Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "allenai/led-large-16384",
+  "_name_or_path": "pszemraj/led-large-book-summary",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",
@@ -31,13 +31,13 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
+  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
   "forced_bos_token_id": 250004,
-  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -50,15 +50,21 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
+  "length_penalty": 0.8,
   "max_decoder_position_embeddings": 1024,
   "max_encoder_position_embeddings": 16384,
+  "max_length": 1024,
+  "min_length": 8,
   "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
   "num_hidden_layers": 12,
   "output_past": false,
   "pad_token_id": 1,
   "prefix": " ",
+  "repetition_penalty": 3.5,
   "torch_dtype": "float32",
   "transformers_version": "4.21.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 250054
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54629937655a047c0144b67353ee7c3e6e24bcbb648682ac413a6a8922f01246
+oid sha256:f7b0217ceae77d2785cb904ee679bef28815c590f35f39011b5c03887cf2b302
 size 2658739697

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0885919c5521630eb0309e8ee23cdd39d751945418b5da81a2a53113651f9de5
+oid sha256:d14aef286a630f17d3c4dca5c4d75919e8eb4bf5770486d9bccd7be7579c9ab0
 size 3567