d82fa1115c4bc0a8c
 size 1134425553

runs/Feb15_07-53-26_e220f522c880/events.out.tfevents.1676447621.e220f522c880.495.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10b4927301c942673e8c171300cc1481b2f2efdb1f5cf8e239edc99ad8f3db1
-size 13631
+oid sha256:518feec74482da6cde3e3024307a9336fc4da2eb5db7da26cd3bbb4810be382c
+size 13985