trained another 12 epochs

config.json

@@ -13,6 +13,7 @@
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
     "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
     "eos_token_id": null,
@@ -41,16 +42,20 @@
     "model_type": "bert",
     "no_repeat_ngram_size": 0,
     "num_attention_heads": 12,
+    "num_beam_groups": 1,
     "num_beams": 1,
     "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
+    "output_scores": false,
     "pad_token_id": 0,
+    "position_embedding_type": "absolute",
     "prefix": null,
     "pruned_heads": {},
     "repetition_penalty": 1.0,
-    "return_dict": false,
+    "return_dict": true,
+    "return_dict_in_generate": false,
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
@@ -60,6 +65,7 @@
     "top_k": 50,
     "top_p": 1.0,
     "torchscript": false,
+    "transformers_version": "4.2.2",
     "type_vocab_size": 2,
     "use_bfloat16": false,
     "use_cache": true,
@@ -79,6 +85,7 @@
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
     "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
     "eos_token_id": null,
@@ -107,16 +114,20 @@
     "model_type": "bert",
     "no_repeat_ngram_size": 0,
     "num_attention_heads": 12,
+    "num_beam_groups": 1,
     "num_beams": 1,
     "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
+    "output_scores": false,
     "pad_token_id": 0,
+    "position_embedding_type": "absolute",
     "prefix": null,
     "pruned_heads": {},
     "repetition_penalty": 1.0,
-    "return_dict": false,
+    "return_dict": true,
+    "return_dict_in_generate": false,
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
@@ -126,6 +137,7 @@
     "top_k": 50,
     "top_p": 1.0,
     "torchscript": false,
+    "transformers_version": "4.2.2",
     "type_vocab_size": 2,
     "use_bfloat16": false,
     "use_cache": true,
@@ -135,11 +147,11 @@
   "eos_token_id": 1,
   "is_encoder_decoder": true,
   "length_penalty": 2.0,
-  "max_length": 142,
-  "min_length": 56,
+  "max_length": 40,
+  "min_length": 20,
   "model_type": "encoder-decoder",
   "no_repeat_ngram_size": 3,
-  "num_beams": 4,
+  "num_beams": 10,
   "pad_token_id": 2,
   "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff5b143c3a27cb464c410ffbc8f61f720242c8fbafba10fa314ef9a29813bd4
+oid sha256:bce5258851b5aae797fd0ff45c1d52ce82105493144b1eaff6d0eb880b8d592c
 size 998778130