Upload . with huggingface_hub

config.json

@@ -0,0 +1,56 @@
+{
+  "_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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.3",
+  "use_cache": true,
+  "vocab_size": 30000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "pad_token_id": 3,
+  "transformers_version": "4.27.3"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83262f26b22348a126b62a2f8396b525be29f661c837495b9562919da9c2470b
+size 991031749

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2632724b241c11873d92cf28251f2e9224aa1bebd6c9a63d501eef623ce6a86
+size 495648413

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0982167c9ca59ff663a78c6364cf73f269cf72d0cb94615b3bec6b16a21b3686
+size 14511

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3c85bae217509569c1fc8eea3e743f610b1887b228722b8b36d1c064637015
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a8249f7ef0efaae29f161e335cb4486a054c9ef7bfadb38e322ca24dfc81cc
+size 627

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 @@
+{
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--gogamza--kobart-base-v2/snapshots/f9f2ec35d3c32a1ecc7a3281f9626b7ec1913fed/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 99.905,
+  "best_model_checkpoint": "/content/drive/MyDrive/230327_sentence_split/KoBart-base/checkpoint-504",
+  "epoch": 9.0,
+  "global_step": 504,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2e-05,
+      "loss": 0.3919,
+      "step": 56
+    },
+    {
+      "epoch": 1.0,
+      "eval_chrFpp": 98.4453,
+      "eval_loss": 0.029023436829447746,
+      "eval_newline": 0.9217,
+      "eval_precision": 97.193,
+      "eval_recall": 97.5906,
+      "eval_runtime": 43.3012,
+      "eval_samples_per_second": 23.094,
+      "eval_steps_per_second": 0.185,
+      "step": 56
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.0227,
+      "step": 112
+    },
+    {
+      "epoch": 2.0,
+      "eval_chrFpp": 99.7204,
+      "eval_loss": 0.013132547028362751,
+      "eval_newline": 0.9697,
+      "eval_precision": 99.5582,
+      "eval_recall": 99.4243,
+      "eval_runtime": 32.4583,
+      "eval_samples_per_second": 30.809,
+      "eval_steps_per_second": 0.246,
+      "step": 112
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.0132,
+      "step": 168
+    },
+    {
+      "epoch": 3.0,
+      "eval_chrFpp": 99.7754,
+      "eval_loss": 0.009210724383592606,
+      "eval_newline": 0.98,
+      "eval_precision": 99.5141,
+      "eval_recall": 99.5944,
+      "eval_runtime": 34.866,
+      "eval_samples_per_second": 28.681,
+      "eval_steps_per_second": 0.229,
+      "step": 168
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0094,
+      "step": 224
+    },
+    {
+      "epoch": 4.0,
+      "eval_chrFpp": 99.8305,
+      "eval_loss": 0.0075386036187410355,
+      "eval_newline": 0.9844,
+      "eval_precision": 99.6357,
+      "eval_recall": 99.6919,
+      "eval_runtime": 33.2189,
+      "eval_samples_per_second": 30.103,
+      "eval_steps_per_second": 0.241,
+      "step": 224
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.0073,
+      "step": 280
+    },
+    {
+      "epoch": 5.0,
+      "eval_chrFpp": 99.8624,
+      "eval_loss": 0.006770443171262741,
+      "eval_newline": 0.9867,
+      "eval_precision": 99.7468,
+      "eval_recall": 99.755,
+      "eval_runtime": 32.3374,
+      "eval_samples_per_second": 30.924,
+      "eval_steps_per_second": 0.247,
+      "step": 280
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0063,
+      "step": 336
+    },
+    {
+      "epoch": 6.0,
+      "eval_chrFpp": 99.867,
+      "eval_loss": 0.006090933922678232,
+      "eval_newline": 0.9877,
+      "eval_precision": 99.711,
+      "eval_recall": 99.7674,
+      "eval_runtime": 33.0211,
+      "eval_samples_per_second": 30.284,
+      "eval_steps_per_second": 0.242,
+      "step": 336
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0055,
+      "step": 392
+    },
+    {
+      "epoch": 7.0,
+      "eval_chrFpp": 99.9029,
+      "eval_loss": 0.005742599256336689,
+      "eval_newline": 0.989,
+      "eval_precision": 99.8187,
+      "eval_recall": 99.8286,
+      "eval_runtime": 32.8202,
+      "eval_samples_per_second": 30.469,
+      "eval_steps_per_second": 0.244,
+      "step": 392
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0053,
+      "step": 448
+    },
+    {
+      "epoch": 8.0,
+      "eval_chrFpp": 99.9041,
+      "eval_loss": 0.0055114831775426865,
+      "eval_newline": 0.9885,
+      "eval_precision": 99.8169,
+      "eval_recall": 99.828,
+      "eval_runtime": 32.3504,
+      "eval_samples_per_second": 30.912,
+      "eval_steps_per_second": 0.247,
+      "step": 448
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.005,
+      "step": 504
+    },
+    {
+      "epoch": 9.0,
+      "eval_chrFpp": 99.905,
+      "eval_loss": 0.00544079951941967,
+      "eval_newline": 0.9885,
+      "eval_precision": 99.8225,
+      "eval_recall": 99.8288,
+      "eval_runtime": 32.4696,
+      "eval_samples_per_second": 30.798,
+      "eval_steps_per_second": 0.246,
+      "step": 504
+    }
+  ],
+  "max_steps": 560,
+  "num_train_epochs": 10,
+  "total_flos": 1.982368980393984e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a5cda630e04edc4b7964b797fb1030a661b87e681f18094fc4b22ed6d41227
+size 3771