Training in progress, epoch 0

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end>": 50266,
+  "<start>": 50265
+}

config.json

@@ -0,0 +1,223 @@
+{
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "studio-ousia/luke-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "LukeForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bert_model_name": "roberta-base",
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "entity_emb_size": 256,
+    "entity_vocab_size": 500000,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "O",
+      "1": "B-COURT",
+      "2": "B-PETITIONER",
+      "3": "B-RESPONDENT",
+      "4": "B-JUDGE",
+      "5": "B-DATE",
+      "6": "B-ORG",
+      "7": "B-GPE",
+      "8": "B-STATUTE",
+      "9": "B-PROVISION",
+      "10": "B-PRECEDENT",
+      "11": "B-CASE_NUMBER",
+      "12": "B-WITNESS",
+      "13": "B-OTHER_PERSON",
+      "14": "B-LAWYER",
+      "15": "I-COURT",
+      "16": "I-PETITIONER",
+      "17": "I-RESPONDENT",
+      "18": "I-JUDGE",
+      "19": "I-DATE",
+      "20": "I-ORG",
+      "21": "I-GPE",
+      "22": "I-STATUTE",
+      "23": "I-PROVISION",
+      "24": "I-PRECEDENT",
+      "25": "I-CASE_NUMBER",
+      "26": "I-WITNESS",
+      "27": "I-OTHER_PERSON",
+      "28": "I-LAWYER"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-CASE_NUMBER": 11,
+      "B-COURT": 1,
+      "B-DATE": 5,
+      "B-GPE": 7,
+      "B-JUDGE": 4,
+      "B-LAWYER": 14,
+      "B-ORG": 6,
+      "B-OTHER_PERSON": 13,
+      "B-PETITIONER": 2,
+      "B-PRECEDENT": 10,
+      "B-PROVISION": 9,
+      "B-RESPONDENT": 3,
+      "B-STATUTE": 8,
+      "B-WITNESS": 12,
+      "I-CASE_NUMBER": 25,
+      "I-COURT": 15,
+      "I-DATE": 19,
+      "I-GPE": 21,
+      "I-JUDGE": 18,
+      "I-LAWYER": 28,
+      "I-ORG": 20,
+      "I-OTHER_PERSON": 27,
+      "I-PETITIONER": 16,
+      "I-PRECEDENT": 24,
+      "I-PROVISION": 23,
+      "I-RESPONDENT": 17,
+      "I-STATUTE": 22,
+      "I-WITNESS": 26,
+      "O": 0
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "luke",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.36.0",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_entity_aware_attention": true,
+    "vocab_size": 50272
+  },
+  "entity_max_length": 6,
+  "id2label": {
+    "0": "O",
+    "1": "CASE_NUMBER",
+    "2": "COURT",
+    "3": "DATE",
+    "4": "GPE",
+    "5": "JUDGE",
+    "6": "LAWYER",
+    "7": "ORG",
+    "8": "OTHER_PERSON",
+    "9": "PETITIONER",
+    "10": "PRECEDENT",
+    "11": "PROVISION",
+    "12": "RESPONDENT",
+    "13": "STATUTE",
+    "14": "WITNESS"
+  },
+  "id2reduced_id": {
+    "0": 0,
+    "1": 2,
+    "2": 9,
+    "3": 12,
+    "4": 5,
+    "5": 3,
+    "6": 7,
+    "7": 4,
+    "8": 13,
+    "9": 11,
+    "10": 10,
+    "11": 1,
+    "12": 14,
+    "13": 8,
+    "14": 6,
+    "15": 2,
+    "16": 9,
+    "17": 12,
+    "18": 5,
+    "19": 3,
+    "20": 7,
+    "21": 4,
+    "22": 13,
+    "23": 11,
+    "24": 10,
+    "25": 1,
+    "26": 14,
+    "27": 8,
+    "28": 6
+  },
+  "label2id": {
+    "CASE_NUMBER": 1,
+    "COURT": 2,
+    "DATE": 3,
+    "GPE": 4,
+    "JUDGE": 5,
+    "LAWYER": 6,
+    "O": 0,
+    "ORG": 7,
+    "OTHER_PERSON": 8,
+    "PETITIONER": 9,
+    "PRECEDENT": 10,
+    "PROVISION": 11,
+    "RESPONDENT": 12,
+    "STATUTE": 13,
+    "WITNESS": 14
+  },
+  "marker_max_length": 64,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": 128,
+  "model_max_length_default": 512,
+  "model_type": "span-marker",
+  "span_marker_version": "1.5.0",
+  "torch_dtype": "float32",
+  "trained_with_document_context": false,
+  "transformers_version": "4.36.0",
+  "vocab_size": 50272
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503e08c5ddae5dd24f872b1c41f788fbd6599f6ec93871c303bc7f845be192ca
+size 1098150108

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "content": "<end>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0917c5917d5d3266823cba631ea6a4b82994c2b9d4ff3f1ee83e6074978b85e9
+size 4347