Upload folder using huggingface_hub

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Sehong/kobart-QuestionGeneration",
+  "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": 0,
+  "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": 1.0,
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 30000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "pad_token_id": 3,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3357e283dfca49c40094ed831aba9e9e892e95511be414cebe22a3965e3a2ad0
-size 495591624
+oid sha256:4cb58df9146fed9c484ec8c6ea9243a5fabbbdf62f0194f7fa4d97b582776a32
+size 495589768

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a271c1271b39754bb7472945fbae4c6fd1233fefe48ea49d54d924222b7abcc9
+size 991096314

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad45e9b6a0721ac3a745848f271b2e5eb3e745394903d5e675b6ad61e8139692
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af698246b2b59d7b4ea24706b357fc72fa57c54cc412ce2bfa6f9f34cd405616
+size 1064

trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": 2.6636579036712646,
+  "best_model_checkpoint": "./trained_qg_models/Sehong/kobart-QuestionGeneration/checkpoint-38",
+  "epoch": 0.08444444444444445,
+  "eval_steps": 2,
+  "global_step": 38,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "eval_loss": 5.902864456176758,
+      "eval_runtime": 1.4756,
+      "eval_samples_per_second": 67.767,
+      "eval_steps_per_second": 33.883,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 5.208019256591797,
+      "eval_runtime": 1.4619,
+      "eval_samples_per_second": 68.403,
+      "eval_steps_per_second": 34.202,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 3.895578622817993,
+      "eval_runtime": 1.4664,
+      "eval_samples_per_second": 68.194,
+      "eval_steps_per_second": 34.097,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 3.8213446140289307,
+      "eval_runtime": 1.4649,
+      "eval_samples_per_second": 68.265,
+      "eval_steps_per_second": 34.133,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 3.764300584793091,
+      "eval_runtime": 1.4644,
+      "eval_samples_per_second": 68.288,
+      "eval_steps_per_second": 34.144,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 3.6308743953704834,
+      "eval_runtime": 1.4631,
+      "eval_samples_per_second": 68.347,
+      "eval_steps_per_second": 34.173,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 3.361673355102539,
+      "eval_runtime": 1.4641,
+      "eval_samples_per_second": 68.303,
+      "eval_steps_per_second": 34.151,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 3.1514954566955566,
+      "eval_runtime": 1.4639,
+      "eval_samples_per_second": 68.309,
+      "eval_steps_per_second": 34.154,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 3.0636467933654785,
+      "eval_runtime": 1.464,
+      "eval_samples_per_second": 68.307,
+      "eval_steps_per_second": 34.153,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 3.003873348236084,
+      "eval_runtime": 1.4646,
+      "eval_samples_per_second": 68.28,
+      "eval_steps_per_second": 34.14,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.9242141246795654,
+      "eval_runtime": 1.462,
+      "eval_samples_per_second": 68.4,
+      "eval_steps_per_second": 34.2,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.862067222595215,
+      "eval_runtime": 1.4652,
+      "eval_samples_per_second": 68.25,
+      "eval_steps_per_second": 34.125,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 2.82049560546875,
+      "eval_runtime": 1.4635,
+      "eval_samples_per_second": 68.331,
+      "eval_steps_per_second": 34.165,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 2.7904272079467773,
+      "eval_runtime": 1.4633,
+      "eval_samples_per_second": 68.337,
+      "eval_steps_per_second": 34.168,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 2.7638421058654785,
+      "eval_runtime": 1.463,
+      "eval_samples_per_second": 68.352,
+      "eval_steps_per_second": 34.176,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 2.739243268966675,
+      "eval_runtime": 1.4634,
+      "eval_samples_per_second": 68.336,
+      "eval_steps_per_second": 34.168,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 2.7041234970092773,
+      "eval_runtime": 1.4667,
+      "eval_samples_per_second": 68.182,
+      "eval_steps_per_second": 34.091,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 2.684762954711914,
+      "eval_runtime": 1.4638,
+      "eval_samples_per_second": 68.317,
+      "eval_steps_per_second": 34.158,
+      "step": 36
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 2.6636579036712646,
+      "eval_runtime": 1.4652,
+      "eval_samples_per_second": 68.252,
+      "eval_steps_per_second": 34.126,
+      "step": 38
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 2,
+  "total_flos": 23169985413120.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb4f53bf867a79d02358f5e73e812dc640b1142502d96a9310d794e3e72bda7
+size 4856