Training in progress, step 500

config.json

@@ -1,35 +1,27 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-xsmall",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "DebertaV2ForQuestionAnswering"
+    "RobertaForQuestionAnswering"
   ],
   "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": 384,
+  "hidden_size": 768,
   "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,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
   "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,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.30.0",
-  "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 sha256:41b7b02297e34a90addc97dc3156e8de2b9ee4bfffa32b8fa11d06722ca6435a
-size 282804977
+oid sha256:ae35ac107303676e63c92b575612e7ee09a31ebf3026a7ef86f3a0d32dbc52c1
+size 496299053

runs/Oct08_22-05-34_c40f4e962aca/events.out.tfevents.1696802819.c40f4e962aca.16390.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdae5265976799a3af75b249e708012656fc8afbdd9b87f8cfc50fdbd3dabf57
+size 8204

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

@@ -1,16 +1,15 @@
 {
-  "bos_token": "[CLS]",
+  "add_prefix_space": false,
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "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 sha256:1163893f7dda364ad7c5d113ac797c3c1bac4afd5cc7c1953a59ee227909640d
+oid sha256:58b590b0e720eca8dcdd515b019db8f7b3bf66f2ec385c90887963fda5a34e4b
 size 3963