Training in progress, step 500

added_tokens.json

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

config.json

@@ -1,30 +1,41 @@
 {
   "architectures": [
-    "BertForQuestionAnswering"
+    "DebertaV2ForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "cell": {},
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "language": "english",
-  "layer_norm_eps": 1e-12,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "name": "Bert",
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "name": "DebertaV2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "pre_trained": "",
-  "structure": [],
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0,
+  "summary_type": "first",
+  "summary_use_proj": false,
   "torch_dtype": "float32",
   "transformers_version": "4.53.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0bb0d6d062a7c49d93cf87a5f525ae23c4579b57316f622c391a477d7d360aa
-size 265475832
+oid sha256:321521dbae8739126272b9b2f3fb9cb7e686f1027b23c24472b3e1b91e6c1c2b
+size 735356752

runs/Jul22_14-09-26_2c6cb13cc16e/events.out.tfevents.1753193367.2c6cb13cc16e.714.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890e55213c827c2ad4a30d6738897d62ad18f0c284b277ff5b31794e976d4da3
-size 6077
+oid sha256:a9ccb988d57a40823b925715bb7bf49e4f237283addff4ceaec28029e4075ef9
+size 6702

runs/Jul22_14-37-53_2c6cb13cc16e/events.out.tfevents.1753195075.2c6cb13cc16e.714.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a40cbd0462d1fd9699704f14e99b04217d1401afef01ba686598f6f37591448
+size 6358

special_tokens_map.json

@@ -1,4 +1,11 @@
 {
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,
@@ -6,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "[MASK]",
     "lstrip": false,

spm.model

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88288f3bbc81d03d5cc31434d30f8bd3c80771c9875a75fa763d167a8e34889e
-size 711661
+oid sha256:b3d4c2cda7fd3cb0a4a0460686f9a1f9ef4ca3ce478e30993b1162b64493f55e
+size 8649130

tokenizer_config.json

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
+    "128000": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,18 +41,19 @@
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670df5286d4561e247870dae44502640f0876c3a672ea41f8485db46a5736acd
+oid sha256:07ae19866cfe2d0d5c037c7e41148938b0f200bfd5edcaeaddf9f96d417f5641
 size 5304