Training in progress, step 500

config.json

@@ -1,30 +1,29 @@
 {
-  "_name_or_path": "facebook/bart-large-cnn",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/bart-base",
+  "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,
-  "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,
-  "force_bos_token_to_be_generated": true,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
@@ -40,31 +39,37 @@
     "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,
+  "normalize_embedding": true,
   "num_beams": 4,
-  "num_hidden_layers": 12,
-  "output_past": true,
+  "num_hidden_layers": 6,
   "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": "4.35.2",
   "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:fe8f2ebb9f9e1de2c367236939da2c3eb3471b7ba5fdb0c867e04bf74480542c
-size 1625422896
+oid sha256:988930d6982f864362abf561026725862aa23b22397b33f59a7680e2004ba113
+size 557912620

runs/Jan28_21-32-16_27ed338ff3c6/events.out.tfevents.1706477543.27ed338ff3c6.1846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3634620ca9a26f3b900020dfe74d13cee346f1dac4f426e4c456574ccced44
+size 5609

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d4bb09b1e946fdf48fdf0c69a660dceceaf7e25b18b18f50e4b9d926247c20
+oid sha256:08d0a7a1515fea1594fa47e80da7e3629d3d32c11e0541ab0363affe4fe45b32
 size 4728