Training in progress, step 500

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "Tiabet/kogpt2-base-v2-finetuned-koGPT-complete_story",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "author": "Heewon Jeon(madjakarta@gmail.com)",
+  "bos_token_id": 51200,
+  "created_date": "2021-04-28",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 51201,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "license": "CC-BY-NC-SA 4.0",
+  "mask_token_id": 6,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 3,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "sep_token_id": 51202,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "unk_token_id": 5,
+  "use_cache": true,
+  "vocab_size": 51203
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954e1add1d73663c472143cc7bdbef948f6164479eaf1057ed3ede65db7006c4
+size 500713309

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sep_token": "<sep>",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af28519bf2f9b7712559d8d91f1bdc604c0e33dafca43dd02f43037831e2c902
+size 4155