Training in progress epoch 0

README.md

@@ -0,0 +1,52 @@
+---
+license: cc-by-nc-sa-4.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: madatnlp/sk-kogptv2-kormath-causal
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# madatnlp/sk-kogptv2-kormath-causal
+
+This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: nan
+- Epoch: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Epoch |
+|:----------:|:-----:|
+| nan        | 0     |
+
+
+### Framework versions
+
+- Transformers 4.19.1
+- TensorFlow 2.8.0
+- Datasets 2.2.1
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,50 @@
+{
+  "_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",
+  "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,
+  "license": "CC-BY-NC-SA 4.0",
+  "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,
+  "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
+    }
+  },
+  "transformers_version": "4.19.1",
+  "use_cache": true,
+  "vocab_size": 51205
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "</s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "</s>", "mask_token": "<mask>", "additional_special_tokens": ["°", "□", "÷", "×", "‘", "○", "’", "캤", "쨰", "츌", "잌", "찗"]}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a58bddccac971176ae05c41c44713160db5dfd316a39811f8e746174b1a091
+size 658153136

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "</s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "skt/kogpt2-base-v2", "tokenizer_class": "PreTrainedTokenizerFast"}