Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: madatnlp/gamza-bart-for-kormath128
+  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/gamza-bart-for-kormath128
+
+This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 6.2266
+- Validation Loss: 3.4709
+- 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': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 6.2266     | 3.4709          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- TensorFlow 2.8.0
+- Datasets 2.1.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "gogamza/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(madjakarta@gmail.com)",
+  "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",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 30000
+}

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988eddce8a3ea73c0b1f2358a5fbe1bf0a83cf73fc61314561f11deb918ce7af
+size 495849544

tokenizer_config.json

@@ -0,0 +1 @@
+{"special_tokens_map_file": "/root/.cache/huggingface/transformers/a87d2ed77831bb40ce806a97c04126addf5ecc82b3e23ecf916b2a4acdb9c29a.c23d5e62137984cf842a885705037b25b156747d145406702932d5f5d5e7c88e", "name_or_path": "gogamza/kobart-base-v2", "tokenizer_class": "PreTrainedTokenizerFast"}