Init: Model Upload

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 5.13,
+    "eval_bleu": 0.9161441917016176,
+    "eval_brevity_penalty": 1.0,
+    "eval_length_ratio": 1.054187205187115,
+    "eval_loss": 0.04431833699345589,
+    "eval_reference_length": 753868,
+    "eval_rouge1": 0.9502159661745533,
+    "eval_rouge2": 0.9313935147887745,
+    "eval_rougeL": 0.950015374196916,
+    "eval_rougeLsum": 0.9500390902948073,
+    "eval_runtime": 377.0831,
+    "eval_samples_per_second": 113.691,
+    "eval_steps_per_second": 9.475,
+    "eval_translation_length": 794718,
+    "train_loss": 0.20675974475976192,
+    "train_runtime": 80753.8777,
+    "train_samples_per_second": 24.519,
+    "train_steps_per_second": 4.086
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "/data2/bart/temp_workspace/nlp/models/kobart-base-v2",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "author": "Heewon Jeon([email protected])",
+  "bos_token_id": 1,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.1,
+  "d_model": 768,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "kobart_version": 2.0,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 1026,
+  "model_type": "bart",
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a52c360fae6152d2f0a194e47fd4682dc71205c06b3d01f852f2848b65f7c3
+size 495646265

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,5 @@
+{
+  "name_or_path": "/data2/bart/temp_workspace/nlp/models/kobart-base-v2",
+  "special_tokens_map_file": "/data2/bart/temp_workspace/nlp/models/kobart-base-v2/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15afb77fd7795f05dace0ebc5b610fa64d9e1242e477358ed76f63a579b7133
+size 3695