Training in progress, epoch 1

config.json

@@ -1,35 +1,34 @@
 {
-  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
-  "activation": "gelu",
+  "_name_or_path": "gchhablani/fnet-base-finetuned-wnli",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "FNetForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "finetuning_task": "sst-2",
-  "hidden_dim": 3072,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "wnli",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "negative",
     "1": "potitive"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "negative": 0,
     "positive": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
+  "model_type": "fnet",
+  "num_hidden_layers": 12,
+  "pad_token_id": 3,
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
+  "tpu_short_seq_length": 512,
   "transformers_version": "4.30.2",
-  "vocab_size": 30522
+  "type_vocab_size": 4,
+  "use_tpu_fourier_optimizations": false,
+  "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164fd50493cf88e0cd39fb484a031b51a70ef4ff8882a1d6ce4d2dfa527f8246
-size 267855533
+oid sha256:82f11cee37da54f2fd602ee84f52489f591b4e3ba6484f953beb618d2c86d2f9
+size 331490685

runs/Jun24_11-41-06_783533aedfec/events.out.tfevents.1687606999.783533aedfec.3425.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce17eff0ee6a31cb5d705bcbd303f69a2274e93c5d9664a1b3cea571d70965a
+size 4457

special_tokens_map.json

@@ -1,7 +1,13 @@
 {
   "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,15 +1,21 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "do_lower_case": false,
+  "keep_accents": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
+  "remove_space": true,
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "tokenizer_class": "FNetTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125d3743a125ff0c8c3128b422eaef8a82675c1fcb9104adf2ae0ed662bc4e87
+oid sha256:a297155d2fe508459f64f6bc990a6aef52a187d965947186a4b30d8990884970
 size 3963