Training in progress, epoch 1

config.json

@@ -1,71 +1,25 @@
 {
-  "_name_or_path": "facebook/bart-large-xsum",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
     "Model"
   ],
-  "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,
-  "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "eos_token_ids": [
-    2
-  ],
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_length": 62,
-  "max_position_embeddings": 1024,
-  "min_length": 11,
-  "model_type": "bart",
-  "n_gram_lm": false,
-  "n_grams": 0,
-  "n_grams_lambda": 0.1,
-  "no_base_loss": false,
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": 6,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "prefix": " ",
-  "replacing_rate": 0,
-  "scale_embedding": false,
-  "static_position_embeddings": false,
-  "student_decoder_layers": null,
-  "student_encoder_layers": null,
-  "task_specific_params": {},
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "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": "4.34.0",
-  "use_cache": true,
-  "vocab_size": 50264
+  "transformers_version": "4.32.1",
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e67c2eb35fd34aa24a34f2d744eab173d68244e177b821e8eed1148565804b7
-size 1625537293
+oid sha256:029477366ee6fa8f344f3bb7f9277602fcef147884c91aab3e0fd0d9b085c415
+size 267854321

special_tokens_map.json

@@ -1,9 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "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

@@ -1,58 +1,13 @@
 {
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
-  "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 sha256:03ad4843c0e0e2e8a021ce43c8b07e744464d576d3bf8ec159c6320a693422f4
-size 4219
+oid sha256:530e8ea82920bb2125663a09343b7ab11445f9fb3285fe308614cd8513d004c3
+size 4015