kogpt2-base-v2-simple-qa

README.md

@@ -0,0 +1,53 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: skt/kogpt2-base-v2
+tags:
+- generated_from_trainer
+model-index:
+- name: test_v4
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# test_v4
+
+This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on an unknown dataset.
+
+## 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:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.13.1+cu116
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "skt/kogpt2-base-v2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "author": "Heewon Jeon([email protected])",
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 3,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25602869a96c0c252611bd4ccae8c3080805affefc35a3bcc9596e5dd3e224ac
+size 500671104

runs/Nov22_03-18-13_75d5a95252af/events.out.tfevents.1700623095.75d5a95252af.19524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba17b104efc5ca946d47e5eb3e2d9792233daa8cd7997c2334ed2f6fb744aefc
+size 6928

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 3,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.587155963302753e-05,
+      "loss": 3.2425,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.170141784820684e-05,
+      "loss": 3.0793,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.753127606338616e-05,
+      "loss": 3.0799,
+      "step": 1500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.336113427856547e-05,
+      "loss": 2.978,
+      "step": 2000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.919099249374479e-05,
+      "loss": 2.9351,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5020850708924103e-05,
+      "loss": 2.9011,
+      "step": 3000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.085070892410342e-05,
+      "loss": 2.2736,
+      "step": 3500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.6680567139282734e-05,
+      "loss": 2.2694,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.2510425354462051e-05,
+      "loss": 2.2537,
+      "step": 4500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.340283569641367e-06,
+      "loss": 2.2018,
+      "step": 5000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 4.1701417848206835e-06,
+      "loss": 2.2193,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 2.1927,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "step": 6000,
+      "total_flos": 1554073145856000.0,
+      "train_loss": 2.635530497233073,
+      "train_runtime": 489.5458,
+      "train_samples_per_second": 49.025,
+      "train_steps_per_second": 12.256
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6000,
+  "num_train_epochs": 2,
+  "save_steps": 5000,
+  "total_flos": 1554073145856000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cdfb7e6b238b63bba9737748b1b64eeec818ab74e15891a892024e281b7cae
+size 4091