Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "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,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7314dfb2411fb5d7e6db7c6c3af9e0407da2930b5e84f67ebd2ea1cd421cf366
+size 1625537293

runs/Jul03_16-19-25_teesta/1688381374.1936774/events.out.tfevents.1688381374.teesta.3958.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b07fb552921ed2f72d6ccbb163bd23cbcc9cbd0c816e1062005d32086fb5bc3
+size 5734

runs/Jul03_16-19-25_teesta/events.out.tfevents.1688381374.teesta.3958.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955805d3ff67fbc08fdd84571efc48d861e59e8de3ea75f4a67d690cfdbaadc3
+size 4136

runs/Jul03_16-23-24_teesta/1688381610.6068606/events.out.tfevents.1688381610.teesta.7060.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d4f3b7273280f42fe50c9ac2fcdf8d4b954178b2fddf50d4beeb2e3c17720f
+size 5734

runs/Jul03_16-23-24_teesta/events.out.tfevents.1688381610.teesta.7060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f3555007bb3c2a76fde21df5447f13a504f05fe6436fa8948d57a07111884c
+size 4839

runs/Jul03_20-09-18_teesta/1688395163.8046238/events.out.tfevents.1688395163.teesta.35666.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991404c3102a42c18168e1c2055cebf4e5e9ff2db4e07a3d29b0a43ecf9db99b
+size 5734

runs/Jul03_20-09-18_teesta/events.out.tfevents.1688395163.teesta.35666.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72aedff0e3117a602625639bb604b626de3a42d484420def8d171b9497724bbe
+size 6571

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "name_or_path": "facebook/bart-large-cnn",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a47ac6d17f808b8e7df6c0d4e81f0d48e407f69c8a97935f8b012c24f839766
+size 3579