Training in progress, step 500

.gitignore

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

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "domenicrosati/deberta-v3-large-dapt-scientific-papers-pubmed",
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721678f5fbdd7120344a19e24fb3c62d24d543dd2fbe67da4d2220f46b003e01
+size 1740906345

runs/Jun30_14-29-40_6ceed87a35c4/1656599394.652181/events.out.tfevents.1656599394.6ceed87a35c4.33.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a048a1a4a1e235d9ba3ccfdaf6a069333abac1427e0acfc064cd35665d809494
+size 4950

runs/Jun30_14-29-40_6ceed87a35c4/events.out.tfevents.1656599394.6ceed87a35c4.33.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ff61ce397517e18dd30295b5d1fb1e21eaa8b11412a83fdd1539a8b1282ae4
+size 40

runs/Jun30_14-32-28_6ceed87a35c4/1656599557.2046044/events.out.tfevents.1656599557.6ceed87a35c4.531.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3900efcacd73768eec4a4eb631f0266bf8596edb29fcfac0ad8f532467ee783
+size 4950

runs/Jun30_14-32-28_6ceed87a35c4/events.out.tfevents.1656599557.6ceed87a35c4.531.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073e788449a1b586a4322db80f651ad9836cc33d9cf9a88133968f51c2920d6a
+size 3865

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:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

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, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "name_or_path": "domenicrosati/deberta-v3-large-dapt-scientific-papers-pubmed", "tokenizer_class": "DebertaV2Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b1b3f369ad601c733b5218512fdfd14ac54aa669c9362f4b3e27f0bfe9f8d5
+size 3183