Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -1,19 +1,12 @@
 {
-  "_name_or_path": "xlnet-base-cased",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "XLNetForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
-  "attn_type": "bi",
-  "bi_data": false,
-  "bos_token_id": 1,
-  "clamp_len": -1,
-  "d_head": 64,
-  "d_inner": 3072,
-  "d_model": 768,
-  "dropout": 0.1,
-  "end_n_top": 5,
-  "eos_token_id": 2,
-  "ff_activation": "gelu",
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "sadness",
     "1": "joy",
@@ -23,6 +16,7 @@
     "5": "surprise"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "anger": 3,
     "fear": 4,
@@ -31,30 +25,27 @@
     "sadness": 0,
     "surprise": 5
   },
-  "layer_norm_eps": 1e-12,
-  "mem_len": null,
-  "model_type": "xlnet",
-  "n_head": 12,
-  "n_layer": 12,
-  "pad_token_id": 5,
-  "problem_type": "single_label_classification",
-  "reuse_len": null,
-  "same_length": false,
-  "start_n_top": 5,
-  "summary_activation": "tanh",
-  "summary_last_dropout": 0.1,
-  "summary_type": "last",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 250
-    }
-  },
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "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": "4.41.2",
-  "untie_r": true,
-  "use_mems_eval": true,
-  "use_mems_train": false,
-  "vocab_size": 32000
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c21f0080fa377cc979c322efe453e7a77380a02c1401f71d7da263c55e70bd5
-size 469276904
+oid sha256:c90d3bd617c65252a65962bafb91e064f390c85fd7a755738074848955d84152
+size 737731584

runs/Jul02_17-26-28_42319f0ca930/events.out.tfevents.1719941190.42319f0ca930.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7fee7c8aebd17eb4caad7bd9274866641971e7456c3881f1f5d448fdf9b52f
+size 9267

special_tokens_map.json

@@ -1,19 +1,15 @@
 {
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
-  "bos_token": "<s>",
-  "cls_token": "<cls>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "<sep>",
-  "unk_token": "<unk>"
+  }
 }

spm.model

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

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,47 +25,15 @@
       "special": true
     },
     "3": {
-      "content": "<cls>",
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<sep>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<eod>",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "8": {
-      "content": "<eop>",
+    "128000": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -73,21 +41,18 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<cls>",
+  "cls_token": "[CLS]",
   "do_lower_case": false,
-  "eos_token": "</s>",
-  "keep_accents": false,
-  "mask_token": "<mask>",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "<sep>",
-  "tokenizer_class": "XLNetTokenizer",
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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 sha256:682d859bc9f242ecb3ab91da17bb24d4b7e405c5432a0077401c8bf3173001fb
+oid sha256:e72eff599e60c87d3cc6791cee19af44b4d0ba95a9617f287c4c0180401d1d9e
 size 5112