Training in progress, step 500

config.json

@@ -1,38 +1,30 @@
 {
-  "_name_or_path": "microsoft/deberta-base",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "DebertaForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 768,
-  "pos_att_type": [
-    "c2p",
-    "p2c"
-  ],
-  "position_biased_input": false,
-  "relative_attention": true,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.20.1",
-  "type_vocab_size": 0,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd41efbc575dd0687d31ce9ee305cc891349538fb6b6dfab1357de8b958cbd8
-size 556843759
+oid sha256:a7d4146a8d687bbd7aec9e919b0246b4d2a34518295b38f3471a24962d542df8
+size 267851249

runs/Jul20_15-50-39_13a322e3f7f6/events.out.tfevents.1658332243.13a322e3f7f6.80.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00214a3c3652502a1f506a4aa55f72843c8f3cc0b449cf961fb638b346f97f9
-size 4350
+oid sha256:ca696bc8ff1bbb56e2b15061deb0f5b2ffc785ecfb36022dd59bd5d1a148cc9b
+size 6830

runs/Jul20_16-09-53_13a322e3f7f6/1658333397.3432662/events.out.tfevents.1658333397.13a322e3f7f6.80.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace1e7f32ef98bfa49336404e7ee93a1aad224a96fb2b67e295f01ba45f1a070
+size 5327

runs/Jul20_16-09-53_13a322e3f7f6/events.out.tfevents.1658333397.13a322e3f7f6.80.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7788227df55752a525009f7911b3fcf5390fb59c8b61eefbb2c8b2351edc065
+size 4180

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,67 +1,14 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "__type": "AddedToken",
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "do_lower_case": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "microsoft/deberta-base",
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "__type": "AddedToken",
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "special_tokens_map_file": null,
-  "tokenizer_class": "DebertaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "vocab_type": "gpt2"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebff1b2578d1a609fbff8f596d5266adde7240d5506f8aa5559e22b3db7fa4c5
+oid sha256:8af8eb6f8b1d61a5dd1ebd13f6717fd7112feb2a903f24c3b202ec356fcd37ed
 size 3247