Training in progress, step 400, checkpoint

checkpoint-400/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-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f2e93e9e8fe8a743be08110302ade3e0a0d4387734e78424576ed8af1785e5
+size 1134332228

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2e24a756c312996065380ec2bbe3755fd29cc25757bac5d4b24ba8fbb08934
+size 2265914014

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99a64e57ebe46b8c692a3d62fe6ba40a21098b994c532d59b224553bcda3498
+size 13990

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ebf4532421974ac997edf5046ea573694bab465d22a36da7d62cac55a93f90
+size 1064

checkpoint-400/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-400/tokenizer.json

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

checkpoint-400/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-400/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.7780849810853703,
+  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-300",
+  "epoch": 0.21321961620469082,
+  "eval_steps": 100,
+  "global_step": 400,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1876,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 890151164313600.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

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