Training in progress, step 500

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,98 +1,111 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "/content/drive/MyDrive/project/kobigbird/first_model",
-  "add_cross_attention": true,
+  "_name_or_path": "/content/drive/MyDrive/project/kobigbird/new_model",
   "architectures": [
     "EncoderDecoderModel"
   ],
-  "attention_type": "original_full",
   "decoder": {
-    "_name_or_path": "monologg/kobigbird-bert-base",
+    "_name_or_path": "ainize/kobart-news",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
     "add_cross_attention": true,
+    "add_final_layer_norm": false,
     "architectures": [
-      "BigBirdForMaskedLM"
+      "BartForConditionalGeneration"
     ],
-    "attention_probs_dropout_prob": 0.1,
-    "attention_type": "block_sparse",
+    "attention_dropout": 0.0,
     "bad_words_ids": null,
-    "block_size": 64,
-    "bos_token_id": 5,
+    "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
-    "classifier_dropout": null,
+    "classif_dropout": 0.1,
+    "classifier_dropout": 0.1,
     "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
+    "d_model": 768,
+    "decoder_attention_heads": 6,
+    "decoder_ffn_dim": 3072,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 0,
     "diversity_penalty": 0.0,
+    "do_blenderbot_90_layernorm": false,
     "do_sample": false,
+    "dropout": 0.1,
     "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 3072,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 6,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 6,
+    "eos_token_id": 1,
     "exponential_decay_length_penalty": null,
+    "extra_pos_embeddings": 2,
     "finetuning_task": null,
+    "force_bos_token_to_be_generated": false,
     "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
+    "forced_eos_token_id": 2,
     "gradient_checkpointing": false,
-    "hidden_act": "gelu_new",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 768,
     "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
+      "0": "NEGATIVE",
+      "1": "POSITIVE"
     },
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
+    "init_std": 0.02,
     "is_decoder": true,
-    "is_encoder_decoder": false,
+    "is_encoder_decoder": true,
     "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
+      "NEGATIVE": 0,
+      "POSITIVE": 1
     },
-    "layer_norm_eps": 1e-12,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 4096,
+    "max_position_embeddings": 1026,
     "min_length": 0,
-    "model_type": "big_bird",
+    "model_type": "bart",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 6,
+    "normalize_before": false,
+    "normalize_embedding": true,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_hidden_layers": 6,
-    "num_random_blocks": 3,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 0,
-    "position_embedding_type": "absolute",
+    "pad_token_id": 3,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
-    "rescale_embeddings": false,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "sep_token_id": 3,
-    "task_specific_params": null,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "static_position_embeddings": false,
+    "task_specific_params": {
+      "summarization": {
+        "length_penalty": 1.0,
+        "max_length": 128,
+        "min_length": 12,
+        "num_beams": 4
+      }
+    },
     "temperature": 1.0,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
-    "tokenizer_class": "BertTokenizer",
+    "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
     "transformers_version": "4.22.0",
-    "type_vocab_size": 2,
     "typical_p": 1.0,
     "use_bfloat16": false,
-    "use_bias": true,
     "use_cache": true,
-    "vocab_size": 32500
+    "vocab_size": 30000
   },
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
+  "decoder_start_token_id": 0,
   "encoder": {
     "_name_or_path": "monologg/kobigbird-bert-base",
     "add_cross_attention": false,
@@ -107,10 +120,11 @@
     "chunk_size_feed_forward": 0,
     "classifier_dropout": null,
     "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
+    "decoder_start_token_id": 0,
     "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
+    "encoder_layers": 6,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 6,
     "exponential_decay_length_penalty": null,
@@ -149,7 +163,7 @@
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 0,
+    "pad_token_id": 3,
     "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
@@ -176,16 +190,11 @@
     "use_bfloat16": false,
     "use_bias": true,
     "use_cache": true,
-    "vocab_size": 32500
+    "vocab_size": 30000
   },
-  "encoder_layers": 6,
-  "is_decoder": true,
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
-  "num_attention_heads": 6,
-  "num_hidden_layers": 6,
-  "pad_token_id": 0,
+  "pad_token_id": 3,
   "torch_dtype": "float32",
-  "transformers_version": null,
-  "vocab_size": 32500
+  "transformers_version": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a3be97724979cecd41e5f5de6ace62863f02570fccefdf72c99550a857ca9e
-size 629203807
+oid sha256:3c565a530a893b515d527b715d8d63dc9ec85130bb90d68b68e01d1cf9242a27
+size 599515441

runs/Sep16_10-14-08_648715bc8f44/1663323508.8070502/events.out.tfevents.1663323508.648715bc8f44.78.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b874e8b2dcd9fc3c589910da851ac3b00e154c2215b226b31f683451b3586c
+size 5801

runs/Sep16_10-14-08_648715bc8f44/events.out.tfevents.1663323508.648715bc8f44.78.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f84d897244e519c5fa565b558e3a3ad25c9e201410aa90753fd6f861113324
+size 8232

runs/Sep16_10-19-52_648715bc8f44/1663323646.7311208/events.out.tfevents.1663323646.648715bc8f44.662.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd8378f3303d8999b1b402936b797a420ebf96d3cf19a2476f1d520904f408d
+size 5801

runs/Sep16_10-19-52_648715bc8f44/events.out.tfevents.1663323646.648715bc8f44.662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e6943d852352a7ef29dc60c3d70f030169b713479d0da466376a76787ce143
+size 8729

runs/Sep16_10-25-07_648715bc8f44/1663323918.1056142/events.out.tfevents.1663323918.648715bc8f44.897.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97517e4f6866cb29ff2772388a7b8597a11eb21ba2aa2669b74ad1dfff49357b
+size 5801

runs/Sep16_10-25-07_648715bc8f44/events.out.tfevents.1663323918.648715bc8f44.897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c37fe0dc1caf776d07b0cc14788792513d7dbda48419cb876ff6c632c2f6cc
+size 8886

special_tokens_map.json

@@ -1,9 +1,15 @@
 {
   "bos_token": "<s>",
-  "cls_token": "[CLS]",
+  "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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

@@ -1,18 +1,15 @@
 {
+  "add_prefix_space": false,
   "bos_token": "<s>",
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
+  "cls_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
-  "mask_token": "[MASK]",
-  "model_max_length": 4096,
-  "name_or_path": "/content/drive/MyDrive/project/kobigbird/first_model",
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--monologg--kobigbird-bert-base/snapshots/ceacda477e20abef2c929adfa4a07c6f811323be/special_tokens_map.json",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "name_or_path": "/content/drive/MyDrive/project/kobigbird/new_model",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c56219765e2b892daf6010000c5bb4b5dbf4eb6ccbb64845394bbad3b4a3353
+oid sha256:51d677c252f1fdd8ce2123964948abfe4e05ed0c9e41865a40bfc914f9fcbc79
 size 3567