Training in progress, epoch 1

config.json

@@ -1,36 +1,33 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "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": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "non_joke",
     "1": "joke"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "joke": 1,
     "non_joke": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e9d2f8f9f00c1809c8d0bd90e596eca2bf2d32485622916a5fb55495a6c25bb
-size 498612824
+oid sha256:d42b6eabf3778ad6adc39d7ae9286d99aaffc5306c298d1b8ee7238b9aa29e83
+size 267832560

runs/Apr01_21-53-49_843ec8d82c44/events.out.tfevents.1712008431.843ec8d82c44.402.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99da26c7122cd6a5e44681209e3468b73824ed495ca7531fc206c76a6ee9afc
-size 4970
+oid sha256:60deadedb17545f125b78c73533bb639413599dfd56411727bc0374993542022
+size 5635

runs/Apr01_22-33-46_843ec8d82c44/events.out.tfevents.1712010827.843ec8d82c44.12778.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db7dae5fbcf355841a3b6fe77ee0671d26dd13f8b46ceeb9ecd2394fb520e8a
+size 4861

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "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>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,57 +1,55 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "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>"
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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:ed69ac954b5ee7e35926123a9994752572efd9b7c725ad43f0b406d7a08a6d08
+oid sha256:ee439cf97939f05e5b65581458fff1094a2d629700310ea5adca77b9c906f6fa
 size 4856