Training in progress, epoch 1

config.json

@@ -1,52 +1,35 @@
 {
-  "_name_or_path": "facebook/bart-large-mnli",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_final_layer_norm": false,
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BartForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
+  "attention_dropout": 0.1,
+  "dim": 768,
   "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "negative",
     "1": "neutral",
     "2": "positive"
   },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
+  "initializer_range": 0.02,
   "label2id": {
     "negative": 0,
     "neutral": 1,
     "positive": 2
   },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "normalize_before": false,
-  "num_hidden_layers": 12,
-  "output_past": false,
-  "pad_token_id": 1,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
-  "scale_embedding": false,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
-  "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:843e770a6582a868a23ff895dd456fba51ad14f8a8b8fcde40105fbdaece8636
-size 1629436964
+oid sha256:8cca5145d524138de61d748db2dc05319e8f017f2caea2e58e12fbb379de70fe
+size 267835644

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "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,
-      "normalized": 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": 1024,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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:f15268bee85aec42089e12372b6de9dd430e8f42f7a7ec8e6dd35a10adae6e71
+oid sha256:7f2922f4a8ffc0bca73a9bbc77bc4a174dc82f12f29922f4a6f19e335d0589c6
 size 4984