Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "microsoft/prophetnet-large-uncased",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_cross_attention": true,
+  "architectures": [
+    "ProphetNetForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 102,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_max_position_embeddings": 514,
+  "decoder_start_token_id": 102,
+  "disable_ngram_loss": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_max_position_embeddings": 513,
+  "eos_token_id": 102,
+  "eps": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 512,
+  "model_type": "prophetnet",
+  "ngram": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "num_buckets": 32,
+  "num_decoder_attention_heads": 16,
+  "num_decoder_layers": 12,
+  "num_encoder_attention_heads": 16,
+  "num_encoder_layers": 12,
+  "output_past": false,
+  "pad_token_id": 0,
+  "prefix": " ",
+  "relative_max_distance": 128,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18b587127250dc7278a0e882228d9c25ca05be9dc3ff39e0c6143f579ca40fc
+size 1565471185

runs/Jun19_11-11-28_g3071/1655662325.7621264/events.out.tfevents.1655662325.g3071.24996.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ea718f8b5ccb7617499114db3e368d3db7211e86621dc1a57a14a8545b655f
+size 5397

runs/Jun19_11-11-28_g3071/events.out.tfevents.1655662325.g3071.24996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b416f888adc3d6f992fed99dd7a7165c7b12818751480a20e094e952e77754
+size 82632

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "x_sep_token": "[X_SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/gscratch/efml/anasa2/.huggingface/73e9134d07adccf5cf38d24c2f241f87e3febd91b209b279fff2741c9ff2ab4f.6fa7d8b91dc65e73f96549c829087df43aa7359e1d576908a012e7747d67c6c2", "name_or_path": "microsoft/prophetnet-large-uncased", "tokenizer_class": "ProphetNetTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c66a3086f3e05b3044001d040b5e526fd423e51d50ec6bb31e544eb10989e2
+size 3311