Training in progress, step 1300, checkpoint

checkpoint-1300/config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "zwaarcontrast/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": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5722b15344beb0fbdfa8f91a4bcdd4140f05665baafb753deaa96981fafda2bc
+size 1134332228

checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9fadd5dfbdef43340f39f81aad3a67b86cdcfca4e0b7f97f42ce153daf640b
+size 2265914014

checkpoint-1300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd981aed8e37f6c3a54196634252b3763336ae20606052647020e2b77961fd8
+size 13990

checkpoint-1300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad652e532cac6613b553a3b2db86bc62525f13cc456ed2dbcb2c1f13fa72a3d
+size 1064

checkpoint-1300/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d744d03ec3af69401e720d3867d9f13d4211c73a66a7d43d194d9ea218a4af
+size 17082955

checkpoint-1300/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1300/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": 0.827712178226716,
+  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-500",
+  "epoch": 0.6929637526652452,
+  "eval_steps": 100,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.687484404164213,
+      "eval_f1": 0.687484404164213,
+      "eval_loss": 0.11619879305362701,
+      "eval_precision": 0.687484404164213,
+      "eval_recall": 0.687484404164213,
+      "eval_runtime": 114.5058,
+      "eval_samples_per_second": 14.034,
+      "eval_steps_per_second": 0.882,
+      "step": 100
+    },
+    {
+      "epoch": 0.11,
+      "eval_accuracy": 0.6755467276193519,
+      "eval_f1": 0.6755467276193519,
+      "eval_loss": 0.1096724346280098,
+      "eval_precision": 0.6755467276193519,
+      "eval_recall": 0.6755467276193519,
+      "eval_runtime": 97.2211,
+      "eval_samples_per_second": 16.529,
+      "eval_steps_per_second": 1.039,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.7780849810853704,
+      "eval_f1": 0.7780849810853703,
+      "eval_loss": 0.08659958839416504,
+      "eval_precision": 0.7780849810853704,
+      "eval_recall": 0.7780849810853704,
+      "eval_runtime": 98.762,
+      "eval_samples_per_second": 16.271,
+      "eval_steps_per_second": 1.023,
+      "step": 300
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.7477716669827422,
+      "eval_f1": 0.7477716669827422,
+      "eval_loss": 0.10182594507932663,
+      "eval_precision": 0.7477716669827422,
+      "eval_recall": 0.7477716669827422,
+      "eval_runtime": 99.9428,
+      "eval_samples_per_second": 16.079,
+      "eval_steps_per_second": 1.011,
+      "step": 400
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.4669509594882732e-05,
+      "loss": 0.0975,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "eval_accuracy": 0.827712178226716,
+      "eval_f1": 0.827712178226716,
+      "eval_loss": 0.06453556567430496,
+      "eval_precision": 0.827712178226716,
+      "eval_recall": 0.827712178226716,
+      "eval_runtime": 100.1167,
+      "eval_samples_per_second": 16.051,
+      "eval_steps_per_second": 1.009,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.7984968109634982,
+      "eval_f1": 0.7984968109634982,
+      "eval_loss": 0.07669692486524582,
+      "eval_precision": 0.7984968109634982,
+      "eval_recall": 0.7984968109634982,
+      "eval_runtime": 101.2405,
+      "eval_samples_per_second": 15.873,
+      "eval_steps_per_second": 0.998,
+      "step": 600
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.7903320790122471,
+      "eval_f1": 0.7903320790122471,
+      "eval_loss": 0.07575991004705429,
+      "eval_precision": 0.7903320790122471,
+      "eval_recall": 0.7903320790122471,
+      "eval_runtime": 99.3914,
+      "eval_samples_per_second": 16.168,
+      "eval_steps_per_second": 1.016,
+      "step": 700
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy": 0.7865491530837334,
+      "eval_f1": 0.7865491530837335,
+      "eval_loss": 0.08622009307146072,
+      "eval_precision": 0.7865491530837334,
+      "eval_recall": 0.7865491530837334,
+      "eval_runtime": 102.0728,
+      "eval_samples_per_second": 15.744,
+      "eval_steps_per_second": 0.989,
+      "step": 800
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.6891712497629433,
+      "eval_f1": 0.6891712497629433,
+      "eval_loss": 0.12430301308631897,
+      "eval_precision": 0.6891712497629433,
+      "eval_recall": 0.6891712497629433,
+      "eval_runtime": 101.8092,
+      "eval_samples_per_second": 15.784,
+      "eval_steps_per_second": 0.992,
+      "step": 900
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.339019189765458e-06,
+      "loss": 0.1389,
+      "step": 1000
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.8255961352271253,
+      "eval_f1": 0.8255961352271252,
+      "eval_loss": 0.07946911454200745,
+      "eval_precision": 0.8255961352271253,
+      "eval_recall": 0.8255961352271253,
+      "eval_runtime": 101.762,
+      "eval_samples_per_second": 15.792,
+      "eval_steps_per_second": 0.993,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "eval_accuracy": 0.470200724644914,
+      "eval_f1": 0.470200724644914,
+      "eval_loss": 0.1683182567358017,
+      "eval_precision": 0.470200724644914,
+      "eval_recall": 0.470200724644914,
+      "eval_runtime": 100.8271,
+      "eval_samples_per_second": 15.938,
+      "eval_steps_per_second": 1.002,
+      "step": 1100
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.6635990697395869,
+      "eval_f1": 0.6635990697395869,
+      "eval_loss": 0.12526559829711914,
+      "eval_precision": 0.6635990697395869,
+      "eval_recall": 0.6635990697395869,
+      "eval_runtime": 98.9873,
+      "eval_samples_per_second": 16.234,
+      "eval_steps_per_second": 1.02,
+      "step": 1200
+    },
+    {
+      "epoch": 0.69,
+      "eval_accuracy": 0.7294758801042052,
+      "eval_f1": 0.7294758801042052,
+      "eval_loss": 0.10443996638059616,
+      "eval_precision": 0.7294758801042052,
+      "eval_recall": 0.7294758801042052,
+      "eval_runtime": 98.9922,
+      "eval_samples_per_second": 16.234,
+      "eval_steps_per_second": 1.02,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1876,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 2892991284019200.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b0d2133f50cb264ebc324905cfe0c128a8af522d0c9dae9836e41dc0a2d2c3
+size 4792