Training in progress, epoch 1

config.json

@@ -1,34 +1,37 @@
 {
-  "_name_or_path": "gchhablani/fnet-base-finetuned-wnli",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "FNetForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "finetuning_task": "wnli",
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "negative",
-    "1": "potitive"
+    "1": "potitive",
+    "2": "neutral",
+    "3": "mixed"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
+    "mixed": 3,
     "negative": 0,
+    "neutral": 2,
     "positive": 1
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "fnet",
-  "num_hidden_layers": 12,
-  "pad_token_id": 3,
+  "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",
-  "tpu_short_seq_length": 512,
   "transformers_version": "4.30.2",
-  "type_vocab_size": 4,
-  "use_tpu_fourier_optimizations": false,
-  "vocab_size": 32000
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fa57d4422b32040a56251f2aac3b582faeffeb699b4b98f8e4094c07e19466
-size 331490685
+oid sha256:b04e070ef7ca437cb1e47cf6f331104e841f550182d1adb7e94ba1c094bdd7b6
+size 267861677

runs/Jun24_13-03-25_783533aedfec/events.out.tfevents.1687611810.783533aedfec.3425.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca717a1257398993ed188eaa663aac5adb8de0a108fdcee38b477dba3fecd82
+size 4140

runs/Jun24_13-20-44_783533aedfec/events.out.tfevents.1687612846.783533aedfec.3425.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ef9f0dd1239f2303277a88179681c53083bad5b5fda9de368ca549a675bd8f
+size 4404

special_tokens_map.json

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

tokenizer_config.json

@@ -1,21 +1,13 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "keep_accents": true,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "remove_space": true,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "FNetTokenizer",
-  "unk_token": "<unk>"
+  "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:c867e16fb4edf700edf53d4d5b5f744a2dd66e62ea022992a9a52da82c2649cb
+oid sha256:4d85aee64ab09d67eda5cf4f1e13b1af9687490812fd2942b91216c296370f32
 size 3963