Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,96 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "text-generation",
+    "1": "fill-mask",
+    "2": "text-classification",
+    "3": "multiple-choice",
+    "4": "question-answering",
+    "5": "sentence-similarity",
+    "6": "token-classification",
+    "7": "image-to-text",
+    "8": "summarization",
+    "9": "text-to-image",
+    "10": "text2text-generation",
+    "11": "other",
+    "12": "text-retrieval",
+    "13": "image-classification",
+    "14": "translation",
+    "15": "automatic-speech-recognition",
+    "16": "zero-shot-classification",
+    "17": "audio-classification",
+    "18": "image-segmentation",
+    "19": "conversational",
+    "20": "tabular-classification",
+    "21": "object-detection",
+    "22": "feature-extraction",
+    "23": "table-question-answering"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "audio-classification": 17,
+    "automatic-speech-recognition": 15,
+    "conversational": 19,
+    "feature-extraction": 22,
+    "fill-mask": 1,
+    "image-classification": 13,
+    "image-segmentation": 18,
+    "image-to-text": 7,
+    "multiple-choice": 3,
+    "object-detection": 21,
+    "other": 11,
+    "question-answering": 4,
+    "sentence-similarity": 5,
+    "summarization": 8,
+    "table-question-answering": 23,
+    "tabular-classification": 20,
+    "text-classification": 2,
+    "text-generation": 0,
+    "text-retrieval": 12,
+    "text-to-image": 9,
+    "text2text-generation": 10,
+    "token-classification": 6,
+    "translation": 14,
+    "zero-shot-classification": 16
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "problem_type": "multi_label_classification",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e73d4c5d703c3c1d3dbdd01e77e645e57d26ce47b2ef0494b21b3238cc9816
+size 594806929

runs/Jun27_14-31-52_193385804fff/events.out.tfevents.1687876317.193385804fff.1946.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e035d7c34a4abfbfd1aace8995c055407b0a6e1407d4d850fddf36641d2744
+size 6206

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 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d10ee89fda81e9be235e963ae87e2712203d4d8f7f1e6bdd8189d8d69b8fff1
+size 4027