BART Base.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "GanjinZero/biobart-v2-large",
+  "_name_or_path": "facebook/bart-base",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
@@ -11,19 +11,20 @@
   "bos_token_id": 0,
   "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 6,
   "eos_token_id": 2,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -42,8 +43,9 @@
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
   "normalize_before": false,
+  "normalize_embedding": true,
   "num_beams": 4,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
   "task_specific_params": {
@@ -69,5 +71,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
   "use_cache": true,
-  "vocab_size": 85401
+  "vocab_size": 50265
 }

generation_config.json

@@ -4,6 +4,7 @@
   "decoder_start_token_id": 2,
   "early_stopping": true,
   "eos_token_id": 2,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "no_repeat_ngram_size": 3,
   "num_beams": 4,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031c863f7ee87721b817325dd893fcb516a41481aa86091abff948a90ee89ba1
-size 1769595457
+oid sha256:45f41c21fb1b0df315980f344c84a6e37a6b10a2df97296ee9d9174e862eb045
+size 557969145

runs/Aug25_15-53-19_cn1104/events.out.tfevents.1692993200.cn1104.1067234.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93ba3803fd935cf20088c617cf2e62ca960f9c34582a6ab4ec117199ff9c964
+size 6506

tokenizer_config.json

@@ -34,7 +34,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 1024,
   "pad_token": {
     "__type": "AddedToken",
     "content": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cadde693bfd534e88c76b9e818a472edaa811d79f7fd36cf03a6ee45e784ccb2
+oid sha256:5ca0fb80157a81b5266ae0137998d8a4a854fb82fa382f32acb5cfeac38b5321
 size 3887