Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-xsmall",
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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": 6,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364f67cc4ed2583b296455d1488454d439624055f9e5a8d0f8624fb458354a0c
+size 283908201

runs/Jun28_23-53-44_nyg7op6wha/1656460432.3726847/events.out.tfevents.1656460432.nyg7op6wha.109.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9969ed6284ab911b96aa8082f0e9d8a3b0dc9bd0699fa8dceff7fe2c321d3be1
+size 5322

runs/Jun28_23-53-44_nyg7op6wha/events.out.tfevents.1656460432.nyg7op6wha.109.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ceca5e41f8746669b979daa0b07c02c6577e906272dac89bf7dbfe804025828
+size 3746

runs/Jun28_23-59-40_nyg7op6wha/1656460789.229485/events.out.tfevents.1656460789.nyg7op6wha.669.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b62054a2468b24246f1983acded31f491771a463c70c37d3400d5c4e3153aa
+size 5322

runs/Jun28_23-59-40_nyg7op6wha/events.out.tfevents.1656460789.nyg7op6wha.669.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79348e34d40e5b413e07752f1e58f7258a61d1c7faa8a3215ce2b6d31e60250d
+size 4420

runs/Jun29_00-08-07_nyg7op6wha/1656461292.1205132/events.out.tfevents.1656461292.nyg7op6wha.669.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804b16cfbca4fcfe20c8e89aef8d7792c3975646211f6fd48cce0ad99225be8e
+size 5322

runs/Jun29_00-08-07_nyg7op6wha/events.out.tfevents.1656461292.nyg7op6wha.669.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4b7da32378f79b7835164e18f3593370b95eb7171089156fc70d96586b834d
+size 4224

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "name_or_path": "microsoft/deberta-v3-xsmall",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543eac7e1d13ec033ea4a4001b88b6e175e91079552fdcdf57601ee8191e4e65
+size 3311