Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "uw-madison/nystromformer-512",
+  "architectures": [
+    "NystromformerForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "conv_kernel_size": 65,
+  "eos_token_id": 2,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "inv_coeff_init_option": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "nystromformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_landmarks": 64,
+  "pad_token_id": 1,
+  "segment_means_seq_len": 64,
+  "tokenizer_class": "AlbertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673a0fb4e2beb95da531c7861a2221abdd54b3fe1c0bd1d01ea47919790d6092
+size 438836377

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ee5d0cd20ab9616138d90a6d9c811ed41aba04a95d515bee6d4d5cd42ef0a6
+size 761089

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "C:\\Users\\prana/.cache\\huggingface\\transformers\\d225353999b4547543d7b66be9304faa64950fec7fb25e2d220dd84ee3f8b991.15ed5b79b197b4fcc5f3f80b2ee89a5a3ad708dbd076575cd22cffd9e1a56284", "name_or_path": "uw-madison/nystromformer-512", "tokenizer_class": "AlbertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98e44113a26c353c01ebbb80c2b9e89cb317b2227f2761f5334f93dc5be3551
+size 3183