End of training

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "sshleifer/distilbart-xsum-12-3",
+  "_name_or_path": "facebook/bart-large-cnn",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
@@ -16,7 +15,7 @@
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 3,
+  "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": true,
@@ -25,11 +24,8 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "eos_token_ids": [
-    2
-  ],
-  "extra_pos_embeddings": 2,
-  "force_bos_token_to_be_generated": false,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -44,22 +40,29 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": 62,
+  "length_penalty": 2.0,
+  "max_length": 142,
   "max_position_embeddings": 1024,
-  "min_length": 11,
+  "min_length": 56,
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
   "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": 6,
+  "num_beams": 4,
   "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
   "prefix": " ",
-  "save_step": 58,
   "scale_embedding": false,
-  "static_position_embeddings": false,
-  "task_specific_params": {},
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.23.1",
   "use_cache": true,

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684468bb56035050a220c19f71f253ad3957f4cc34661e0c92bfde5825369d42
-size 1020774805
+oid sha256:ab503efc55df0c3c9b653a6c3fc42b2630369ad48ad43f22c28dc6552d7ed70a
+size 1625533697

tokenizer_config.json

@@ -34,7 +34,7 @@
     "single_word": false
   },
   "model_max_length": 1024,
-  "name_or_path": "sshleifer/distilbart-xsum-12-3",
+  "name_or_path": "facebook/bart-large-cnn",
   "pad_token": {
     "__type": "AddedToken",
     "content": "<pad>",
@@ -51,9 +51,8 @@
     "rstrip": false,
     "single_word": false
   },
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--sshleifer--distilbart-xsum-12-3/snapshots/1d2bfbc16dcdd28720f9f1d37be764e5cc5c78c8/special_tokens_map.json",
+  "special_tokens_map_file": null,
   "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
   "unk_token": {
     "__type": "AddedToken",
     "content": "<unk>",