Training in progress, step 500

config.json

@@ -1,45 +1,39 @@
 {
-  "_name_or_path": "cross-encoder/nli-deberta-v3-large",
+  "_name_or_path": "roberta-large-mnli",
+  "_num_labels": 3,
   "architectures": [
-    "DebertaV2ForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "id2label": {
-    "0": "contradiction",
-    "1": "entailment",
-    "2": "neutral"
+    "0": "CONTRADICTION",
+    "1": "NEUTRAL",
+    "2": "ENTAILMENT"
   },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "label2id": {
-    "contradiction": 0,
-    "entailment": 1,
-    "neutral": 2
+    "CONTRADICTION": 0,
+    "ENTAILMENT": 2,
+    "NEUTRAL": 1
   },
-  "layer_norm_eps": 1e-07,
-  "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "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,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.25.1",
-  "type_vocab_size": 0,
-  "vocab_size": 128100
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae24e029aa5c6d4fc27f0a765d055f75b8bdf172a30cdd67645af05924c13d60
-size 1740400377
+oid sha256:eab7ca94f54f489b969c58d02d327a4259f260e7f67cd6553e006a5e405aa539
+size 1421591285

runs/Dec09_21-28-29_a03200a6b5c6/events.out.tfevents.1670621316.a03200a6b5c6.340.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9c76ac660ebbb5147831433556821ae8458c8449c6a31bbee153ffadeaf93d
-size 4292
+oid sha256:bf3b519c12b97480800b8084123fa7c80d76fde92d898bda1db423dcb7416aca
+size 4606

runs/Dec09_21-49-05_a03200a6b5c6/1670622556.690126/events.out.tfevents.1670622556.a03200a6b5c6.340.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0412c0442b80f99c85bc4dedf7b5601d191736c5fb1db3114d1b679819bbf9
+size 5494

runs/Dec09_21-49-05_a03200a6b5c6/events.out.tfevents.1670622556.a03200a6b5c6.340.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752954e1f8d251018c3e75375009e4b0c2c66c5a3a28aee35776a705338f7a75
+size 40

runs/Dec09_21-50-54_a03200a6b5c6/1670622665.1440845/events.out.tfevents.1670622665.a03200a6b5c6.1013.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bac52941a42a774dfbdc8a64552600f24b655644eeaaa7c1623ed03a444c87
+size 5494

runs/Dec09_21-50-54_a03200a6b5c6/events.out.tfevents.1670622665.a03200a6b5c6.1013.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e48ec5b4390d9d7f1c520bfc61341a86b7e8c1a21664d8d4599b379cb637c03
+size 4086

special_tokens_map.json

@@ -1,9 +1,15 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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

@@ -1,17 +1,16 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "cross-encoder/nli-deberta-v3-large",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
+  "name_or_path": "roberta-large-mnli",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
   "special_tokens_map_file": null,
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcfbf4f0b8c7852533b42f545f4c02c964dc386cfc55c34deed5e22fdc43711f
+oid sha256:7590f2d41797aed6227e5b8de15a7619827e3f5b09b1441d4560384fc53e98f5
 size 3387