Training in progress, step 500

config.json

@@ -1,15 +1,15 @@
 {
-  "_name_or_path": "facebook/bart-large-cnn",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
   "activation_function": "gelu",
+  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
+  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
@@ -24,7 +24,6 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "force_bos_token_to_be_generated": true,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
@@ -40,31 +39,36 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "length_penalty": 2.0,
-  "max_length": 142,
   "max_position_embeddings": 1024,
-  "min_length": 56,
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
   "normalize_before": false,
   "num_beams": 4,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
-  "prefix": " ",
   "scale_embedding": false,
   "task_specific_params": {
     "summarization": {
-      "early_stopping": true,
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
       "length_penalty": 2.0,
       "max_length": 142,
       "min_length": 56,
-      "no_repeat_ngram_size": 3,
       "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
     }
   },
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e760f442fb265a7abf7be0e0a21b05cc3a54834c73f1e27fda9947f8c6e4fa
-size 1625422896
+oid sha256:539b9ceb3800f193474046fb24cf534d3323366f503ef168390de95ff7539f68
+size 1625426996

runs/Aug28_16-08-10_f2727cab06bd/events.out.tfevents.1724861291.f2727cab06bd.1638.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3be47423f96209c4c573839d4a562b31744f42126ec8f13290ae3b5b22a667b
+size 6207

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -48,10 +48,9 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24938bfd345faf72ae66614a4cfd22dcfbdb520225dd353c154249bd165db7cc
+oid sha256:03e4179db771ab1a1e94875407da46a78b6e5fc750d4dca212e37a14ad5c30e3
 size 5240