Training in progress, step 1000

.gitignore

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

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "skt/kogpt2-base-v2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "author": "Heewon Jeon(madjakarta@gmail.com)",
+  "bos_token_id": 0,
+  "created_date": "2021-04-28",
+  "early_stopping": true,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "length_penalty": 5.0,
+  "license": "CC-BY-NC-SA 4.0",
+  "min_length": 30,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 5,
+  "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": 51200,
+  "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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 51201
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b011fc7f3f2e8d60ca67ec91339c42eeae9ddd5d5ae1e5b31a68e896622a83
+size 513296489

runs/Jan28_16-35-48_24c5be87015a/1674923778.4091966/events.out.tfevents.1674923778.24c5be87015a.28389.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4baaefba43e30dc960b26b438750a5d52f0272863d912c53130bc3c06cc39e
+size 5565

runs/Jan28_16-35-48_24c5be87015a/events.out.tfevents.1674923778.24c5be87015a.28389.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc57b69089b676e57cdf211ea5c46b8d4efd757e2776c167895c57035722f48
+size 4136

runs/Jan28_16-41-11_24c5be87015a/1674924098.3893764/events.out.tfevents.1674924098.24c5be87015a.29662.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4127a32d68f31a384f7ca0ecb37004d9a67222b06248b1cd2bb7fc674ad5002a
+size 5565

runs/Jan28_16-41-11_24c5be87015a/events.out.tfevents.1674924098.24c5be87015a.29662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b9d21eb941e280a692694403ebe9c367fda81c1d3cdbd3b23098312ddfeb13
+size 4868

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "skt/kogpt2-base-v2",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce6aa1a7f3bb0e51067564c3cbec38ed0e9078d94e8a0ec7713b32e89870b4b
+size 3503