Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForQuestionAnswering"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d5649d953d89a0a488abf1d6e71842686c02dfa13f6d3b1aa1219b75813dd6
+size 592407201

runs/Jul20_16-41-04_4026ac268057/1658335276.527695/events.out.tfevents.1658335276.4026ac268057.77.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18621d84d0e7d1a8b6f612396902965138a8a65fa4d160feeb5f89c9a820fd5b
+size 5446

runs/Jul20_16-41-04_4026ac268057/events.out.tfevents.1658335276.4026ac268057.77.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7c6bc59be53a95def7f86d8e009483e92216100e40c8a9d8ab645770e99aa9
+size 4432

runs/Jul20_17-19-16_4026ac268057/1658337561.8857462/events.out.tfevents.1658337561.4026ac268057.276.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31003398641748ead08409f53bf6c67d8b5db588f5f948bfcd1669295eeaad65
+size 5446

runs/Jul20_17-19-16_4026ac268057/events.out.tfevents.1658337561.4026ac268057.276.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a630cb1896a14702e8839ce7c049ce0f97b2aa9be872473cc75c30a0104883
+size 5531

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 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "name_or_path": "allenai/longformer-base-4096",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "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:e336c4663d8abaf412024da9bdfb49215137646be6fed4b41703f5f1be17248c
+size 3375