Training in progress, step 500

added_tokens.json

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

config.json

@@ -0,0 +1,249 @@
+{
+  "architectures": [
+    "SpanMarkerModel"
+  ],
+  "encoder": {
+    "_name_or_path": "numind/generic-entity_recognition_NER-v1",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "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,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "O",
+      "1": "B-PERSON",
+      "2": "I-PERSON",
+      "3": "B-NORP",
+      "4": "I-NORP",
+      "5": "B-FAC",
+      "6": "I-FAC",
+      "7": "B-ORG",
+      "8": "I-ORG",
+      "9": "B-GPE",
+      "10": "I-GPE",
+      "11": "B-LOC",
+      "12": "I-LOC",
+      "13": "B-PRODUCT",
+      "14": "I-PRODUCT",
+      "15": "B-DATE",
+      "16": "I-DATE",
+      "17": "B-TIME",
+      "18": "I-TIME",
+      "19": "B-PERCENT",
+      "20": "I-PERCENT",
+      "21": "B-MONEY",
+      "22": "I-MONEY",
+      "23": "B-QUANTITY",
+      "24": "I-QUANTITY",
+      "25": "B-ORDINAL",
+      "26": "I-ORDINAL",
+      "27": "B-CARDINAL",
+      "28": "I-CARDINAL",
+      "29": "B-EVENT",
+      "30": "I-EVENT",
+      "31": "B-WORK_OF_ART",
+      "32": "I-WORK_OF_ART",
+      "33": "B-LAW",
+      "34": "I-LAW",
+      "35": "B-LANGUAGE",
+      "36": "I-LANGUAGE"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-CARDINAL": 27,
+      "B-DATE": 15,
+      "B-EVENT": 29,
+      "B-FAC": 5,
+      "B-GPE": 9,
+      "B-LANGUAGE": 35,
+      "B-LAW": 33,
+      "B-LOC": 11,
+      "B-MONEY": 21,
+      "B-NORP": 3,
+      "B-ORDINAL": 25,
+      "B-ORG": 7,
+      "B-PERCENT": 19,
+      "B-PERSON": 1,
+      "B-PRODUCT": 13,
+      "B-QUANTITY": 23,
+      "B-TIME": 17,
+      "B-WORK_OF_ART": 31,
+      "I-CARDINAL": 28,
+      "I-DATE": 16,
+      "I-EVENT": 30,
+      "I-FAC": 6,
+      "I-GPE": 10,
+      "I-LANGUAGE": 36,
+      "I-LAW": 34,
+      "I-LOC": 12,
+      "I-MONEY": 22,
+      "I-NORP": 4,
+      "I-ORDINAL": 26,
+      "I-ORG": 8,
+      "I-PERCENT": 20,
+      "I-PERSON": 2,
+      "I-PRODUCT": 14,
+      "I-QUANTITY": 24,
+      "I-TIME": 18,
+      "I-WORK_OF_ART": 32,
+      "O": 0
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "roberta",
+    "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_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": "4.35.2",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50272
+  },
+  "entity_max_length": 8,
+  "id2label": {
+    "0": "O",
+    "1": "CARDINAL",
+    "2": "DATE",
+    "3": "EVENT",
+    "4": "FAC",
+    "5": "GPE",
+    "6": "LANGUAGE",
+    "7": "LAW",
+    "8": "LOC",
+    "9": "MONEY",
+    "10": "NORP",
+    "11": "ORDINAL",
+    "12": "ORG",
+    "13": "PERCENT",
+    "14": "PERSON",
+    "15": "PRODUCT",
+    "16": "QUANTITY",
+    "17": "TIME",
+    "18": "WORK_OF_ART"
+  },
+  "id2reduced_id": {
+    "0": 0,
+    "1": 14,
+    "2": 14,
+    "3": 10,
+    "4": 10,
+    "5": 4,
+    "6": 4,
+    "7": 12,
+    "8": 12,
+    "9": 5,
+    "10": 5,
+    "11": 8,
+    "12": 8,
+    "13": 15,
+    "14": 15,
+    "15": 2,
+    "16": 2,
+    "17": 17,
+    "18": 17,
+    "19": 13,
+    "20": 13,
+    "21": 9,
+    "22": 9,
+    "23": 16,
+    "24": 16,
+    "25": 11,
+    "26": 11,
+    "27": 1,
+    "28": 1,
+    "29": 3,
+    "30": 3,
+    "31": 18,
+    "32": 18,
+    "33": 7,
+    "34": 7,
+    "35": 6,
+    "36": 6
+  },
+  "label2id": {
+    "CARDINAL": 1,
+    "DATE": 2,
+    "EVENT": 3,
+    "FAC": 4,
+    "GPE": 5,
+    "LANGUAGE": 6,
+    "LAW": 7,
+    "LOC": 8,
+    "MONEY": 9,
+    "NORP": 10,
+    "O": 0,
+    "ORDINAL": 11,
+    "ORG": 12,
+    "PERCENT": 13,
+    "PERSON": 14,
+    "PRODUCT": 15,
+    "QUANTITY": 16,
+    "TIME": 17,
+    "WORK_OF_ART": 18
+  },
+  "marker_max_length": 128,
+  "max_next_context": null,
+  "max_prev_context": null,
+  "model_max_length": 256,
+  "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": "4.35.2",
+  "vocab_size": 50272
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e7f6d308c67df7339649b79f1ece8eb9dbc797a83e2ae705faa32cbc02866b
+size 498744980

runs/Nov27_10-15-36_trinity/events.out.tfevents.1701080205.trinity.366901.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc61177433392ecb454f7b5cfaaa1ee3acb3e6f8613985a6c2d14bf278238959
+size 10697

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "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": true,
+      "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>",
+  "entity_max_length": 8,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "marker_max_length": 128,
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "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:da7e4fe8cb64dc135350b383a78feba60942f5cc614f4232b645f9528907de78
+size 4600