Upload 13 files

added_tokens.json

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

config.json

@@ -1,26 +1,35 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/Data_For_Bert/BERT_racism/checkpoint-50000",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "BertForMaskedLM"
+    "DebertaV2ForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
+  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "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,
   "torch_dtype": "float32",
   "transformers_version": "4.26.0.dev0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05e868010f5e38e988f3ade184a099a65edf59ecac4fb0efff26d6347bba9d0
+size 1476533253

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b640f7341c7ccd6e234cd565b259e07dfa5845f9a8c0bead04be2c5a53c79d13
-size 438127737
+oid sha256:0173d21586112b8601479e48ed3efffa9b41aecda2240159515ced577fb29163
+size 738281789

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900ccb2263373e20e1a9291738273aea97fb7af3f259bd1d1f868d7b5167fc78
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc24c666d0ee5e2ab531f21956dee285e32fd041bcf6c5e29acc33488cfd06aa
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8d1121a288dd7c9c595784689eff9db447fb5bed7439cffcb92d4a0dc7484e
+size 627

special_tokens_map.json

@@ -1,5 +1,7 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

spm.model

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

tokenizer_config.json

@@ -1,16 +1,17 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "name_or_path": "/content/drive/MyDrive/Data_For_Bert/BERT_racism",
-  "never_split": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "microsoft/deberta-v3-base",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
   "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 1662,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.337121285067684e-06,
+      "loss": 3.63,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.442531108856201,
+      "eval_runtime": 165.1636,
+      "eval_samples_per_second": 160.968,
+      "eval_steps_per_second": 5.031,
+      "step": 831
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 5.009099042085838e-06,
+      "loss": 3.6184,
+      "step": 1000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.0015755222436686e-05,
+      "loss": 3.5811,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.3535778522491455,
+      "eval_runtime": 165.2268,
+      "eval_samples_per_second": 160.906,
+      "eval_steps_per_second": 5.029,
+      "step": 1662
+    }
+  ],
+  "max_steps": 3324,
+  "num_train_epochs": 4,
+  "total_flos": 1.401078900289536e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d53b5744def8c6041beb8c113c38b90d34f39043189e6b9fae97fbd99284d1
-size 3515
+oid sha256:8f52b2a73b34885d0c54f53c2b6ebea31bd615f0dc8d82b754ac2d57b64ad9d5
+size 3579