Training in progress, step 500

config.json

@@ -1,8 +1,9 @@
 {
-  "_name_or_path": "facebook/bart-large-cnn",
+  "_name_or_path": "sshleifer/distilbart-xsum-12-6",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
@@ -15,7 +16,7 @@
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": true,
@@ -24,8 +25,10 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "force_bos_token_to_be_generated": true,
-  "forced_bos_token_id": 0,
+  "eos_token_ids": [
+    2
+  ],
+  "extra_pos_embeddings": 2,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -40,29 +43,26 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "length_penalty": 2.0,
-  "max_length": 142,
+  "length_penalty": 0.5,
+  "max_length": 62,
   "max_position_embeddings": 1024,
-  "min_length": 56,
+  "min_length": 11,
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
   "normalize_before": false,
-  "num_beams": 4,
+  "normalize_embedding": true,
+  "num_beams": 6,
   "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
   "prefix": " ",
+  "replacing_rate": 0,
+  "save_step": 58,
   "scale_embedding": false,
-  "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
-    }
-  },
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {},
   "torch_dtype": "float32",
   "transformers_version": "4.28.1",
   "use_cache": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8577d66fd770bd0b6e6221be6393cd9e5830cfe5849488cbe10d6d30fceeb01c
-size 1625537293
+oid sha256:61af7dbaf40b66e1411ba12d137a1ad9555c082f683bae587b6c52ed676df22e
+size 1222363741

runs/Apr22_12-18-45_0943f7874f3f/1682166323.1325157/events.out.tfevents.1682166323.0943f7874f3f.184.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ab88e794da596ec4676dbe35ecd045e4caf3093e5c48d8ddd45a0f5dc4b35c
+size 6182

runs/Apr22_12-18-45_0943f7874f3f/events.out.tfevents.1682166323.0943f7874f3f.184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6db05d422981e156f9747705258dc1a0ff9d0a24f0aed196cc78a2a8ddf31b7
+size 5317

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d090541b797207cd5d97fec2e8071952f7386cea72f7a776de1b78eaa21b1ec3
+oid sha256:6f4f505825ebe3eeadd2e439b069a4bda24a9a30bb879b8ea16bffc792aae427
 size 3771