Training in progress, step 500

config.json

@@ -1,60 +1,55 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "google/pegasus-cnn_dailymail",
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
   "architectures": [
-    "T5ForConditionalGeneration"
+    "PegasusForConditionalGeneration"
   ],
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 512,
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 16,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
-  "dropout_rate": 0.1,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
-  "initializer_factor": 1.0,
+  "extra_pos_embeddings": 1,
+  "forced_eos_token_id": 1,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "max_position_embeddings": 1024,
+  "min_length": 32,
+  "model_type": "pegasus",
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_cache": true,
-  "vocab_size": 32128
+  "vocab_size": 96103
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba1662e726c4fd94862a6749293b88d00fb75fbfe98f13e44c329a7b05eb976
-size 242071641
+oid sha256:cd8a9154e65069cc4dddc88f1e79caaede8e92d5ed41952fdf937bafc64526a2
+size 2283804653

runs/Aug17_03-57-51_1162c040e07d/events.out.tfevents.1692244765.1162c040e07d.1751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d1eef3a3982a6d732178815aa95c95d339d034dc8276340b20fb8c48869afa
+size 4862

runs/Aug17_04-02-13_1162c040e07d/events.out.tfevents.1692244951.1162c040e07d.1751.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835ebd9f040c9c8bc5f7e0fa5c4ebcc0e80645104bead389b57599e23819ac05
+size 4184

runs/Aug17_04-03-49_1162c040e07d/events.out.tfevents.1692245038.1162c040e07d.5822.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534d312a804235a0f17f991bcdf28068f3d43be27232bc2375246a4f58d0c4ed
+size 4184

runs/Aug17_04-06-50_1162c040e07d/events.out.tfevents.1692245218.1162c040e07d.6757.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed39d47681c880b525cbe5b8b7d0ab08f5da3e16a0d32dc7635d69f9e0cd853
+size 5017

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d542685af45c6bc3be8f3dd0869855e67f6c1cfd6795362fd90ca68eb6c4592e
+oid sha256:e6e10716ad5be60585c81b027eba536985aa2b26e7bc927d11542b3d31e0474d
 size 4091