Training in progress, epoch 0

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"[MASK]": 128000}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "microsoft/deberta-v2-xlarge",
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1536,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f53688b06df080c292c01da24f7da11aea983fcc61d8ffb3bb6794c274bb8d
+size 3547871969

runs/Apr24_11-09-07_2c630289b464/1650798612.6371834/events.out.tfevents.1650798612.2c630289b464.13978.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8c72374b19f08ddfbe9609bc06bb69ce9f71e5cdf43b45b295d4022912e99b
+size 4989

runs/Apr24_11-09-07_2c630289b464/events.out.tfevents.1650798612.2c630289b464.13978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947f126a9179a868d9b020ac360b7615101251ba9b52ec9a382c271d14e62492
+size 4407

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": "[MASK]"}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
+size 2447305

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "vocab_type": "spm", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/deberta-v2-xlarge", "sp_model_kwargs": {}, "tokenizer_class": "DebertaV2Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e208a25e16ade4c14ca7291ab36ffd2307625f6585c33903d94e0315c51f780
+size 3183